diff --git a/src/backend/access/heap/Makefile b/src/backend/access/heap/Makefile
index 3a712191a496ebeaf50151b95d0ed6f841759dfb..ac2401232bb25aeece49dec4850fc451ec73f064 100644
--- a/src/backend/access/heap/Makefile
+++ b/src/backend/access/heap/Makefile
@@ -4,7 +4,7 @@
# Makefile for access/heap
#
# IDENTIFICATION
-# $PostgreSQL: pgsql/src/backend/access/heap/Makefile,v 1.15 2007/04/08 01:26:27 tgl Exp $
+# $PostgreSQL: pgsql/src/backend/access/heap/Makefile,v 1.16 2007/06/08 18:23:52 tgl Exp $
#
#-------------------------------------------------------------------------
@@ -12,7 +12,7 @@ subdir = src/backend/access/heap
top_builddir = ../../../..
include $(top_builddir)/src/Makefile.global
-OBJS = heapam.o hio.o rewriteheap.o tuptoaster.o
+OBJS = heapam.o hio.o rewriteheap.o syncscan.o tuptoaster.o
all: SUBSYS.o
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 0b20e5e9a8db2671ee9331a20bfcfc868aeea588..a0b561c209e046ce2ef00981ab9aa61520c4b88d 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/backend/access/heap/heapam.c,v 1.234 2007/05/30 20:11:53 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/access/heap/heapam.c,v 1.235 2007/06/08 18:23:52 tgl Exp $
*
*
* INTERFACE ROUTINES
@@ -78,29 +78,44 @@ initscan(HeapScanDesc scan, ScanKey key)
* Determine the number of blocks we have to scan.
*
* It is sufficient to do this once at scan start, since any tuples added
- * while the scan is in progress will be invisible to my transaction
- * anyway...
+ * while the scan is in progress will be invisible to my snapshot
+ * anyway. (That is not true when using a non-MVCC snapshot. However,
+ * we couldn't guarantee to return tuples added after scan start anyway,
+ * since they might go into pages we already scanned. To guarantee
+ * consistent results for a non-MVCC snapshot, the caller must hold some
+ * higher-level lock that ensures the interesting tuple(s) won't change.)
*/
scan->rs_nblocks = RelationGetNumberOfBlocks(scan->rs_rd);
/*
* If the table is large relative to NBuffers, use a bulk-read access
- * strategy, else use the default random-access strategy. During a
- * rescan, don't make a new strategy object if we don't have to.
+ * strategy and enable synchronized scanning (see syncscan.c). Although
+ * the thresholds for these features could be different, we make them the
+ * same so that there are only two behaviors to tune rather than four.
+ *
+ * During a rescan, don't make a new strategy object if we don't have to.
*/
if (scan->rs_nblocks > NBuffers / 4 &&
!scan->rs_rd->rd_istemp)
{
if (scan->rs_strategy == NULL)
scan->rs_strategy = GetAccessStrategy(BAS_BULKREAD);
+
+ scan->rs_syncscan = true;
+ scan->rs_startblock = ss_get_location(scan->rs_rd, scan->rs_nblocks);
}
else
{
if (scan->rs_strategy != NULL)
FreeAccessStrategy(scan->rs_strategy);
scan->rs_strategy = NULL;
+
+ scan->rs_syncscan = false;
+ scan->rs_startblock = 0;
}
+ /* rs_pageatatime was set when the snapshot was filled in */
+
scan->rs_inited = false;
scan->rs_ctup.t_data = NULL;
ItemPointerSetInvalid(&scan->rs_ctup.t_self);
@@ -229,6 +244,7 @@ heapgettup(HeapScanDesc scan,
Snapshot snapshot = scan->rs_snapshot;
bool backward = ScanDirectionIsBackward(dir);
BlockNumber page;
+ bool finished;
Page dp;
int lines;
OffsetNumber lineoff;
@@ -251,7 +267,7 @@ heapgettup(HeapScanDesc scan,
tuple->t_data = NULL;
return;
}
- page = 0; /* first page */
+ page = scan->rs_startblock; /* first page */
heapgetpage(scan, page);
lineoff = FirstOffsetNumber; /* first offnum */
scan->rs_inited = true;
@@ -285,7 +301,18 @@ heapgettup(HeapScanDesc scan,
tuple->t_data = NULL;
return;
}
- page = scan->rs_nblocks - 1; /* final page */
+ /*
+ * Disable reporting to syncscan logic in a backwards scan; it's
+ * not very likely anyone else is doing the same thing at the same
+ * time, and much more likely that we'll just bollix things for
+ * forward scanners.
