On Mon, Mar 14, 2016 at 6:46 PM, David Steele <da...@pgmasters.net> wrote:
> On 2/24/16 12:40 AM, Michael Paquier wrote:
>
>> This has the merit to be clear, thanks for the input. Whatever the
>> approach taken at the end we have two candidates:
>> - Extend XLogInsert() with an extra argument for flags (Andres)
>> - Introduce XLogInsertExtended with this extra argument and let
>> XLogInsert() in peace (Robert and I).
>> Actually, I lied, there was still something I could do for this
>> thread: attached are two patches implementing both approaches as
>> respectively a-1 and a-2. Patch b is the set of logs I used for the
>> tests to show with a low checkpoint_timeout that checkpoints are
>> getting correctly skipped on an idle system.
>
>
> Unfortunately neither A nor B apply anymore.
>
> However, since the patches can still be read through I wonder if Robert or
> Andres would care to opine on whether A or B is better now that they can see
> the full implementation?
>
> For my 2c I'm happy with XLogInsertExtended() since it seems to be a rare
> use case where flags are required. This can always be refactored in the
> future if/when the use of flags spreads.
>
> I think it would be good to make a decision on this before asking Michael to
> rebase.
That's a bit embarrassing, the last versions should be able to apply
cleanly as there have not been changes in this area of the code
lately... But... I did a mistake when generating the patches by
diff'ing them from an incorrect commit number... This explains why
they exploded in size, so attached are the corrected rebased versions.
Too many patches I guess.. And both of them are attached by the way.
--
Michael
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index d7973bc..a2b4aff 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -8343,8 +8343,12 @@ CreateCheckPoint(int flags)
if ((flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY |
CHECKPOINT_FORCE)) == 0)
{
+ elog(LOG, "Not a forced or shutdown checkpoint: progress_lsn %X/%X, ckpt %X/%X",
+ (uint32) (progress_lsn >> 32), (uint32) progress_lsn,
+ (uint32) (ControlFile->checkPoint >> 32), (uint32) ControlFile->checkPoint);
if (progress_lsn == ControlFile->checkPoint)
{
+ elog(LOG, "Checkpoint is skipped");
WALInsertLockRelease();
LWLockRelease(CheckpointLock);
END_CRIT_SECTION();
@@ -8511,7 +8515,11 @@ CreateCheckPoint(int flags)
* recovery we don't need to write running xact data.
*/
if (!shutdown && XLogStandbyInfoActive())
- LogStandbySnapshot();
+ {
+ XLogRecPtr lsn = LogStandbySnapshot();
+ elog(LOG, "snapshot taken by checkpoint %X/%X",
+ (uint32) (lsn >> 32), (uint32) lsn);
+ }
START_CRIT_SECTION();
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 79cfd7b..082e589 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -333,7 +333,9 @@ BackgroundWriterMain(void)
GetLastCheckpointRecPtr() < current_progress_lsn &&
last_progress_lsn < current_progress_lsn)
{
- (void) LogStandbySnapshot();
+ XLogRecPtr lsn = LogStandbySnapshot();
+ elog(LOG, "snapshot taken by bgwriter %X/%X",
+ (uint32) (lsn >> 32), (uint32) lsn);
last_snapshot_ts = now;
last_progress_lsn = current_progress_lsn;
}
diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c
index c740952..22ebba5 100644
--- a/src/backend/access/brin/brin.c
+++ b/src/backend/access/brin/brin.c
@@ -634,7 +634,7 @@ brinbuild(Relation heap, Relation index, IndexInfo *indexInfo)
XLogRegisterData((char *) &xlrec, SizeOfBrinCreateIdx);
XLogRegisterBuffer(0, meta, REGBUF_WILL_INIT);
- recptr = XLogInsert(RM_BRIN_ID, XLOG_BRIN_CREATE_INDEX);
+ recptr = XLogInsert(RM_BRIN_ID, XLOG_BRIN_CREATE_INDEX, 0);
page = BufferGetPage(meta);
PageSetLSN(page, recptr);
diff --git a/src/backend/access/brin/brin_pageops.c b/src/backend/access/brin/brin_pageops.c
index d0ca485..98fcc2c 100644
--- a/src/backend/access/brin/brin_pageops.c
+++ b/src/backend/access/brin/brin_pageops.c
@@ -199,7 +199,7 @@ brin_doupdate(Relation idxrel, BlockNumber pagesPerRange,
XLogRegisterBuffer(0, oldbuf, REGBUF_STANDARD);
XLogRegisterBufData(0, (char *) newtup, newsz);
- recptr = XLogInsert(RM_BRIN_ID, info);
+ recptr = XLogInsert(RM_BRIN_ID, info, 0);
PageSetLSN(oldpage, recptr);
}
@@ -294,7 +294,7 @@ brin_doupdate(Relation idxrel, BlockNumber pagesPerRange,
/* old page */
XLogRegisterBuffer(2, oldbuf, REGBUF_STANDARD);
- recptr = XLogInsert(RM_BRIN_ID, info);
+ recptr = XLogInsert(RM_BRIN_ID, info, 0);
PageSetLSN(oldpage, recptr);
PageSetLSN(newpage, recptr);
@@ -444,7 +444,7 @@ brin_doinsert(Relation idxrel, BlockNumber pagesPerRange,
XLogRegisterBuffer(1, revmapbuf, 0);
- recptr = XLogInsert(RM_BRIN_ID, info);
+ recptr = XLogInsert(RM_BRIN_ID, info, 0);
PageSetLSN(page, recptr);
PageSetLSN(BufferGetPage(revmapbuf), recptr);
diff --git a/src/backend/access/brin/brin_revmap.c b/src/backend/access/brin/brin_revmap.c
index b2c273d..d30345f 100644
--- a/src/backend/access/brin/brin_revmap.c
+++ b/src/backend/access/brin/brin_revmap.c
@@ -487,7 +487,7 @@ revmap_physical_extend(BrinRevmap *revmap)
XLogRegisterBuffer(1, buf, REGBUF_WILL_INIT);
- recptr = XLogInsert(RM_BRIN_ID, XLOG_BRIN_REVMAP_EXTEND);
+ recptr = XLogInsert(RM_BRIN_ID, XLOG_BRIN_REVMAP_EXTEND, 0);
PageSetLSN(metapage, recptr);
PageSetLSN(page, recptr);
}
diff --git a/src/backend/access/gin/ginbtree.c b/src/backend/access/gin/ginbtree.c
index 06ba9cb..db2f959 100644
--- a/src/backend/access/gin/ginbtree.c
+++ b/src/backend/access/gin/ginbtree.c
@@ -415,7 +415,7 @@ ginPlaceToPage(GinBtree btree, GinBtreeStack *stack,
sizeof(BlockIdData) * 2);
}
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_INSERT);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_INSERT, 0);
PageSetLSN(page, recptr);
if (childbuf != InvalidBuffer)
PageSetLSN(childpage, recptr);
@@ -576,7 +576,7 @@ ginPlaceToPage(GinBtree btree, GinBtreeStack *stack,
XLogRegisterData((char *) &data, sizeof(ginxlogSplit));
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_SPLIT);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_SPLIT, 0);
PageSetLSN(BufferGetPage(stack->buffer), recptr);
PageSetLSN(BufferGetPage(rbuffer), recptr);
if (stack->parent == NULL)
diff --git a/src/backend/access/gin/gindatapage.c b/src/backend/access/gin/gindatapage.c
index a55bb4a..5799c0a 100644
--- a/src/backend/access/gin/gindatapage.c
+++ b/src/backend/access/gin/gindatapage.c
@@ -829,7 +829,7 @@ ginVacuumPostingTreeLeaf(Relation indexrel, Buffer buffer, GinVacuumState *gvs)
{
XLogRecPtr recptr;
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_VACUUM_DATA_LEAF_PAGE);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_VACUUM_DATA_LEAF_PAGE, 0);
PageSetLSN(page, recptr);
}
@@ -1748,7 +1748,7 @@ createPostingTree(Relation index, ItemPointerData *items, uint32 nitems,
rootsize);
XLogRegisterBuffer(0, buffer, REGBUF_WILL_INIT);
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_CREATE_PTREE);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_CREATE_PTREE, 0);
PageSetLSN(page, recptr);
}
diff --git a/src/backend/access/gin/ginfast.c b/src/backend/access/gin/ginfast.c
index 2ddf568..7211dee 100644
--- a/src/backend/access/gin/ginfast.c
+++ b/src/backend/access/gin/ginfast.c
@@ -124,7 +124,7 @@ writeListPage(Relation index, Buffer buffer,
XLogRegisterBuffer(0, buffer, REGBUF_WILL_INIT);
XLogRegisterBufData(0, workspace, size);
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_INSERT_LISTPAGE);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_INSERT_LISTPAGE, 0);
PageSetLSN(page, recptr);
}
@@ -406,7 +406,7 @@ ginHeapTupleFastInsert(GinState *ginstate, GinTupleCollector *collector)
XLogRegisterBuffer(0, metabuffer, REGBUF_WILL_INIT);
XLogRegisterData((char *) &data, sizeof(ginxlogUpdateMeta));
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_UPDATE_META_PAGE);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_UPDATE_META_PAGE, 0);
