kernel-ark/tools/perf/util/thread.c

92 lines
1.7 KiB
C
Raw Normal View History

#include "../perf.h"
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include "session.h"
#include "thread.h"
#include "util.h"
#include "debug.h"
struct thread *thread__new(pid_t pid, pid_t tid)
{
struct thread *self = zalloc(sizeof(*self));
if (self != NULL) {
map_groups__init(&self->mg);
self->pid_ = pid;
self->tid = tid;
self->ppid = -1;
self->comm = malloc(32);
if (self->comm)
snprintf(self->comm, 32, ":%d", self->tid);
}
return self;
}
void thread__delete(struct thread *self)
{
map_groups__exit(&self->mg);
free(self->comm);
free(self);
}
int thread__set_comm(struct thread *self, const char *comm)
{
int err;
if (self->comm)
free(self->comm);
self->comm = strdup(comm);
err = self->comm == NULL ? -ENOMEM : 0;
if (!err) {
self->comm_set = true;
}
return err;
}
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 thread__comm_len(struct thread *self)
{
if (!self->comm_len) {
if (!self->comm)
return 0;
self->comm_len = strlen(self->comm);
}
return self->comm_len;
}
size_t thread__fprintf(struct thread *thread, FILE *fp)
{
return fprintf(fp, "Thread %d %s\n", thread->tid, thread->comm) +
map_groups__fprintf(&thread->mg, verbose, fp);
}
perf tools: Use rb_tree for maps Threads can have many and kernel modules will be represented as a tree of maps as well. Ah, and for a perf.data with 146607 samples: Before: [root@doppio ~]# perf stat -r 5 perf report > /dev/null Performance counter stats for 'perf report' (5 runs): 699.823680 task-clock-msecs # 0.991 CPUs ( +- 0.454% ) 74 context-switches # 0.000 M/sec ( +- 1.709% ) 2 CPU-migrations # 0.000 M/sec ( +- 17.008% ) 23114 page-faults # 0.033 M/sec ( +- 0.000% ) 1381257019 cycles # 1973.721 M/sec ( +- 0.290% ) 1456894438 instructions # 1.055 IPC ( +- 0.007% ) 18779818 cache-references # 26.835 M/sec ( +- 0.380% ) 641799 cache-misses # 0.917 M/sec ( +- 1.200% ) 0.705972729 seconds time elapsed ( +- 0.501% ) [root@doppio ~]# After Performance counter stats for 'perf report' (5 runs): 691.261451 task-clock-msecs # 0.993 CPUs ( +- 0.307% ) 72 context-switches # 0.000 M/sec ( +- 0.829% ) 6 CPU-migrations # 0.000 M/sec ( +- 18.409% ) 23127 page-faults # 0.033 M/sec ( +- 0.000% ) 1366395876 cycles # 1976.670 M/sec ( +- 0.153% ) 1443136016 instructions # 1.056 IPC ( +- 0.012% ) 17956402 cache-references # 25.976 M/sec ( +- 0.325% ) 661924 cache-misses # 0.958 M/sec ( +- 1.335% ) 0.696127275 seconds time elapsed ( +- 0.377% ) I.e. we see some speedup too. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: "H. Peter Anvin" <hpa@zytor.com> LKML-Reference: <20090928174846.GA3361@ghostprotocols.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-28 17:48:46 +00:00
void thread__insert_map(struct thread *self, struct map *map)
{
map_groups__fixup_overlappings(&self->mg, map, verbose, stderr);
map_groups__insert(&self->mg, map);
}
int thread__fork(struct thread *self, struct thread *parent)
{
int i;
if (parent->comm_set) {
if (self->comm)
free(self->comm);
self->comm = strdup(parent->comm);
if (!self->comm)
return -ENOMEM;
self->comm_set = true;
}
for (i = 0; i < MAP__NR_TYPES; ++i)
if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
return -ENOMEM;
self->ppid = parent->tid;
return 0;
}