OpenCloudOS-Kernel/tools/perf/util/event.h

397 lines
9.2 KiB
C
Raw Normal View History

perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
#ifndef __PERF_RECORD_H
#define __PERF_RECORD_H
#include <limits.h>
#include <stdio.h>
#include "../perf.h"
#include "map.h"
#include "build-id.h"
#include "perf_regs.h"
struct mmap_event {
struct perf_event_header header;
u32 pid, tid;
u64 start;
u64 len;
u64 pgoff;
char filename[PATH_MAX];
};
struct mmap2_event {
struct perf_event_header header;
u32 pid, tid;
u64 start;
u64 len;
u64 pgoff;
u32 maj;
u32 min;
u64 ino;
u64 ino_generation;
u32 prot;
u32 flags;
char filename[PATH_MAX];
};
struct comm_event {
struct perf_event_header header;
u32 pid, tid;
char comm[16];
};
struct fork_event {
struct perf_event_header header;
u32 pid, ppid;
u32 tid, ptid;
u64 time;
};
struct lost_event {
struct perf_event_header header;
u64 id;
u64 lost;
};
/*
* PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
*/
struct read_event {
struct perf_event_header header;
u32 pid, tid;
u64 value;
u64 time_enabled;
u64 time_running;
u64 id;
};
struct throttle_event {
struct perf_event_header header;
u64 time;
u64 id;
u64 stream_id;
};
#define PERF_SAMPLE_MASK \
(PERF_SAMPLE_IP | PERF_SAMPLE_TID | \
PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR | \
PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID | \
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD | \
PERF_SAMPLE_IDENTIFIER)
/* perf sample has 16 bits size limit */
#define PERF_SAMPLE_MAX_SIZE (1 << 16)
struct sample_event {
struct perf_event_header header;
u64 array[];
};
struct regs_dump {
u64 abi;
u64 mask;
u64 *regs;
/* Cached values/mask filled by first register access. */
u64 cache_regs[PERF_REGS_MAX];
u64 cache_mask;
};
struct stack_dump {
u16 offset;
u64 size;
char *data;
};
struct sample_read_value {
u64 value;
u64 id;
};
struct sample_read {
u64 time_enabled;
u64 time_running;
union {
struct {
u64 nr;
struct sample_read_value *values;
} group;
struct sample_read_value one;
};
};
struct ip_callchain {
u64 nr;
u64 ips[0];
};
struct branch_flags {
u64 mispred:1;
u64 predicted:1;
u64 in_tx:1;
u64 abort:1;
u64 reserved:60;
};
struct branch_entry {
u64 from;
u64 to;
struct branch_flags flags;
};
struct branch_stack {
u64 nr;
struct branch_entry entries[0];
};
enum {
PERF_IP_FLAG_BRANCH = 1ULL << 0,
PERF_IP_FLAG_CALL = 1ULL << 1,
PERF_IP_FLAG_RETURN = 1ULL << 2,
PERF_IP_FLAG_CONDITIONAL = 1ULL << 3,
PERF_IP_FLAG_SYSCALLRET = 1ULL << 4,
PERF_IP_FLAG_ASYNC = 1ULL << 5,
PERF_IP_FLAG_INTERRUPT = 1ULL << 6,
PERF_IP_FLAG_TX_ABORT = 1ULL << 7,
PERF_IP_FLAG_TRACE_BEGIN = 1ULL << 8,
PERF_IP_FLAG_TRACE_END = 1ULL << 9,
PERF_IP_FLAG_IN_TX = 1ULL << 10,
};
#define PERF_BRANCH_MASK (\
PERF_IP_FLAG_BRANCH |\
PERF_IP_FLAG_CALL |\
PERF_IP_FLAG_RETURN |\
PERF_IP_FLAG_CONDITIONAL |\
PERF_IP_FLAG_SYSCALLRET |\
PERF_IP_FLAG_ASYNC |\
PERF_IP_FLAG_INTERRUPT |\
PERF_IP_FLAG_TX_ABORT |\
PERF_IP_FLAG_TRACE_BEGIN |\
PERF_IP_FLAG_TRACE_END)
struct perf_sample {
u64 ip;
u32 pid, tid;
u64 time;
u64 addr;
u64 id;
u64 stream_id;
u64 period;
u64 weight;
u64 transaction;
u32 cpu;
u32 raw_size;
u64 data_src;
u32 flags;
u16 insn_len;
void *raw_data;
struct ip_callchain *callchain;
struct branch_stack *branch_stack;
struct regs_dump user_regs;
struct regs_dump intr_regs;
struct stack_dump user_stack;
struct sample_read read;
};
#define PERF_MEM_DATA_SRC_NONE \
(PERF_MEM_S(OP, NA) |\
PERF_MEM_S(LVL, NA) |\
PERF_MEM_S(SNOOP, NA) |\
PERF_MEM_S(LOCK, NA) |\
PERF_MEM_S(TLB, NA))