+ */
+ scan->rs_syncscan = false;
+ /* start from last page of the scan */
+ if (scan->rs_startblock > 0)
+ page = scan->rs_startblock - 1;
+ else
+ page = scan->rs_nblocks - 1;
heapgetpage(scan, page);
}
else
@@ -397,10 +424,43 @@ heapgettup(HeapScanDesc scan,
*/
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
+ /*
+ * advance to next/prior page and detect end of scan
+ */
+ if (backward)
+ {
+ finished = (page == scan->rs_startblock);
+ if (page == 0)
+ page = scan->rs_nblocks;
+ page--;
+ }
+ else
+ {
+ page++;
+ if (page >= scan->rs_nblocks)
+ page = 0;
+ finished = (page == scan->rs_startblock);
+
+ /*
+ * Report our new scan position for synchronization purposes.
+ * We don't do that when moving backwards, however. That would
+ * just mess up any other forward-moving scanners.
+ *
+ * Note: we do this before checking for end of scan so that the
+ * final state of the position hint is back at the start of the
+ * rel. That's not strictly necessary, but otherwise when you run
+ * the same query multiple times the starting position would shift
+ * a little bit backwards on every invocation, which is confusing.
+ * We don't guarantee any specific ordering in general, though.
+ */
+ if (scan->rs_syncscan)
+ ss_report_location(scan->rs_rd, page);
+ }
+
/*
* return NULL if we've exhausted all the pages
*/
- if (backward ? (page == 0) : (page + 1 >= scan->rs_nblocks))
+ if (finished)
{
if (BufferIsValid(scan->rs_cbuf))
ReleaseBuffer(scan->rs_cbuf);
@@ -411,8 +471,6 @@ heapgettup(HeapScanDesc scan,
return;
}
- page = backward ? (page - 1) : (page + 1);
-
heapgetpage(scan, page);
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
@@ -455,6 +513,7 @@ heapgettup_pagemode(HeapScanDesc scan,
HeapTuple tuple = &(scan->rs_ctup);
bool backward = ScanDirectionIsBackward(dir);
BlockNumber page;
+ bool finished;
Page dp;
int lines;
int lineindex;
@@ -478,7 +537,7 @@ heapgettup_pagemode(HeapScanDesc scan,
tuple->t_data = NULL;
return;
}
- page = 0; /* first page */
+ page = scan->rs_startblock; /* first page */
heapgetpage(scan, page);
lineindex = 0;
scan->rs_inited = true;
@@ -509,7 +568,18 @@ heapgettup_pagemode(HeapScanDesc scan,
tuple->t_data = NULL;
return;
}
- page = scan->rs_nblocks - 1; /* final page */
+ /*
+ * Disable reporting to syncscan logic in a backwards scan; it's
+ * not very likely anyone else is doing the same thing at the same
+ * time, and much more likely that we'll just bollix things for
+ * forward scanners.
+ */
+ scan->rs_syncscan = false;
+ /* start from last page of the scan */
+ if (scan->rs_startblock > 0)
+ page = scan->rs_startblock - 1;
+ else
+ page = scan->rs_nblocks - 1;
heapgetpage(scan, page);
}
else
@@ -616,11 +686,40 @@ heapgettup_pagemode(HeapScanDesc scan,
* if we get here, it means we've exhausted the items on this page and
* it's time to move to the next.
*/
+ if (backward)
+ {
+ finished = (page == scan->rs_startblock);
+ if (page == 0)
+ page = scan->rs_nblocks;
+ page--;
+ }
+ else
+ {
+ page++;
+ if (page >= scan->rs_nblocks)
+ page = 0;
+ finished = (page == scan->rs_startblock);
+
+ /*
+ * Report our new scan position for synchronization purposes.
