For bulk write operations (eg COPY IN), use a ring buffer of 16MB instead

of the 256KB limit originally enforced by a patch committed 2008-11-06.
Per recent test results, the smaller size resulted in an undesirable decrease
in bulk data loading speed, due to COPY processing frequently getting blocked
for WAL flushing.  This area might need more tweaking later, but this setting
seems to be good enough for 8.4.

diff --git a/src/backend/storage/buffer/README b/src/backend/storage/buffer/README
index bfacfea0f1d2d997a4c1032ed2e1f12028173e07..6669ab4028e0cffd7a57764ea6d212c8accac2d0 100644 (file)
--- a/src/backend/storage/buffer/README
+++ b/src/backend/storage/buffer/README
@@ -237,7 +237,12 @@ buffer, resulting in excessive WAL flushing.  Allowing VACUUM to update
 
 Bulk writes work similarly to VACUUM.  Currently this applies only to
 COPY IN and CREATE TABLE AS SELECT.  (Might it be interesting to make
-seqscan UPDATE and DELETE use the bulkwrite strategy?)
+seqscan UPDATE and DELETE use the bulkwrite strategy?)  For bulk writes
+we use a ring size of 16MB (but not more than 1/8th of shared_buffers).
+Smaller sizes have been shown to result in the COPY blocking too often
+for WAL flushes.  While it's okay for a background vacuum to be slowed by
+doing its own WAL flushing, we'd prefer that COPY not be subject to that,
+so we let it use up a bit more of the buffer arena.
 
 
 Background Writer's Processing

diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index b52a0c03d1b7e026431507a01f88e2d086790545..d16efcfbcd7506a95470acb8cb03c9daeada39b9 100644 (file)
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -368,9 +368,7 @@ GetAccessStrategy(BufferAccessStrategyType btype)
        int                     ring_size;
 
        /*
-        * Select ring size to use.  See buffer/README for rationales. (Currently
-        * all cases are the same size, but keep this code structure for
-        * flexibility.)
+        * Select ring size to use.  See buffer/README for rationales.
         *
         * Note: if you change the ring size for BAS_BULKREAD, see also
         * SYNC_SCAN_REPORT_INTERVAL in access/heap/syncscan.c.
@@ -385,7 +383,7 @@ GetAccessStrategy(BufferAccessStrategyType btype)
                        ring_size = 256 * 1024 / BLCKSZ;
                        break;
                case BAS_BULKWRITE:
-                       ring_size = 256 * 1024 / BLCKSZ;
+                       ring_size = 16 * 1024 * 1024 / BLCKSZ;
                        break;
                case BAS_VACUUM:
                        ring_size = 256 * 1024 / BLCKSZ;