linux/tools/perf/util/thread.h

91 lines
2.3 KiB
C
Raw Normal View History

#ifndef __PERF_THREAD_H
#define __PERF_THREAD_H
#include <linux/rbtree.h>
#include <linux/list.h>
#include <unistd.h>
#include <sys/types.h>
#include "symbol.h"
#include <strlist.h>
struct thread {
union {
struct rb_node rb_node;
struct list_head node;
};
struct map_groups *mg;
pid_t pid_; /* Not all tools update this */
pid_t tid;
pid_t ppid;
int cpu;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 15:40:48 +00:00
char shortname[3];
bool comm_set;
perf tools: Sample after exit loses thread correlation Occassionally events (e.g., context-switch, sched tracepoints) are losing the conversion of sample data associated with a thread. For example: $ perf record -e sched:sched_switch -c 1 -a -- sleep 5 $ perf script <selected events shown> ls 30482 [000] 1379727.583037: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.586339: sched:sched_switch: prev_comm=ls prev_pid=30482 ... :30482 30482 [000] 1379727.589462: sched:sched_switch: prev_comm=ls prev_pid=30482 ... The last line lost the conversion from tid to comm. If you look at the events (perf script -D) you see why - a SAMPLE event is generated after the EXIT: 0 1379727589449774 0x1540b0 [0x38]: PERF_RECORD_EXIT(30482:30482):(30482:30482) 0 1379727589462497 0x1540e8 [0x80]: PERF_RECORD_SAMPLE(IP, 1): 30482/30482: 0xffffffff816416f1 period: 1 addr: 0 ... thread: :30482:30482 When perf processes the EXIT event the thread is moved to the dead_threads list. When the SAMPLE event is processed no thread exists for the pid so a new one is created by machine__findnew_thread. This patch address the problem by delaying the move to the dead_threads list until the tid is re-used (per Adrian's suggestion). With this patch we get the previous example shows: ls 30482 [000] 1379727.583037: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.586339: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.589462: sched:sched_switch: prev_comm=ls prev_pid=30482 ... and 0 1379727589449774 0x1540b0 [0x38]: PERF_RECORD_EXIT(30482:30482):(30482:30482) 0 1379727589462497 0x1540e8 [0x80]: PERF_RECORD_SAMPLE(IP, 1): 30482/30482: 0xffffffff816416f1 period: 1 addr: 0 ... thread: ls:30482 v4: per Arnaldo's request add dead flag to thread struct and set when task exits v3: re-do from a time based check to a delayed move to dead_threads list v2: Rebased to latest perf/core branch. Changed time comparison to use a macro which explicitly shows the time basis Signed-off-by: David Ahern <dsahern@gmail.com> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1376491767-84171-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-14 14:49:27 +00:00
bool dead; /* if set thread has exited */
struct list_head comm_list;
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>
2009-10-22 21:23:23 +00:00
int comm_len;
perf kvm: Events analysis tool Add 'perf kvm stat' support to analyze kvm vmexit/mmio/ioport smartly Usage: - kvm stat run a command and gather performance counter statistics, it is the alias of perf stat - trace kvm events: perf kvm stat record, or, if other tracepoints are interesting as well, we can append the events like this: perf kvm stat record -e timer:* -a If many guests are running, we can track the specified guest by using -p or --pid, -a is used to track events generated by all guests. - show the result: perf kvm stat report The output example is following: 13005 13059 total 2 guests are running on the host Then, track the guest whose pid is 13059: ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.253 MB perf.data.guest (~11065 samples) ] See the vmexit events: Analyze events for all VCPUs: VM-EXIT Samples Samples% Time% Avg time APIC_ACCESS 460 70.55% 0.01% 22.44us ( +- 1.75% ) HLT 93 14.26% 99.98% 832077.26us ( +- 10.42% ) EXTERNAL_INTERRUPT 64 9.82% 0.00% 35.35us ( +- 14.21% ) PENDING_INTERRUPT 24 3.68% 0.00% 9.29us ( +- 31.39% ) CR_ACCESS 7 1.07% 0.00% 8.12us ( +- 5.76% ) IO_INSTRUCTION 3 0.46% 0.00% 18.00us ( +- 11.79% ) EXCEPTION_NMI 1 0.15% 0.00% 5.83us ( +- -nan% ) Total Samples:652, Total events handled time:77396109.80us. See the mmio events: Analyze events for all VCPUs: MMIO Access Samples Samples% Time% Avg time 0xfee00380:W 387 84.31% 79.28% 8.29us ( +- 3.32% ) 0xfee00300:W 24 5.23% 9.96% 16.79us ( +- 1.97% ) 0xfee00300:R 24 5.23% 7.83% 13.20us ( +- 3.00% ) 0xfee00310:W 24 5.23% 2.93% 4.94us ( +- 3.84% ) Total Samples:459, Total events handled time:4044.59us. See the ioport event: Analyze events for all VCPUs: IO Port Access Samples Samples% Time% Avg time 0xc050:POUT 3 100.00% 100.00% 13.75us ( +- 10.83% ) Total Samples:3, Total events handled time:41.26us. And, --vcpu is used to track the specified vcpu and --key is used to sort the result: Analyze events for VCPU 0: VM-EXIT Samples Samples% Time% Avg time HLT 27 13.85% 99.97% 405790.24us ( +- 