+ * We don't do that when moving backwards, however. That would
+ * just mess up any other forward-moving scanners.
+ *
+ * Note: we do this before checking for end of scan so that the
+ * final state of the position hint is back at the start of the
+ * rel. That's not strictly necessary, but otherwise when you run
+ * the same query multiple times the starting position would shift
+ * a little bit backwards on every invocation, which is confusing.
+ * We don't guarantee any specific ordering in general, though.
+ */
+ if (scan->rs_syncscan)
+ ss_report_location(scan->rs_rd, page);
+ }
/*
* return NULL if we've exhausted all the pages
*/
- if (backward ? (page == 0) : (page + 1 >= scan->rs_nblocks))
+ if (finished)
{
if (BufferIsValid(scan->rs_cbuf))
ReleaseBuffer(scan->rs_cbuf);
@@ -631,7 +730,6 @@ heapgettup_pagemode(HeapScanDesc scan,
return;
}
- page = backward ? (page - 1) : (page + 1);
heapgetpage(scan, page);
dp = (Page) BufferGetPage(scan->rs_cbuf);
diff --git a/src/backend/access/heap/syncscan.c b/src/backend/access/heap/syncscan.c
new file mode 100644
index 0000000000000000000000000000000000000000..795efccc090843e5909966cbf63dfc04d829f330
--- /dev/null
+++ b/src/backend/access/heap/syncscan.c
@@ -0,0 +1,318 @@
+/*-------------------------------------------------------------------------
+ *
+ * syncscan.c
+ * heap scan synchronization support
+ *
+ * When multiple backends run a sequential scan on the same table, we try
+ * to keep them synchronized to reduce the overall I/O needed. The goal is
+ * to read each page into shared buffer cache only once, and let all backends
+ * that take part in the shared scan process the page before it falls out of
+ * the cache.
+ *
+ * Since the "leader" in a pack of backends doing a seqscan will have to wait
+ * for I/O, while the "followers" don't, there is a strong self-synchronizing
+ * effect once we can get the backends examining approximately the same part
+ * of the table at the same time. Hence all that is really needed is to get
+ * a new backend beginning a seqscan to begin it close to where other backends
+ * are reading. We can scan the table circularly, from block X up to the
+ * end and then from block 0 to X-1, to ensure we visit all rows while still
+ * participating in the common scan.
+ *
+ * To accomplish that, we keep track of the scan position of each table, and
+ * start new scans close to where the previous scan(s) are. We don't try to
+ * do any extra synchronization to keep the scans together afterwards; some
+ * scans might progress much more slowly than others, for example if the
+ * results need to be transferred to the client over a slow network, and we
+ * don't want such queries to slow down others.
+ *
+ * There can realistically only be a few large sequential scans on different
+ * tables in progress at any time. Therefore we just keep the scan positions
+ * in a small LRU list which we scan every time we need to look up or update a
+ * scan position. The whole mechanism is only applied for tables exceeding
+ * a threshold size (but that is not the concern of this module).
+ *
+ * INTERFACE ROUTINES
+ * ss_get_location - return current scan location of a relation
+ * ss_report_location - update current scan location
+ *
+ *
+ * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ * $PostgreSQL: pgsql/src/backend/access/heap/syncscan.c,v 1.1 2007/06/08 18:23:52 tgl Exp $
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "access/heapam.h"
+#include "miscadmin.h"
+
+
+/* GUC variables */
+#ifdef TRACE_SYNCSCAN
+bool trace_syncscan = false;
+#endif
+
+
+/*
+ * Size of the LRU list.
+ *
+ * Note: the code assumes that SYNC_SCAN_NELEM > 1.
+ *
+ * XXX: What's a good value? It should be large enough to hold the
+ * maximum number of large tables scanned simultaneously. But a larger value
+ * means more traversing of the LRU list when starting a new scan.
+ */
+#define SYNC_SCAN_NELEM 20
+
+/*
+ * Interval between reports of the location of the current scan, in pages.