PageSetLSN(metapage, recptr);
if (buffer != InvalidBuffer)
@@ -601,7 +601,7 @@ shiftList(Relation index, Buffer metabuffer, BlockNumber newHead,
XLogRegisterData((char *) &data,
sizeof(ginxlogDeleteListPages));
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_DELETE_LISTPAGE);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_DELETE_LISTPAGE, 0);
PageSetLSN(metapage, recptr);
for (i = 0; i < data.ndeleted; i++)
diff --git a/src/backend/access/gin/gininsert.c b/src/backend/access/gin/gininsert.c
index cd21e0e..b8268da 100644
--- a/src/backend/access/gin/gininsert.c
+++ b/src/backend/access/gin/gininsert.c
@@ -350,7 +350,7 @@ ginbuild(Relation heap, Relation index, IndexInfo *indexInfo)
XLogRegisterBuffer(0, MetaBuffer, REGBUF_WILL_INIT);
XLogRegisterBuffer(1, RootBuffer, REGBUF_WILL_INIT);
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_CREATE_INDEX);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_CREATE_INDEX, 0);
page = BufferGetPage(RootBuffer);
PageSetLSN(page, recptr);
diff --git a/src/backend/access/gin/ginutil.c b/src/backend/access/gin/ginutil.c
index 9450267..c9f61af 100644
--- a/src/backend/access/gin/ginutil.c
+++ b/src/backend/access/gin/ginutil.c
@@ -658,7 +658,7 @@ ginUpdateStats(Relation index, const GinStatsData *stats)
XLogRegisterData((char *) &data, sizeof(ginxlogUpdateMeta));
XLogRegisterBuffer(0, metabuffer, REGBUF_WILL_INIT);
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_UPDATE_META_PAGE);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_UPDATE_META_PAGE, 0);
PageSetLSN(metapage, recptr);
}
diff --git a/src/backend/access/gin/ginvacuum.c b/src/backend/access/gin/ginvacuum.c
index 6a4b98a..35f8f17 100644
--- a/src/backend/access/gin/ginvacuum.c
+++ b/src/backend/access/gin/ginvacuum.c
@@ -104,7 +104,7 @@ xlogVacuumPage(Relation index, Buffer buffer)
XLogBeginInsert();
XLogRegisterBuffer(0, buffer, REGBUF_FORCE_IMAGE | REGBUF_STANDARD);
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_VACUUM_PAGE);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_VACUUM_PAGE, 0);
PageSetLSN(page, recptr);
}
@@ -265,7 +265,7 @@ ginDeletePage(GinVacuumState *gvs, BlockNumber deleteBlkno, BlockNumber leftBlkn
XLogRegisterData((char *) &data, sizeof(ginxlogDeletePage));
- recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_DELETE_PAGE);
+ recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_DELETE_PAGE, 0);
PageSetLSN(page, recptr);
PageSetLSN(parentPage, recptr);
PageSetLSN(BufferGetPage(lBuffer), recptr);
diff --git a/src/backend/access/gist/gistbuild.c b/src/backend/access/gist/gistbuild.c
index 4e43a69..6b41bdc 100644
--- a/src/backend/access/gist/gistbuild.c
+++ b/src/backend/access/gist/gistbuild.c
@@ -184,7 +184,7 @@ gistbuild(Relation heap, Relation index, IndexInfo *indexInfo)
XLogBeginInsert();
XLogRegisterBuffer(0, buffer, REGBUF_WILL_INIT);
- recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_CREATE_INDEX);
+ recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_CREATE_INDEX, 0);
PageSetLSN(page, recptr);
}
else
diff --git a/src/backend/access/gist/gistxlog.c b/src/backend/access/gist/gistxlog.c
index b48e97c..d066677 100644
--- a/src/backend/access/gist/gistxlog.c
+++ b/src/backend/access/gist/gistxlog.c
@@ -370,7 +370,7 @@ gistXLogSplit(RelFileNode node, BlockNumber blkno, bool page_is_leaf,
i++;
}
- recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_SPLIT);
+ recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_SPLIT, 0);
return recptr;
}
@@ -416,7 +416,7 @@ gistXLogUpdate(RelFileNode node, Buffer buffer,
if (BufferIsValid(leftchildbuf))
XLogRegisterBuffer(1, leftchildbuf, REGBUF_STANDARD);
- recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_UPDATE);
+ recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_UPDATE, 0);
return recptr;
}
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 34ba385..fe82073 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -2510,7 +2510,7 @@ heap_insert(Relation relation, HeapTuple tup, CommandId cid,
/* filtering by origin on a row level is much more efficient */
XLogIncludeOrigin();
- recptr = XLogInsert(RM_HEAP_ID, info);
+ recptr = XLogInsert(RM_HEAP_ID, info, 0);
PageSetLSN(page, recptr);
}
@@ -2849,7 +2849,7 @@ heap_multi_insert(Relation relation, HeapTuple *tuples, int ntuples,
/* filtering by origin on a row level is much more efficient */
XLogIncludeOrigin();
- recptr = XLogInsert(RM_HEAP2_ID, info);
+ recptr = XLogInsert(RM_HEAP2_ID, info, 0);
PageSetLSN(page, recptr);
}
@@ -3311,7 +3311,7 @@ l1:
/* filtering by origin on a row level is much more efficient */
XLogIncludeOrigin();
- recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE);
+ recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE, 0);
PageSetLSN(page, recptr);
}
@@ -5064,7 +5064,7 @@ failed:
/* we don't decode row locks atm, so no need to log the origin */
- recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_LOCK);
+ recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_LOCK, 0);
PageSetLSN(page, recptr);
}
@@ -5706,7 +5706,7 @@ l4:
XLogRegisterData((char *) &xlrec, SizeOfHeapLockUpdated);
- recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_LOCK_UPDATED);
+ recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_LOCK_UPDATED, 0);
PageSetLSN(page, recptr);
}
@@ -5846,7 +5846,7 @@ heap_finish_speculative(Relation relation, HeapTuple tuple)
XLogRegisterData((char *) &xlrec, SizeOfHeapConfirm);
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
- recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_CONFIRM);
+ recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_CONFIRM, 0);
PageSetLSN(page, recptr);
}
@@ -5980,7 +5980,7 @@ heap_abort_speculative(Relation relation, HeapTuple tuple)
/* No replica identity & replication origin logged */
- recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE);
+ recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE, 0);
PageSetLSN(page, recptr);
}
@@ -6084,7 +6084,7 @@ heap_inplace_update(Relation relation, HeapTuple tuple)
/* inplace updates aren't decoded atm, don't log the origin */
- recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_INPLACE);
+ recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_INPLACE, 0);
PageSetLSN(page, recptr);
}
@@ -7143,7 +7143,7 @@ log_heap_cleanup_info(RelFileNode rnode, TransactionId latestRemovedXid)
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfHeapCleanupInfo);
- recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_CLEANUP_INFO);
+ recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_CLEANUP_INFO, 0);
return recptr;
}
@@ -7202,7 +7202,7 @@ log_heap_clean(Relation reln, Buffer buffer,
XLogRegisterBufData(0, (char *) nowunused,
nunused * sizeof(OffsetNumber));
- recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_CLEAN);
+ recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_CLEAN, 0);
return recptr;
}
@@ -7238,7 +7238,7 @@ log_heap_freeze(Relation reln, Buffer buffer, TransactionId cutoff_xid,
XLogRegisterBufData(0, (char *) tuples,
ntuples * sizeof(xl_heap_freeze_tuple));
- recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_FREEZE_PAGE);
+ recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_FREEZE_PAGE, 0);
return recptr;
}
@@ -7275,7 +7275,7 @@ log_heap_visible(RelFileNode rnode, Buffer heap_buffer, Buffer vm_buffer,
flags |= REGBUF_NO_IMAGE;
XLogRegisterBuffer(1, heap_buffer, flags);
- recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_VISIBLE);
+ recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_VISIBLE, 0);
return recptr;
}
@@ -7495,7 +7495,7 @@ log_heap_update(Relation reln, Buffer oldbuf,
/* filtering by origin on a row level is much more efficient */
XLogIncludeOrigin();
- recptr = XLogInsert(RM_HEAP_ID, info);
+ recptr = XLogInsert(RM_HEAP_ID, info, 0);
