Free disk space for dropped relations on commit.

When committing a transaction that dropped a relation, we previously
truncated only the first segment file to free up disk space (the one
that won't be unlinked until the next checkpoint).

Truncate higher numbered segments too, even though we unlink them on
commit.  This frees the disk space immediately, even if other backends
have open file descriptors and might take a long time to get around to
handling shared invalidation events and closing them.  Also extend the
same behavior to the first segment, in recovery.

Back-patch to all supported releases.

Bug: #16663
Reported-by: Denis Patron <denis.patron@previnet.it>
Reviewed-by: Pavel Borisov <pashkin.elfe@gmail.com>
Reviewed-by: Neil Chen <carpenter.nail.cz@gmail.com>
Reviewed-by: David Zhang <david.zhang@highgo.ca>
Discussion: https://postgr.es/m/16663-fe97ccf9932fc800%40postgresql.org
This commit is contained in:
Thomas Munro 2020-12-01 13:46:27 +13:00
parent ed9c9b0335
commit d5706ad7b7
1 changed files with 65 additions and 24 deletions

View File

@ -406,6 +406,41 @@ mdunlink(RelFileNodeBackend rnode, ForkNumber forkNum, bool isRedo)
mdunlinkfork(rnode, forkNum, isRedo);
}
/*
* Truncate a file to release disk space.
*/
static int
do_truncate(const char *path)
{
int save_errno;
int ret;
int fd;
/* truncate(2) would be easier here, but Windows hasn't got it */
fd = OpenTransientFile(path, O_RDWR | PG_BINARY);
if (fd >= 0)
{
ret = ftruncate(fd, 0);
save_errno = errno;
CloseTransientFile(fd);
errno = save_errno;
}
else
ret = -1;
/* Log a warning here to avoid repetition in callers. */
if (ret < 0 && errno != ENOENT)
{
save_errno = errno;
ereport(WARNING,
(errcode_for_file_access(),
errmsg("could not truncate file \"%s\": %m", path)));
errno = save_errno;
}
return ret;
}
static void
mdunlinkfork(RelFileNodeBackend rnode, ForkNumber forkNum, bool isRedo)
{
@ -419,33 +454,28 @@ mdunlinkfork(RelFileNodeBackend rnode, ForkNumber forkNum, bool isRedo)
*/
if (isRedo || forkNum != MAIN_FORKNUM || RelFileNodeBackendIsTemp(rnode))
{
ret = unlink(path);
if (ret < 0 && errno != ENOENT)
ereport(WARNING,
(errcode_for_file_access(),
errmsg("could not remove file \"%s\": %m", path)));
if (!RelFileNodeBackendIsTemp(rnode))
{
/* Prevent other backends' fds from holding on to the disk space */
ret = do_truncate(path);
}
else
ret = 0;
/* Next unlink the file, unless it was already found to be missing */
if (ret == 0 || errno != ENOENT)
{
ret = unlink(path);
if (ret < 0 && errno != ENOENT)
ereport(WARNING,
(errcode_for_file_access(),
errmsg("could not remove file \"%s\": %m", path)));
}
}
else
{
/* truncate(2) would be easier here, but Windows hasn't got it */
int fd;
fd = OpenTransientFile(path, O_RDWR | PG_BINARY);
if (fd >= 0)
{
int save_errno;
ret = ftruncate(fd, 0);
save_errno = errno;
CloseTransientFile(fd);
errno = save_errno;
}
else
ret = -1;
if (ret < 0 && errno != ENOENT)
ereport(WARNING,
(errcode_for_file_access(),
errmsg("could not truncate file \"%s\": %m", path)));
/* Prevent other backends' fds from holding on to the disk space */
ret = do_truncate(path);
/* Register request to unlink first segment later */
register_unlink(rnode);
@ -466,6 +496,17 @@ mdunlinkfork(RelFileNodeBackend rnode, ForkNumber forkNum, bool isRedo)
for (segno = 1;; segno++)
{
sprintf(segpath, "%s.%u", path, segno);
if (!RelFileNodeBackendIsTemp(rnode))
{
/*
* Prevent other backends' fds from holding on to the disk
* space.
*/
if (do_truncate(segpath) < 0 && errno == ENOENT)
break;
}
if (unlink(segpath) < 0)
{
/* ENOENT is expected after the last segment... */