linux-sg2042/tools/perf/util/sort.c

341 lines
7.8 KiB
C
Raw Normal View History

#include "sort.h"
#include "hist.h"
regex_t parent_regex;
const char default_parent_pattern[] = "^sys_|^do_page_fault";
const char *parent_pattern = default_parent_pattern;
const char default_sort_order[] = "comm,dso,symbol";
const char *sort_order = default_sort_order;
int sort__need_collapse = 0;
int sort__has_parent = 0;
perf tools: Bind callchains to the first sort dimension column Currently, the callchains are displayed using a constant left margin. So depending on the current sort dimension configuration, callchains may appear to be well attached to the first sort dimension column field which is mostly the case, except when the first dimension of sorting is done by comm, because these are right aligned. This patch binds the callchain to the first letter in the first column, whatever type of column it is (dso, comm, symbol). Before: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent After: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent Also, for clarity, we don't put anymore the callchain as is but: - If we have a top level ancestor in the callchain, start it with a first ascii hook. Before: 0.80% perf [kernel] [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] After: 0.80% perf [kernel] [k] __lock_acquire | --- __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] - Otherwise, if we have several top level ancestors, then display these like we did before: 1.69% Xorg | |--21.21%-- vread_hpet | 0x7fffd85b46fc | 0x7fffd85b494d | 0x7f4fafb4e54d | |--15.15%-- exaOffscreenAlloc | |--9.09%-- I830WaitLpRing Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 05:23:23 +08:00
enum sort_type sort__first_dimension;
char * field_sep;
LIST_HEAD(hist_entry__sort_list);
static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
{
int n;
va_list ap;
va_start(ap, fmt);
n = vsnprintf(bf, size, fmt, ap);
if (field_sep && n > 0) {
char *sep = bf;
while (1) {
sep = strchr(sep, *field_sep);
if (sep == NULL)
break;
*sep = '.';
}
}
va_end(ap);
return n;
}
static int64_t cmp_null(void *l, void *r)
{
if (!l && !r)
return 0;
else if (!l)
return -1;
else
return 1;
}
/* --sort pid */
static int64_t
sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
{
return right->thread->pid - left->thread->pid;
}
static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%*s:%5d", width,
self->thread->comm ?: "", self->thread->pid);
}
struct sort_entry sort_thread = {
.se_header = "Command: Pid",
.se_cmp = sort__thread_cmp,
.se_snprintf = hist_entry__thread_snprintf,
.se_width_idx = HISTC_THREAD,
};
/* --sort comm */
static int64_t
sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
{
return right->thread->pid - left->thread->pid;
}
static int64_t
sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
{
char *comm_l = left->thread->comm;
char *comm_r = right->thread->comm;
if (!comm_l || !comm_r)
return cmp_null(comm_l, comm_r);
return strcmp(comm_l, comm_r);
}
static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
}
struct sort_entry sort_comm = {
.se_header = "Command",
.se_cmp = sort__comm_cmp,
.se_collapse = sort__comm_collapse,
.se_snprintf = hist_entry__comm_snprintf,
.se_width_idx = HISTC_COMM,
};
/* --sort dso */
static int64_t
sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct dso *dso_l = left->ms.map ? left->ms.map->dso : NULL;
struct dso *dso_r = right->ms.map ? right->ms.map->dso : NULL;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 14:29:58 +08:00
const char *dso_name_l, *dso_name_r;
if (!dso_l || !dso_r)
return cmp_null(dso_l, dso_r);
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 14:29:58 +08:00
if (verbose) {
dso_name_l = dso_l->long_name;
dso_name_r = dso_r->long_name;
} else {
dso_name_l = dso_l->short_name;
dso_name_r = dso_r->short_name;
}
return strcmp(dso_name_l, dso_name_r);
}