+ *
+ * Note: This should be smaller than the ring size (see buffer/freelist.c)
+ * we use for bulk reads. Otherwise a scan joining other scans might start
+ * from a page that's no longer in the buffer cache. This is a bit fuzzy;
+ * there's no guarantee that the new scan will read the page before it leaves
+ * the buffer cache anyway, and on the other hand the page is most likely
+ * still in the OS cache.
+ */
+#define SYNC_SCAN_REPORT_INTERVAL (128 * 1024 / BLCKSZ)
+
+
+/*
+ * The scan locations structure is essentially a doubly-linked LRU with head
+ * and tail pointer, but designed to hold a fixed maximum number of elements in
+ * fixed-size shared memory.
+ */
+typedef struct ss_scan_location_t
+{
+ RelFileNode relfilenode; /* identity of a relation */
+ BlockNumber location; /* last-reported location in the relation */
+} ss_scan_location_t;
+
+typedef struct ss_lru_item_t
+{
+ struct ss_lru_item_t *prev;
+ struct ss_lru_item_t *next;
+ ss_scan_location_t location;
+} ss_lru_item_t;
+
+typedef struct ss_scan_locations_t
+{
+ ss_lru_item_t *head;
+ ss_lru_item_t *tail;
+ ss_lru_item_t items[1]; /* SYNC_SCAN_NELEM items */
+} ss_scan_locations_t;
+
+#define SizeOfScanLocations(N) offsetof(ss_scan_locations_t, items[N])
+
+/* Pointer to struct in shared memory */
+static ss_scan_locations_t *scan_locations;
+
+/* prototypes for internal functions */
+static BlockNumber ss_search(RelFileNode relfilenode,
+ BlockNumber location, bool set);
+
+
+/*
+ * SyncScanShmemSize --- report amount of shared memory space needed
+ */
+Size
+SyncScanShmemSize(void)
+{
+ return SizeOfScanLocations(SYNC_SCAN_NELEM);
+}
+
+/*
+ * SyncScanShmemInit --- initialize this module's shared memory
+ */
+void
+SyncScanShmemInit(void)
+{
+ int i;
+ bool found;
+
+ scan_locations = (ss_scan_locations_t *)
+ ShmemInitStruct("Sync Scan Locations List",
+ SizeOfScanLocations(SYNC_SCAN_NELEM),
+ &found);
+
+ if (!IsUnderPostmaster)
+ {
+ /* Initialize shared memory area */
+ Assert(!found);
+
+ scan_locations->head = &scan_locations->items[0];
+ scan_locations->tail = &scan_locations->items[SYNC_SCAN_NELEM - 1];
+
+ for (i = 0; i < SYNC_SCAN_NELEM; i++)
+ {
+ ss_lru_item_t *item = &scan_locations->items[i];
+
+ /*
+ * Initialize all slots with invalid values. As scans are started,
+ * these invalid entries will fall off the LRU list and get
+ * replaced with real entries.
+ */
+ item->location.relfilenode.spcNode = InvalidOid;
+ item->location.relfilenode.dbNode = InvalidOid;
+ item->location.relfilenode.relNode = InvalidOid;
+ item->location.location = InvalidBlockNumber;
+
+ item->prev = (i > 0) ?
+ (&scan_locations->items[i - 1]) : NULL;
+ item->next = (i < SYNC_SCAN_NELEM - 1) ?
+ (&scan_locations->items[i + 1]) : NULL;
+ }
+ }
+ else
+ Assert(found);
+}
+
+/*
+ * ss_search --- search the scan_locations structure for an entry with the
+ * given relfilenode.
+ *
+ * If "set" is true, the location is updated to the given location. If no
+ * entry for the given relfilenode is found, it will be created at the head
+ * of the list with the given location, even if "set" is false.
+ *
+ * In any case, the location after possible update is returned.
+ *
+ * Caller is responsible for having acquired suitable lock on the shared
+ * data structure.
