Sync unlogged relations to disk after they have been reset.

Unlogged relations are only reset when performing a unclean
restart. That means they have to be synced to disk during clean
shutdowns. During normal processing that's achieved by registering a
buffer's file to be fsynced at the next checkpoint when flushed. But
ResetUnloggedRelations() doesn't go through the buffer manager, so
nothing will force reset relations to disk before the next shutdown
checkpoint.

So just make ResetUnloggedRelations() fsync the newly created main
forks to disk.

Discussion: 20140912112246.GA4984@alap3.anarazel.de

Backpatch to 9.1 where unlogged tables were introduced.

Abhijit Menon-Sen and Andres Freund

diff --git a/src/backend/storage/file/reinit.c b/src/backend/storage/file/reinit.c
index 3229f41d62b120347681412c7e691f28c0ee8d75..2a31ace2c5a7f7947a2c9ba9bb5b4f19db9bf3cd 100644 (file)
--- a/src/backend/storage/file/reinit.c
+++ b/src/backend/storage/file/reinit.c
@@ -339,6 +339,53 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
                }
 
                FreeDir(dbspace_dir);
+
+               /*
+                * copy_file() above has already called pg_flush_data() on the
+                * files it created. Now we need to fsync those files, because
+                * a checkpoint won't do it for us while we're in recovery. We
+                * do this in a separate pass to allow the kernel to perform
+                * all the flushes (especially the metadata ones) at once.
+                */
+               dbspace_dir = AllocateDir(dbspacedirname);
+               if (dbspace_dir == NULL)
+               {
+                       /* we just saw this directory, so it really ought to be there */
+                       elog(LOG,
+                                "could not open dbspace directory \"%s\": %m",
+                                dbspacedirname);
+                       return;
+               }
+
+               while ((de = ReadDir(dbspace_dir, dbspacedirname)) != NULL)
+               {
+                       ForkNumber      forkNum;
+                       int                     oidchars;
+                       char            oidbuf[OIDCHARS + 1];
+                       char            mainpath[MAXPGPATH];
+
+                       /* Skip anything that doesn't look like a relation data file. */
+                       if (!parse_filename_for_nontemp_relation(de->d_name, &oidchars,
+                                                                                                        &forkNum))
+                               continue;
+
+                       /* Also skip it unless this is the init fork. */
+                       if (forkNum != INIT_FORKNUM)
+                               continue;
+
+                       /* Construct main fork pathname. */
+                       memcpy(oidbuf, de->d_name, oidchars);
+                       oidbuf[oidchars] = '\0';
+                       snprintf(mainpath, sizeof(mainpath), "%s/%s%s",
+                                        dbspacedirname, oidbuf, de->d_name + oidchars + 1 +
+                                        strlen(forkNames[INIT_FORKNUM]));
+
+                       fsync_fname(mainpath, false);
+               }
+
+               FreeDir(dbspace_dir);
+
+               fsync_fname((char *) dbspacedirname, true);
        }
 }