static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
if (self->ms.map && self->ms.map->dso) {
const char *dso_name = !verbose ? self->ms.map->dso->short_name :
self->ms.map->dso->long_name;
return repsep_snprintf(bf, size, "%-*s", width, dso_name);
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 14:29:58 +08:00
}
return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
}
struct sort_entry sort_dso = {
.se_header = "Shared Object",
.se_cmp = sort__dso_cmp,
.se_snprintf = hist_entry__dso_snprintf,
.se_width_idx = HISTC_DSO,
};
/* --sort symbol */
static int64_t
sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
{
u64 ip_l, ip_r;
perf sort: Fix symbol sort output by separating unresolved samples by type I took a profile that suggested 60% of total CPU time was in the hypervisor: ... 60.20% [H] 0x33d43c 4.43% [k] ._spin_lock_irqsave 1.07% [k] ._spin_lock Using perf stat to get the user/kernel/hypervisor breakdown contradicted this. The problem is we merge all unresolved samples into the one unknown bucket. If add a comparison by sample type to sort__sym_cmp we get the real picture: ... 57.11% [.] 0x80fbf63c 4.43% [k] ._spin_lock_irqsave 1.07% [k] ._spin_lock 0.65% [H] 0x33d43c So it was almost all userspace, not hypervisor as the initial profile suggested. I found another issue while adding this. Symbol sorting sometimes shows multiple entries for the unknown bucket: ... 16.65% [.] 0x6cd3a8 7.25% [.] 0x422460 5.37% [.] yylex 4.79% [.] malloc 4.78% [.] _int_malloc 4.03% [.] _int_free 3.95% [.] hash_source_code_string 2.82% [.] 0x532908 2.64% [.] 0x36b538 0.94% [H] 0x8000000000e132a4 0.82% [H] 0x800000000000e8b0 This happens because we aren't consistent with our sorting. On one hand we check to see if both symbols match and for two unresolved samples sym is NULL so we match: if (left->ms.sym == right->ms.sym) return 0; On the other hand we use sample IP for unresolved samples when comparing against a symbol: ip_l = left->ms.sym ? left->ms.sym->start : left->ip; ip_r = right->ms.sym ? right->ms.sym->start : right->ip; This means unresolved samples end up spread across the rbtree and we can't merge them all. If we use cmp_null all unresolved samples will end up in the one bucket and the output makes more sense: ... 39.12% [.] 0x36b538 5.37% [.] yylex 4.79% [.] malloc 4.78% [.] _int_malloc 4.03% [.] _int_free 3.95% [.] hash_source_code_string 2.26% [H] 0x800000000000e8b0 Acked-by: Eric B Munson <emunson@mgebm.net> Cc: Eric B Munson <emunson@mgebm.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ian Munsie <imunsie@au1.ibm.com> Link: http://lkml.kernel.org/r/20110831115145.4f598ab2@kryten Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-31 09:51:45 +08:00
if (!left->ms.sym && !right->ms.sym)
return right->level - left->level;
if (!left->ms.sym || !right->ms.sym)
return cmp_null(left->ms.sym, right->ms.sym);
if (left->ms.sym == right->ms.sym)
return 0;
perf sort: Fix symbol sort output by separating unresolved samples by type I took a profile that suggested 60% of total CPU time was in the hypervisor: ... 60.20% [H] 0x33d43c 4.43% [k] ._spin_lock_irqsave 1.07% [k] ._spin_lock Using perf stat to get the user/kernel/hypervisor breakdown contradicted this. The problem is we merge all unresolved samples into the one unknown bucket. If add a comparison by sample type to sort__sym_cmp we get the real picture: ... 57.11% [.] 0x80fbf63c 4.43% [k] ._spin_lock_irqsave 1.07% [k] ._spin_lock 0.65% [H] 0x33d43c So it was almost all userspace, not hypervisor as the initial profile suggested. I found another issue while adding this. Symbol sorting sometimes shows multiple entries for the unknown bucket: ... 16.65% [.] 0x6cd3a8 7.25% [.] 0x422460 5.37% [.] yylex 4.79% [.] malloc 4.78% [.] _int_malloc 4.03% [.] _int_free 3.95% [.] hash_source_code_string 2.82% [.] 0x532908 2.64% [.] 