+ */
+static BlockNumber
+ss_search(RelFileNode relfilenode, BlockNumber location, bool set)
+{
+ ss_lru_item_t *item;
+
+ item = scan_locations->head;
+ for (;;)
+ {
+ bool match;
+
+ match = RelFileNodeEquals(item->location.relfilenode, relfilenode);
+
+ if (match || item->next == NULL)
+ {
+ /*
+ * If we reached the end of list and no match was found,
+ * take over the last entry
+ */
+ if (!match)
+ {
+ item->location.relfilenode = relfilenode;
+ item->location.location = location;
+ }
+ else if (set)
+ item->location.location = location;
+
+ /* Move the entry to the front of the LRU list */
+ if (item != scan_locations->head)
+ {
+ /* unlink */
+ if (item == scan_locations->tail)
+ scan_locations->tail = item->prev;
+ item->prev->next = item->next;
+ if (item->next)
+ item->next->prev = item->prev;
+
+ /* link */
+ item->prev = NULL;
+ item->next = scan_locations->head;
+ scan_locations->head->prev = item;
+ scan_locations->head = item;
+ }
+
+ return item->location.location;
+ }
+
+ item = item->next;
+ }
+
+ /* not reached */
+}
+
+/*
+ * ss_get_location --- get the optimal starting location for scan
+ *
+ * Returns the last-reported location of a sequential scan on the
+ * relation, or 0 if no valid location is found.
+ *
+ * We expect the caller has just done RelationGetNumberOfBlocks(), and
+ * so that number is passed in rather than computing it again. The result
+ * is guaranteed less than relnblocks (assuming that's > 0).
+ */
+BlockNumber
+ss_get_location(Relation rel, BlockNumber relnblocks)
+{
+ BlockNumber startloc;
+
+ LWLockAcquire(SyncScanLock, LW_EXCLUSIVE);
+ startloc = ss_search(rel->rd_node, 0, false);
+ LWLockRelease(SyncScanLock);
+
+ /*
+ * If the location is not a valid block number for this scan, start at 0.
+ *
+ * This can happen if for instance a VACUUM truncated the table
+ * since the location was saved.
+ */
+ if (startloc >= relnblocks)
+ startloc = 0;
+
+#ifdef TRACE_SYNCSCAN
+ if (trace_syncscan)
+ elog(LOG,
+ "SYNC_SCAN: start \"%s\" (size %u) at %u",
+ RelationGetRelationName(rel), relnblocks, startloc);
+#endif
+
+ return startloc;
+}
+
+/*
+ * ss_report_location --- update the current scan location
+ *
+ * Writes an entry into the shared Sync Scan state of the form
+ * (relfilenode, blocknumber), overwriting any existing entry for the
+ * same relfilenode.
+ */
+void
+ss_report_location(Relation rel, BlockNumber location)
+{
+#ifdef TRACE_SYNCSCAN
+ if (trace_syncscan)
+ {
+ if ((location % 1024) == 0)
+ elog(LOG,
+ "SYNC_SCAN: scanning \"%s\" at %u",
+ RelationGetRelationName(rel), location);
+ }
+#endif
+
+ /*
+ * To reduce lock contention, only report scan progress every N pages.
+ * For the same reason, don't block if the lock isn't immediately
+ * available. Missing a few updates isn't critical, it just means that a
+ * new scan that wants to join the pack will start a little bit behind the
+ * head of the scan. Hopefully the pages are still in OS cache and the
+ * scan catches up quickly.
+ */
+ if ((location % SYNC_SCAN_REPORT_INTERVAL) == 0)
+ {
+ if (LWLockConditionalAcquire(SyncScanLock, LW_EXCLUSIVE))
+ {
+ (void) ss_search(rel->rd_node, location, true);
+ LWLockRelease(SyncScanLock);
+ }
+#ifdef TRACE_SYNCSCAN
+ else if (trace_syncscan)
+ elog(LOG,
+ "SYNC_SCAN: missed update for \"%s\" at %u",
+ RelationGetRelationName(rel), location);
+#endif
+ }
+}
diff --git a/src/backend/storage/buffer/freelist.c b/src/backend/storage/buffer/freelist.c
index d8eec0f8231110f5bf3cc3108487b5a7312bbb61..a3e2c7c442244e40de9cf07a15a40a954c03953c 100644
--- a/src/backend/storage/buffer/freelist.c
+++ b/src/backend/storage/buffer/freelist.c
@@ -9,7 +9,7 @@
*
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/backend/storage/buffer/freelist.c,v 1.59 2007/05/30 20:11:59 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/storage/buffer/freelist.c,v 1.60 2007/06/08 18:23:52 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -340,6 +340,9 @@ GetAccessStrategy(BufferAccessStrategyType btype)
* Select ring size to use. See buffer/README for rationales.