12.70% ) EXTERNAL_INTERRUPT 13 6.67% 0.00% 27.94us ( +- 22.26% ) APIC_ACCESS 146 74.87% 0.03% 21.69us ( +- 2.91% ) IO_INSTRUCTION 2 1.03% 0.00% 17.77us ( +- 20.56% ) CR_ACCESS 2 1.03% 0.00% 8.55us ( +- 6.47% ) PENDING_INTERRUPT 5 2.56% 0.00% 6.27us ( +- 3.94% ) Total Samples:195, Total events handled time:10959950.90us. Signed-off-by: Dong Hao <haodong@linux.vnet.ibm.com> Signed-off-by: Runzhen Wang <runzhen@linux.vnet.ibm.com> [ Dong Hao <haodong@linux.vnet.ibm.com> Runzhen Wang <runzhen@linux.vnet.ibm.com>: - rebase it on current acme's tree - fix the compiling-error on i386 ] Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Acked-by: David Ahern <dsahern@gmail.com> Cc: Avi Kivity <avi@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: kvm@vger.kernel.org Cc: Runzhen Wang <runzhen@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1347870675-31495-4-git-send-email-haodong@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-17 08:31:15 +00:00
void *priv;
};
struct machine;
struct comm;
struct thread *thread__new(pid_t pid, pid_t tid);
int thread__init_map_groups(struct thread *thread, struct machine *machine);
void thread__delete(struct thread *thread);
perf tools: Sample after exit loses thread correlation Occassionally events (e.g., context-switch, sched tracepoints) are losing the conversion of sample data associated with a thread. For example: $ perf record -e sched:sched_switch -c 1 -a -- sleep 5 $ perf script <selected events shown> ls 30482 [000] 1379727.583037: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.586339: sched:sched_switch: prev_comm=ls prev_pid=30482 ... :30482 30482 [000] 1379727.589462: sched:sched_switch: prev_comm=ls prev_pid=30482 ... The last line lost the conversion from tid to comm. If you look at the events (perf script -D) you see why - a SAMPLE event is generated after the EXIT: 0 1379727589449774 0x1540b0 [0x38]: PERF_RECORD_EXIT(30482:30482):(30482:30482) 0 1379727589462497 0x1540e8 [0x80]: PERF_RECORD_SAMPLE(IP, 1): 30482/30482: 0xffffffff816416f1 period: 1 addr: 0 ... thread: :30482:30482 When perf processes the EXIT event the thread is moved to the dead_threads list. When the SAMPLE event is processed no thread exists for the pid so a new one is created by machine__findnew_thread. This patch address the problem by delaying the move to the dead_threads list until the tid is re-used (per Adrian's suggestion). With this patch we get the previous example shows: ls 30482 [000] 1379727.583037: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.586339: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.589462: sched:sched_switch: prev_comm=ls prev_pid=30482 ... and 0 1379727589449774 0x1540b0 [0x38]: PERF_RECORD_EXIT(30482:30482):(30482:30482) 0 1379727589462497 0x1540e8 [0x80]: PERF_RECORD_SAMPLE(IP, 1): 30482/30482: 0xffffffff816416f1 period: 1 addr: 0 ... thread: ls:30482 v4: per Arnaldo's request add dead flag to thread struct and set when task exits v3: re-do from a time based check to a delayed move to dead_threads list v2: Rebased to latest perf/core branch. Changed time comparison to use a macro which explicitly shows the time basis Signed-off-by: David Ahern <dsahern@gmail.com> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1376491767-84171-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-14 14:49:27 +00:00
static inline void thread__exited(struct thread *thread)
{
thread->dead = true;
}
int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
bool exec);
static inline int thread__set_comm(struct thread *thread, const char *comm,
u64 timestamp)
{
return __thread__set_comm(thread, comm, timestamp, false);
}
int thread__comm_len(struct thread *thread);
struct comm *thread__comm(const struct thread *thread);
struct comm *thread__exec_comm(const struct thread *thread);
const char *thread__comm_str(const struct thread *thread);
void thread__insert_map(struct thread *thread, struct map *map);
int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
size_t thread__fprintf(struct thread *thread, FILE *fp);
void thread__find_addr_map(struct thread *thread, struct machine *machine,
u8 cpumode, enum map_type type, u64 addr,
struct addr_location *al);
void thread__find_addr_location(struct thread *thread, struct machine *machine,
u8 cpumode, enum map_type type, u64 addr,
struct addr_location *al);
void thread__find_cpumode_addr_location(struct thread *thread,
struct machine *machine,
enum map_type type, u64 addr,
struct addr_location *al);
static inline void *thread__priv(struct thread *thread)
{
return thread->priv;
}
static inline void thread__set_priv(struct thread *thread, void *p)
{
thread->priv = p;
}
static inline bool thread__is_filtered(struct thread *thread)
{
if (symbol_conf.comm_list &&
!strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) {
return true;
}
return false;
}
#endif /* __PERF_THREAD_H */