0x36b538 0.94% [H] 0x8000000000e132a4 0.82% [H] 0x800000000000e8b0 This happens because we aren't consistent with our sorting. On one hand we check to see if both symbols match and for two unresolved samples sym is NULL so we match: if (left->ms.sym == right->ms.sym) return 0; On the other hand we use sample IP for unresolved samples when comparing against a symbol: ip_l = left->ms.sym ? left->ms.sym->start : left->ip; ip_r = right->ms.sym ? right->ms.sym->start : right->ip; This means unresolved samples end up spread across the rbtree and we can't merge them all. If we use cmp_null all unresolved samples will end up in the one bucket and the output makes more sense: ... 39.12% [.] 0x36b538 5.37% [.] yylex 4.79% [.] malloc 4.78% [.] _int_malloc 4.03% [.] _int_free 3.95% [.] hash_source_code_string 2.26% [H] 0x800000000000e8b0 Acked-by: Eric B Munson <emunson@mgebm.net> Cc: Eric B Munson <emunson@mgebm.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ian Munsie <imunsie@au1.ibm.com> Link: http://lkml.kernel.org/r/20110831115145.4f598ab2@kryten Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-31 09:51:45 +08:00
ip_l = left->ms.sym->start;
ip_r = right->ms.sym->start;
return (int64_t)(ip_r - ip_l);
}
static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width __used)
{
size_t ret = 0;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 14:29:58 +08:00
if (verbose) {
char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
ret += repsep_snprintf(bf, size, "%-#*llx %c ",
BITS_PER_LONG / 4, self->ip, o);
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 14:29:58 +08:00
}
if (!sort_dso.elide)
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level);
if (self->ms.sym)
ret += repsep_snprintf(bf + ret, size - ret, "%s",
self->ms.sym->name);
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 14:29:58 +08:00
else
ret += repsep_snprintf(bf + ret, size - ret, "%-#*llx",
BITS_PER_LONG / 4, self->ip);
return ret;
}
struct sort_entry sort_sym = {
.se_header = "Symbol",
.se_cmp = sort__sym_cmp,
.se_snprintf = hist_entry__sym_snprintf,
.se_width_idx = HISTC_SYMBOL,
};
/* --sort parent */
static int64_t
sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct symbol *sym_l = left->parent;
struct symbol *sym_r = right->parent;
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
return strcmp(sym_l->name, sym_r->name);
}
static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*s", width,
self->parent ? self->parent->name : "[other]");
}
struct sort_entry sort_parent = {
.se_header = "Parent symbol",
.se_cmp = sort__parent_cmp,
.se_snprintf = hist_entry__parent_snprintf,
.se_width_idx = HISTC_PARENT,
};
/* --sort cpu */
static int64_t
sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
{
return right->cpu - left->cpu;
}
static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*d", width, self->cpu);
}
struct sort_entry sort_cpu = {
.se_header = "CPU",
.se_cmp = sort__cpu_cmp,
.se_snprintf = hist_entry__cpu_snprintf,
.se_width_idx = HISTC_CPU,
};
struct sort_dimension {
const char *name;
struct sort_entry *entry;
int taken;
};
static struct sort_dimension sort_dimensions[] = {
{ .name = "pid", .entry = &sort_thread, },
{ .name = "comm", .entry = &sort_comm, },
{ .name = "dso", .entry = &sort_dso, },
{ .name = "symbol", .entry = &sort_sym, },
{ .name = "parent", .entry = &sort_parent, },
{ .name = "cpu", .entry = &sort_cpu, },
};
int sort_dimension__add(const char *tok)
{
unsigned int i;
for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
struct sort_dimension *sd = &sort_dimensions[i];
if (strncasecmp(tok, sd->name, strlen(tok)))
continue;
if (sd->entry == &sort_parent) {
int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
if (ret) {
char err[BUFSIZ];
regerror(ret, &parent_regex, err, sizeof(err));
pr_err("Invalid regex: %s\n%s", parent_pattern, err);
return -EINVAL;
}
sort__has_parent = 1;
