perf data: Increase RLIMIT_NOFILE limit when open too many files in perf_data__create...

If using parallel threads to collect data, perf record needs at least 6 fds
per CPU. (one for sys_perf_event_open, four for pipe msg and ack of the
pipe, see record__thread_data_open_pipes(), and one for open perf.data.XXX)
For an environment with more than 100 cores, if perf record uses both
`-a` and `--threads` options, it is easy to exceed the upper limit of the
file descriptor number, when we run out of them try to increase the limits.

Before:
  $ ulimit -n
  1024
  $ lscpu | grep 'On-line CPU(s)'
  On-line CPU(s) list:                0-159
  $ perf record --threads -a sleep 1
  Failed to create data directory: Too many open files

After:
  $ ulimit -n
  1024
  $ lscpu | grep 'On-line CPU(s)'
  On-line CPU(s) list:                0-159
  $ perf record --threads -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.394 MB perf.data (1576 samples) ]

Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20231013075945.698874-1-yangjihong1@huawei.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index fc16299c915f9b51c79f79a77307c35b8dabbe57..098f9e3bb2e7690916682c604aa1d2cce421d3e0 100644 (file)
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -17,6 +17,7 @@
 #include "util.h" // rm_rf_perf_data()
 #include "debug.h"
 #include "header.h"
+#include "evsel.h"
 #include <internal/lib.h>
 
 static void close_dir(struct perf_data_file *files, int nr)
@@ -35,6 +36,7 @@ void perf_data__close_dir(struct perf_data *data)
 
 int perf_data__create_dir(struct perf_data *data, int nr)
 {
+       enum rlimit_action set_rlimit = NO_CHANGE;
        struct perf_data_file *files = NULL;
        int i, ret;
 
@@ -54,11 +56,21 @@ int perf_data__create_dir(struct perf_data *data, int nr)
                        goto out_err;
                }
 
+retry_open:
                ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR);
                if (ret < 0) {
+                       /*
+                        * If using parallel threads to collect data,
+                        * perf record needs at least 6 fds per CPU.
+                        * When we run out of them try to increase the limits.
+                        */
+                       if (errno == EMFILE && evsel__increase_rlimit(&set_rlimit))
+                               goto retry_open;
+
                        ret = -errno;
                        goto out_err;
                }
+               set_rlimit = NO_CHANGE;
 
                file->fd = ret;
        }