perf symbols: Use the buildids if present With this change 'perf record' will intercept PERF_RECORD_MMAP calls, creating a linked list of DSOs, then when the session finishes, it will traverse this list and read the buildids, stashing them at the end of the file and will set up a new feature bit in the header bitmask. 'perf report' will then notice this feature and populate the 'dsos' list and set the build ids. When reading the symtabs it will refuse to load from a file that doesn't have the same build id. This improves the reliability of the profiler output, as symbols and profiling data is more guaranteed to match. Example: [root@doppio ~]# perf report | head /home/acme/bin/perf with build id b1ea544ac3746e7538972548a09aadecc5753868 not found, continuing without symbols # Samples: 2621434559 # # Overhead Command Shared Object Symbol # ........ ............... ............................. ...... # 7.91% init [kernel] [k] read_hpet 7.64% init [kernel] [k] mwait_idle_with_hints 7.60% swapper [kernel] [k] read_hpet 7.60% swapper [kernel] [k] mwait_idle_with_hints 3.65% init [kernel] [k] 0xffffffffa02339d9 [root@doppio ~]# In this case the 'perf' binary was an older one, vanished, so its symbols probably wouldn't match or would cause subtly different (and misleading) output. Next patches will support the kernel as well, reading the build id notes for it and the modules from /sys. Another patch should also introduce a new plumbing command: 'perf list-buildids' that will then be used in porcelain that is distro specific to fetch -debuginfo packages where such buildids are present. This will in turn allow for one to run 'perf record' in one machine and 'perf report' in another. Future work on having the buildid sent directly from the kernel in the PERF_RECORD_MMAP event is needed to close races, as the DSO can be changed during a 'perf record' session, but this patch at least helps with non-corner cases and current/older kernels. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: K. Prasad <prasad@linux.vnet.ibm.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roland McGrath <roland@redhat.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1257367843-26224-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-05 04:50:43 +08:00
struct build_id_event {
struct perf_event_header header;
pid_t pid;
perf tools: fix ALIGN redefinition in system headers On some systems (e.g. Android), ALIGN is defined in system headers as ALIGN(p). The definition of ALIGN used in perf takes 2 parameters: ALIGN(x,a). This leads to redefinition conflicts. Redefinition error on Android: In file included from util/include/linux/list.h:1:0, from util/callchain.h:5, from util/hist.h:6, from util/session.h:4, from util/build-id.h:4, from util/annotate.c:11: util/include/linux/kernel.h:11:0: error: "ALIGN" redefined [-Werror] bionic/libc/include/sys/param.h:38:0: note: this is the location of the previous definition Conflics with system defined ALIGN in Android: util/event.c: In function 'perf_event__synthesize_comm': util/event.c:115:32: error: macro "ALIGN" passed 2 arguments, but takes just 1 util/event.c:115:9: error: 'ALIGN' undeclared (first use in this function) util/event.c:115:9: note: each undeclared identifier is reported only once for each function it appears in In order to avoid this redefinition, ALIGN is renamed to PERF_ALIGN. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Irina Tirdea <irina.tirdea@intel.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-5-git-send-email-irina.tirdea@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:01 +08:00
u8 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
perf symbols: Use the buildids if present With this change 'perf record' will intercept PERF_RECORD_MMAP calls, creating a linked list of DSOs, then when the session finishes, it will traverse this list and read the buildids, stashing them at the end of the file and will set up a new feature bit in the header bitmask. 'perf report' will then notice this feature and populate the 'dsos' list and set the build ids. When reading the symtabs it will refuse to load from a file that doesn't have the same build id. This improves the reliability of the profiler output, as symbols and profiling data is more guaranteed to match. Example: [root@doppio ~]# perf report | head /home/acme/bin/perf with build id b1ea544ac3746e7538972548a09aadecc5753868 not found, continuing without symbols # Samples: 2621434559 # # Overhead Command Shared Object Symbol # ........ ............... ............................. ...... # 7.91% init [kernel] [k] read_hpet 7.64% init [kernel] [k] mwait_idle_with_hints 7.60% swapper [kernel] [k] read_hpet 7.60% swapper [kernel] [k] mwait_idle_with_hints 3.65% init [kernel] [k] 0xffffffffa02339d9 [root@doppio ~]# In this case the 'perf' binary was an older one, vanished, so its symbols probably wouldn't match or would cause subtly different (and misleading) output. Next patches will support the kernel as well, reading the build id notes for it and the modules from /sys. Another patch should also introduce a new plumbing command: 'perf list-buildids' that will then be used in porcelain that is distro specific to fetch -debuginfo packages where such buildids are present. This will in turn allow for one to run 'perf record' in one machine and 'perf report' in another. Future work on having the buildid sent directly from the kernel in the PERF_RECORD_MMAP event is needed to close races, as the DSO can be changed during a 'perf record' session, but this patch at least helps with non-corner cases and current/older kernels. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: K. Prasad <prasad@linux.vnet.ibm.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roland McGrath <roland@redhat.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1257367843-26224-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-05 04:50:43 +08:00
char filename[];
};
enum perf_user_event_type { /* above any possible kernel type */
PERF_RECORD_USER_TYPE_START = 64,
PERF_RECORD_HEADER_ATTR = 64,
PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */
PERF_RECORD_HEADER_TRACING_DATA = 66,
PERF_RECORD_HEADER_BUILD_ID = 67,
PERF_RECORD_FINISHED_ROUND = 68,
perf tools: Add id index Add an index of the event identifiers, in preparation for Intel PT. The event id (also called the sample id) is a unique number allocated by the kernel to the event created by perf_event_open(). Events can include the event id by having a sample type including PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER. Currently the main use of the event id is to match an event back to the evsel to which it belongs i.e. perf_evlist__id2evsel() The purpose of this patch is to make it possible to match an event back to the mmap from which it was read. The reason that is useful is because the mmap represents a time-ordered context (either for a cpu or for a thread). Intel PT decodes trace information on that basis. In full-trace mode, that information can be recorded when the Intel PT trace is read, but in sample-mode the Intel PT trace data is embedded in a sample and it is in that case that the "id index" is needed. So the mmaps are numbered (idx) and the cpu and tid recorded against the id by perf_evlist__set_sid_idx() which is called by perf_evlist__mmap_per_evsel(). That information is recorded on the perf.data file in the new "id index". idx, cpu and tid are added to struct perf_sample_id (which is the node of evlist's hash table to match ids to evsels). The information can be retrieved using perf_evlist__id2sid(). Note however this all depends on having a sample type including PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER, otherwise ids are not recorded. The "id index" is a synthesized event record which will be created when Intel PT sampling is used by calling perf_event__synthesize_id_index(). Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1414417770-18602-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-27 21:49:22 +08:00
PERF_RECORD_ID_INDEX = 69,
PERF_RECORD_HEADER_MAX
};
/*
* The kernel collects the number of events it couldn't send in a stretch and
* when possible sends this number in a PERF_RECORD_LOST event. The number of
* such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
* total_lost tells exactly how many events the kernel in fact lost, i.e. it is
* the sum of all struct lost_event.lost fields reported.
*
* The total_period is needed because by default auto-freq is used, so
* multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
* the total number of low level events, it is necessary to to sum all struct
* sample_event.period and stash the result in total_period.