}
if (sd->taken)
return 0;
if (sd->entry->se_collapse)
sort__need_collapse = 1;
perf tools: Bind callchains to the first sort dimension column Currently, the callchains are displayed using a constant left margin. So depending on the current sort dimension configuration, callchains may appear to be well attached to the first sort dimension column field which is mostly the case, except when the first dimension of sorting is done by comm, because these are right aligned. This patch binds the callchain to the first letter in the first column, whatever type of column it is (dso, comm, symbol). Before: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent After: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent Also, for clarity, we don't put anymore the callchain as is but: - If we have a top level ancestor in the callchain, start it with a first ascii hook. Before: 0.80% perf [kernel] [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] After: 0.80% perf [kernel] [k] __lock_acquire | --- __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] - Otherwise, if we have several top level ancestors, then display these like we did before: 1.69% Xorg | |--21.21%-- vread_hpet | 0x7fffd85b46fc | 0x7fffd85b494d | 0x7f4fafb4e54d | |--15.15%-- exaOffscreenAlloc | |--9.09%-- I830WaitLpRing Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 05:23:23 +08:00
if (list_empty(&hist_entry__sort_list)) {
if (!strcmp(sd->name, "pid"))
sort__first_dimension = SORT_PID;
else if (!strcmp(sd->name, "comm"))
sort__first_dimension = SORT_COMM;
else if (!strcmp(sd->name, "dso"))
sort__first_dimension = SORT_DSO;
else if (!strcmp(sd->name, "symbol"))
sort__first_dimension = SORT_SYM;
else if (!strcmp(sd->name, "parent"))
sort__first_dimension = SORT_PARENT;
else if (!strcmp(sd->name, "cpu"))
sort__first_dimension = SORT_CPU;
perf tools: Bind callchains to the first sort dimension column Currently, the callchains are displayed using a constant left margin. So depending on the current sort dimension configuration, callchains may appear to be well attached to the first sort dimension column field which is mostly the case, except when the first dimension of sorting is done by comm, because these are right aligned. This patch binds the callchain to the first letter in the first column, whatever type of column it is (dso, comm, symbol). Before: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent After: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent Also, for clarity, we don't put anymore the callchain as is but: - If we have a top level ancestor in the callchain, start it with a first ascii hook. Before: 0.80% perf [kernel] [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] After: 0.80% perf [kernel] [k] __lock_acquire | --- __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] - Otherwise, if we have several top level ancestors, then display these like we did before: 1.69% Xorg | |--21.21%-- vread_hpet | 0x7fffd85b46fc | 0x7fffd85b494d | 0x7f4fafb4e54d | |--15.15%-- exaOffscreenAlloc | |--9.09%-- I830WaitLpRing Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 05:23:23 +08:00
}
list_add_tail(&sd->entry->list, &hist_entry__sort_list);
sd->taken = 1;
return 0;
}
return -ESRCH;
}
void setup_sorting(const char * const usagestr[], const struct option *opts)
{
char *tmp, *tok, *str = strdup(sort_order);
for (tok = strtok_r(str, ", ", &tmp);
tok; tok = strtok_r(NULL, ", ", &tmp)) {
if (sort_dimension__add(tok) < 0) {
error("Unknown --sort key: `%s'", tok);
usage_with_options(usagestr, opts);
}
}
free(str);
}
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
void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
const char *list_name, FILE *fp)
{
if (list && strlist__nr_entries(list) == 1) {
if (fp != NULL)
fprintf(fp, "# %s: %s\n", list_name,
strlist__entry(list, 0)->s);
self->elide = true;
}
}