From ff78bf796d8069002eb75edd0d5fc7fc6bf0a63b Mon Sep 17 00:00:00 2001 From: Thomas Munro Date: Wed, 13 Jul 2022 16:16:07 +1200 Subject: [PATCH] Block signals while allocating DSM memory. On Linux, we call posix_fallocate() on shm_open()'d memory to avoid later potential SIGBUS (see commit 899bd785). Based on field reports of systems stuck in an EINTR retry loop there, there, we made it possible to break out of that loop via slightly odd coding where the CHECK_FOR_INTERRUPTS() call was somewhat removed from the loop (see commit 422952ee). On further reflection, that was not a great choice for at least two reasons: 1. If interrupts were held, the CHECK_FOR_INTERRUPTS() would do nothing and the EINTR error would be surfaced to the user. 2. If EINTR was reported but neither QueryCancelPending nor ProcDiePending was set, then we'd dutifully retry, but with a bit more understanding of how posix_fallocate() works, it's now clear that you can get into a loop that never terminates. posix_fallocate() is not a function that can do some of the job and tell you about progress if it's interrupted, it has to undo what it's done so far and report EINTR, and if signals keep arriving faster than it can complete (cf recovery conflict signals), you're stuck. Therefore, for now, we'll simply block most signals to guarantee progress. SIGQUIT is not blocked (see InitPostmasterChild()), because its expected handler doesn't return, and unblockable signals like SIGCONT are not expected to arrive at a high rate. For good measure, we'll include the ftruncate() call in the blocked region, and add a retry loop. Back-patch to all supported releases. Reported-by: Alvaro Herrera Reported-by: Nicola Contu Reviewed-by: Alvaro Herrera Reviewed-by: Andres Freund Discussion: https://postgr.es/m/20220701154105.jjfutmngoedgiad3%40alvherre.pgsql --- src/backend/storage/ipc/dsm_impl.c | 39 ++++++++++++++++++------------ 1 file changed, 24 insertions(+), 15 deletions(-) diff --git a/src/backend/storage/ipc/dsm_impl.c b/src/backend/storage/ipc/dsm_impl.c index 33ebe94021..69567fc5a2 100644 --- a/src/backend/storage/ipc/dsm_impl.c +++ b/src/backend/storage/ipc/dsm_impl.c @@ -61,9 +61,10 @@ #ifdef HAVE_SYS_SHM_H #include #endif -#include "common/file_perm.h" -#include "pgstat.h" +#include "common/file_perm.h" +#include "libpq/pqsignal.h" /* for PG_SETMASK macro */ +#include "pgstat.h" #include "portability/mem.h" #include "storage/dsm_impl.h" #include "storage/fd.h" @@ -298,14 +299,6 @@ dsm_impl_posix(dsm_op op, dsm_handle handle, Size request_size, shm_unlink(name); errno = save_errno; - /* - * If we received a query cancel or termination signal, we will have - * EINTR set here. If the caller said that errors are OK here, check - * for interrupts immediately. - */ - if (errno == EINTR && elevel >= ERROR) - CHECK_FOR_INTERRUPTS(); - ereport(elevel, (errcode_for_dynamic_shared_memory(), errmsg("could not resize shared memory segment \"%s\" to %zu bytes: %m", @@ -351,9 +344,21 @@ static int dsm_impl_posix_resize(int fd, off_t size) { int rc; + int save_errno; + + /* + * Block all blockable signals, except SIGQUIT. posix_fallocate() can run + * for quite a long time, and is an all-or-nothing operation. If we + * allowed SIGUSR1 to interrupt us repeatedly (for example, due to recovery + * conflicts), the retry loop might never succeed. + */ + PG_SETMASK(&BlockSig); /* Truncate (or extend) the file to the requested size. */ - rc = ftruncate(fd, size); + do + { + rc = ftruncate(fd, size); + } while (rc < 0 && errno == EINTR); /* * On Linux, a shm_open fd is backed by a tmpfs file. After resizing with @@ -367,14 +372,14 @@ dsm_impl_posix_resize(int fd, off_t size) if (rc == 0) { /* - * We may get interrupted. If so, just retry unless there is an - * interrupt pending. This avoids the possibility of looping forever - * if another backend is repeatedly trying to interrupt us. + * We still use a traditional EINTR retry loop to handle SIGCONT. + * posix_fallocate() doesn't restart automatically, and we don't want + * this to fail if you attach a debugger. */ do { rc = posix_fallocate(fd, 0, size); - } while (rc == EINTR && !(ProcDiePending || QueryCancelPending)); + } while (rc == EINTR); /* * The caller expects errno to be set, but posix_fallocate() doesn't @@ -385,6 +390,10 @@ dsm_impl_posix_resize(int fd, off_t size) } #endif /* HAVE_POSIX_FALLOCATE && __linux__ */ + save_errno = errno; + PG_SETMASK(&UnBlockSig); + errno = save_errno; + return rc; }