From 051ae7f7344f453616b6b10332d4d8e1d40ed823 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 29 Jun 2009 21:13:21 +1000 Subject: [PATCH] perf_counter tools: Reduce perf stat measurement overhead/skew Vince Weaver reported a 'perf stat' measurement overhead in the count of retired instructions, which can amount to a +6000 instructions inflated count in the reported count. At present, perf stat creates its counters on the perf process. Thus the counters count the fork and various other activity in both the parent and child, such as the resolver overhead for resolving PLT entries for any libc functions that haven't been called before, such as execvp. This reduces the overhead by creating the counters on the child process after the fork, using a couple of pipes to synchronize so that the child process waits until the parent has created the counters before doing the exec. To eliminate the PLT resolution overhead on calling execvp, this does a dummy execvp first which will always fail. With this, the overhead of executing a program goes down from over 4800 instructions to about 90 instructions on powerpc (32-bit). This was measured with a statically-linked program written in assembler which only does the 3 instructions needed to call _exit(0). Before: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 4858 instructions 0.001274523 seconds time elapsed After: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 92 instructions 0.000468153 seconds time elapsed Reported-by: Vince Weaver Signed-off-by: Paul Mackerras Cc: Peter Zijlstra LKML-Reference: <19016.41425.814043.870352@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar --- tools/perf/builtin-stat.c | 64 ++++++++++++++++++++++++++++++--------- 1 file changed, 50 insertions(+), 14 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index c5a290727a92..201ef2367dcb 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -99,7 +99,7 @@ static u64 runtime_cycles_noise; #define ERR_PERF_OPEN \ "Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n" -static void create_perf_stat_counter(int counter) +static void create_perf_stat_counter(int counter, int pid) { struct perf_counter_attr *attr = attrs + counter; @@ -119,7 +119,7 @@ static void create_perf_stat_counter(int counter) attr->inherit = inherit; attr->disabled = 1; - fd[0][counter] = sys_perf_counter_open(attr, 0, -1, -1, 0); + fd[0][counter] = sys_perf_counter_open(attr, pid, -1, -1, 0); if (fd[0][counter] < 0 && verbose) fprintf(stderr, ERR_PERF_OPEN, counter, fd[0][counter], strerror(errno)); @@ -205,12 +205,58 @@ static int run_perf_stat(int argc, const char **argv) int status = 0; int counter; int pid; + int child_ready_pipe[2], go_pipe[2]; + char buf; if (!system_wide) nr_cpus = 1; + if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) { + perror("failed to create pipes"); + exit(1); + } + + if ((pid = fork()) < 0) + perror("failed to fork"); + + if (!pid) { + close(child_ready_pipe[0]); + close(go_pipe[1]); + fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); + + /* + * Do a dummy execvp to get the PLT entry resolved, + * so we avoid the resolver overhead on the real + * execvp call. + */ + execvp("", (char **)argv); + + /* + * Tell the parent we're ready to go + */ + close(child_ready_pipe[1]); + + /* + * Wait until the parent tells us to go. + */ + read(go_pipe[0], &buf, 1); + + execvp(argv[0], (char **)argv); + + perror(argv[0]); + exit(-1); + } + + /* + * Wait for the child to be ready to exec. + */ + close(child_ready_pipe[1]); + close(go_pipe[0]); + read(child_ready_pipe[0], &buf, 1); + close(child_ready_pipe[0]); + for (counter = 0; counter < nr_counters; counter++) - create_perf_stat_counter(counter); + create_perf_stat_counter(counter, pid); /* * Enable counters and exec the command: @@ -218,19 +264,9 @@ static int run_perf_stat(int argc, const char **argv) t0 = rdclock(); prctl(PR_TASK_PERF_COUNTERS_ENABLE); - if ((pid = fork()) < 0) - perror("failed to fork"); - - if (!pid) { - if (execvp(argv[0], (char **)argv)) { - perror(argv[0]); - exit(-1); - } - } - + close(go_pipe[1]); wait(&status); - prctl(PR_TASK_PERF_COUNTERS_DISABLE); t1 = rdclock(); walltime_nsecs[run_idx] = t1 - t0; -- 2.34.1