return recptr;
}
@@ -7570,7 +7570,7 @@ log_heap_new_cid(Relation relation, HeapTuple tup)
/* will be looked at irrespective of origin */
- recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_NEW_CID);
+ recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_NEW_CID, 0);
return recptr;
}
diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c
index f9ce986..df94448 100644
--- a/src/backend/access/heap/rewriteheap.c
+++ b/src/backend/access/heap/rewriteheap.c
@@ -931,7 +931,7 @@ logical_heap_rewrite_flush_mappings(RewriteState state)
XLogRegisterData(waldata_start, len);
/* write xlog record */
- XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_REWRITE);
+ XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_REWRITE, 0);
pfree(waldata_start);
}
diff --git a/src/backend/access/nbtree/nbtinsert.c b/src/backend/access/nbtree/nbtinsert.c
index e3c55eb..a2b10d7 100644
--- a/src/backend/access/nbtree/nbtinsert.c
+++ b/src/backend/access/nbtree/nbtinsert.c
@@ -906,7 +906,7 @@ _bt_insertonpg(Relation rel,
else
XLogRegisterBufData(0, (char *) itup, IndexTupleDSize(*itup));
- recptr = XLogInsert(RM_BTREE_ID, xlinfo);
+ recptr = XLogInsert(RM_BTREE_ID, xlinfo, 0);
if (BufferIsValid(metabuf))
{
@@ -1325,7 +1325,7 @@ _bt_split(Relation rel, Buffer buf, Buffer cbuf, OffsetNumber firstright,
else
xlinfo = newitemonleft ? XLOG_BTREE_SPLIT_L : XLOG_BTREE_SPLIT_R;
- recptr = XLogInsert(RM_BTREE_ID, xlinfo);
+ recptr = XLogInsert(RM_BTREE_ID, xlinfo, 0);
PageSetLSN(origpage, recptr);
PageSetLSN(rightpage, recptr);
@@ -2045,7 +2045,7 @@ _bt_newroot(Relation rel, Buffer lbuf, Buffer rbuf)
((PageHeader) rootpage)->pd_special -
((PageHeader) rootpage)->pd_upper);
- recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_NEWROOT);
+ recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_NEWROOT, 0);
PageSetLSN(lpage, recptr);
PageSetLSN(rootpage, recptr);
diff --git a/src/backend/access/nbtree/nbtpage.c b/src/backend/access/nbtree/nbtpage.c
index 67755d7..9453b0f 100644
--- a/src/backend/access/nbtree/nbtpage.c
+++ b/src/backend/access/nbtree/nbtpage.c
@@ -254,7 +254,7 @@ _bt_getroot(Relation rel, int access)
XLogRegisterData((char *) &xlrec, SizeOfBtreeNewroot);
- recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_NEWROOT);
+ recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_NEWROOT, 0);
PageSetLSN(rootpage, recptr);
PageSetLSN(metapg, recptr);
@@ -551,7 +551,7 @@ _bt_log_reuse_page(Relation rel, BlockNumber blkno, TransactionId latestRemovedX
XLogBeginInsert();
XLogRegisterData((char *) &xlrec_reuse, SizeOfBtreeReusePage);
- XLogInsert(RM_BTREE_ID, XLOG_BTREE_REUSE_PAGE);
+ XLogInsert(RM_BTREE_ID, XLOG_BTREE_REUSE_PAGE, 0);
}
/*
@@ -837,7 +837,7 @@ _bt_delitems_vacuum(Relation rel, Buffer buf,
if (nitems > 0)
XLogRegisterBufData(0, (char *) itemnos, nitems * sizeof(OffsetNumber));
- recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_VACUUM);
+ recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_VACUUM, 0);
PageSetLSN(page, recptr);
}
@@ -911,7 +911,7 @@ _bt_delitems_delete(Relation rel, Buffer buf,
*/
XLogRegisterData((char *) itemnos, nitems * sizeof(OffsetNumber));
- recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_DELETE);
+ recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_DELETE, 0);
PageSetLSN(page, recptr);
}
@@ -1476,7 +1476,7 @@ _bt_mark_page_halfdead(Relation rel, Buffer leafbuf, BTStack stack)
XLogRegisterData((char *) &xlrec, SizeOfBtreeMarkPageHalfDead);
- recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_MARK_PAGE_HALFDEAD);
+ recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_MARK_PAGE_HALFDEAD, 0);
page = BufferGetPage(topparent);
PageSetLSN(page, recptr);
@@ -1820,7 +1820,7 @@ _bt_unlink_halfdead_page(Relation rel, Buffer leafbuf, bool *rightsib_empty)
else
xlinfo = XLOG_BTREE_UNLINK_PAGE;
- recptr = XLogInsert(RM_BTREE_ID, xlinfo);
+ recptr = XLogInsert(RM_BTREE_ID, xlinfo, 0);
if (BufferIsValid(metabuf))
{
diff --git a/src/backend/access/spgist/spgdoinsert.c b/src/backend/access/spgist/spgdoinsert.c
index f090ca5..4d41db7 100644
--- a/src/backend/access/spgist/spgdoinsert.c
+++ b/src/backend/access/spgist/spgdoinsert.c
@@ -304,7 +304,7 @@ addLeafTuple(Relation index, SpGistState *state, SpGistLeafTuple leafTuple,
if (xlrec.offnumParent != InvalidOffsetNumber)
XLogRegisterBuffer(1, parent->buffer, REGBUF_STANDARD);
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_ADD_LEAF);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_ADD_LEAF, 0);
PageSetLSN(current->page, recptr);
@@ -541,7 +541,7 @@ moveLeafs(Relation index, SpGistState *state,
XLogRegisterBuffer(1, nbuf, REGBUF_STANDARD | (xlrec.newPage ? REGBUF_WILL_INIT : 0));
XLogRegisterBuffer(2, parent->buffer, REGBUF_STANDARD);
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_MOVE_LEAFS);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_MOVE_LEAFS, 0);
PageSetLSN(current->page, recptr);
PageSetLSN(npage, recptr);
@@ -1386,7 +1386,7 @@ doPickSplit(Relation index, SpGistState *state,
}
/* Issue the WAL record */
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_PICKSPLIT);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_PICKSPLIT, 0);
/* Update page LSNs on all affected pages */
if (newLeafBuffer != InvalidBuffer)
@@ -1540,7 +1540,7 @@ spgAddNodeAction(Relation index, SpGistState *state,
XLogRegisterBuffer(0, current->buffer, REGBUF_STANDARD);
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_ADD_NODE);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_ADD_NODE, 0);
PageSetLSN(current->page, recptr);
}
@@ -1664,7 +1664,7 @@ spgAddNodeAction(Relation index, SpGistState *state,
XLogRegisterData((char *) &xlrec, sizeof(xlrec));
XLogRegisterData((char *) newInnerTuple, newInnerTuple->size);
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_ADD_NODE);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_ADD_NODE, 0);
/* we don't bother to check if any of these are redundant */
PageSetLSN(current->page, recptr);
@@ -1834,7 +1834,7 @@ spgSplitNodeAction(Relation index, SpGistState *state,
XLogRegisterBuffer(1, newBuffer, flags);
}
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_SPLIT_TUPLE);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_SPLIT_TUPLE, 0);
PageSetLSN(current->page, recptr);
diff --git a/src/backend/access/spgist/spginsert.c b/src/backend/access/spgist/spginsert.c
index 44fd644..507ae74 100644
--- a/src/backend/access/spgist/spginsert.c
+++ b/src/backend/access/spgist/spginsert.c
@@ -113,7 +113,7 @@ spgbuild(Relation heap, Relation index, IndexInfo *indexInfo)
XLogRegisterBuffer(1, rootbuffer, REGBUF_WILL_INIT | REGBUF_STANDARD);
XLogRegisterBuffer(2, nullbuffer, REGBUF_WILL_INIT | REGBUF_STANDARD);
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_CREATE_INDEX);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_CREATE_INDEX, 0);
PageSetLSN(BufferGetPage(metabuffer), recptr);
PageSetLSN(BufferGetPage(rootbuffer), recptr);
diff --git a/src/backend/access/spgist/spgvacuum.c b/src/backend/access/spgist/spgvacuum.c
index 15b867f..5036219 100644
--- a/src/backend/access/spgist/spgvacuum.c
+++ b/src/backend/access/spgist/spgvacuum.c
@@ -389,7 +389,7 @@ vacuumLeafPage(spgBulkDeleteState *bds, Relation index, Buffer buffer,
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_LEAF);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_LEAF, 0);
PageSetLSN(page, recptr);
}
@@ -470,7 +470,7 @@ vacuumLeafRoot(spgBulkDeleteState *bds, Relation index, Buffer buffer)
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_ROOT);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_ROOT, 0);
PageSetLSN(page, recptr);
}
@@ -591,7 +591,7 @@ vacuumRedirectAndPlaceholder(Relation index, Buffer buffer)
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
- recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_REDIRECT);
+ recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_REDIRECT, 0);
PageSetLSN(page, recptr);
}
diff --git a/src/backend/access/transam/clog.c b/src/backend/access/transam/clog.c
index 06aff18..15a5e53 100644
--- a/src/backend/access/transam/clog.c
+++ b/src/backend/access/transam/clog.c
@@ -701,7 +701,7 @@ WriteZeroPageXlogRec(int pageno)
{
XLogBeginInsert();
XLogRegisterData((char *) (&pageno), sizeof(int));
- (void) XLogInsert(RM_CLOG_ID, CLOG_ZEROPAGE);
+ (void) XLogInsert(RM_CLOG_ID, CLOG_ZEROPAGE, 0);
}
/*
@@ -717,7 +717,7 @@ WriteTruncateXlogRec(int pageno)
XLogBeginInsert();
XLogRegisterData((char *) (&pageno), sizeof(int));
- recptr = XLogInsert(RM_CLOG_ID, CLOG_TRUNCATE);
+ recptr = XLogInsert(RM_CLOG_ID, CLOG_TRUNCATE, 0);
XLogFlush(recptr);
}
diff --git a/src/backend/access/transam/commit_ts.c b/src/backend/access/transam/commit_ts.c
index 1713439..adc42fc 100644
--- a/src/backend/access/transam/commit_ts.c
+++ b/src/backend/access/transam/commit_ts.c
@@ -893,7 +893,7 @@ WriteZeroPageXlogRec(int pageno)
{
XLogBeginInsert();
XLogRegisterData((char *) (&pageno), sizeof(int));
- (void) XLogInsert(RM_COMMIT_TS_ID, COMMIT_TS_ZEROPAGE);
+ (void) XLogInsert(RM_COMMIT_TS_ID, COMMIT_TS_ZEROPAGE, 0);
}
/*
@@ -904,7 +904,7 @@ WriteTruncateXlogRec(int pageno)
{
XLogBeginInsert();
XLogRegisterData((char *) (&pageno), sizeof(int));
- (void) XLogInsert(RM_COMMIT_TS_ID, COMMIT_TS_TRUNCATE);
+ (void) XLogInsert(RM_COMMIT_TS_ID, COMMIT_TS_TRUNCATE, 0);
}
/*
@@ -926,7 +926,7 @@ WriteSetTimestampXlogRec(TransactionId mainxid, int nsubxids,
offsetof(xl_commit_ts_set, mainxid) +
sizeof(TransactionId));
XLogRegisterData((char *) subxids, nsubxids * sizeof(TransactionId));
- XLogInsert(RM_COMMIT_TS_ID, COMMIT_TS_SETTS);
+ XLogInsert(RM_COMMIT_TS_ID, COMMIT_TS_SETTS, 0);
}
/*
diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c
index a677af0..9a1ad41 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -814,7 +814,7 @@ MultiXactIdCreateFromMembers(int nmembers, MultiXactMember *members)
XLogRegisterData((char *) (&xlrec), SizeOfMultiXactCreate);
XLogRegisterData((char *) members, nmembers * sizeof(MultiXactMember));
- (void) XLogInsert(RM_MULTIXACT_ID, XLOG_MULTIXACT_CREATE_ID);
+ (void) XLogInsert(RM_MULTIXACT_ID, XLOG_MULTIXACT_CREATE_ID, 0);
/* Now enter the information into the OFFSETs and MEMBERs logs */
RecordNewMultiXact(multi, offset, nmembers, members);
@@ -3177,7 +3177,7 @@ WriteMZeroPageXlogRec(int pageno, uint8 info)
{
XLogBeginInsert();
XLogRegisterData((char *) (&pageno), sizeof(int));
- (void) XLogInsert(RM_MULTIXACT_ID, info);
+ (void) XLogInsert(RM_MULTIXACT_ID, info, 0);
}
/*
@@ -3204,7 +3204,7 @@ WriteMTruncateXlogRec(Oid oldestMultiDB,
XLogBeginInsert();
XLogRegisterData((char *) (&xlrec), SizeOfMultiXactTruncate);
- recptr = XLogInsert(RM_MULTIXACT_ID, XLOG_MULTIXACT_TRUNCATE_ID);
+ recptr = XLogInsert(RM_MULTIXACT_ID, XLOG_MULTIXACT_TRUNCATE_ID, 0);
XLogFlush(recptr);
}
diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c
index c4fd9ef..1eba72d 100644
--- a/src/backend/access/transam/twophase.c
+++ b/src/backend/access/transam/twophase.c
@@ -1063,7 +1063,7 @@ EndPrepare(GlobalTransaction gxact)
XLogBeginInsert();
for (record = records.head; record != NULL; record = record->next)
XLogRegisterData(record->data, record->len);
- gxact->prepare_end_lsn = XLogInsert(RM_XACT_ID, XLOG_XACT_PREPARE);
+ gxact->prepare_end_lsn = XLogInsert(RM_XACT_ID, XLOG_XACT_PREPARE, 0);
XLogFlush(gxact->prepare_end_lsn);
/* If we crash now, we have prepared: WAL replay will fix things */
diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index 8a2cd45..ee3925f 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -630,7 +630,7 @@ AssignTransactionId(TransactionState s)
XLogRegisterData((char *) unreportedXids,
nUnreportedXids * sizeof(TransactionId));
- (void) XLogInsert(RM_XACT_ID, XLOG_XACT_ASSIGNMENT);
+ (void) XLogInsert(RM_XACT_ID, XLOG_XACT_ASSIGNMENT, 0);
nUnreportedXids = 0;
/* mark top, not current xact as having been logged */
@@ -5213,7 +5213,7 @@ XactLogCommitRecord(TimestampTz commit_time,
/* we allow filtering by xacts */
XLogIncludeOrigin();
- return XLogInsert(RM_XACT_ID, info);
+ return XLogInsert(RM_XACT_ID, info, 0);
}
/*
@@ -5300,7 +5300,7 @@ XactLogAbortRecord(TimestampTz abort_time,
if (xl_xinfo.xinfo & XACT_XINFO_HAS_TWOPHASE)
XLogRegisterData((char *) (&xl_twophase), sizeof(xl_xact_twophase));
- return XLogInsert(RM_XACT_ID, info);
+ return XLogInsert(RM_XACT_ID, info, 0);
}
/*
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 5b1c361..d7973bc 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -436,11 +436,30 @@ typedef struct XLogwrtResult
* the WAL record is just copied to the page and the lock is released. But
* to avoid the deadlock-scenario explained above, the indicator is always
* updated before sleeping while holding an insertion lock.
+ *
+ * The progressAt values indicate the insertion progress used to determine
+ * WAL insertion activity since a previous checkpoint, which is aimed at
+ * finding out if a checkpoint should be skipped or not or if standby
+ * activity should be logged. Progress position is basically updated
+ * for all types of records, for the time being only snapshot logging
+ * is out of this scope to properly skip their logging on idle systems.
+ * Tracking the WAL activity directly in WALInsertLock has the advantage
+ * to not rely on taking an exclusive lock on all the WAL insertion locks,
+ * hence reducing the impact of the activity lookup. This takes also
+ * advantage to avoid 8-byte torn reads on some platforms by using the
+ * fact that each insert lock is located on the same cache line.
+ * XXX: There is still room for more improvements here, particularly
+ * WAL operations related to unlogged relations (INIT_FORKNUM) should not
+ * update the progress LSN as those relations are reset during crash
+ * recovery so enforcing buffers of such relations to be flushed for
+ * example in the case of a load only on unlogged relations is a waste
+ * of disk write.
*/
typedef struct
{
LWLock lock;
XLogRecPtr insertingAt;
+ XLogRecPtr progressAt;
} WALInsertLock;
/*
@@ -878,6 +897,9 @@ static void WALInsertLockUpdateInsertingAt(XLogRecPtr insertingAt);
* which pages need a full-page image, and retry. If fpw_lsn is invalid, the
* record is always inserted.
*
+ * 'flags' gives more in-depth control on the record being inserted. As of
+ * now, this controls if the progress LSN positions are updated.
+ *
* The first XLogRecData in the chain must be for the record header, and its
* data must be MAXALIGNed. XLogInsertRecord fills in the xl_prev and
* xl_crc fields in the header, the rest of the header must already be filled
@@ -890,7 +912,9 @@ static void WALInsertLockUpdateInsertingAt(XLogRecPtr insertingAt);
* WAL rule "write the log before the data".)
*/
XLogRecPtr
-XLogInsertRecord(XLogRecData *rdata, XLogRecPtr fpw_lsn)
+XLogInsertRecord(XLogRecData *rdata,
+ XLogRecPtr fpw_lsn,
+ uint8 flags)
{
XLogCtlInsert *Insert = &XLogCtl->Insert;
pg_crc32c rdata_crc;
@@ -989,6 +1013,25 @@ XLogInsertRecord(XLogRecData *rdata, XLogRecPtr fpw_lsn)
inserted = true;
}
+ /*
+ * Update the progress LSN positions. At least one WAL insertion lock
+ * is already taken appropriately before doing that, and it is just more
+ * simple to do that here where WAL record data and type is at hand.
+ * The progress is set at the start position of the record tracked that
+ * is being added, making easier checkpoint progress tracking as the
+ * control file already saves the start LSN position of the last
+ * checkpoint run. If an exclusive lock is taken for WAL insertion,
+ * there is actually no need to update all the progression fields, so
+ * just do it on the first one.
