OpenCloudOS-Kernel/tools/perf/builtin-diff.c

2014 lines
46 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
/*
* builtin-diff.c
*
* Builtin diff command: Analyze two perf.data input files, look up and read
* DSOs and symbol information, sort them and produce a diff.
*/
#include "builtin.h"
#include "perf.h"
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
#include "util/debug.h"
#include "util/event.h"
#include "util/hist.h"
#include "util/evsel.h"
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
#include "util/evlist.h"
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
#include "util/session.h"
#include "util/tool.h"
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
#include "util/sort.h"
#include "util/srcline.h"
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
#include "util/symbol.h"
#include "util/data.h"
#include "util/config.h"
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
#include "util/time-utils.h"
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
#include "util/annotate.h"
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
#include "util/map.h"
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
#include "util/spark.h"
#include "util/block-info.h"
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
#include "util/stream.h"
perf session: Return error code for perf_session__new() function on failure This patch is to return error code of perf_new_session function on failure instead of NULL. Test Results: Before Fix: $ perf c2c report -input failed to open nput: No such file or directory $ echo $? 0 $ After Fix: $ perf c2c report -input failed to open nput: No such file or directory $ echo $? 254 $ Committer notes: Fix 'perf tests topology' case, where we use that TEST_ASSERT_VAL(..., session), i.e. we need to pass zero in case of failure, which was the case before when NULL was returned by perf_session__new() for failure, but now we need to negate the result of IS_ERR(session) to respect that TEST_ASSERT_VAL) expectation of zero meaning failure. Reported-by: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com> Signed-off-by: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com> Acked-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Mukesh Ojha <mojha@codeaurora.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Shawn Landden <shawn@git.icu> Cc: Song Liu <songliubraving@fb.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tzvetomir Stoyanov <tstoyanov@vmware.com> Link: http://lore.kernel.org/lkml/20190822071223.17892.45782.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-22 15:20:49 +08:00
#include <linux/err.h>
#include <linux/zalloc.h>
#include <subcmd/pager.h>
#include <subcmd/parse-options.h>
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
#include <errno.h>
#include <inttypes.h>
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
#include <stdlib.h>
#include <math.h>
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
struct perf_diff {
struct perf_tool tool;
const char *time_str;
struct perf_time_interval *ptime_range;
int range_size;
int range_num;
bool has_br_stack;
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
bool stream;
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
};
/* Diff command specific HPP columns. */
enum {
PERF_HPP_DIFF__BASELINE,
PERF_HPP_DIFF__PERIOD,
PERF_HPP_DIFF__PERIOD_BASELINE,
PERF_HPP_DIFF__DELTA,
PERF_HPP_DIFF__RATIO,
PERF_HPP_DIFF__WEIGHTED_DIFF,
PERF_HPP_DIFF__FORMULA,
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
PERF_HPP_DIFF__DELTA_ABS,
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
PERF_HPP_DIFF__CYCLES,
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
PERF_HPP_DIFF__CYCLES_HIST,
PERF_HPP_DIFF__MAX_INDEX
};
struct diff_hpp_fmt {
struct perf_hpp_fmt fmt;
int idx;
char *header;
int header_width;
};
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
struct data__file {
struct perf_session *session;
struct perf_data data;
int idx;
struct hists *hists;
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
struct evlist_streams *evlist_streams;
struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX];
};
static struct data__file *data__files;
static int data__files_cnt;
#define data__for_each_file_start(i, d, s) \
for (i = s, d = &data__files[s]; \
i < data__files_cnt; \
i++, d = &data__files[i])
#define data__for_each_file(i, d) data__for_each_file_start(i, d, 0)
#define data__for_each_file_new(i, d) data__for_each_file_start(i, d, 1)
static bool force;
static bool show_period;
static bool show_formula;
static bool show_baseline_only;
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
static bool cycles_hist;
static unsigned int sort_compute = 1;
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
static s64 compute_wdiff_w1;
static s64 compute_wdiff_w2;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
enum {
COMPUTE_DELTA,
COMPUTE_RATIO,
COMPUTE_WEIGHTED_DIFF,
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
COMPUTE_DELTA_ABS,
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
COMPUTE_CYCLES,
COMPUTE_MAX,
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
COMPUTE_STREAM, /* After COMPUTE_MAX to avoid use current compute arrays */
};
const char *compute_names[COMPUTE_MAX] = {
[COMPUTE_DELTA] = "delta",
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
[COMPUTE_DELTA_ABS] = "delta-abs",
[COMPUTE_RATIO] = "ratio",
[COMPUTE_WEIGHTED_DIFF] = "wdiff",
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
[COMPUTE_CYCLES] = "cycles",
};
static int compute = COMPUTE_DELTA_ABS;
static int compute_2_hpp[COMPUTE_MAX] = {
[COMPUTE_DELTA] = PERF_HPP_DIFF__DELTA,
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
[COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS,
[COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO,
[COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF,
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
[COMPUTE_CYCLES] = PERF_HPP_DIFF__CYCLES,
};
#define MAX_COL_WIDTH 70
static struct header_column {
const char *name;
int width;
} columns[PERF_HPP_DIFF__MAX_INDEX] = {
[PERF_HPP_DIFF__BASELINE] = {
.name = "Baseline",
},
[PERF_HPP_DIFF__PERIOD] = {
.name = "Period",
.width = 14,
},
[PERF_HPP_DIFF__PERIOD_BASELINE] = {
.name = "Base period",
.width = 14,
},
[PERF_HPP_DIFF__DELTA] = {
.name = "Delta",
.width = 7,
},
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
[PERF_HPP_DIFF__DELTA_ABS] = {
.name = "Delta Abs",
.width = 7,
},
[PERF_HPP_DIFF__RATIO] = {
.name = "Ratio",
.width = 14,
},
[PERF_HPP_DIFF__WEIGHTED_DIFF] = {
.name = "Weighted diff",
.width = 14,
},
[PERF_HPP_DIFF__FORMULA] = {
.name = "Formula",
.width = MAX_COL_WIDTH,
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
},
[PERF_HPP_DIFF__CYCLES] = {
.name = "[Program Block Range] Cycles Diff",
.width = 70,
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
},
[PERF_HPP_DIFF__CYCLES_HIST] = {
.name = "stddev/Hist",
.width = NUM_SPARKS + 9,
}
};
static int setup_compute_opt_wdiff(char *opt)
{
char *w1_str = opt;
char *w2_str;
int ret = -EINVAL;
if (!opt)
goto out;
w2_str = strchr(opt, ',');
if (!w2_str)
goto out;
*w2_str++ = 0x0;
if (!*w2_str)
goto out;
compute_wdiff_w1 = strtol(w1_str, NULL, 10);
compute_wdiff_w2 = strtol(w2_str, NULL, 10);
if (!compute_wdiff_w1 || !compute_wdiff_w2)
goto out;
pr_debug("compute wdiff w1(%" PRId64 ") w2(%" PRId64 ")\n",
compute_wdiff_w1, compute_wdiff_w2);
ret = 0;
out:
if (ret)
pr_err("Failed: wrong weight data, use 'wdiff:w1,w2'\n");
return ret;
}
static int setup_compute_opt(char *opt)
{
if (compute == COMPUTE_WEIGHTED_DIFF)
return setup_compute_opt_wdiff(opt);
if (opt) {
pr_err("Failed: extra option specified '%s'", opt);
return -EINVAL;
}
return 0;
}
static int setup_compute(const struct option *opt, const char *str,
int unset __maybe_unused)
{
int *cp = (int *) opt->value;
char *cstr = (char *) str;
char buf[50];
unsigned i;
char *option;
if (!str) {
*cp = COMPUTE_DELTA;
return 0;
}
option = strchr(str, ':');
if (option) {
unsigned len = option++ - str;
/*
* The str data are not writeable, so we need
* to use another buffer.
*/
/* No option value is longer. */
if (len >= sizeof(buf))
return -EINVAL;
strncpy(buf, str, len);
buf[len] = 0x0;
cstr = buf;
}
for (i = 0; i < COMPUTE_MAX; i++)
if (!strcmp(cstr, compute_names[i])) {
*cp = i;
return setup_compute_opt(option);
}
pr_err("Failed: '%s' is not computation method "
"(use 'delta','ratio' or 'wdiff')\n", str);
return -EINVAL;
}
static double period_percent(struct hist_entry *he, u64 period)
{
u64 total = hists__total_period(he->hists);
return (period * 100.0) / total;
}
static double compute_delta(struct hist_entry *he, struct hist_entry *pair)
{
double old_percent = period_percent(he, he->stat.period);
double new_percent = period_percent(pair, pair->stat.period);
pair->diff.period_ratio_delta = new_percent - old_percent;
pair->diff.computed = true;
return pair->diff.period_ratio_delta;
}
static double compute_ratio(struct hist_entry *he, struct hist_entry *pair)
{
double old_period = he->stat.period ?: 1;
double new_period = pair->stat.period;
pair->diff.computed = true;
pair->diff.period_ratio = new_period / old_period;
return pair->diff.period_ratio;
}
static s64 compute_wdiff(struct hist_entry *he, struct hist_entry *pair)
{
u64 old_period = he->stat.period;
u64 new_period = pair->stat.period;
pair->diff.computed = true;
pair->diff.wdiff = new_period * compute_wdiff_w2 -
old_period * compute_wdiff_w1;
return pair->diff.wdiff;
}
static int formula_delta(struct hist_entry *he, struct hist_entry *pair,
char *buf, size_t size)
{
u64 he_total = he->hists->stats.total_period;
u64 pair_total = pair->hists->stats.total_period;
if (symbol_conf.filter_relative) {
he_total = he->hists->stats.total_non_filtered_period;
pair_total = pair->hists->stats.total_non_filtered_period;
}
return scnprintf(buf, size,
"(%" PRIu64 " * 100 / %" PRIu64 ") - "
"(%" PRIu64 " * 100 / %" PRIu64 ")",
pair->stat.period, pair_total,
he->stat.period, he_total);
}
static int formula_ratio(struct hist_entry *he, struct hist_entry *pair,
char *buf, size_t size)
{
double old_period = he->stat.period;
double new_period = pair->stat.period;
return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period);
}
static int formula_wdiff(struct hist_entry *he, struct hist_entry *pair,
char *buf, size_t size)
{
u64 old_period = he->stat.period;
u64 new_period = pair->stat.period;
return scnprintf(buf, size,
"(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")",
new_period, compute_wdiff_w2, old_period, compute_wdiff_w1);
}
static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
char *buf, size_t size)
{
switch (compute) {
case COMPUTE_DELTA:
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
case COMPUTE_DELTA_ABS:
return formula_delta(he, pair, buf, size);
case COMPUTE_RATIO:
return formula_ratio(he, pair, buf, size);
case COMPUTE_WEIGHTED_DIFF:
return formula_wdiff(he, pair, buf, size);
default:
BUG_ON(1);
}
return -1;
}
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
static void *block_hist_zalloc(size_t size)
{
struct block_hist *bh;
bh = zalloc(size + sizeof(*bh));
if (!bh)
return NULL;
return &bh->he;
}
static void block_hist_free(void *he)
{
struct block_hist *bh;
bh = container_of(he, struct block_hist, he);
hists__delete_entries(&bh->block_hists);
free(bh);
}
struct hist_entry_ops block_hist_ops = {
.new = block_hist_zalloc,
.free = block_hist_free,
};
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
static int diff__process_sample_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct evsel *evsel,
struct machine *machine)
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
{
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool);
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
struct addr_location al;
struct hists *hists = evsel__hists(evsel);
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
struct hist_entry_iter iter = {
.evsel = evsel,
.sample = sample,
.ops = &hist_iter_normal,
};
perf machine: Protect the machine->threads with a rwlock In addition to using refcounts for the struct thread lifetime management, we need to protect access to machine->threads from concurrent access. That happens in 'perf top', where a thread processes events, inserting and deleting entries from that rb_tree while another thread decays hist_entries, that end up dropping references and ultimately deleting threads from the rb_tree and releasing its resources when no further hist_entry (or other data structures, like in 'perf sched') references it. So the rule is the same for refcounts + protected trees in the kernel, get the tree lock, find object, bump the refcount, drop the tree lock, return, use object, drop the refcount if no more use of it is needed, keep it if storing it in some other data structure, drop when releasing that data structure. I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and "perf_event__preprocess_sample(&al)" with "addr_location__put(&al)". The addr_location__put() one is because as we return references to several data structures, we may end up adding more reference counting for the other data structures and then we'll drop it at addr_location__put() time. Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
int ret = -1;
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
if (perf_time__ranges_skip_sample(pdiff->ptime_range, pdiff->range_num,
sample->time)) {
return 0;
}
if (machine__resolve(machine, &al, sample) < 0) {
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
pr_warning("problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) {
ret = 0;
goto out_put;
}
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
switch (compute) {
case COMPUTE_CYCLES:
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL,
NULL, NULL, sample, true)) {
pr_warning("problem incrementing symbol period, "
"skipping event\n");
goto out_put;
}
hist__account_cycles(sample->branch_stack, &al, sample, false,
NULL);
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
break;
case COMPUTE_STREAM:
if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
NULL)) {
pr_debug("problem adding hist entry, skipping event\n");
goto out_put;
}
break;
default:
if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
true)) {
pr_warning("problem incrementing symbol period, "
"skipping event\n");
goto out_put;
}
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
}
/*
* The total_period is updated here before going to the output
* tree since normally only the baseline hists will call
* hists__output_resort() and precompute needs the total
* period in order to sort entries by percentage delta.
