cmd_ipc4: retry sendmsg on ENOBUFS/ENOMEM/ETOOMANYREFS

I'm seeing ENOBUFS on a RAM-starved system, and slowing the
sender down enough for the receiver to drain the buffers seems
to work.  ENOMEM and ETOOMANYREFS could be in the same boat
as ENOBUFS.

Watching for POLLOUT events via select/poll/epoll_wait doesn't
seem to work, since the kernel can already sleep (or return
EAGAIN) for cases where POLLOUT would work.

diff --git a/lib/PublicInbox/CmdIPC4.pm b/lib/PublicInbox/CmdIPC4.pm
index 74dbf8a12ee4a8090a16d75a8ddbcaee6271cf3b..c3a7f56ec7e3f356243d270447402aa3217c499a 100644 (file)
--- a/lib/PublicInbox/CmdIPC4.pm
+++ b/lib/PublicInbox/CmdIPC4.pm
@@ -17,7 +17,16 @@ no warnings 'once';
        my ($sock, $fds, undef, $flags) = @_;
        my $mh = Socket::MsgHdr->new(buf => $_[2]);
        $mh->cmsghdr(SOL_SOCKET, SCM_RIGHTS, pack('i' x scalar(@$fds), @$fds));
        my ($sock, $fds, undef, $flags) = @_;
        my $mh = Socket::MsgHdr->new(buf => $_[2]);
        $mh->cmsghdr(SOL_SOCKET, SCM_RIGHTS, pack('i' x scalar(@$fds), @$fds));

-       Socket::MsgHdr::sendmsg($sock, $mh, $flags);
+       my $s;
+       my $try = 0;
+       do {
+               $s = Socket::MsgHdr::sendmsg($sock, $mh, $flags);
+       } while (!defined($s) &&
+                       ($!{ENOBUFS} || $!{ENOMEM} || $!{ETOOMANYREFS}) &&
+                       (++$try < 50) &&
+                       warn "sleeping on sendmsg: $! (#$try)\n" &&
+                       select(undef, undef, undef, 0.1) == 0);
+       $s;

 };
 
 *recv_cmd4 = sub ($$$) {
 };
 
 *recv_cmd4 = sub ($$$) {

diff --git a/lib/PublicInbox/Spawn.pm b/lib/PublicInbox/Spawn.pm
index e940d3c9d7f44710e86b8b1118f921cf8cea562e..6ca1ca2a0be3538b3cb9dc663422698b6b94952b 100644 (file)
--- a/lib/PublicInbox/Spawn.pm
+++ b/lib/PublicInbox/Spawn.pm
@@ -34,6 +34,9 @@ BEGIN {
 #include <unistd.h>
 #include <stdlib.h>
 #include <errno.h>
 #include <unistd.h>
 #include <stdlib.h>
 #include <errno.h>

+#include <time.h>
+#include <stdio.h>
+#include <string.h>

 
 /* some platforms need alloca.h, but some don't */
 #if defined(__GNUC__) && !defined(alloca)
 
 /* some platforms need alloca.h, but some don't */
 #if defined(__GNUC__) && !defined(alloca)


@@ -162,6 +165,22 @@ int pi_fork_exec(SV *redirref, SV *file, SV *cmdref, SV *envref, SV *rlimref,
        return (int)pid;
 }
 
        return (int)pid;
 }
 

+static int sleep_wait(unsigned *try, int err)
+{
+       const struct timespec req = { 0, 100000000 }; /* 100ms */
+       switch (err) {
+       case ENOBUFS: case ENOMEM: case ETOOMANYREFS:
+               if (++*try < 50) {
+                       fprintf(stderr, "sleeping on sendmsg: %s (#%u)\n",
+                               strerror(err), *try);
+                       nanosleep(&req, NULL);
+                       return 1;
+               }
+       default:
+               return 0;
+       }
+}
+

 #if defined(CMSG_SPACE) && defined(CMSG_LEN)
 #define SEND_FD_CAPA 10
 #define SEND_FD_SPACE (SEND_FD_CAPA * sizeof(int))
 #if defined(CMSG_SPACE) && defined(CMSG_LEN)
 #define SEND_FD_CAPA 10
 #define SEND_FD_SPACE (SEND_FD_CAPA * sizeof(int))


@@ -180,6 +199,7 @@ SV *send_cmd4(PerlIO *s, SV *svfds, SV *data, int flags)
        AV *fds = (AV *)SvRV(svfds);
        I32 i, nfds = av_len(fds) + 1;
        int *fdp;
        AV *fds = (AV *)SvRV(svfds);
        I32 i, nfds = av_len(fds) + 1;
        int *fdp;

+       unsigned try = 0;

 
        if (SvOK(data)) {
                iov.iov_base = SvPV(data, dlen);
 
        if (SvOK(data)) {
                iov.iov_base = SvPV(data, dlen);


@@ -207,7 +227,9 @@ SV *send_cmd4(PerlIO *s, SV *svfds, SV *data, int flags)
                        *fdp++ = SvIV(*fd);
                }
        }
                        *fdp++ = SvIV(*fd);
                }
        }

-       sent = sendmsg(PerlIO_fileno(s), &msg, flags);
+       do {
+               sent = sendmsg(PerlIO_fileno(s), &msg, flags);
+       } while (sent < 0 && sleep_wait(&try, errno));

        return sent >= 0 ? newSViv(sent) : &PL_sv_undef;
 }
 
        return sent >= 0 ? newSViv(sent) : &PL_sv_undef;
 }
 


@@ -258,9 +280,6 @@ ALL_LIBC
 #include <linux/magic.h>
 #include <linux/fs.h>
 #include <dirent.h>
 #include <linux/magic.h>
 #include <linux/fs.h>
 #include <dirent.h>

-#include <errno.h>
-#include <stdio.h>
-#include <string.h>

 
 void nodatacow_fd(int fd)
 {
 
 void nodatacow_fd(int fd)
 {