+ */
+ if ((flags & XLOG_INSERT_NO_PROGRESS) == 0)
+ {
+ if (holdingAllLocks)
+ WALInsertLocks[0].l.progressAt = StartPos;
+ else
+ WALInsertLocks[MyLockNo].l.progressAt = StartPos;
+ }
+
if (inserted)
{
/*
@@ -4714,6 +4757,7 @@ XLOGShmemInit(void)
{
LWLockInitialize(&WALInsertLocks[i].l.lock, LWTRANCHE_WAL_INSERT);
WALInsertLocks[i].l.insertingAt = InvalidXLogRecPtr;
+ WALInsertLocks[i].l.progressAt = InvalidXLogRecPtr;
}
/*
@@ -7887,6 +7931,55 @@ GetFlushRecPtr(void)
}
/*
+ * GetProgressRecPtr -- Returns the newest WAL activity position, aimed
+ * at the last significant WAL activity, or in other words any activity
+ * not referring to standby logging as of now. Finding the last activity
+ * position is done by scanning each WAL insertion lock by taking directly
+ * the light-weight lock associated to it.
+ */
+XLogRecPtr
+GetProgressRecPtr(void)
+{
+ XLogRecPtr res = InvalidXLogRecPtr;
+ int i;
+
+ /*
+ * Look at the latest LSN position referring to the activity done by
+ * WAL insertion. An exclusive lock is taken because currently the
+ * locking logic for WAL insertion only expects such a level of locking.
+ * Taking a lock is as well necessary to prevent potential torn reads
+ * on some platforms.
+ */
+ for (i = 0; i < NUM_XLOGINSERT_LOCKS; i++)
+ {
+ XLogRecPtr progress_lsn;
+
+ LWLockAcquire(&WALInsertLocks[i].l.lock, LW_EXCLUSIVE);
+ progress_lsn = WALInsertLocks[i].l.progressAt;
+ LWLockRelease(&WALInsertLocks[i].l.lock);
+
+ if (res < progress_lsn)
+ res = progress_lsn;
+ }
+
+ return res;
+}
+
+/*
+ * GetLastCheckpointRecPtr -- Returns the last checkpoint insert position.
+ */
+XLogRecPtr
+GetLastCheckpointRecPtr(void)
+{
+ XLogRecPtr ckpt_lsn;
+
+ LWLockAcquire(ControlFileLock, LW_SHARED);
+ ckpt_lsn = ControlFile->checkPoint;
+ LWLockRelease(ControlFileLock);
+ return ckpt_lsn;
+}
+
+/*
* Get the time of the last xlog segment switch
*/
pg_time_t
@@ -8146,7 +8239,7 @@ CreateCheckPoint(int flags)
uint32 freespace;
XLogRecPtr PriorRedoPtr;
XLogRecPtr curInsert;
- XLogRecPtr prevPtr;
+ XLogRecPtr progress_lsn;
VirtualTransactionId *vxids;
int nvxids;
@@ -8227,34 +8320,30 @@ CreateCheckPoint(int flags)
checkPoint.oldestActiveXid = InvalidTransactionId;
/*
+ * Get progress before acquiring insert locks to shorten the locked
+ * section waiting ahead.
+ */
+ progress_lsn = GetProgressRecPtr();
+
+ /*
* We must block concurrent insertions while examining insert state to
* determine the checkpoint REDO pointer.
*/
WALInsertLockAcquireExclusive();
curInsert = XLogBytePosToRecPtr(Insert->CurrBytePos);
- prevPtr = XLogBytePosToRecPtr(Insert->PrevBytePos);
/*
- * If this isn't a shutdown or forced checkpoint, and we have not inserted
- * any XLOG records since the start of the last checkpoint, skip the
- * checkpoint. The idea here is to avoid inserting duplicate checkpoints
- * when the system is idle. That wastes log space, and more importantly it
- * exposes us to possible loss of both current and previous checkpoint
- * records if the machine crashes just as we're writing the update.
- * (Perhaps it'd make even more sense to checkpoint only when the previous
- * checkpoint record is in a different xlog page?)
- *
- * If the previous checkpoint crossed a WAL segment, however, we create
- * the checkpoint anyway, to have the latest checkpoint fully contained in
- * the new segment. This is for a little bit of extra robustness: it's
- * better if you don't need to keep two WAL segments around to recover the
- * checkpoint.
+ * If this isn't a shutdown or forced checkpoint, and if there has been no
+ * WAL activity, skip the checkpoint. The idea here is to avoid inserting
+ * duplicate checkpoints when the system is idle. That wastes log space,
+ * and more importantly it exposes us to possible loss of both current and
+ * previous checkpoint records if the machine crashes just as we're writing
+ * the update.
*/
if ((flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY |
CHECKPOINT_FORCE)) == 0)
{
- if (prevPtr == ControlFile->checkPointCopy.redo &&
- prevPtr / XLOG_SEG_SIZE == curInsert / XLOG_SEG_SIZE)
+ if (progress_lsn == ControlFile->checkPoint)
{
WALInsertLockRelease();
LWLockRelease(CheckpointLock);
@@ -8433,7 +8522,7 @@ CreateCheckPoint(int flags)
XLogRegisterData((char *) (&checkPoint), sizeof(checkPoint));
recptr = XLogInsert(RM_XLOG_ID,
shutdown ? XLOG_CHECKPOINT_SHUTDOWN :
- XLOG_CHECKPOINT_ONLINE);
+ XLOG_CHECKPOINT_ONLINE, 0);
XLogFlush(recptr);
@@ -8587,7 +8676,7 @@ CreateEndOfRecoveryRecord(void)
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, sizeof(xl_end_of_recovery));
- recptr = XLogInsert(RM_XLOG_ID, XLOG_END_OF_RECOVERY);
+ recptr = XLogInsert(RM_XLOG_ID, XLOG_END_OF_RECOVERY, 0);
XLogFlush(recptr);
@@ -8958,7 +9047,7 @@ XLogPutNextOid(Oid nextOid)
{
XLogBeginInsert();
XLogRegisterData((char *) (&nextOid), sizeof(Oid));
- (void) XLogInsert(RM_XLOG_ID, XLOG_NEXTOID);
+ (void) XLogInsert(RM_XLOG_ID, XLOG_NEXTOID, 0);
/*
* We need not flush the NEXTOID record immediately, because any of the
@@ -8997,7 +9086,7 @@ RequestXLogSwitch(void)
/* XLOG SWITCH has no data */
XLogBeginInsert();
- RecPtr = XLogInsert(RM_XLOG_ID, XLOG_SWITCH);
+ RecPtr = XLogInsert(RM_XLOG_ID, XLOG_SWITCH, 0);
return RecPtr;
}
@@ -9017,7 +9106,7 @@ XLogRestorePoint(const char *rpName)
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, sizeof(xl_restore_point));
- RecPtr = XLogInsert(RM_XLOG_ID, XLOG_RESTORE_POINT);
+ RecPtr = XLogInsert(RM_XLOG_ID, XLOG_RESTORE_POINT, 0);
ereport(LOG,
(errmsg("restore point \"%s\" created at %X/%X",
@@ -9064,7 +9153,7 @@ XLogReportParameters(void)
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, sizeof(xlrec));
- recptr = XLogInsert(RM_XLOG_ID, XLOG_PARAMETER_CHANGE);
+ recptr = XLogInsert(RM_XLOG_ID, XLOG_PARAMETER_CHANGE, 0);
XLogFlush(recptr);
}
@@ -9126,7 +9215,7 @@ UpdateFullPageWrites(void)
XLogBeginInsert();
XLogRegisterData((char *) (&fullPageWrites), sizeof(bool));
- XLogInsert(RM_XLOG_ID, XLOG_FPW_CHANGE);
+ XLogInsert(RM_XLOG_ID, XLOG_FPW_CHANGE, 0);
}
if (!fullPageWrites)
@@ -10439,7 +10528,7 @@ do_pg_stop_backup(char *labelfile, bool waitforarchive, TimeLineID *stoptli_p)
*/
XLogBeginInsert();
XLogRegisterData((char *) (&startpoint), sizeof(startpoint));
- stoppoint = XLogInsert(RM_XLOG_ID, XLOG_BACKUP_END);
+ stoppoint = XLogInsert(RM_XLOG_ID, XLOG_BACKUP_END, 0);
stoptli = ThisTimeLineID;
/*
diff --git a/src/backend/access/transam/xloginsert.c b/src/backend/access/transam/xloginsert.c
index c37003a..bf800db 100644
--- a/src/backend/access/transam/xloginsert.c
+++ b/src/backend/access/transam/xloginsert.c
@@ -396,7 +396,9 @@ XLogIncludeOrigin(void)
/*
* Insert an XLOG record having the specified RMID and info bytes, with the
* body of the record being the data and buffer references registered earlier
- * with XLogRegister* calls.
+ * with XLogRegister* calls. 'flags' allow users to control more in-depth
+ * operations during WAL record insertion. As of now, this gives control on
+ * if the progress LSN positions are updated or not.
*
* Returns XLOG pointer to end of record (beginning of next record).
* This can be used as LSN for data pages affected by the logged action.
@@ -405,7 +407,7 @@ XLogIncludeOrigin(void)
* WAL rule "write the log before the data".)