* (Currently all cases are the same size, but keep this code
* structure for flexibility.)
+ *
+ * Note: if you change the ring size for BAS_BULKREAD, see also
+ * SYNC_SCAN_REPORT_INTERVAL in access/heap/syncscan.c.
*/
switch (btype)
{
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 0296cbbcfc46f3b26651fc82030ceadf7398a609..86c54448e4cf273a7929a4bbfbb7d1dbad8da1d1 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -8,13 +8,14 @@
*
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/backend/storage/ipc/ipci.c,v 1.91 2007/02/15 23:23:23 alvherre Exp $
+ * $PostgreSQL: pgsql/src/backend/storage/ipc/ipci.c,v 1.92 2007/06/08 18:23:52 tgl Exp $
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/clog.h"
+#include "access/heapam.h"
#include "access/multixact.h"
#include "access/nbtree.h"
#include "access/subtrans.h"
@@ -112,6 +113,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
size = add_size(size, BgWriterShmemSize());
size = add_size(size, AutoVacuumShmemSize());
size = add_size(size, BTreeShmemSize());
+ size = add_size(size, SyncScanShmemSize());
#ifdef EXEC_BACKEND
size = add_size(size, ShmemBackendArraySize());
#endif
@@ -216,6 +218,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
* Set up other modules that need some shared memory space
*/
BTreeShmemInit();
+ SyncScanShmemInit();
#ifdef EXEC_BACKEND
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 6e412e328a11a7100e89962b8af33f9138296d20..387c4ae1531052dfae4b709bdc15eb95853963fa 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -10,7 +10,7 @@
* Written by Peter Eisentraut <peter_e@gmx.net>.
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.395 2007/06/05 21:50:19 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.396 2007/06/08 18:23:52 tgl Exp $
*
*--------------------------------------------------------------------
*/
@@ -109,6 +109,9 @@ extern bool fullPageWrites;
#ifdef TRACE_SORT
extern bool trace_sort;
#endif
+#ifdef TRACE_SYNCSCAN
+extern bool trace_syncscan;
+#endif
#ifdef DEBUG_BOUNDED_SORT
extern bool optimize_bounded_sort;
#endif
@@ -970,6 +973,19 @@ static struct config_bool ConfigureNamesBool[] =
},
#endif
+#ifdef TRACE_SYNCSCAN
+ /* this is undocumented because not exposed in a standard build */
+ {
+ {"trace_syncscan", PGC_USERSET, DEVELOPER_OPTIONS,
+ gettext_noop("Generate debugging output for synchronized scanning."),
+ NULL,
+ GUC_NOT_IN_SAMPLE
+ },
+ &trace_syncscan,
+ false, NULL, NULL
+ },
+#endif
+
#ifdef DEBUG_BOUNDED_SORT
/* this is undocumented because not exposed in a standard build */
{
diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h
index ebb2e984c24903ddea1c07db8d3a42485c6a6036..206159bdad7fd4a2eedd777f84afb5b21af4e045 100644
--- a/src/include/access/heapam.h
+++ b/src/include/access/heapam.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $PostgreSQL: pgsql/src/include/access/heapam.h,v 1.124 2007/05/27 03:50:39 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/access/heapam.h,v 1.125 2007/06/08 18:23:53 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -112,6 +112,13 @@ extern Datum fastgetattr(HeapTuple tup, int attnum, TupleDesc tupleDesc,
)
+typedef enum
+{
+ LockTupleShared,
+ LockTupleExclusive
+} LockTupleMode;
+
+
/* ----------------
* function prototypes for heap access method
*
@@ -120,14 +127,7 @@ extern Datum fastgetattr(HeapTuple tup, int attnum, TupleDesc tupleDesc,