*/
hists->stats.total_period += sample->period;
if (!al.filtered)
hists->stats.total_non_filtered_period += sample->period;
perf machine: Protect the machine->threads with a rwlock In addition to using refcounts for the struct thread lifetime management, we need to protect access to machine->threads from concurrent access. That happens in 'perf top', where a thread processes events, inserting and deleting entries from that rb_tree while another thread decays hist_entries, that end up dropping references and ultimately deleting threads from the rb_tree and releasing its resources when no further hist_entry (or other data structures, like in 'perf sched') references it. So the rule is the same for refcounts + protected trees in the kernel, get the tree lock, find object, bump the refcount, drop the tree lock, return, use object, drop the refcount if no more use of it is needed, keep it if storing it in some other data structure, drop when releasing that data structure. I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and "perf_event__preprocess_sample(&al)" with "addr_location__put(&al)". The addr_location__put() one is because as we return references to several data structures, we may end up adding more reference counting for the other data structures and then we'll drop it at addr_location__put() time. Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
ret = 0;
out_put:
addr_location__put(&al);
return ret;
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
}
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
static struct perf_diff pdiff = {
.tool = {
.sample = diff__process_sample_event,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.lost = perf_event__process_lost,
.namespaces = perf_event__process_namespaces,
.cgroup = perf_event__process_cgroup,
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
.ordered_events = true,
.ordering_requires_timestamps = true,
},
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
};
static struct evsel *evsel_match(struct evsel *evsel,
struct evlist *evlist)
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
{
struct evsel *e;
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
evlist__for_each_entry(evlist, e) {
if (evsel__match2(evsel, e))
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
return e;
}
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
return NULL;
}
static void evlist__collapse_resort(struct evlist *evlist)
{
struct evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
struct hists *hists = evsel__hists(evsel);
hists__collapse_resort(hists, NULL);
}
}
static struct data__file *fmt_to_data_file(struct perf_hpp_fmt *fmt)
{
struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt);
void *ptr = dfmt - dfmt->idx;
struct data__file *d = container_of(ptr, struct data__file, fmt);
return d;
}
static struct hist_entry*
get_pair_data(struct hist_entry *he, struct data__file *d)
{
if (hist_entry__has_pairs(he)) {
struct hist_entry *pair;
list_for_each_entry(pair, &he->pairs.head, pairs.node)
if (pair->hists == d->hists)
return pair;
}
return NULL;
}
static struct hist_entry*
get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt)
{
struct data__file *d = fmt_to_data_file(&dfmt->fmt);
return get_pair_data(he, d);
}
static void hists__baseline_only(struct hists *hists)
{
struct rb_root_cached *root;
struct rb_node *next;
if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
next = rb_first_cached(root);
while (next != NULL) {
struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in);
next = rb_next(&he->rb_node_in);
if (!hist_entry__next_pair(he)) {
rb_erase_cached(&he->rb_node_in, root);
hist_entry__delete(he);
}
}
}
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
static int64_t block_cycles_diff_cmp(struct hist_entry *left,
struct hist_entry *right)
{
bool pairs_left = hist_entry__has_pairs(left);
bool pairs_right = hist_entry__has_pairs(right);
s64 l, r;
if (!pairs_left && !pairs_right)
return 0;
l = llabs(left->diff.cycles);
r = llabs(right->diff.cycles);
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
return r - l;
}
static int64_t block_sort(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
return block_cycles_diff_cmp(right, left);
}
static void init_block_hist(struct block_hist *bh)
{
__hists__init(&bh->block_hists, &bh->block_list);
perf_hpp_list__init(&bh->block_list);
INIT_LIST_HEAD(&bh->block_fmt.list);
INIT_LIST_HEAD(&bh->block_fmt.sort_list);
bh->block_fmt.cmp = block_info__cmp;
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
bh->block_fmt.sort = block_sort;
perf_hpp_list__register_sort_field(&bh->block_list,
&bh->block_fmt);
bh->valid = true;
}
static struct hist_entry *get_block_pair(struct hist_entry *he,
struct hists *hists_pair)
{
struct rb_root_cached *root = hists_pair->entries_in;
struct rb_node *next = rb_first_cached(root);
int64_t cmp;
while (next != NULL) {
struct hist_entry *he_pair = rb_entry(next, struct hist_entry,
rb_node_in);
next = rb_next(&he_pair->rb_node_in);
cmp = __block_info__cmp(he_pair, he);
if (!cmp)
return he_pair;
}
return NULL;
}
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
static void init_spark_values(unsigned long *svals, int num)
{
for (int i = 0; i < num; i++)
svals[i] = 0;
}
static void update_spark_value(unsigned long *svals, int num,
struct stats *stats, u64 val)
{
int n = stats->n;
if (n < num)
svals[n] = val;
}
static void compute_cycles_diff(struct hist_entry *he,
struct hist_entry *pair)
{
pair->diff.computed = true;
if (pair->block_info->num && he->block_info->num) {
pair->diff.cycles =
pair->block_info->cycles_aggr / pair->block_info->num_aggr -
he->block_info->cycles_aggr / he->block_info->num_aggr;
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
if (!cycles_hist)
return;
init_stats(&pair->diff.stats);
init_spark_values(pair->diff.svals, NUM_SPARKS);
for (int i = 0; i < pair->block_info->num; i++) {
u64 val;
if (i >= he->block_info->num || i >= NUM_SPARKS)
break;
val = llabs(pair->block_info->cycles_spark[i] -
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
he->block_info->cycles_spark[i]);
update_spark_value(pair->diff.svals, NUM_SPARKS,
&pair->diff.stats, val);
update_stats(&pair->diff.stats, val);
}
}
}
static void block_hists_match(struct hists *hists_base,
struct hists *hists_pair)
{
struct rb_root_cached *root = hists_base->entries_in;
struct rb_node *next = rb_first_cached(root);
while (next != NULL) {
struct hist_entry *he = rb_entry(next, struct hist_entry,
rb_node_in);
struct hist_entry *pair = get_block_pair(he, hists_pair);
next = rb_next(&he->rb_node_in);
if (pair) {
hist_entry__add_pair(pair, he);
compute_cycles_diff(he, pair);
}
}
}
static void hists__precompute(struct hists *hists)
{
struct rb_root_cached *root;
struct rb_node *next;
if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
next = rb_first_cached(root);
while (next != NULL) {
struct block_hist *bh, *pair_bh;
struct hist_entry *he, *pair;
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
struct data__file *d;
int i;
he = rb_entry(next, struct hist_entry, rb_node_in);
next = rb_next(&he->rb_node_in);
if (compute == COMPUTE_CYCLES) {
bh = container_of(he, struct block_hist, he);
init_block_hist(bh);
block_info__process_sym(he, bh, NULL, 0);
}
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
data__for_each_file_new(i, d) {
pair = get_pair_data(he, d);
if (!pair)
continue;
switch (compute) {
case COMPUTE_DELTA:
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
case COMPUTE_DELTA_ABS:
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
compute_delta(he, pair);
break;
case COMPUTE_RATIO:
compute_ratio(he, pair);
break;
case COMPUTE_WEIGHTED_DIFF:
compute_wdiff(he, pair);
break;
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
case COMPUTE_CYCLES:
pair_bh = container_of(pair, struct block_hist,
he);
init_block_hist(pair_bh);
block_info__process_sym(pair, pair_bh, NULL, 0);
bh = container_of(he, struct block_hist, he);
if (bh->valid && pair_bh->valid) {
block_hists_match(&bh->block_hists,
&pair_bh->block_hists);
hists__output_resort(&pair_bh->block_hists,
NULL);
}
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
break;
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
default:
BUG_ON(1);
}
}
}
}
static int64_t cmp_doubles(double l, double r)
{
if (l > r)
return -1;
else if (l < r)
return 1;
else
return 0;
}
static int64_t
__hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
int c)
{
switch (c) {
case COMPUTE_DELTA:
{
double l = left->diff.period_ratio_delta;
double r = right->diff.period_ratio_delta;
return cmp_doubles(l, r);
}
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
case COMPUTE_DELTA_ABS:
{
double l = fabs(left->diff.period_ratio_delta);
double r = fabs(right->diff.period_ratio_delta);
return cmp_doubles(l, r);
}
case COMPUTE_RATIO:
{
double l = left->diff.period_ratio;
double r = right->diff.period_ratio;
return cmp_doubles(l, r);
}
case COMPUTE_WEIGHTED_DIFF:
{
s64 l = left->diff.wdiff;
s64 r = right->diff.wdiff;
return r - l;
}
default:
BUG_ON(1);
}
return 0;
}
static int64_t
hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
int c, int sort_idx)
{
bool pairs_left = hist_entry__has_pairs(left);
bool pairs_right = hist_entry__has_pairs(right);
struct hist_entry *p_right, *p_left;
if (!pairs_left && !pairs_right)
return 0;
if (!pairs_left || !pairs_right)
return pairs_left ? -1 : 1;
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
p_left = get_pair_data(left, &data__files[sort_idx]);
p_right = get_pair_data(right, &data__files[sort_idx]);
if (!p_left && !p_right)
return 0;
if (!p_left || !p_right)
return p_left ? -1 : 1;
/*
* We have 2 entries of same kind, let's
* make the data comparison.
