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

diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 1d4aa482ccdd04e1c287e7bc46b30ead47c71e4a..c697af00d98c58b53223d53bc7a6af45fdec8a92 100644 (file)
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -286,6 +286,41 @@ 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)
 {
@@ -299,38 +334,31 @@ mdunlinkfork(RelFileNodeBackend rnode, ForkNumber forkNum, bool isRedo)
     */
    if (isRedo || forkNum != MAIN_FORKNUM || RelFileNodeBackendIsTemp(rnode))
    {
-       /* First, forget any pending sync requests for the first segment */
        if (!RelFileNodeBackendIsTemp(rnode))
+       {
+           /* Prevent other backends' fds from holding on to the disk space */
+           ret = do_truncate(path);
+
+           /* Forget any pending sync requests for the first segment */
            register_forget_request(rnode, forkNum, 0 /* first seg */ );
+       }
+       else
+           ret = 0;
 
-       /* Next unlink the file */
-       ret = unlink(path);
-       if (ret < 0 && errno != ENOENT)
-           ereport(WARNING,
-                   (errcode_for_file_access(),
-                    errmsg("could not remove file \"%s\": %m", path)));
+       /* 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_segment(rnode, forkNum, 0 /* first seg */ );
@@ -350,14 +378,24 @@ mdunlinkfork(RelFileNodeBackend rnode, ForkNumber forkNum, bool isRedo)
         */
        for (segno = 1;; segno++)
        {
-           /*
-            * Forget any pending sync requests for this segment before we try
-            * to unlink.
-            */
+           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;
+
+               /*
+                * Forget any pending sync requests for this segment before we
+                * try to unlink.
+                */
                register_forget_request(rnode, forkNum, segno);
+           }
 
-           sprintf(segpath, "%s.%u", path, segno);
            if (unlink(segpath) < 0)
            {
                /* ENOENT is expected after the last segment... */