* ----------------
*/
-/* heapam.c */
-
-typedef enum
-{
- LockTupleShared,
- LockTupleExclusive
-} LockTupleMode;
-
+/* in heap/heapam.c */
extern Relation relation_open(Oid relationId, LOCKMODE lockmode);
extern Relation try_relation_open(Oid relationId, LOCKMODE lockmode);
extern Relation relation_open_nowait(Oid relationId, LOCKMODE lockmode);
@@ -240,4 +240,10 @@ extern HeapTuple heap_addheader(int natts, bool withoid,
extern void heap_sync(Relation relation);
+/* in heap/syncscan.c */
+extern void ss_report_location(Relation rel, BlockNumber location);
+extern BlockNumber ss_get_location(Relation rel, BlockNumber relnblocks);
+extern void SyncScanShmemInit(void);
+extern Size SyncScanShmemSize(void);
+
#endif /* HEAPAM_H */
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 200b45713e737ad01f74974a041e26df380057e6..b45b2caabf19af25bb23b63b9a0e9b71a63cdbf3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $PostgreSQL: pgsql/src/include/access/relscan.h,v 1.54 2007/05/30 20:12:02 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/access/relscan.h,v 1.55 2007/06/08 18:23:53 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -26,9 +26,13 @@ typedef struct HeapScanDescData
Snapshot rs_snapshot; /* snapshot to see */
int rs_nkeys; /* number of scan keys */
ScanKey rs_key; /* array of scan key descriptors */
+
+ /* state set up at initscan time */
BlockNumber rs_nblocks; /* number of blocks to scan */
+ BlockNumber rs_startblock; /* block # to start at */
BufferAccessStrategy rs_strategy; /* access strategy for reads */
bool rs_pageatatime; /* verify visibility page-at-a-time? */
+ bool rs_syncscan; /* report location to syncscan logic? */
/* scan current state */
bool rs_inited; /* false = scan not init'd yet */
diff --git a/src/include/pg_config_manual.h b/src/include/pg_config_manual.h
index a5b3f98a8eb58fad9d062186669a4595dba9f304..354a3d370eb5e78ed6b0baba13a24b1f01aa48f1 100644
--- a/src/include/pg_config_manual.h
+++ b/src/include/pg_config_manual.h
@@ -6,7 +6,7 @@
* for developers. If you edit any of these, be sure to do a *full*
* rebuild (and an initdb if noted).
*
- * $PostgreSQL: pgsql/src/include/pg_config_manual.h,v 1.26 2007/02/23 21:36:19 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/pg_config_manual.h,v 1.27 2007/06/08 18:23:53 tgl Exp $
*------------------------------------------------------------------------
*/
@@ -249,6 +249,11 @@
*/
#define TRACE_SORT 1
+/*
+ * Enable tracing of syncscan operations (see also the trace_syncscan GUC var).
+ */
+/* #define TRACE_SYNCSCAN */
+
/*
* Other debug #defines (documentation, anyone?)
*/
diff --git a/src/include/storage/lwlock.h b/src/include/storage/lwlock.h
index 477284b7d1d50d883a4f584c81118e6545db0f85..046064cdc1feb10362482fa9e10b8ad84e4fb84b 100644
--- a/src/include/storage/lwlock.h
+++ b/src/include/storage/lwlock.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $PostgreSQL: pgsql/src/include/storage/lwlock.h,v 1.36 2007/04/16 18:30:04 alvherre Exp $
+ * $PostgreSQL: pgsql/src/include/storage/lwlock.h,v 1.37 2007/06/08 18:23:53 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -62,6 +62,7 @@ typedef enum LWLockId
AddinShmemInitLock,
AutovacuumLock,
AutovacuumScheduleLock,
+ SyncScanLock,
/* Individual lock IDs end here */
FirstBufMappingLock,
FirstLockMgrLock = FirstBufMappingLock + NUM_BUFFER_PARTITIONS,