*/
return __hist_entry__cmp_compute(p_left, p_right, c);
}
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
static int64_t
hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right,
int c, int sort_idx)
{
struct hist_entry *p_right, *p_left;
p_left = get_pair_data(left, &data__files[sort_idx]);
p_right = get_pair_data(right, &data__files[sort_idx]);
if (!p_left && !p_right)
return 0;
if (!p_left || !p_right)
return p_left ? -1 : 1;
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) {
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
/*
* The delta can be computed without the baseline, but
* others are not. Put those entries which have no
* values below.
*/
if (left->dummy && right->dummy)
return 0;
if (left->dummy || right->dummy)
return left->dummy ? 1 : -1;
}
return __hist_entry__cmp_compute(p_left, p_right, c);
}
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
static int64_t
hist_entry__cmp_nop(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left __maybe_unused,
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
struct hist_entry *right __maybe_unused)
{
return 0;
}
static int64_t
hist_entry__cmp_baseline(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
{
if (left->stat.period == right->stat.period)
return 0;
return left->stat.period > right->stat.period ? 1 : -1;
}
static int64_t
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
hist_entry__cmp_delta(struct perf_hpp_fmt *fmt,
struct hist_entry *left, struct hist_entry *right)
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
{
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
struct data__file *d = fmt_to_data_file(fmt);
return hist_entry__cmp_compute(right, left, COMPUTE_DELTA, d->idx);
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
}
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
static int64_t
hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt,
struct hist_entry *left, struct hist_entry *right)
{
struct data__file *d = fmt_to_data_file(fmt);
return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx);
}
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
static int64_t
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt,
struct hist_entry *left, struct hist_entry *right)
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
{
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
struct data__file *d = fmt_to_data_file(fmt);
return hist_entry__cmp_compute(right, left, COMPUTE_RATIO, d->idx);
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
}
static int64_t
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
hist_entry__cmp_wdiff(struct perf_hpp_fmt *fmt,
struct hist_entry *left, struct hist_entry *right)
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
{
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
struct data__file *d = fmt_to_data_file(fmt);
return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF, d->idx);
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
}
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
static int64_t
hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA,
sort_compute);
}
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
static int64_t
hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS,
sort_compute);
}
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
static int64_t
hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
return hist_entry__cmp_compute_idx(right, left, COMPUTE_RATIO,
sort_compute);
}
static int64_t
hist_entry__cmp_wdiff_idx(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left, struct hist_entry *right)
{
return hist_entry__cmp_compute_idx(right, left, COMPUTE_WEIGHTED_DIFF,
sort_compute);
}
static void hists__process(struct hists *hists)
{
if (show_baseline_only)
hists__baseline_only(hists);
perf diff: Fix output ordering to honor next column When perf diff prints output, it sorts the entries using baseline field by default, but entries which don't have baseline are not sorted properly. This patch makes it sorted by values of next column. Before: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 After: # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... # 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt 1.31% +0.03% -0.06% a.out [.] malloc@plt 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-7-git-send-email-namhyung@kernel.org [ Fixed up hist_entry__cmp_ method signatures, fallout from making previous cset buildable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:47 +08:00
hists__precompute(hists);
hists__output_resort(hists, NULL);
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
if (compute == COMPUTE_CYCLES)
symbol_conf.report_block = true;
perf diff: Add -q/--quiet option The -q/--quiet option is to suppress any message. Sometimes users just want to see the numbers and it can be used for that case. Committer notes: Before: # perf diff | head -10 Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-2646.map, continuing without symbols # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... .......................... ............................................ # 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 After: # perf diff -q | head -10 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 1.86% +0.95% [kernel.vmlinux] [k] update_blocked_averages 0.80% -0.70% [kernel.vmlinux] [k] native_sched_clock 0.74% -0.58% [kernel.vmlinux] [k] native_write_msr 0.76% -0.56% qemu-system-x86_64 [.] 0x00000000002395c0 +0.54% libpulsecommon-10.0.so [.] 0x000000000002d91b # Signed-off-by: Namhyung Kim <namhyung@kernel.org> Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170217081742.17417-5-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-17 16:17:40 +08:00
hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
!symbol_conf.use_callchain);
}
static void data__fprintf(void)
{
struct data__file *d;
int i;
fprintf(stdout, "# Data files:\n");
data__for_each_file(i, d)
fprintf(stdout, "# [%d] %s %s\n",
d->idx, d->data.path,
!d->idx ? "(Baseline)" : "");
fprintf(stdout, "#\n");
}
static void data_process(void)
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
{
struct evlist *evlist_base = data__files[0].session->evlist;
struct evsel *evsel_base;
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
bool first = true;
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
evlist__for_each_entry(evlist_base, evsel_base) {
struct hists *hists_base = evsel__hists(evsel_base);
struct data__file *d;
int i;
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
data__for_each_file_new(i, d) {
struct evlist *evlist = d->session->evlist;
struct evsel *evsel;
struct hists *hists;
evsel = evsel_match(evsel_base, evlist);
if (!evsel)
continue;
hists = evsel__hists(evsel);
d->hists = hists;
hists__match(hists_base, hists);
if (!show_baseline_only)
hists__link(hists_base, hists);
}
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
perf diff: Add -q/--quiet option The -q/--quiet option is to suppress any message. Sometimes users just want to see the numbers and it can be used for that case. Committer notes: Before: # perf diff | head -10 Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-2646.map, continuing without symbols # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... .......................... ............................................ # 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 After: # perf diff -q | head -10 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 1.86% +0.95% [kernel.vmlinux] [k] update_blocked_averages 0.80% -0.70% [kernel.vmlinux] [k] native_sched_clock 0.74% -0.58% [kernel.vmlinux] [k] native_write_msr 0.76% -0.56% qemu-system-x86_64 [.] 0x00000000002395c0 +0.54% libpulsecommon-10.0.so [.] 0x000000000002d91b # Signed-off-by: Namhyung Kim <namhyung@kernel.org> Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170217081742.17417-5-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-17 16:17:40 +08:00
if (!quiet) {
fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
evsel__name(evsel_base));
perf diff: Add -q/--quiet option The -q/--quiet option is to suppress any message. Sometimes users just want to see the numbers and it can be used for that case. Committer notes: Before: # perf diff | head -10 Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-2646.map, continuing without symbols # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... .......................... ............................................ # 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 After: # perf diff -q | head -10 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 1.86% +0.95% [kernel.vmlinux] [k] update_blocked_averages 0.80% -0.70% [kernel.vmlinux] [k] native_sched_clock 0.74% -0.58% [kernel.vmlinux] [k] native_write_msr 0.76% -0.56% qemu-system-x86_64 [.] 0x00000000002395c0 +0.54% libpulsecommon-10.0.so [.] 0x000000000002d91b # Signed-off-by: Namhyung Kim <namhyung@kernel.org> Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170217081742.17417-5-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-17 16:17:40 +08:00
}
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
first = false;
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
perf diff: Add -q/--quiet option The -q/--quiet option is to suppress any message. Sometimes users just want to see the numbers and it can be used for that case. Committer notes: Before: # perf diff | head -10 Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-2646.map, continuing without symbols # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... .......................... ............................................ # 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 After: # perf diff -q | head -10 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 1.86% +0.95% [kernel.vmlinux] [k] update_blocked_averages 0.80% -0.70% [kernel.vmlinux] [k] native_sched_clock 0.74% -0.58% [kernel.vmlinux] [k] native_write_msr 0.76% -0.56% qemu-system-x86_64 [.] 0x00000000002395c0 +0.54% libpulsecommon-10.0.so [.] 0x000000000002d91b # Signed-off-by: Namhyung Kim <namhyung@kernel.org> Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170217081742.17417-5-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-17 16:17:40 +08:00
if (verbose > 0 || ((data__files_cnt > 2) && !quiet))
data__fprintf();
perf callchain: Allow disabling call graphs per event This patch introduce "call-graph=no" to disable per-event callgraph. Here is an example. perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1 perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6 of event 'cpu/cpu-cycles,call-graph=fp/' # Event count (approx.): 774218 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ........................................ # 61.94% 0.00% sleep [kernel.vmlinux] [k] entry_SYSCALL_64_fastpath | ---entry_SYSCALL_64_fastpath | |--97.30%-- __brk | --2.70%-- mmap64 _dl_check_map_versions _dl_check_all_versions 61.94% 0.00% sleep [kernel.vmlinux] [k] perf_event_mmap | ---perf_event_mmap | |--97.30%-- do_brk | sys_brk | entry_SYSCALL_64_fastpath | __brk | --2.70%-- mmap_region do_mmap_pgoff vm_mmap_pgoff sys_mmap_pgoff sys_mmap entry_SYSCALL_64_fastpath mmap64 _dl_check_map_versions _dl_check_all_versions ...... # Samples: 6 of event 'cpu/instructions,call-graph=no/' # Event count (approx.): 359692 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ................................. # 89.03% 0.00% sleep [unknown] [.] 0xffff6598ffff6598 89.03% 0.00% sleep ld-2.17.so [.] _dl_resolve_conflicts 89.03% 0.00% sleep [kernel.vmlinux] [k] page_fault Signed-off-by: Kan Liang <kan.liang@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 18:30:48 +08:00
/* Don't sort callchain for perf diff */
evsel__reset_sample_bit(evsel_base, CALLCHAIN);
perf callchain: Allow disabling call graphs per event This patch introduce "call-graph=no" to disable per-event callgraph. Here is an example. perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1 perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6 of event 'cpu/cpu-cycles,call-graph=fp/' # Event count (approx.): 774218 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ........................................ # 61.94% 0.00% sleep [kernel.vmlinux] [k] entry_SYSCALL_64_fastpath | ---entry_SYSCALL_64_fastpath | |--97.30%-- __brk | --2.70%-- mmap64 _dl_check_map_versions _dl_check_all_versions 61.94% 0.00% sleep [kernel.vmlinux] [k] perf_event_mmap | ---perf_event_mmap | |--97.30%-- do_brk | sys_brk | entry_SYSCALL_64_fastpath | __brk | --2.70%-- mmap_region do_mmap_pgoff vm_mmap_pgoff sys_mmap_pgoff sys_mmap entry_SYSCALL_64_fastpath mmap64 _dl_check_map_versions _dl_check_all_versions ...... # Samples: 6 of event 'cpu/instructions,call-graph=no/' # Event count (approx.): 359692 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ................................. # 89.03% 0.00% sleep [unknown] [.] 0xffff6598ffff6598 89.03% 0.00% sleep ld-2.17.so [.] _dl_resolve_conflicts 89.03% 0.00% sleep [kernel.vmlinux] [k] page_fault Signed-off-by: Kan Liang <kan.liang@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 18:30:48 +08:00
hists__process(hists_base);
}
}
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
static int process_base_stream(struct data__file *data_base,
struct data__file *data_pair,
const char *title __maybe_unused)
{
struct evlist *evlist_base = data_base->session->evlist;
struct evlist *evlist_pair = data_pair->session->evlist;
struct evsel *evsel_base, *evsel_pair;
struct evsel_streams *es_base, *es_pair;
evlist__for_each_entry(evlist_base, evsel_base) {
evsel_pair = evsel_match(evsel_base, evlist_pair);
if (!evsel_pair)
continue;
es_base = evsel_streams__entry(data_base->evlist_streams,
evsel_base->idx);
if (!es_base)
return -1;
es_pair = evsel_streams__entry(data_pair->evlist_streams,
evsel_pair->idx);
if (!es_pair)
return -1;
evsel_streams__match(es_base, es_pair);
evsel_streams__report(es_base, es_pair);
}
return 0;
}
static void stream_process(void)
{
/*
* Stream comparison only supports two data files.