*/
struct events_stats {
u64 total_period;
u64 total_non_filtered_period;
u64 total_lost;
u64 total_invalid_chains;
u32 nr_events[PERF_RECORD_HEADER_MAX];
u32 nr_non_filtered_samples;
u32 nr_lost_warned;
u32 nr_unknown_events;
u32 nr_invalid_chains;
u32 nr_unknown_id;
u32 nr_unprocessable_samples;
u32 nr_unordered_events;
};
struct attr_event {
struct perf_event_header header;
struct perf_event_attr attr;
u64 id[];
};
#define MAX_EVENT_NAME 64
struct perf_trace_event_type {
u64 event_id;
char name[MAX_EVENT_NAME];
};
struct event_type_event {
struct perf_event_header header;
struct perf_trace_event_type event_type;
};
struct tracing_data_event {
struct perf_event_header header;
u32 size;
};
perf tools: Add id index Add an index of the event identifiers, in preparation for Intel PT. The event id (also called the sample id) is a unique number allocated by the kernel to the event created by perf_event_open(). Events can include the event id by having a sample type including PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER. Currently the main use of the event id is to match an event back to the evsel to which it belongs i.e. perf_evlist__id2evsel() The purpose of this patch is to make it possible to match an event back to the mmap from which it was read. The reason that is useful is because the mmap represents a time-ordered context (either for a cpu or for a thread). Intel PT decodes trace information on that basis. In full-trace mode, that information can be recorded when the Intel PT trace is read, but in sample-mode the Intel PT trace data is embedded in a sample and it is in that case that the "id index" is needed. So the mmaps are numbered (idx) and the cpu and tid recorded against the id by perf_evlist__set_sid_idx() which is called by perf_evlist__mmap_per_evsel(). That information is recorded on the perf.data file in the new "id index". idx, cpu and tid are added to struct perf_sample_id (which is the node of evlist's hash table to match ids to evsels). The information can be retrieved using perf_evlist__id2sid(). Note however this all depends on having a sample type including PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER, otherwise ids are not recorded. The "id index" is a synthesized event record which will be created when Intel PT sampling is used by calling perf_event__synthesize_id_index(). Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1414417770-18602-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-27 21:49:22 +08:00
struct id_index_entry {
u64 id;
u64 idx;
u64 cpu;
u64 tid;
};
struct id_index_event {
struct perf_event_header header;
u64 nr;
struct id_index_entry entries[0];
};
union perf_event {
struct perf_event_header header;
struct mmap_event mmap;
struct mmap2_event mmap2;
struct comm_event comm;
struct fork_event fork;
struct lost_event lost;
struct read_event read;
struct throttle_event throttle;
struct sample_event sample;
struct attr_event attr;
struct event_type_event event_type;
struct tracing_data_event tracing_data;
struct build_id_event build_id;
perf tools: Add id index Add an index of the event identifiers, in preparation for Intel PT. The event id (also called the sample id) is a unique number allocated by the kernel to the event created by perf_event_open(). Events can include the event id by having a sample type including PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER. Currently the main use of the event id is to match an event back to the evsel to which it belongs i.e. perf_evlist__id2evsel() The purpose of this patch is to make it possible to match an event back to the mmap from which it was read. The reason that is useful is because the mmap represents a time-ordered context (either for a cpu or for a thread). Intel PT decodes trace information on that basis. In full-trace mode, that information can be recorded when the Intel PT trace is read, but in sample-mode the Intel PT trace data is embedded in a sample and it is in that case that the "id index" is needed. So the mmaps are numbered (idx) and the cpu and tid recorded against the id by perf_evlist__set_sid_idx() which is called by perf_evlist__mmap_per_evsel(). That information is recorded on the perf.data file in the new "id index". idx, cpu and tid are added to struct perf_sample_id (which is the node of evlist's hash table to match ids to evsels). The information can be retrieved using perf_evlist__id2sid(). Note however this all depends on having a sample type including PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER, otherwise ids are not recorded. The "id index" is a synthesized event record which will be created when Intel PT sampling is used by calling perf_event__synthesize_id_index(). Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1414417770-18602-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-27 21:49:22 +08:00
struct id_index_event id_index;
};
void perf_event__print_totals(void);
struct perf_tool;
