BUG/MINOR: checks: make external-checks restore the original rlim_fd_cur/max

It's not normal that external processes are run with high FD limits,
as quite often such processes (especially shell scripts) will iterate
over all FDs to close them. Ideally we should even provide a tunable
with the external-check directive to adjust this value, but at least
we need to restore it to the value that was active when starting
haproxy (before it was adjusted for maxconn). Additionally with very
low maxconn values causing rlim_fd_cur to be low, some heavy checks
could possibly fail. This was also mentioned in issue #45.

Currently the following config and scripts report this :

  $ cat rlim.cfg
  global
      maxconn 500000
      external-check

  listen www
      bind :8001
      timeout client 5s
      timeout server 5s
      timeout connect 5s
      option external-check
      external-check command "$PWD/sleep1.sh"
      server local 127.0.0.1:80 check inter 1s

  $ cat sleep1.sh
  #!/bin/sh
  /bin/sleep 0.1
  echo -n "soft: ";ulimit -S -n
  echo -n "hard: ";ulimit -H -n

  # ./haproxy -db -f rlim.cfg
  soft: 1000012
  hard: 1000012
  soft: 1000012
  hard: 1000012

Now with the fix :
  # ./haproxy -db -f rlim.cfg
  soft: 1024
  hard: 4096
  soft: 1024
  hard: 4096

This fix should be backported to stable versions but it depends on
"MINOR: global: keep a copy of the initial rlim_fd_cur and rlim_fd_max
values" and "BUG/MINOR: init: never lower rlim_fd_max".

diff --git a/src/checks.c b/src/checks.c
index 6d7b6aa..2359176 100644 (file)
--- a/src/checks.c
+++ b/src/checks.c
@@ -22,6 +22,7 @@
 #include <string.h>
 #include <time.h>
 #include <unistd.h>
+#include <sys/resource.h>
 #include <sys/socket.h>
 #include <sys/types.h>
 #include <sys/wait.h>
@@ -1965,6 +1966,7 @@ static int connect_proc_chk(struct task *t)
        if (pid == 0) {
                /* Child */
                extern char **environ;
+               struct rlimit limit;
                int fd;
 
                /* close all FDs. Keep stdin/stdout/stderr in verbose mode */
@@ -1972,6 +1974,16 @@ static int connect_proc_chk(struct task *t)
 
                my_closefrom(fd);
 
+               /* restore the initial FD limits */
+               limit.rlim_cur = rlim_fd_cur_at_boot;
+               limit.rlim_max = rlim_fd_max_at_boot;
+               if (setrlimit(RLIMIT_NOFILE, &limit) == -1) {
+                       getrlimit(RLIMIT_NOFILE, &limit);
+                       ha_warning("External check: failed to restore initial FD limits (cur=%u max=%u), using cur=%u max=%u\n",
+                                  rlim_fd_cur_at_boot, rlim_fd_max_at_boot,
+                                  (unsigned int)limit.rlim_cur, (unsigned int)limit.rlim_max);
+               }
+
                environ = check->envp;
                extchk_setenv(check, EXTCHK_HAPROXY_SERVER_CURCONN, ultoa_r(s->cur_sess, buf, sizeof(buf)));
                execvp(px->check_command, check->argv);