* perf.data.old and perf.data. data__files[0] is perf.data.old,
* data__files[1] is perf.data.
*/
process_base_stream(&data__files[0], &data__files[1],
"# Output based on old perf data:\n#\n");
}
static void data__free(struct data__file *d)
{
int col;
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
if (d->evlist_streams)
evlist_streams__delete(d->evlist_streams);
for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) {
struct diff_hpp_fmt *fmt = &d->fmt[col];
zfree(&fmt->header);
}
}
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
static int abstime_str_dup(char **pstr)
{
char *str = NULL;
if (pdiff.time_str && strchr(pdiff.time_str, ':')) {
str = strdup(pdiff.time_str);
if (!str)
return -ENOMEM;
}
*pstr = str;
return 0;
}
static int parse_absolute_time(struct data__file *d, char **pstr)
{
char *p = *pstr;
int ret;
/*
* Absolute timestamp for one file has the format: a.b,c.d
* For multiple files, the format is: a.b,c.d:a.b,c.d
*/
p = strchr(*pstr, ':');
if (p) {
if (p == *pstr) {
pr_err("Invalid time string\n");
return -EINVAL;
}
*p = 0;
p++;
if (*p == 0) {
pr_err("Invalid time string\n");
return -EINVAL;
}
}
ret = perf_time__parse_for_ranges(*pstr, d->session,
&pdiff.ptime_range,
&pdiff.range_size,
&pdiff.range_num);
if (ret < 0)
return ret;
if (!p || *p == 0)
*pstr = NULL;
else
*pstr = p;
return ret;
}
static int parse_percent_time(struct data__file *d)
{
int ret;
ret = perf_time__parse_for_ranges(pdiff.time_str, d->session,
&pdiff.ptime_range,
&pdiff.range_size,
&pdiff.range_num);
return ret;
}
static int parse_time_str(struct data__file *d, char *abstime_ostr,
char **pabstime_tmp)
{
int ret = 0;
if (abstime_ostr)
ret = parse_absolute_time(d, pabstime_tmp);
else if (pdiff.time_str)
ret = parse_percent_time(d);
return ret;
}
static int check_file_brstack(void)
{
struct data__file *d;
bool has_br_stack;
int i;
data__for_each_file(i, d) {
d->session = perf_session__new(&d->data, false, &pdiff.tool);
perf session: Return error code for perf_session__new() function on failure This patch is to return error code of perf_new_session function on failure instead of NULL. Test Results: Before Fix: $ perf c2c report -input failed to open nput: No such file or directory $ echo $? 0 $ After Fix: $ perf c2c report -input failed to open nput: No such file or directory $ echo $? 254 $ Committer notes: Fix 'perf tests topology' case, where we use that TEST_ASSERT_VAL(..., session), i.e. we need to pass zero in case of failure, which was the case before when NULL was returned by perf_session__new() for failure, but now we need to negate the result of IS_ERR(session) to respect that TEST_ASSERT_VAL) expectation of zero meaning failure. Reported-by: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com> Signed-off-by: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com> Acked-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Mukesh Ojha <mojha@codeaurora.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Shawn Landden <shawn@git.icu> Cc: Song Liu <songliubraving@fb.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tzvetomir Stoyanov <tstoyanov@vmware.com> Link: http://lore.kernel.org/lkml/20190822071223.17892.45782.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-22 15:20:49 +08:00
if (IS_ERR(d->session)) {
pr_err("Failed to open %s\n", d->data.path);
perf session: Return error code for perf_session__new() function on failure This patch is to return error code of perf_new_session function on failure instead of NULL. Test Results: Before Fix: $ perf c2c report -input failed to open nput: No such file or directory $ echo $? 0 $ After Fix: $ perf c2c report -input failed to open nput: No such file or directory $ echo $? 254 $ Committer notes: Fix 'perf tests topology' case, where we use that TEST_ASSERT_VAL(..., session), i.e. we need to pass zero in case of failure, which was the case before when NULL was returned by perf_session__new() for failure, but now we need to negate the result of IS_ERR(session) to respect that TEST_ASSERT_VAL) expectation of zero meaning failure. Reported-by: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com> Signed-off-by: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com> Acked-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Mukesh Ojha <mojha@codeaurora.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Shawn Landden <shawn@git.icu> Cc: Song Liu <songliubraving@fb.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tzvetomir Stoyanov <tstoyanov@vmware.com> Link: http://lore.kernel.org/lkml/20190822071223.17892.45782.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-22 15:20:49 +08:00
return PTR_ERR(d->session);
}
has_br_stack = perf_header__has_feat(&d->session->header,
HEADER_BRANCH_STACK);
perf_session__delete(d->session);
if (!has_br_stack)
return 0;
}
/* Set only all files having branch stacks */
pdiff.has_br_stack = true;
return 0;
}
static int __cmd_diff(void)
{
struct data__file *d;
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
int ret, i;
char *abstime_ostr, *abstime_tmp;
ret = abstime_str_dup(&abstime_ostr);
if (ret)
return ret;
abstime_tmp = abstime_ostr;
ret = -EINVAL;
data__for_each_file(i, d) {
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
d->session = perf_session__new(&d->data, false, &pdiff.tool);
perf session: Return error code for perf_session__new() function on failure This patch is to return error code of perf_new_session function on failure instead of NULL. Test Results: Before Fix: $ perf c2c report -input failed to open nput: No such file or directory $ echo $? 0 $ After Fix: $ perf c2c report -input failed to open nput: No such file or directory $ echo $? 254 $ Committer notes: Fix 'perf tests topology' case, where we use that TEST_ASSERT_VAL(..., session), i.e. we need to pass zero in case of failure, which was the case before when NULL was returned by perf_session__new() for failure, but now we need to negate the result of IS_ERR(session) to respect that TEST_ASSERT_VAL) expectation of zero meaning failure. Reported-by: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com> Signed-off-by: Mamatha Inamdar <mamatha4@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Nageswara R Sastry <rnsastry@linux.vnet.ibm.com> Acked-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Mukesh Ojha <mojha@codeaurora.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Shawn Landden <shawn@git.icu> Cc: Song Liu <songliubraving@fb.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tzvetomir Stoyanov <tstoyanov@vmware.com> Link: http://lore.kernel.org/lkml/20190822071223.17892.45782.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-22 15:20:49 +08:00
if (IS_ERR(d->session)) {
ret = PTR_ERR(d->session);
pr_err("Failed to open %s\n", d->data.path);
goto out_delete;
}
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
if (pdiff.time_str) {
ret = parse_time_str(d, abstime_ostr, &abstime_tmp);
if (ret < 0)
goto out_delete;
}
if (cpu_list) {
ret = perf_session__cpu_bitmap(d->session, cpu_list,
cpu_bitmap);
if (ret < 0)
goto out_delete;
}
ret = perf_session__process_events(d->session);
if (ret) {
pr_err("Failed to process %s\n", d->data.path);
goto out_delete;
}
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
evlist__collapse_resort(d->session->evlist);
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
if (pdiff.ptime_range)
zfree(&pdiff.ptime_range);
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
if (compute == COMPUTE_STREAM) {
d->evlist_streams = evlist__create_streams(
d->session->evlist, 5);
if (!d->evlist_streams) {
ret = -ENOMEM;
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
goto out_delete;
}
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
}
}
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
if (compute == COMPUTE_STREAM)
stream_process();
else
data_process();
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
out_delete:
data__for_each_file(i, d) {
perf diff: Don't crash on freeing errno-session on the error path __cmd_diff() sets result of perf_session__new() to d->session. In case of failure, it's errno and perf-diff may crash with: failed to open perf.data: Permission denied Failed to open perf.data Segmentation fault (core dumped) From the coredump: 0 0x00005569a62b5955 in auxtrace__free (session=0xffffffffffffffff) at util/auxtrace.c:2681 1 0x00005569a626b37d in perf_session__delete (session=0xffffffffffffffff) at util/session.c:295 2 perf_session__delete (session=0xffffffffffffffff) at util/session.c:291 3 0x00005569a618008a in __cmd_diff () at builtin-diff.c:1239 4 cmd_diff (argc=<optimized out>, argv=<optimized out>) at builtin-diff.c:2011 [..] Funny enough, it won't always crash. For me it crashes only if failed file is second in cmd-line: the reason is that cmd_diff() check files for branch-stacks [in check_file_brstack()] and if the first file doesn't have brstacks, it doesn't proceed to try open other files from cmd-line. Check d->session before calling perf_session__delete(). Another solution would be assigning to temporary variable, checking it, but I find it easier to follow with IS_ERR() check in the same function. After some time it's still obvious why the check is needed, and with temp variable it's possible to make the same mistake. Committer testing: $ perf record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ] $ perf diff failed to open perf.data.old: No such file or directory Failed to open perf.data.old $ perf record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ] $ perf diff # Event 'cycles:u' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .......................... # 0.92% +87.66% [unknown] [k] 0xffffffff8825de16 11.39% +0.04% ld-2.32.so [.] __GI___tunables_init 87.70% ld-2.32.so [.] _dl_check_map_versions $ sudo chown root:root perf.data [sudo] password for acme: $ perf diff failed to open perf.data: Permission denied Failed to open perf.data Segmentation fault (core dumped) $ After the patch: $ perf diff failed to open perf.data: Permission denied Failed to open perf.data $ Signed-off-by: Dmitry Safonov <dima@arista.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: dmitry safonov <dima@arista.com> Link: http://lore.kernel.org/lkml/20210302023533.1572231-1-dima@arista.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-03-02 10:35:33 +08:00
if (!IS_ERR(d->session))
perf_session__delete(d->session);
data__free(d);
perf diff: Make diff command work with evsel hists Putting 'perf diff' command back on track with the 'latest' evsel hists changes. Each evsel has its own 'hists' object gathering stats for the particular event. While currently counts are accumulated for the whole session regardless of the events diversification within compared sessions. The 'perf diff' command now outputs all matching events within compared sessions (with event name specified). The per event diff output stays the same. $ ./perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +15.14% [kernel.kallsyms] [k] __wake_up 0.00% +13.38% [kernel.kallsyms] [k] ext4fs_dirhash ... SNIP 0.00% +0.42% [kernel.kallsyms] [k] local_clock 0.17% -0.05% [kernel.kallsyms] [k] native_write_msr_safe # Event 'faults' # # Baseline Delta Shared Object Symbol # ........ .......... ................. .............................. # 0.00% +79.12% ld-2.15.so [.] _dl_relocate_object 0.00% +11.62% ld-2.15.so [.] openaux Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1346946426-13496-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-06 23:46:55 +08:00
}
perf diff: Fix support for all --sort combinations When we finish creating the hist_entries we _already_ have them sorted "by name", in fact by what is in --sort, that is exactly how we can find the pairs in perf_session__match_hists as 'comm', 'dso' & 'symbol' all are strings we need to find the matches in the baseline session. So only do the sort by hits followed by a resort by --sort if we need to find the position for shwowing the --displacement of hist entries. Now all these modes work correctly: Example is a simple 'perf record -f find / > /dev/null' ran twice then followed by the following commands: $ perf diff -f --sort comm # Baseline Delta Command # ........ .......... ....... # 0.00% +100.00% find $ perf diff -f --sort dso # Baseline Delta Shared Object # ........ .......... .................. # 59.97% -0.44% [kernel] 21.17% +0.28% libc-2.5.so 18.49% +0.16% [ext3] 0.37% find $ perf diff -f --sort symbol | head -8 # Baseline Delta Symbol # ........ .......... ...... # 6.21% +0.36% [k] ext3fs_dirhash 3.43% +0.41% [.] __GI_strlen 3.53% +0.16% [k] __kmalloc 3.17% +0.49% [k] system_call 3.06% +0.37% [k] ext3_htree_store_dirent $ perf diff -f --sort dso,symbol | head -8 # Baseline Delta Shared Object Symbol # ........ .......... .................. ...... # 6.21% +0.36% [ext3] [k] ext3fs_dirhash 3.43% +0.41% libc-2.5.so [.] __GI_strlen 3.53% +0.16% [kernel] [k] __kmalloc 3.17% +0.49% [kernel] [k] system_call 3.06% +0.37% [ext3] [k] ext3_htree_store_dirent $ And we don't have to do two expensive resorts in the common, non --displacement case. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1262047716-23171-5-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-29 08:48:36 +08:00
free(data__files);
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
if (pdiff.ptime_range)
zfree(&pdiff.ptime_range);
if (abstime_ostr)
free(abstime_ostr);
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
return ret;
}
static const char * const diff_usage[] = {
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
"perf diff [<options>] [old_file] [new_file]",
NULL,
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
};
static const struct option options[] = {
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
OPT_INCR('v', "verbose", &verbose,
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
"be more verbose (show symbol address, etc)"),
perf diff: Add -q/--quiet option The -q/--quiet option is to suppress any message. Sometimes users just want to see the numbers and it can be used for that case. Committer notes: Before: # perf diff | head -10 Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-2646.map, continuing without symbols # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... .......................... ............................................ # 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 After: # perf diff -q | head -10 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 1.86% +0.95% [kernel.vmlinux] [k] update_blocked_averages 0.80% -0.70% [kernel.vmlinux] [k] native_sched_clock 0.74% -0.58% [kernel.vmlinux] [k] native_write_msr 0.76% -0.56% qemu-system-x86_64 [.] 0x00000000002395c0 +0.54% libpulsecommon-10.0.so [.] 0x000000000002d91b # Signed-off-by: Namhyung Kim <namhyung@kernel.org> Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170217081742.17417-5-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-17 16:17:40 +08:00
OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
"Show only items with match in baseline"),
OPT_CALLBACK('c', "compute", &compute,
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
"delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs),cycles",
"Entries differential computation selection",
setup_compute),
OPT_BOOLEAN('p', "period", &show_period,
"Show period values."),
OPT_BOOLEAN('F', "formula", &show_formula,
"Show formula."),
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
OPT_BOOLEAN(0, "cycles-hist", &cycles_hist,
"Show cycles histogram and standard deviation "
"- WARNING: use only with -c cycles."),
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
"file", "kallsyms pathname"),
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
"load module symbols - WARNING: use only with -k and LIVE kernel"),
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
"only consider symbols in these comms"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
"only consider these symbols"),
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 23:49:27 +08:00
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline, ..."