perf tools: Fix thread_map event synthesizing in top and record Jeff Moyer reported these messages: Warning: ... trying to fall back to cpu-clock-ticks couldn't open /proc/-1/status couldn't open /proc/-1/maps [ls output] [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.008 MB perf.data (~363 samples) ] That lead me and David Ahern to see that something was fishy on the thread synthesizing routines, at least for the case where the workload is started from 'perf record', as -1 is the default for target_tid in 'perf record --tid' parameter, so somehow we were trying to synthesize the PERF_RECORD_MMAP and PERF_RECORD_COMM events for the thread -1, a bug. So I investigated this and noticed that when we introduced support for recording a process and its threads using --pid some bugs were introduced and that the way to fix it was to instead of passing the target_tid to the event synthesizing routines we should better pass the thread_map that has the list of threads for a --pid or just the single thread for a --tid. Checked in the following ways: On a 8-way machine run cyclictest: [root@emilia ~]# perf record cyclictest -a -t -n -p99 -i100 -d50 policy: fifo: loadavg: 0.00 0.13 0.31 2/139 28798 T: 0 (28791) P:99 I:100 C: 25072 Min: 4 Act: 5 Avg: 6 Max: 122 T: 1 (28792) P:98 I:150 C: 16715 Min: 4 Act: 6 Avg: 5 Max: 27 T: 2 (28793) P:97 I:200 C: 12534 Min: 4 Act: 5 Avg: 4 Max: 8 T: 3 (28794) P:96 I:250 C: 10028 Min: 4 Act: 5 Avg: 5 Max: 96 T: 4 (28795) P:95 I:300 C: 8357 Min: 5 Act: 6 Avg: 5 Max: 12 T: 5 (28796) P:94 I:350 C: 7163 Min: 5 Act: 6 Avg: 5 Max: 12 T: 6 (28797) P:93 I:400 C: 6267 Min: 4 Act: 5 Avg: 5 Max: 9 T: 7 (28798) P:92 I:450 C: 5571 Min: 4 Act: 5 Avg: 5 Max: 9 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.108 MB perf.data (~4719 samples) ] [root@emilia ~]# This will create one extra thread per CPU: [root@emilia ~]# tuna -t cyclictest -CP thread ctxt_switches pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 28825 OTHER 0 0xff 2169 671 cyclictest 28832 FIFO 93 6 52338 1 cyclictest 28833 FIFO 92 7 46524 1 cyclictest 28826 FIFO 99 0 209360 1 cyclictest 28827 FIFO 98 1 139577 1 cyclictest 28828 FIFO 97 2 104686 0 cyclictest 28829 FIFO 96 3 83751 1 cyclictest 28830 FIFO 95 4 69794 1 cyclictest 28831 FIFO 94 5 59825 1 cyclictest [root@emilia ~]# So we should expect only samples for the above 9 threads when using the --dump-raw-trace|-D perf report switch to look at the column with the tid: [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 629 28825 110 28826 491 28827 308 28828 198 28829 621 28830 225 28831 203 28832 89 28833 [root@emilia ~]# So for workloads started by 'perf record' seems to work, now for existing workloads, just run cyclictest first, without 'perf record': [root@emilia ~]# tuna -t cyclictest -CP thread ctxt_switches pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 28859 OTHER 0 0xff 594 200 cyclictest 28864 FIFO 95 4 16587 1 cyclictest 28865 FIFO 94 5 14219 1 cyclictest 28866 FIFO 93 6 12443 0 cyclictest 28867 FIFO 92 7 11062 1 cyclictest 28860 FIFO 99 0 49779 1 cyclictest 28861 FIFO 98 1 33190 1 cyclictest 28862 FIFO 97 2 24895 1 cyclictest 28863 FIFO 96 3 19918 1 cyclictest [root@emilia ~]# and then later did: [root@emilia ~]# perf record --pid 28859 sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.027 MB perf.data (~1195 samples) ] [root@emilia ~]# To collect 3 seconds worth of samples for pid 28859 and its children: [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 15 28859 33 28860 19 28861 13 28862 13 28863 10 28864 11 28865 9 28866 255 28867 [root@emilia ~]# Works, last thing is to check if looking at just one of those threads also works: [root@emilia ~]# perf record --tid 28866 sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.006 MB perf.data (~242 samples) ] [root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c 3 28866 [root@emilia ~]# Works too. Reported-by: Jeff Moyer <jmoyer@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-02-10 22:52:47 +08:00
struct thread_map;
typedef int (*perf_event__handler_t)(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
int perf_event__synthesize_thread_map(struct perf_tool *tool,
struct thread_map *threads,
perf_event__handler_t process,
struct machine *machine, bool mmap_data);
int perf_event__synthesize_threads(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine, bool mmap_data);
int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine);
int perf_event__synthesize_modules(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine);
int perf_event__process_comm(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
int perf_event__process_lost(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
int perf_event__process_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
int perf_event__process_mmap2(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
int perf_event__process_fork(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
int perf_event__process_exit(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
int perf_event__process(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
struct addr_location;
int perf_event__preprocess_sample(const union perf_event *event,
struct machine *machine,
struct addr_location *al,
struct perf_sample *sample);
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-28 02:29:23 +08:00
struct thread;
bool is_bts_event(struct perf_event_attr *attr);
bool sample_addr_correlates_sym(struct perf_event_attr *attr);
void perf_event__preprocess_sample_addr(union perf_event *event,
struct perf_sample *sample,
struct thread *thread,
struct addr_location *al);
const char *perf_event__name(unsigned int id);
size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
u64 read_format);
int perf_event__synthesize_sample(union perf_event *event, u64 type,
u64 read_format,
const struct perf_sample *sample,
bool swapped);
int perf_event__synthesize_mmap_events(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid,
perf_event__handler_t process,
struct machine *machine,
bool mmap_data);
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
u64 kallsyms__get_function_start(const char *kallsyms_filename,
const char *symbol_name);
#endif /* __PERF_RECORD_H */