*/
XLogRecPtr
-XLogInsert(RmgrId rmid, uint8 info)
+XLogInsert(RmgrId rmid, uint8 info, uint8 flags)
{
XLogRecPtr EndPos;
@@ -450,7 +452,7 @@ XLogInsert(RmgrId rmid, uint8 info)
rdt = XLogRecordAssemble(rmid, info, RedoRecPtr, doPageWrites,
&fpw_lsn);
- EndPos = XLogInsertRecord(rdt, fpw_lsn);
+ EndPos = XLogInsertRecord(rdt, fpw_lsn, flags);
} while (EndPos == InvalidXLogRecPtr);
XLogResetInsertion();
@@ -915,7 +917,7 @@ XLogSaveBufferForHint(Buffer buffer, bool buffer_std)
BufferGetTag(buffer, &rnode, &forkno, &blkno);
XLogRegisterBlock(0, &rnode, forkno, blkno, copied_buffer, flags);
- recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI_FOR_HINT);
+ recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI_FOR_HINT, 0);
}
return recptr;
@@ -946,7 +948,7 @@ log_newpage(RelFileNode *rnode, ForkNumber forkNum, BlockNumber blkno,
XLogBeginInsert();
XLogRegisterBlock(0, rnode, forkNum, blkno, page, flags);
- recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI);
+ recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI, 0);
/*
* The page may be uninitialized. If so, we can't set the LSN because that
diff --git a/src/backend/catalog/storage.c b/src/backend/catalog/storage.c
index fe68c99..1064600 100644
--- a/src/backend/catalog/storage.c
+++ b/src/backend/catalog/storage.c
@@ -134,7 +134,7 @@ log_smgrcreate(RelFileNode *rnode, ForkNumber forkNum)
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, sizeof(xlrec));
- XLogInsert(RM_SMGR_ID, XLOG_SMGR_CREATE | XLR_SPECIAL_REL_UPDATE);
+ XLogInsert(RM_SMGR_ID, XLOG_SMGR_CREATE | XLR_SPECIAL_REL_UPDATE, 0);
}
/*
@@ -273,7 +273,7 @@ RelationTruncate(Relation rel, BlockNumber nblocks)
XLogRegisterData((char *) &xlrec, sizeof(xlrec));
lsn = XLogInsert(RM_SMGR_ID,
- XLOG_SMGR_TRUNCATE | XLR_SPECIAL_REL_UPDATE);
+ XLOG_SMGR_TRUNCATE | XLR_SPECIAL_REL_UPDATE, 0);
/*
* Flush, because otherwise the truncation of the main relation might
diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c
index c1c0223..feae710 100644
--- a/src/backend/commands/dbcommands.c
+++ b/src/backend/commands/dbcommands.c
@@ -630,7 +630,8 @@ createdb(const CreatedbStmt *stmt)
XLogRegisterData((char *) &xlrec, sizeof(xl_dbase_create_rec));
(void) XLogInsert(RM_DBASE_ID,
- XLOG_DBASE_CREATE | XLR_SPECIAL_REL_UPDATE);
+ XLOG_DBASE_CREATE | XLR_SPECIAL_REL_UPDATE,
+ 0);
}
}
heap_endscan(scan);
@@ -1238,7 +1239,8 @@ movedb(const char *dbname, const char *tblspcname)
XLogRegisterData((char *) &xlrec, sizeof(xl_dbase_create_rec));
(void) XLogInsert(RM_DBASE_ID,
- XLOG_DBASE_CREATE | XLR_SPECIAL_REL_UPDATE);
+ XLOG_DBASE_CREATE | XLR_SPECIAL_REL_UPDATE,
+ 0);
}
/*
@@ -1338,7 +1340,8 @@ movedb(const char *dbname, const char *tblspcname)
XLogRegisterData((char *) &xlrec, sizeof(xl_dbase_drop_rec));
(void) XLogInsert(RM_DBASE_ID,
- XLOG_DBASE_DROP | XLR_SPECIAL_REL_UPDATE);
+ XLOG_DBASE_DROP | XLR_SPECIAL_REL_UPDATE,
+ 0);
}
/* Now it's safe to release the database lock */
@@ -1879,7 +1882,8 @@ remove_dbtablespaces(Oid db_id)
XLogRegisterData((char *) &xlrec, sizeof(xl_dbase_drop_rec));
(void) XLogInsert(RM_DBASE_ID,
- XLOG_DBASE_DROP | XLR_SPECIAL_REL_UPDATE);
+ XLOG_DBASE_DROP | XLR_SPECIAL_REL_UPDATE,
+ 0);
}
pfree(dstpath);
diff --git a/src/backend/commands/sequence.c b/src/backend/commands/sequence.c
index c98f981..766b542 100644
--- a/src/backend/commands/sequence.c
+++ b/src/backend/commands/sequence.c
@@ -388,7 +388,7 @@ fill_seq_with_data(Relation rel, HeapTuple tuple)
XLogRegisterData((char *) &xlrec, sizeof(xl_seq_rec));
XLogRegisterData((char *) tuple->t_data, tuple->t_len);
- recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG);
+ recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG, 0);
PageSetLSN(page, recptr);
}
@@ -472,7 +472,7 @@ AlterSequence(AlterSeqStmt *stmt)
XLogRegisterData((char *) seqtuple.t_data, seqtuple.t_len);
- recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG);
+ recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG, 0);
PageSetLSN(page, recptr);
}
@@ -749,7 +749,7 @@ nextval_internal(Oid relid)
XLogRegisterData((char *) &xlrec, sizeof(xl_seq_rec));
XLogRegisterData((char *) seqtuple.t_data, seqtuple.t_len);
- recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG);
+ recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG, 0);
PageSetLSN(page, recptr);
}
@@ -932,7 +932,7 @@ do_setval(Oid relid, int64 next, bool iscalled)
XLogRegisterData((char *) &xlrec, sizeof(xl_seq_rec));
XLogRegisterData((char *) seqtuple.t_data, seqtuple.t_len);
- recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG);
+ recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG, 0);
PageSetLSN(page, recptr);
}
diff --git a/src/backend/commands/tablespace.c b/src/backend/commands/tablespace.c
index 1ff5728..2fde0ac 100644
--- a/src/backend/commands/tablespace.c
+++ b/src/backend/commands/tablespace.c
@@ -368,7 +368,7 @@ CreateTableSpace(CreateTableSpaceStmt *stmt)
offsetof(xl_tblspc_create_rec, ts_path));
XLogRegisterData((char *) location, strlen(location) + 1);
- (void) XLogInsert(RM_TBLSPC_ID, XLOG_TBLSPC_CREATE);
+ (void) XLogInsert(RM_TBLSPC_ID, XLOG_TBLSPC_CREATE, 0);
}
/*
@@ -523,7 +523,7 @@ DropTableSpace(DropTableSpaceStmt *stmt)
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, sizeof(xl_tblspc_drop_rec));
- (void) XLogInsert(RM_TBLSPC_ID, XLOG_TBLSPC_DROP);
+ (void) XLogInsert(RM_TBLSPC_ID, XLOG_TBLSPC_DROP, 0);
}
/*
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 00f03d8..79cfd7b 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -78,12 +78,12 @@ int BgWriterDelay = 200;
#define LOG_SNAPSHOT_INTERVAL_MS 15000
/*
- * LSN and timestamp at which we last issued a LogStandbySnapshot(), to avoid
- * doing so too often or repeatedly if there has been no other write activity
- * in the system.
+ * Last progress LSN and timestamp at which we last logged a standby
+ * snapshot, to avoid doing so too often or repeatedly if there has been
+ * no other write activity in the system.
*/
static TimestampTz last_snapshot_ts;
-static XLogRecPtr last_snapshot_lsn = InvalidXLogRecPtr;
+static XLogRecPtr last_progress_lsn = InvalidXLogRecPtr;
/*
* Flags set by interrupt handlers for later service in the main loop.
@@ -310,7 +310,7 @@ BackgroundWriterMain(void)
* check whether there has been any WAL inserted since the last time
* we've logged a running xacts.
*
- * We do this logging in the bgwriter as its the only process that is
+ * We do this logging in the bgwriter as it is the only process that is
* run regularly and returns to its mainloop all the time. E.g.
* Checkpointer, when active, is barely ever in its mainloop and thus
* makes it hard to log regularly.
@@ -319,19 +319,23 @@ BackgroundWriterMain(void)
{
TimestampTz timeout = 0;
TimestampTz now = GetCurrentTimestamp();
+ XLogRecPtr current_progress_lsn = GetProgressRecPtr();
timeout = TimestampTzPlusMilliseconds(last_snapshot_ts,
LOG_SNAPSHOT_INTERVAL_MS);
/*
- * only log if enough time has passed and some xlog record has
- * been inserted.
+ * only log if enough time has passed, that some WAL activity
+ * has happened since last checkpoint, and that some xlog record
+ * has been inserted.