" Please refer the man page for the complete list."),
OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator",
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 23:49:27 +08:00
"separator for columns, no spaces will be added between "
"columns '.' is reserved."),
OPT_CALLBACK(0, "symfs", NULL, "directory",
"Look for files with symbols relative to this directory",
symbol__config_symfs),
OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
"How to display percentage of filtered entries", parse_filter_percentage),
perf diff: Support --time filter option To improve 'perf diff', implement a --time filter option to diff the samples within given time window. It supports time percent with multiple time ranges. The time string format is 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'. For example: Select the second 10% time slice to diff: perf diff --time 10%/2 Select from 0% to 10% time slice to diff: perf diff --time 0%-10% Select the first and the second 10% time slices to diff: perf diff --time 10%/1,10%/2 Select from 0% to 10% and 30% to 40% slices to diff: perf diff --time 0%-10%,30%-40% It also supports analysing samples within a given time window <start>,<stop>. Times have the format seconds.microseconds. If 'start' is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If the stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. Time string is 'a1.b1,c1.d1:a2.b2,c2.d2'. Use ':' to separate timestamps for different perf.data files. For example, we get the timestamp information from perf script. perf script -i perf.data.old mgen 13940 [000] 3946.361400: ... perf script -i perf.data mgen 13940 [000] 3971.150589 ... perf diff --time 3946.361400,:3971.150589, It analyzes the perf.data.old from the timestamp 3946.361400 to the end of perf.data.old and analyzes the perf.data from the timestamp 3971.150589 to the end of perf.data. v4: --- Update abstime_str_dup(), let it return error if strdup is failed, and update __cmd_diff() accordingly. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1551791143-10334-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-05 21:05:41 +08:00
OPT_STRING(0, "time", &pdiff.time_str, "str",
"Time span (time percent or absolute timestamp)"),
OPT_STRING(0, "cpu", &cpu_list, "cpu", "list of cpus to profile"),
OPT_STRING(0, "pid", &symbol_conf.pid_list_str, "pid[,pid...]",
"only consider symbols in these pids"),
OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
"only consider symbols in these tids"),
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
OPT_BOOLEAN(0, "stream", &pdiff.stream,
"Enable hot streams comparison."),
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
OPT_END()
};
static double baseline_percent(struct hist_entry *he)
{
u64 total = hists__total_period(he->hists);
return 100.0 * he->stat.period / total;
}
static int hpp__color_baseline(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he)
{
struct diff_hpp_fmt *dfmt =
container_of(fmt, struct diff_hpp_fmt, fmt);
double percent = baseline_percent(he);
char pfmt[20] = " ";
if (!he->dummy) {
scnprintf(pfmt, 20, "%%%d.2f%%%%", dfmt->header_width - 1);
return percent_color_snprintf(hpp->buf, hpp->size,
pfmt, percent);
} else
return scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, pfmt);
}
static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size)
{
double percent = baseline_percent(he);
const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
int ret = 0;
if (!he->dummy)
ret = scnprintf(buf, size, fmt, percent);
return ret;
}
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
static int cycles_printf(struct hist_entry *he, struct hist_entry *pair,
struct perf_hpp *hpp, int width)
{
struct block_hist *bh = container_of(he, struct block_hist, he);
struct block_hist *bh_pair = container_of(pair, struct block_hist, he);
struct hist_entry *block_he;
struct block_info *bi;
char buf[128];
char *start_line, *end_line;
block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx);
if (!block_he) {
hpp->skip = true;
return 0;
}
/*
* Avoid printing the warning "addr2line_init failed for ..."
*/
symbol_conf.disable_add2line_warn = true;
bi = block_he->block_info;
start_line = map__srcline(he->ms.map, bi->sym->start + bi->start,
he->ms.sym);
end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
he->ms.sym);
perf diff: Fix undefined string comparison spotted by clang's -Wstring-compare clang warns: util/block-info.c:298:18: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:51: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:18: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:51: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/map.c:434:15: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if (srcline != SRCLINE_UNKNOWN) ^ ~~~~~~~~~~~~~~~ Reviewer Notes: Looks good to me. Some more context: https://clang.llvm.org/docs/DiagnosticsReference.html#wstring-compare The spec says: J.1 Unspecified behavior The following are unspecified: .. Whether two string literals result in distinct arrays (6.4.5). Signed-off-by: Nick Desaulniers <nick.desaulniers@gmail.com> Reviewed-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Changbin Du <changbin.du@intel.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Keeping <john@metanate.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: clang-built-linux@googlegroups.com Link: https://github.com/ClangBuiltLinux/linux/issues/900 Link: http://lore.kernel.org/lkml/20200223193456.25291-1-nick.desaulniers@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-24 03:34:49 +08:00
if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) &&
(strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) {
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld",
start_line, end_line, block_he->diff.cycles);
} else {
scnprintf(buf, sizeof(buf), "[%7lx -> %7lx] %4ld",
bi->start, bi->end, block_he->diff.cycles);
}
free_srcline(start_line);
free_srcline(end_line);
return scnprintf(hpp->buf, hpp->size, "%*s", width, buf);
}
static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he,
int comparison_method)
{
struct diff_hpp_fmt *dfmt =
container_of(fmt, struct diff_hpp_fmt, fmt);
struct hist_entry *pair = get_pair_fmt(he, dfmt);
double diff;
s64 wdiff;
char pfmt[20] = " ";
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
if (!pair) {
if (comparison_method == COMPUTE_CYCLES) {
struct block_hist *bh;
bh = container_of(he, struct block_hist, he);
if (bh->block_idx)
hpp->skip = true;
}
perf diff: Print diff result more precisely Current perf diff result is somewhat confusing since it sometimes hide small result and sometimes there's no result. So do not hide small result (less than 0.01%) and print "N/A" if baseline is not recorded (for ratio and wdiff only). Blank means the baseline is available but its pairs are not. Before: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt [kernel.kallsyms] [k] read_tsc After: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock +0.01% [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:31 +08:00
goto no_print;
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
}
switch (comparison_method) {
case COMPUTE_DELTA:
if (pair->diff.computed)
diff = pair->diff.period_ratio_delta;
else
diff = compute_delta(he, pair);
scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1);
return percent_color_snprintf(hpp->buf, hpp->size,
pfmt, diff);
case COMPUTE_RATIO:
if (he->dummy)
goto dummy_print;
if (pair->diff.computed)
diff = pair->diff.period_ratio;
else
diff = compute_ratio(he, pair);
scnprintf(pfmt, 20, "%%%d.6f", dfmt->header_width);
return value_color_snprintf(hpp->buf, hpp->size,
pfmt, diff);
case COMPUTE_WEIGHTED_DIFF:
if (he->dummy)
goto dummy_print;
if (pair->diff.computed)
wdiff = pair->diff.wdiff;
else
wdiff = compute_wdiff(he, pair);
scnprintf(pfmt, 20, "%%14ld", dfmt->header_width);
return color_snprintf(hpp->buf, hpp->size,
get_percent_color(wdiff),
pfmt, wdiff);
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
case COMPUTE_CYCLES:
return cycles_printf(he, pair, hpp, dfmt->header_width);
default:
BUG_ON(1);
}
dummy_print:
perf diff: Print diff result more precisely Current perf diff result is somewhat confusing since it sometimes hide small result and sometimes there's no result. So do not hide small result (less than 0.01%) and print "N/A" if baseline is not recorded (for ratio and wdiff only). Blank means the baseline is available but its pairs are not. Before: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt [kernel.kallsyms] [k] read_tsc After: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock +0.01% [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:31 +08:00
return scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, "N/A");
no_print:
return scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, pfmt);
}
static int hpp__color_delta(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he)
{
return __hpp__color_compare(fmt, hpp, he, COMPUTE_DELTA);
}
static int hpp__color_ratio(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he)
{
return __hpp__color_compare(fmt, hpp, he, COMPUTE_RATIO);
}
static int hpp__color_wdiff(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he)
{
return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF);
}
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
static int hpp__color_cycles(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he)
{
return __hpp__color_compare(fmt, hpp, he, COMPUTE_CYCLES);
}
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
static int all_zero(unsigned long *vals, int len)
{
int i;
for (i = 0; i < len; i++)
if (vals[i] != 0)
return 0;
return 1;
}
static int print_cycles_spark(char *bf, int size, unsigned long *svals, u64 n)
{
int printed;
if (n <= 1)
return 0;
if (n > NUM_SPARKS)
n = NUM_SPARKS;
if (all_zero(svals, n))
return 0;
printed = print_spark(bf, size, svals, n);
printed += scnprintf(bf + printed, size - printed, " ");
return printed;
}
static int hpp__color_cycles_hist(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp, struct hist_entry *he)
{
struct diff_hpp_fmt *dfmt =
container_of(fmt, struct diff_hpp_fmt, fmt);
struct hist_entry *pair = get_pair_fmt(he, dfmt);
struct block_hist *bh = container_of(he, struct block_hist, he);
struct block_hist *bh_pair;
struct hist_entry *block_he;
char spark[32], buf[128];
double r;
int ret, pad;
if (!pair) {
if (bh->block_idx)
hpp->skip = true;
goto no_print;
}
bh_pair = container_of(pair, struct block_hist, he);
block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx);
if (!block_he) {
hpp->skip = true;
goto no_print;
}
ret = print_cycles_spark(spark, sizeof(spark), block_he->diff.svals,
block_he->diff.stats.n);
r = rel_stddev_stats(stddev_stats(&block_he->diff.stats),
avg_stats(&block_he->diff.stats));
if (ret) {
/*
* Padding spaces if number of sparks less than NUM_SPARKS
* otherwise the output is not aligned.
