Allow hint bits to be set sooner for temporary and unlogged tables.

We need not wait until the commit record is durably on disk, because
in the event of a crash the page we're updating with hint bits will
be gone anyway.  Per off-list report from Heikki Linnakangas, this
can significantly degrade the performance of unlogged tables; I was
able to show a 2x speedup from this patch on a pgbench run with scale
factor 15.  In practice, this will mostly help small, heavily updated
tables, because on larger tables you're unlikely to run into the same
row again before the commit record makes it out to disk.

diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index 8647eddcb427682b3b7c85980bfa056af9e5ee34..f47f1b66b1f34246141bc51694b336159b124841 100644 (file)
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -1929,6 +1929,35 @@ RelationGetNumberOfBlocksInFork(Relation relation, ForkNumber forkNum)
    return smgrnblocks(relation->rd_smgr, forkNum);
 }
 
+/*
+ * BufferIsPermanent
+ *     Determines whether a buffer will potentially still be around after
+ *     a crash.  Caller must hold a buffer pin.
+ */
+bool
+BufferIsPermanent(Buffer buffer)
+{
+   volatile BufferDesc *bufHdr;
+
+   /* Local buffers are used only for temp relations. */
+   if (BufferIsLocal(buffer))
+       return false;
+
+   /* Make sure we've got a real buffer, and that we hold a pin on it. */
+   Assert(BufferIsValid(buffer));
+   Assert(BufferIsPinned(buffer));
+
+   /*
+    * BM_PERMANENT can't be changed while we hold a pin on the buffer, so
+    * we need not bother with the buffer header spinlock.  Even if someone
+    * else changes the buffer header flags while we're doing this, we assume
+    * that changing an aligned 2-byte BufFlags value is atomic, so we'll read
+    * the old value or the new value, but not random garbage.
+    */
+   bufHdr = &BufferDescriptors[buffer - 1];
+   return (bufHdr->flags & BM_PERMANENT) != 0;
+}
+
 /* ---------------------------------------------------------------------
  *     DropRelFileNodeBuffers
  *

diff --git a/src/backend/utils/time/tqual.c b/src/backend/utils/time/tqual.c
index d81ee7de062500714a8cb960add31ba40e8794c9..1c4b74d94b51e9ae91e2453402c54db6a7927f99 100644 (file)
--- a/src/backend/utils/time/tqual.c
+++ b/src/backend/utils/time/tqual.c
@@ -82,10 +82,12 @@ static bool XidInMVCCSnapshot(TransactionId xid, Snapshot snapshot);
  * Set commit/abort hint bits on a tuple, if appropriate at this time.
  *
  * It is only safe to set a transaction-committed hint bit if we know the
- * transaction's commit record has been flushed to disk.  We cannot change
- * the LSN of the page here because we may hold only a share lock on the
- * buffer, so we can't use the LSN to interlock this; we have to just refrain
- * from setting the hint bit until some future re-examination of the tuple.
+ * transaction's commit record has been flushed to disk, or if the table is
+ * temporary or unlogged and will be obliterated by a crash anyway.  We
+ * cannot change the LSN of the page here because we may hold only a share
+ * lock on the buffer, so we can't use the LSN to interlock this; we have to
+ * just refrain from setting the hint bit until some future re-examination
+ * of the tuple.
  *
  * We can always set hint bits when marking a transaction aborted. (Some
  * code in heapam.c relies on that!)
@@ -113,7 +115,7 @@ SetHintBits(HeapTupleHeader tuple, Buffer buffer,
        /* NB: xid must be known committed here! */
        XLogRecPtr  commitLSN = TransactionIdGetCommitLSN(xid);
 
-       if (XLogNeedsFlush(commitLSN))
+       if (XLogNeedsFlush(commitLSN) && BufferIsPermanent(buffer))
            return;             /* not flushed yet, so don't set hint */
    }
 

diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index 82b43006f3e0be0e5dd724de943c48e270edc4db..49b5d314ff0331f8c140f97b7d4a6bfd68cc6fea 100644 (file)
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -192,6 +192,8 @@ extern void DropDatabaseBuffers(Oid dbid);
 #define RelationGetNumberOfBlocks(reln) \
    RelationGetNumberOfBlocksInFork(reln, MAIN_FORKNUM)
 
+extern bool BufferIsPermanent(Buffer buffer);
+
 #ifdef NOT_USED
 extern void PrintPinnedBufs(void);
 #endif