*/
if (now >= timeout &&
- last_snapshot_lsn != GetXLogInsertRecPtr())
+ GetLastCheckpointRecPtr() < current_progress_lsn &&
+ last_progress_lsn < current_progress_lsn)
{
- last_snapshot_lsn = LogStandbySnapshot();
+ (void) LogStandbySnapshot();
last_snapshot_ts = now;
+ last_progress_lsn = current_progress_lsn;
}
}
diff --git a/src/backend/replication/logical/origin.c b/src/backend/replication/logical/origin.c
index 8c8833b..8870a27 100644
--- a/src/backend/replication/logical/origin.c
+++ b/src/backend/replication/logical/origin.c
@@ -362,7 +362,7 @@ replorigin_drop(RepOriginId roident)
xlrec.node_id = roident;
XLogBeginInsert();
XLogRegisterData((char *) (&xlrec), sizeof(xlrec));
- XLogInsert(RM_REPLORIGIN_ID, XLOG_REPLORIGIN_DROP);
+ XLogInsert(RM_REPLORIGIN_ID, XLOG_REPLORIGIN_DROP, 0);
}
/* then reset the in-memory entry */
@@ -894,7 +894,7 @@ replorigin_advance(RepOriginId node,
XLogBeginInsert();
XLogRegisterData((char *) (&xlrec), sizeof(xlrec));
- XLogInsert(RM_REPLORIGIN_ID, XLOG_REPLORIGIN_SET);
+ XLogInsert(RM_REPLORIGIN_ID, XLOG_REPLORIGIN_SET, 0);
}
/*
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index 6a9bf84..4f934bb 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -952,7 +952,8 @@ LogStandbySnapshot(void)
* The definitions of RunningTransactionsData and xl_xact_running_xacts
* are similar. We keep them separate because xl_xact_running_xacts
* is a contiguous chunk of memory and never exists fully until it is
- * assembled in WAL.
+ * assembled in WAL. Progress of WAL activity is not updated when
+ * this record is logged.
*/
static XLogRecPtr
LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
@@ -976,7 +977,8 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
XLogRegisterData((char *) CurrRunningXacts->xids,
(xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
- recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
+ recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS,
+ XLOG_INSERT_NO_PROGRESS);
if (CurrRunningXacts->subxid_overflow)
elog(trace_recovery(DEBUG2),
@@ -1024,7 +1026,8 @@ LogAccessExclusiveLocks(int nlocks, xl_standby_lock *locks)
XLogRegisterData((char *) &xlrec, offsetof(xl_standby_locks, locks));
XLogRegisterData((char *) locks, nlocks * sizeof(xl_standby_lock));
- (void) XLogInsert(RM_STANDBY_ID, XLOG_STANDBY_LOCK);
+ (void) XLogInsert(RM_STANDBY_ID, XLOG_STANDBY_LOCK,
+ XLOG_INSERT_NO_PROGRESS);
}
/*
diff --git a/src/backend/utils/cache/relmapper.c b/src/backend/utils/cache/relmapper.c
index 6a63b5e..146ad3b 100644
--- a/src/backend/utils/cache/relmapper.c
+++ b/src/backend/utils/cache/relmapper.c
@@ -767,7 +767,7 @@ write_relmap_file(bool shared, RelMapFile *newmap,
XLogRegisterData((char *) (&xlrec), MinSizeOfRelmapUpdate);
XLogRegisterData((char *) newmap, sizeof(RelMapFile));
- lsn = XLogInsert(RM_RELMAP_ID, XLOG_RELMAP_UPDATE);
+ lsn = XLogInsert(RM_RELMAP_ID, XLOG_RELMAP_UPDATE, 0);
/* As always, WAL must hit the disk before the data update does */
XLogFlush(lsn);
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index ecd30ce..7844844 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -210,7 +210,9 @@ extern CheckpointStatsData CheckpointStats;
struct XLogRecData;
-extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata, XLogRecPtr fpw_lsn);
+extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
+ XLogRecPtr fpw_lsn,
+ uint8 flags);
extern void XLogFlush(XLogRecPtr RecPtr);
extern bool XLogBackgroundFlush(void);
extern bool XLogNeedsFlush(XLogRecPtr RecPtr);
@@ -261,6 +263,8 @@ extern void GetFullPageWriteInfo(XLogRecPtr *RedoRecPtr_p, bool *doPageWrites_p)
extern XLogRecPtr GetRedoRecPtr(void);
extern XLogRecPtr GetInsertRecPtr(void);
extern XLogRecPtr GetFlushRecPtr(void);
+extern XLogRecPtr GetProgressRecPtr(void);
+extern XLogRecPtr GetLastCheckpointRecPtr(void);
extern void GetNextXidAndEpoch(TransactionId *xid, uint32 *epoch);
extern void RemovePromoteSignalFiles(void);
diff --git a/src/include/access/xloginsert.h b/src/include/access/xloginsert.h
index cc0177e..271a26e 100644
--- a/src/include/access/xloginsert.h
+++ b/src/include/access/xloginsert.h
@@ -38,10 +38,14 @@
#define REGBUF_KEEP_DATA 0x10/* include data even if a full-page image is
* taken */
+/* flags for XLogInsert */
+#define XLOG_INSERT_NO_PROGRESS 0x01 /* do not update progress LSN
+ * when inserting record */
+
/* prototypes for public functions in xloginsert.c: */
extern void XLogBeginInsert(void);
extern void XLogIncludeOrigin(void);
-extern XLogRecPtr XLogInsert(RmgrId rmid, uint8 info);
+extern XLogRecPtr XLogInsert(RmgrId rmid, uint8 info, uint8 flags);
extern void XLogEnsureRecordSpace(int nbuffers, int ndatas);
extern void XLogRegisterData(char *data, int len);
extern void XLogRegisterBuffer(uint8 block_id, Buffer buffer, uint8 flags);
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 5b1c361..0ebd8fb 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -436,11 +436,30 @@ typedef struct XLogwrtResult
* the WAL record is just copied to the page and the lock is released. But
* to avoid the deadlock-scenario explained above, the indicator is always
* updated before sleeping while holding an insertion lock.
+ *
+ * The progressAt values indicate the insertion progress used to determine
+ * WAL insertion activity since a previous checkpoint, which is aimed at
+ * finding out if a checkpoint should be skipped or not or if standby
+ * activity should be logged. Progress position is basically updated
+ * for all types of records, for the time being only snapshot logging
+ * is out of this scope to properly skip their logging on idle systems.
+ * Tracking the WAL activity directly in WALInsertLock has the advantage
+ * to not rely on taking an exclusive lock on all the WAL insertion locks,
+ * hence reducing the impact of the activity lookup. This takes also
+ * advantage to avoid 8-byte torn reads on some platforms by using the
+ * fact that each insert lock is located on the same cache line.
+ * XXX: There is still room for more improvements here, particularly
+ * WAL operations related to unlogged relations (INIT_FORKNUM) should not
+ * update the progress LSN as those relations are reset during crash
+ * recovery so enforcing buffers of such relations to be flushed for
+ * example in the case of a load only on unlogged relations is a waste
+ * of disk write.
*/
typedef struct
{
LWLock lock;
XLogRecPtr insertingAt;
+ XLogRecPtr progressAt;
} WALInsertLock;
/*
@@ -878,6 +897,9 @@ static void WALInsertLockUpdateInsertingAt(XLogRecPtr insertingAt);
* which pages need a full-page image, and retry. If fpw_lsn is invalid, the
* record is always inserted.
*
+ * 'flags' gives more in-depth control on the record being inserted. As of
+ * now, this controls if the progress LSN positions are updated.
+ *
* The first XLogRecData in the chain must be for the record header, and its
* data must be MAXALIGNed. XLogInsertRecord fills in the xl_prev and
* xl_crc fields in the header, the rest of the header must already be filled
@@ -890,7 +912,9 @@ static void WALInsertLockUpdateInsertingAt(XLogRecPtr insertingAt);
* WAL rule "write the log before the data".)
*/
XLogRecPtr
-XLogInsertRecord(XLogRecData *rdata, XLogRecPtr fpw_lsn)
+XLogInsertRecord(XLogRecData *rdata,
+ XLogRecPtr fpw_lsn,
+ uint8 flags)
{
XLogCtlInsert *Insert = &XLogCtl->Insert;
pg_crc32c rdata_crc;
@@ -989,6 +1013,25 @@ XLogInsertRecord(XLogRecData *rdata, XLogRecPtr fpw_lsn)
inserted = true;
}
+ /*
+ * Update the progress LSN positions. At least one WAL insertion lock
+ * is already taken appropriately before doing that, and it is just more
+ * simple to do that here where WAL record data and type is at hand.
+ * The progress is set at the start position of the record tracked that
+ * is being added, making easier checkpoint progress tracking as the
+ * control file already saves the start LSN position of the last
+ * checkpoint run. If an exclusive lock is taken for WAL insertion,
+ * there is actually no need to update all the progression fields, so
+ * just do it on the first one.