*/
pad = NUM_SPARKS - ((ret - 1) / 3);
scnprintf(buf, sizeof(buf), "%s%5.1f%% %s", "\u00B1", r, spark);
ret = scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, buf);
if (pad) {
ret += scnprintf(hpp->buf + ret, hpp->size - ret,
"%-*s", pad, " ");
}
return ret;
}
no_print:
return scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, " ");
}
static void
hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
{
switch (idx) {
case PERF_HPP_DIFF__PERIOD_BASELINE:
scnprintf(buf, size, "%" PRIu64, he->stat.period);
break;
default:
break;
}
}
static void
hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
int idx, char *buf, size_t size)
{
double diff;
double ratio;
s64 wdiff;
switch (idx) {
case PERF_HPP_DIFF__DELTA:
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
case PERF_HPP_DIFF__DELTA_ABS:
if (pair->diff.computed)
diff = pair->diff.period_ratio_delta;
else
diff = compute_delta(he, pair);
perf diff: Print diff result more precisely Current perf diff result is somewhat confusing since it sometimes hide small result and sometimes there's no result. So do not hide small result (less than 0.01%) and print "N/A" if baseline is not recorded (for ratio and wdiff only). Blank means the baseline is available but its pairs are not. Before: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt [kernel.kallsyms] [k] read_tsc After: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock +0.01% [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:31 +08:00
scnprintf(buf, size, "%+4.2F%%", diff);
break;
case PERF_HPP_DIFF__RATIO:
/* No point for ratio number if we are dummy.. */
perf diff: Print diff result more precisely Current perf diff result is somewhat confusing since it sometimes hide small result and sometimes there's no result. So do not hide small result (less than 0.01%) and print "N/A" if baseline is not recorded (for ratio and wdiff only). Blank means the baseline is available but its pairs are not. Before: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt [kernel.kallsyms] [k] read_tsc After: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock +0.01% [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:31 +08:00
if (he->dummy) {
scnprintf(buf, size, "N/A");
break;
perf diff: Print diff result more precisely Current perf diff result is somewhat confusing since it sometimes hide small result and sometimes there's no result. So do not hide small result (less than 0.01%) and print "N/A" if baseline is not recorded (for ratio and wdiff only). Blank means the baseline is available but its pairs are not. Before: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt [kernel.kallsyms] [k] read_tsc After: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock +0.01% [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:31 +08:00
}
if (pair->diff.computed)
ratio = pair->diff.period_ratio;
else
ratio = compute_ratio(he, pair);
if (ratio > 0.0)
scnprintf(buf, size, "%14.6F", ratio);
break;
case PERF_HPP_DIFF__WEIGHTED_DIFF:
/* No point for wdiff number if we are dummy.. */
perf diff: Print diff result more precisely Current perf diff result is somewhat confusing since it sometimes hide small result and sometimes there's no result. So do not hide small result (less than 0.01%) and print "N/A" if baseline is not recorded (for ratio and wdiff only). Blank means the baseline is available but its pairs are not. Before: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt [kernel.kallsyms] [k] read_tsc After: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock +0.01% [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:31 +08:00
if (he->dummy) {
scnprintf(buf, size, "N/A");
break;
perf diff: Print diff result more precisely Current perf diff result is somewhat confusing since it sometimes hide small result and sometimes there's no result. So do not hide small result (less than 0.01%) and print "N/A" if baseline is not recorded (for ratio and wdiff only). Blank means the baseline is available but its pairs are not. Before: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt [kernel.kallsyms] [k] read_tsc After: # Baseline Delta Shared Object Symbol # ........ ....... ................. ......................... # ... 0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 0.01% [kernel.kallsyms] [k] scheduler_tick 0.01% [kernel.kallsyms] [k] native_read_msr_safe 0.00% [kernel.kallsyms] [k] __rcu_read_unlock +0.01% [kernel.kallsyms] [k] _raw_spin_lock +0.01% [kernel.kallsyms] [k] apic_timer_interrupt +0.01% [kernel.kallsyms] [k] read_tsc Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:31 +08:00
}
if (pair->diff.computed)
wdiff = pair->diff.wdiff;
else
wdiff = compute_wdiff(he, pair);
if (wdiff != 0)
scnprintf(buf, size, "%14ld", wdiff);
break;
case PERF_HPP_DIFF__FORMULA:
formula_fprintf(he, pair, buf, size);
break;
case PERF_HPP_DIFF__PERIOD:
scnprintf(buf, size, "%" PRIu64, pair->stat.period);
break;
default:
BUG_ON(1);
}
}
static void
__hpp__entry_global(struct hist_entry *he, struct diff_hpp_fmt *dfmt,
char *buf, size_t size)
{
struct hist_entry *pair = get_pair_fmt(he, dfmt);
int idx = dfmt->idx;
/* baseline is special */
if (idx == PERF_HPP_DIFF__BASELINE)
hpp__entry_baseline(he, buf, size);
else {
if (pair)
hpp__entry_pair(he, pair, idx, buf, size);
else
hpp__entry_unpair(he, idx, buf, size);
}
}
static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
struct hist_entry *he)
{
struct diff_hpp_fmt *dfmt =
container_of(_fmt, struct diff_hpp_fmt, fmt);
char buf[MAX_COL_WIDTH] = " ";
__hpp__entry_global(he, dfmt, buf, MAX_COL_WIDTH);
if (symbol_conf.field_sep)
return scnprintf(hpp->buf, hpp->size, "%s", buf);
else
return scnprintf(hpp->buf, hpp->size, "%*s",
dfmt->header_width, buf);
}
static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hists *hists __maybe_unused,
int line __maybe_unused,
int *span __maybe_unused)
{
struct diff_hpp_fmt *dfmt =
container_of(fmt, struct diff_hpp_fmt, fmt);
BUG_ON(!dfmt->header);
return scnprintf(hpp->buf, hpp->size, dfmt->header);
}
static int hpp__width(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp __maybe_unused,
struct hists *hists __maybe_unused)
{
struct diff_hpp_fmt *dfmt =
container_of(fmt, struct diff_hpp_fmt, fmt);
BUG_ON(dfmt->header_width <= 0);
return dfmt->header_width;
}
static void init_header(struct data__file *d, struct diff_hpp_fmt *dfmt)
{
#define MAX_HEADER_NAME 100
char buf_indent[MAX_HEADER_NAME];
char buf[MAX_HEADER_NAME];
const char *header = NULL;
int width = 0;
BUG_ON(dfmt->idx >= PERF_HPP_DIFF__MAX_INDEX);
header = columns[dfmt->idx].name;
width = columns[dfmt->idx].width;
/* Only our defined HPP fmts should appear here. */
BUG_ON(!header);
if (data__files_cnt > 2)
scnprintf(buf, MAX_HEADER_NAME, "%s/%d", header, d->idx);
#define NAME (data__files_cnt > 2 ? buf : header)
dfmt->header_width = width;
width = (int) strlen(NAME);
if (dfmt->header_width < width)
dfmt->header_width = width;
scnprintf(buf_indent, MAX_HEADER_NAME, "%*s",
dfmt->header_width, NAME);
dfmt->header = strdup(buf_indent);
#undef MAX_HEADER_NAME
#undef NAME
}
static void data__hpp_register(struct data__file *d, int idx)
{
struct diff_hpp_fmt *dfmt = &d->fmt[idx];
struct perf_hpp_fmt *fmt = &dfmt->fmt;
dfmt->idx = idx;
fmt->header = hpp__header;
fmt->width = hpp__width;
fmt->entry = hpp__entry_global;
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
fmt->cmp = hist_entry__cmp_nop;
fmt->collapse = hist_entry__cmp_nop;
/* TODO more colors */
switch (idx) {
case PERF_HPP_DIFF__BASELINE:
fmt->color = hpp__color_baseline;
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
fmt->sort = hist_entry__cmp_baseline;
break;
case PERF_HPP_DIFF__DELTA:
fmt->color = hpp__color_delta;
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
fmt->sort = hist_entry__cmp_delta;
break;
case PERF_HPP_DIFF__RATIO:
fmt->color = hpp__color_ratio;
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
fmt->sort = hist_entry__cmp_ratio;
break;
case PERF_HPP_DIFF__WEIGHTED_DIFF:
fmt->color = hpp__color_wdiff;
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
fmt->sort = hist_entry__cmp_wdiff;
break;
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
case PERF_HPP_DIFF__DELTA_ABS:
fmt->color = hpp__color_delta;
fmt->sort = hist_entry__cmp_delta_abs;
break;
perf diff: Print the basic block cycles diff $ perf record -b ./div $ perf record -b ./div Following is the default perf diff output $ perf diff # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... ................ .................................. # 48.75% +0.33% div [.] main 8.21% -0.20% div [.] compute_flag 19.02% -0.12% libc-2.23.so [.] __random_r 16.17% -0.09% libc-2.23.so [.] __random 2.27% -0.03% div [.] rand@plt +0.02% [i915] [k] gen8_irq_handler 5.52% +0.02% libc-2.23.so [.] rand This patch creates a new computation selection 'cycles'. $ perf diff -c cycles # Event 'cycles' # # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ ....................................... ......................................... # 48.75% [div.c:42 -> div.c:45] 147 div [.] main 48.75% [div.c:31 -> div.c:40] 4 div [.] main 48.75% [div.c:40 -> div.c:40] 0 div [.] main 48.75% [div.c:42 -> div.c:42] 0 div [.] main 48.75% [div.c:42 -> div.c:44] 0 div [.] main 19.02% [random_r.c:357 -> random_r.c:360] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:373] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:376] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:380] 0 libc-2.23.so [.] __random_r 19.02% [random_r.c:357 -> random_r.c:392] 0 libc-2.23.so [.] __random_r 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:295] 0 libc-2.23.so [.] __random 16.17% [random.c:288 -> random.c:297] 0 libc-2.23.so [.] __random 16.17% [random.c:291 -> random.c:291] 0 libc-2.23.so [.] __random 16.17% [random.c:293 -> random.c:293] 0 libc-2.23.so [.] __random 8.21% [div.c:22 -> div.c:22] 148 div [.] compute_flag 8.21% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.21% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.52% [rand.c:26 -> rand.c:27] 0 libc-2.23.so [.] rand 5.52% [rand.c:26 -> rand.c:28] 0 libc-2.23.so [.] rand 2.27% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.01% [entry_64.S:694 -> entry_64.S:694] 16 [vmlinux] [k] native_irq_return_iret 0.00% [fair.c:7676 -> fair.c:7665] 162 [vmlinux] [k] update_blocked_averages "[Program Block Range]" indicates the range of program basic block (start -> end). If we can find the source line it prints the source line otherwise it prints the symbol+offset instead. v4: --- Use source lines or symbol+offset to indicate the basic block. It should be easier to understand. v3: --- Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf. Use symbol_conf.report_block to check if executing hist_entry__block_fprintf. v2: --- Keep standard perf diff format and display the 'Baseline' and 'Shared Object'. The output is sorted by "Baseline" and the basic blocks in the same function are sorted by cycles diff. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:03 +08:00
case PERF_HPP_DIFF__CYCLES:
fmt->color = hpp__color_cycles;
fmt->sort = hist_entry__cmp_nop;
break;
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
case PERF_HPP_DIFF__CYCLES_HIST:
fmt->color = hpp__color_cycles_hist;
fmt->sort = hist_entry__cmp_nop;
break;
default:
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
fmt->sort = hist_entry__cmp_nop;
break;
}
init_header(d, dfmt);
perf_hpp__column_register(fmt);
perf diff: Fix to sort by baseline field by default The currently perf diff didn't add the baseline and delta (or other compute) fields to the sort list so output will be sorted by other fields like alphabetical order of DSO or symbol as below example. Fix it by adding hpp formats for the fields and provides default compare functions. Before: $ perf diff # Event 'cycles' # # Baseline Delta Shared Object Symbol # ........ ....... .................. ............................... # [bridge] [k] ip_sabotage_in [btrfs] [k] __etree_search.constprop.47 0.01% [btrfs] [k] btrfs_file_mmap 0.01% -0.01% [btrfs] [k] btrfs_getattr [e1000e] [k] e1000_watchdog 0.00% [kernel.vmlinux] [k] PageHuge 0.00% [kernel.vmlinux] [k] __acct_update_integrals 0.00% [kernel.vmlinux] [k] __activate_page [kernel.vmlinux] [k] __alloc_fd 0.02% +0.02% [kernel.vmlinux] [k] __alloc_pages_nodemask ... After: # Baseline Delta Shared Object Symbol # ........ ....... .................. ................................ # 24.73% -4.62% perf [.] append_chain_children 7.96% -1.29% perf [.] dso__find_symbol 6.97% -2.07% libc-2.20.so [.] vfprintf 4.61% +0.88% libc-2.20.so [.] __fprintf_chk 4.41% +2.43% perf [.] sort__comm_cmp 4.10% -0.16% perf [.] comm__str 4.03% -0.93% perf [.] machine__findnew_thread_time 3.82% +3.09% perf [.] __hists__add_entry 2.95% -0.18% perf [.] sort__dso_cmp ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1419656793-32756-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-12-27 13:06:29 +08:00
perf_hpp__register_sort_field(fmt);
}
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
static int ui_init(void)
{
struct data__file *d;
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
struct perf_hpp_fmt *fmt;
int i;
data__for_each_file(i, d) {
/*
* Baseline or compute realted columns:
*
* PERF_HPP_DIFF__BASELINE
* PERF_HPP_DIFF__DELTA
* PERF_HPP_DIFF__RATIO
* PERF_HPP_DIFF__WEIGHTED_DIFF
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
* PERF_HPP_DIFF__CYCLES
*/
data__hpp_register(d, i ? compute_2_hpp[compute] :
PERF_HPP_DIFF__BASELINE);
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
if (cycles_hist && i)
data__hpp_register(d, PERF_HPP_DIFF__CYCLES_HIST);
/*
* And the rest:
*
* PERF_HPP_DIFF__FORMULA
* PERF_HPP_DIFF__PERIOD
* PERF_HPP_DIFF__PERIOD_BASELINE
*/
if (show_formula && i)
data__hpp_register(d, PERF_HPP_DIFF__FORMULA);
if (show_period)
data__hpp_register(d, i ? PERF_HPP_DIFF__PERIOD :
PERF_HPP_DIFF__PERIOD_BASELINE);
}
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
if (!sort_compute)
return 0;
/*
* Prepend an fmt to sort on columns at 'sort_compute' first.
* This fmt is added only to the sort list but not to the
* output fields list.
*
* Note that this column (data) can be compared twice - one
* for this 'sort_compute' fmt and another for the normal
* diff_hpp_fmt. But it shouldn't a problem as most entries
* will be sorted out by first try or baseline and comparing
* is not a costly operation.
*/
fmt = zalloc(sizeof(*fmt));
if (fmt == NULL) {
pr_err("Memory allocation failed\n");
return -1;
}
fmt->cmp = hist_entry__cmp_nop;
fmt->collapse = hist_entry__cmp_nop;
switch (compute) {
case COMPUTE_DELTA:
fmt->sort = hist_entry__cmp_delta_idx;
break;
case COMPUTE_RATIO:
fmt->sort = hist_entry__cmp_ratio_idx;
break;
case COMPUTE_WEIGHTED_DIFF:
fmt->sort = hist_entry__cmp_wdiff_idx;
break;
perf diff: Add 'delta-abs' compute method The 'delta-abs' compute method is same as 'delta' but shows entries with bigger absolute delta first instead of sorting numerically. This is only useful together with -o option. Below is default output (-c delta): $ perf diff -o 1 -c delta | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock +1.15% [kernel.kallsyms] [k] copy_user_generic_string 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk +0.64% [kernel.kallsyms] [k] kmem_cache_alloc 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock +0.45% [kernel.kallsyms] [k] alloc_set_pte 0.16% +0.45% [kernel.kallsyms] [k] menu_select +0.41% ld-2.24.so [.] do_lookup_x Now with 'delta-abs' it shows entries have bigger delta value either positive or negative. $ perf diff -o 1 -c delta-abs | grep -v ^# | head 42.22% +4.97% [kernel.kallsyms] [k] cfb_imageblit 12.72% -3.01% [kernel.kallsyms] [k] intel_idle 9.72% -1.31% [unknown] [.] 0x0000000000411343 0.62% +1.23% [kernel.kallsyms] [k] mutex_lock 2.40% +0.95% [kernel.kallsyms] [k] bit_putcs 0.31% +0.79% [kernel.kallsyms] [k] link_path_walk 1.35% -0.71% [kernel.kallsyms] [k] smp_call_function_single 0.00% +0.57% [kernel.kallsyms] [k] __rcu_read_unlock 0.16% +0.45% [kernel.kallsyms] [k] menu_select 0.72% -0.44% [kernel.kallsyms] [k] lookup_fast Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170210073614.24584-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-10 15:36:11 +08:00
case COMPUTE_DELTA_ABS:
fmt->sort = hist_entry__cmp_delta_abs_idx;
break;
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
case COMPUTE_CYCLES:
/*
* Should set since 'fmt->sort' is called without
* checking valid during sorting
*/
fmt->sort = hist_entry__cmp_nop;
break;
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
default:
BUG_ON(1);
}
perf_hpp__prepend_sort_field(fmt);
perf diff: Fix -o/--order option behavior The prior change fixes default output ordering with each column but it breaks -o/--order option. This patch prepends a new hpp fmt struct to sort list but not to output field list so that it can affect ordering without adding a new output column. The new hpp fmt uses its own compare functions which treats dummy entries (which have no baseline) little differently - the delta field can be computed without baseline but others (ratio and wdiff) are not. The new output will look like below: $ perf diff -o 2 perf.data.{old,cur,new} ... # Baseline/0 Delta/1 Delta/2 Shared Object Symbol # .......... ....... ....... ................. .......................................... 22.98% +0.51% +0.52% libc-2.20.so [.] _int_malloc 5.70% +0.28% +0.30% libc-2.20.so [.] free 4.38% -0.21% +0.25% a.out [.] main 1.32% -0.15% +0.05% a.out [.] free@plt +0.01% [kernel.kallsyms] [k] intel_pstate_timer_func +0.01% [kernel.kallsyms] [k] _raw_spin_lock_irqsave +0.01% [kernel.kallsyms] [k] timekeeping_update.constprop.8 +0.01% +0.01% [kernel.kallsyms] [k] apic_timer_interrupt 0.01% -0.00% [kernel.kallsyms] [k] native_read_msr_safe 0.01% -0.01% -0.01% [kernel.kallsyms] [k] native_write_msr_safe 1.31% +0.03% -0.06% a.out [.] malloc@plt 31.50% -0.74% -0.23% libc-2.20.so [.] _int_free 32.75% +0.28% -0.83% libc-2.20.so [.] malloc 0.01% [kernel.kallsyms] [k] scheduler_tick +0.01% [kernel.kallsyms] [k] read_tsc +0.01% [kernel.kallsyms] [k] perf_adjust_freq_unthr_context.part.82 In above example, the output was sorted by 'Delta/2' column first, and then 'Baseline/0' and finally 'Delta/1'. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1420677949-6719-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-01-08 08:45:48 +08:00
return 0;
}
static int data_init(int argc, const char **argv)
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
{
struct data__file *d;
static const char *defaults[] = {
"perf.data.old",
"perf.data",
};
bool use_default = true;
int i;
data__files_cnt = 2;
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
if (argc) {
if (argc == 1)
defaults[1] = argv[0];
else {
data__files_cnt = argc;
use_default = false;
}
} else if (perf_guest) {
defaults[0] = "perf.data.host";
defaults[1] = "perf.data.guest";
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
}
if (sort_compute >= (unsigned int) data__files_cnt) {
pr_err("Order option out of limit.\n");
return -EINVAL;
}
data__files = zalloc(sizeof(*data__files) * data__files_cnt);
if (!data__files)
return -ENOMEM;
data__for_each_file(i, d) {
struct perf_data *data = &d->data;
data->path = use_default ? defaults[i] : argv[i];
data->mode = PERF_DATA_MODE_READ,
data->force = force,
d->idx = i;
}
return 0;
}
static int diff__config(const char *var, const char *value,
void *cb __maybe_unused)
{
if (!strcmp(var, "diff.order")) {
int ret;
if (perf_config_int(&ret, var, value) < 0)
return -1;
sort_compute = ret;
return 0;
}
if (!strcmp(var, "diff.compute")) {
if (!strcmp(value, "delta")) {
compute = COMPUTE_DELTA;
} else if (!strcmp(value, "delta-abs")) {
compute = COMPUTE_DELTA_ABS;
} else if (!strcmp(value, "ratio")) {
compute = COMPUTE_RATIO;
} else if (!strcmp(value, "wdiff")) {
compute = COMPUTE_WEIGHTED_DIFF;
} else {
pr_err("Invalid compute method: %s\n", value);
return -1;
}
}
return 0;
}
int cmd_diff(int argc, const char **argv)
{
int ret = hists__init();
if (ret < 0)
return ret;
perf_config(diff__config, NULL);
argc = parse_options(argc, argv, options, diff_usage, 0);
perf diff: Add -q/--quiet option The -q/--quiet option is to suppress any message. Sometimes users just want to see the numbers and it can be used for that case. Committer notes: Before: # perf diff | head -10 Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-6678.map, continuing without symbols Failed to open /tmp/perf-2646.map, continuing without symbols # Event 'cycles' # # Baseline Delta Abs Shared Object Symbol # ........ ......... .......................... ............................................ # 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 After: # perf diff -q | head -10 5.36% -1.76% [kernel.vmlinux] [k] intel_idle 2.80% +1.48% firefox [.] 0x00000000000101fe 57.12% -1.25% libxul.so [.] 0x00000000009bea92 1.36% -1.11% [kernel.vmlinux] [k] __schedule 4.26% -1.00% perf-6678.map [.] 0x00007fac4b0e9320 1.86% +0.95% [kernel.vmlinux] [k] update_blocked_averages 0.80% -0.70% [kernel.vmlinux] [k] native_sched_clock 0.74% -0.58% [kernel.vmlinux] [k] native_write_msr 0.76% -0.56% qemu-system-x86_64 [.] 0x00000000002395c0 +0.54% libpulsecommon-10.0.so [.] 0x000000000002d91b # Signed-off-by: Namhyung Kim <namhyung@kernel.org> Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170217081742.17417-5-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-02-17 16:17:40 +08:00
if (quiet)
perf_quiet_option();
perf diff: Report noisy for cycles diff This patch prints the stddev and hist for the cycles diff of program block. It can help us to understand if the cycles is noisy or not. This patch is inspired by Andi Kleen's patch: https://lwn.net/Articles/600471/ We create new option '--cycles-hist'. Example: perf record -b ./div perf record -b ./div perf diff -c cycles # Baseline [Program Block Range] Cycles Diff Shared Object Symbol # ........ .......................................................... .... ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 div [.] main 46.72% [div.c:42 -> div.c:44] 0 div [.] main 46.72% [div.c:42 -> div.c:39] 0 div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 [kernel.kallsyms] [k] native_write_msr When we enable the option '--cycles-hist', the output is perf diff -c cycles --cycles-hist # Baseline [Program Block Range] Cycles Diff stddev/Hist Shared Object Symbol # ........ .......................................................... .... ................. ................. ............................ # 46.72% [div.c:40 -> div.c:40] 0 ± 37.8% ▁█▁▁██▁█ div [.] main 46.72% [div.c:42 -> div.c:44] 0 ± 49.4% ▁▁▂█▂▂▂▂ div [.] main 46.72% [div.c:42 -> div.c:39] 0 ± 24.1% ▃█▂▄▁▃▂▁ div [.] main 20.54% [random_r.c:357 -> random_r.c:394] 1 ± 33.5% ▅▂▁█▃▁▂▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:357 -> random_r.c:380] 0 ± 39.4% ▁▁█▁██▅▁ libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:388] 0 libc-2.27.so [.] __random_r 20.54% [random_r.c:388 -> random_r.c:391] 0 ± 41.2% ▁▃▁▂█▄▃▁ libc-2.27.so [.] __random_r 17.04% [random.c:288 -> random.c:291] 0 ± 48.8% ▁▁▁▁███▁ libc-2.27.so [.] __random 17.04% [random.c:291 -> random.c:291] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:293 -> random.c:293] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 ±100.0% ▁█▁▁▁▁▁▁ libc-2.27.so [.] __random 17.04% [random.c:295 -> random.c:295] 0 libc-2.27.so [.] __random 17.04% [random.c:298 -> random.c:298] 0 ± 75.6% ▃█▁▁▁▁▁▁ libc-2.27.so [.] __random 8.40% [div.c:22 -> div.c:25] 0 ± 42.1% ▁▃▁▁███▁ div [.] compute_flag 8.40% [div.c:27 -> div.c:28] 0 ± 41.8% ██▁▁▄▁▁▄ div [.] compute_flag 5.14% [rand.c:26 -> rand.c:27] 0 ± 37.8% ▁▁▁████▁ libc-2.27.so [.] rand 5.14% [rand.c:28 -> rand.c:28] 0 libc-2.27.so [.] rand 2.15% [rand@plt+0 -> rand@plt+0] 0 div [.] rand@plt 0.00% [kernel.kallsyms] [k] __x86_indirect_thunk_rax 0.00% [do_mmap+714 -> do_mmap+732] -10 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+737 -> do_mmap+765] 1 [kernel.kallsyms] [k] do_mmap 0.00% [do_mmap+262 -> do_mmap+299] 0 [kernel.kallsyms] [k] do_mmap 0.00% [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0] 7 [kernel.kallsyms] [k] __x86_indirect_thunk_r15 0.00% [native_sched_clock+0 -> native_sched_clock+119] -1 ± 38.5% ▄█▁ [kernel.kallsyms] [k] native_sched_clock 0.00% [native_write_msr+0 -> native_write_msr+16] -13 ± 47.1% ▁█▇▃▁▁ [kernel.kallsyms] [k] native_write_msr v8: --- Rebase to perf/core branch v7: --- 1. v6 got Jiri's ACK. 2. Rebase to latest perf/core branch. v6: --- 1. Jiri provides better code for using data__hpp_register() in ui_init(). Use this code in v6. v5: --- 1. Refine the use of data__hpp_register() in ui_init() according to Jiri's suggestion. v4: --- 1. Rename the new option from '--noisy' to '--cycles-hist' 2. Remove the option '-n'. 3. Only update the spark value and stats when '--cycles-hist' is enabled. 4. Remove the code of printing '..'. v3: --- 1. Move the histogram to a separate column 2. Move the svals[] out of struct stats v2: --- Jiri got a compile error, CC builtin-diff.o builtin-diff.c: In function ‘compute_cycles_diff’: builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value] 712 | labs(pair->block_info->cycles_spark[i] - | ^~~~ Because the result of u64 - u64 is still u64. Now we change the type of cycles_spark[] to s64. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-25 09:14:46 +08:00
if (cycles_hist && (compute != COMPUTE_CYCLES))
usage_with_options(diff_usage, options);
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
if (pdiff.stream)
compute = COMPUTE_STREAM;
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
symbol__annotation_init();
perf tools: Check recorded kernel version when finding vmlinux Currently vmlinux_path__init() only tries to find vmlinux file from current directory, /boot and some canonical directories with version number of the running kernel. This can be a problem when reporting old data recorded on a kernel version not running currently. We can use --symfs option for this but it's annoying for user to do it always. As we already have the info in the perf.data file, it can be changed to use it for the search automatically. Before: $ perf report ... # Samples: 4K of event 'cpu-clock' # Event count (approx.): 1067250000 # # Overhead Command Shared Object Symbol # ........ .......... ................. .............................. 71.87% swapper [kernel.kallsyms] [k] recover_probed_instruction After: # Overhead Command Shared Object Symbol # ........ .......... ................. .................... 71.87% swapper [kernel.kallsyms] [k] native_safe_halt This requires to change signature of symbol__init() to receive struct perf_session_env *. Reported-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1407825645-24586-14-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-12 14:40:45 +08:00
if (symbol__init(NULL) < 0)
return -1;
if (data_init(argc, argv) < 0)
return -1;
if (check_file_brstack() < 0)
return -1;
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
if ((compute == COMPUTE_CYCLES || compute == COMPUTE_STREAM)
&& !pdiff.has_br_stack) {
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
return -1;
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
}
perf diff: Use hists to manage basic blocks per symbol The hist__account_cycles() can account cycles per basic block. The basic block information is saved in cycles_hist structure. This patch processes each symbol, get basic blocks from cycles_hist and add the basic block entries to a new hists (in 'struct block_hist'). Using a hists is because we need to compare, sort and print the basic blocks later. v6: --- Since 'ops' argument is removed from hists__add_entry_block, update the code accordingly. No functional change. v5: --- Since now we still carry block_info in 'struct hist_entry' we don't need to use our own new/free ops for hist entries. And the block_info is released in hist_entry__delete. v3: --- 1. In v2, we put block stuffs in 'struct hist_entry', but it's not a good design. In v3, we create a new 'struct block_hist' and cast the 'struct hist_entry' to 'struct block_hist' in some places, which can avoid adding new stuffs in 'struct hist_entry'. 2. abs() -> labs(), in block_cycles_diff_cmp(). v2: --- v1 adds the basic block entries to per data-file hists but v2 adds the basic block entries to per symbol hists. That is to keep current perf-diff format. Will show the result in next patches. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-06-28 17:23:01 +08:00
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
if (compute == COMPUTE_STREAM) {
symbol_conf.show_branchflag_count = true;
symbol_conf.disable_add2line_warn = true;
callchain_param.mode = CHAIN_FLAT;
callchain_param.key = CCKEY_SRCLINE;
callchain_param.branch_callstack = 1;
symbol_conf.use_callchain = true;
callchain_register_param(&callchain_param);
sort_order = "srcline,symbol,dso";
} else {
if (ui_init() < 0)
return -1;
perf diff: Support hot streams comparison This patch enables perf-diff with "--stream" option. "--stream": Enable hot streams comparison Now let's see example. perf record -b ... Generate perf.data.old with branch data perf record -b ... Generate perf.data with branch data perf diff --stream [ Matched hot streams ] hot chain pair 1: cycles: 1, hits: 27.77% cycles: 1, hits: 9.24% --------------------------- -------------------------- main div.c:39 main div.c:39 main div.c:44 main div.c:44 hot chain pair 2: cycles: 34, hits: 20.06% cycles: 27, hits: 16.98% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 __random_r random_r.c:357 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 __random random.c:288 rand rand.c:27 rand rand.c:27 rand rand.c:26 rand rand.c:26 rand@plt rand@plt rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:25 compute_flag div.c:22 compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:40 main div.c:40 main div.c:39 main div.c:39 hot chain pair 3: cycles: 9, hits: 4.48% cycles: 6, hits: 4.51% --------------------------- -------------------------- __random_r random_r.c:360 __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:380 [ Hot streams in old perf data only ] hot chain 1: cycles: 18, hits: 6.75% -------------------------- __random_r random_r.c:360 __random_r random_r.c:388 __random_r random_r.c:388 __random_r random_r.c:380 __random_r random_r.c:357 __random random.c:293 __random random.c:293 __random random.c:291 __random random.c:291 __random random.c:291 __random random.c:288 rand rand.c:27 rand rand.c:26 rand@plt rand@plt compute_flag div.c:25 compute_flag div.c:22 main div.c:40 hot chain 2: cycles: 29, hits: 2.78% -------------------------- compute_flag div.c:22 main div.c:40 main div.c:40 main div.c:39 [ Hot streams in new perf data only ] hot chain 1: cycles: 4, hits: 4.54% -------------------------- main div.c:42 compute_flag div.c:28 hot chain 2: cycles: 5, hits: 3.51% -------------------------- main div.c:39 main div.c:44 main div.c:42 compute_flag div.c:28 Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20201009022845.13141-8-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-10-09 10:28:45 +08:00
sort__mode = SORT_MODE__DIFF;
}
if (setup_sorting(NULL) < 0)
usage_with_options(diff_usage, options);
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
setup_pager();
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 23:49:27 +08:00
sort__setup_elide(NULL);
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 23:49:27 +08:00
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-15 06:09:31 +08:00
return __cmd_diff();
}