+ */
+ if ((flags & XLOG_INSERT_NO_PROGRESS) == 0)
+ {
+ if (holdingAllLocks)
+ WALInsertLocks[0].l.progressAt = StartPos;
+ else
+ WALInsertLocks[MyLockNo].l.progressAt = StartPos;
+ }
+
if (inserted)
{
/*
@@ -4714,6 +4757,7 @@ XLOGShmemInit(void)
{
LWLockInitialize(&WALInsertLocks[i].l.lock, LWTRANCHE_WAL_INSERT);
WALInsertLocks[i].l.insertingAt = InvalidXLogRecPtr;
+ WALInsertLocks[i].l.progressAt = InvalidXLogRecPtr;
}
/*
@@ -7887,6 +7931,55 @@ GetFlushRecPtr(void)
}
/*
+ * GetProgressRecPtr -- Returns the newest WAL activity position, aimed
+ * at the last significant WAL activity, or in other words any activity
+ * not referring to standby logging as of now. Finding the last activity
+ * position is done by scanning each WAL insertion lock by taking directly
+ * the light-weight lock associated to it.
+ */
+XLogRecPtr
+GetProgressRecPtr(void)
+{
+ XLogRecPtr res = InvalidXLogRecPtr;
+ int i;
+
+ /*
+ * Look at the latest LSN position referring to the activity done by
+ * WAL insertion. An exclusive lock is taken because currently the
+ * locking logic for WAL insertion only expects such a level of locking.
+ * Taking a lock is as well necessary to prevent potential torn reads
+ * on some platforms.
+ */
+ for (i = 0; i < NUM_XLOGINSERT_LOCKS; i++)
+ {
+ XLogRecPtr progress_lsn;
+
+ LWLockAcquire(&WALInsertLocks[i].l.lock, LW_EXCLUSIVE);
+ progress_lsn = WALInsertLocks[i].l.progressAt;
+ LWLockRelease(&WALInsertLocks[i].l.lock);
+
+ if (res < progress_lsn)
+ res = progress_lsn;
+ }
+
+ return res;
+}
+
+/*
+ * GetLastCheckpointRecPtr -- Returns the last checkpoint insert position.
+ */
+XLogRecPtr
+GetLastCheckpointRecPtr(void)
+{
+ XLogRecPtr ckpt_lsn;
+
+ LWLockAcquire(ControlFileLock, LW_SHARED);
+ ckpt_lsn = ControlFile->checkPoint;
+ LWLockRelease(ControlFileLock);
+ return ckpt_lsn;
+}
+
+/*
* Get the time of the last xlog segment switch
*/
pg_time_t
@@ -8146,7 +8239,7 @@ CreateCheckPoint(int flags)
uint32 freespace;
XLogRecPtr PriorRedoPtr;
XLogRecPtr curInsert;
- XLogRecPtr prevPtr;
+ XLogRecPtr progress_lsn;
VirtualTransactionId *vxids;
int nvxids;
@@ -8227,34 +8320,30 @@ CreateCheckPoint(int flags)
checkPoint.oldestActiveXid = InvalidTransactionId;
/*
+ * Get progress before acquiring insert locks to shorten the locked
+ * section waiting ahead.
+ */
+ progress_lsn = GetProgressRecPtr();
+
+ /*
* We must block concurrent insertions while examining insert state to
* determine the checkpoint REDO pointer.
*/
WALInsertLockAcquireExclusive();
curInsert = XLogBytePosToRecPtr(Insert->CurrBytePos);
- prevPtr = XLogBytePosToRecPtr(Insert->PrevBytePos);
/*
- * If this isn't a shutdown or forced checkpoint, and we have not inserted
- * any XLOG records since the start of the last checkpoint, skip the
- * checkpoint. The idea here is to avoid inserting duplicate checkpoints
- * when the system is idle. That wastes log space, and more importantly it
- * exposes us to possible loss of both current and previous checkpoint
- * records if the machine crashes just as we're writing the update.
- * (Perhaps it'd make even more sense to checkpoint only when the previous
- * checkpoint record is in a different xlog page?)
- *
- * If the previous checkpoint crossed a WAL segment, however, we create
- * the checkpoint anyway, to have the latest checkpoint fully contained in
- * the new segment. This is for a little bit of extra robustness: it's
- * better if you don't need to keep two WAL segments around to recover the
- * checkpoint.
+ * If this isn't a shutdown or forced checkpoint, and if there has been no
+ * WAL activity, skip the checkpoint. The idea here is to avoid inserting
+ * duplicate checkpoints when the system is idle. That wastes log space,
+ * and more importantly it exposes us to possible loss of both current and
+ * previous checkpoint records if the machine crashes just as we're writing
+ * the update.
*/
if ((flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY |
CHECKPOINT_FORCE)) == 0)
{
- if (prevPtr == ControlFile->checkPointCopy.redo &&
- prevPtr / XLOG_SEG_SIZE == curInsert / XLOG_SEG_SIZE)
+ if (progress_lsn == ControlFile->checkPoint)
{
WALInsertLockRelease();
LWLockRelease(CheckpointLock);
diff --git a/src/backend/access/transam/xloginsert.c b/src/backend/access/transam/xloginsert.c
index c37003a..7cddc55 100644
--- a/src/backend/access/transam/xloginsert.c
+++ b/src/backend/access/transam/xloginsert.c
@@ -394,9 +394,23 @@ XLogIncludeOrigin(void)
}
/*
+ * XLogInsert
+ *
+ * A shorthand for XLogInsertExtended, to update the progress of WAL
+ * activity by default.
+ */
+XLogRecPtr
+XLogInsert(RmgrId rmid, uint8 info)
+{
+ return XLogInsertExtended(rmid, info, 0);
+}
+
+/*
* Insert an XLOG record having the specified RMID and info bytes, with the
* body of the record being the data and buffer references registered earlier
- * with XLogRegister* calls.
+ * with XLogRegister* calls. 'flags' allow users to control more in-depth
+ * operations during WAL record insertion. As of now, this gives control on
+ * if the progress LSN positions are updated or not.
*
* Returns XLOG pointer to end of record (beginning of next record).
* This can be used as LSN for data pages affected by the logged action.
@@ -405,7 +419,7 @@ XLogIncludeOrigin(void)
* WAL rule "write the log before the data".)
*/
XLogRecPtr
-XLogInsert(RmgrId rmid, uint8 info)
+XLogInsertExtended(RmgrId rmid, uint8 info, uint8 flags)
{
XLogRecPtr EndPos;
@@ -450,7 +464,7 @@ XLogInsert(RmgrId rmid, uint8 info)
rdt = XLogRecordAssemble(rmid, info, RedoRecPtr, doPageWrites,
&fpw_lsn);
- EndPos = XLogInsertRecord(rdt, fpw_lsn);
+ EndPos = XLogInsertRecord(rdt, fpw_lsn, flags);
} while (EndPos == InvalidXLogRecPtr);
XLogResetInsertion();
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 00f03d8..79cfd7b 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -78,12 +78,12 @@ int BgWriterDelay = 200;
#define LOG_SNAPSHOT_INTERVAL_MS 15000
/*
- * LSN and timestamp at which we last issued a LogStandbySnapshot(), to avoid
- * doing so too often or repeatedly if there has been no other write activity
- * in the system.
+ * Last progress LSN and timestamp at which we last logged a standby
+ * snapshot, to avoid doing so too often or repeatedly if there has been
+ * no other write activity in the system.
*/
static TimestampTz last_snapshot_ts;
-static XLogRecPtr last_snapshot_lsn = InvalidXLogRecPtr;
+static XLogRecPtr last_progress_lsn = InvalidXLogRecPtr;
/*
* Flags set by interrupt handlers for later service in the main loop.
@@ -310,7 +310,7 @@ BackgroundWriterMain(void)
* check whether there has been any WAL inserted since the last time
* we've logged a running xacts.
*
- * We do this logging in the bgwriter as its the only process that is
+ * We do this logging in the bgwriter as it is the only process that is
* run regularly and returns to its mainloop all the time. E.g.
* Checkpointer, when active, is barely ever in its mainloop and thus
* makes it hard to log regularly.
@@ -319,19 +319,23 @@ BackgroundWriterMain(void)
{
TimestampTz timeout = 0;
TimestampTz now = GetCurrentTimestamp();
+ XLogRecPtr current_progress_lsn = GetProgressRecPtr();
timeout = TimestampTzPlusMilliseconds(last_snapshot_ts,
LOG_SNAPSHOT_INTERVAL_MS);
/*
- * only log if enough time has passed and some xlog record has
- * been inserted.
+ * only log if enough time has passed, that some WAL activity
+ * has happened since last checkpoint, and that some xlog record
+ * has been inserted.
*/
if (now >= timeout &&
- last_snapshot_lsn != GetXLogInsertRecPtr())
+ GetLastCheckpointRecPtr() < current_progress_lsn &&
+ last_progress_lsn < current_progress_lsn)
{
- last_snapshot_lsn = LogStandbySnapshot();
+ (void) LogStandbySnapshot();
last_snapshot_ts = now;
+ last_progress_lsn = current_progress_lsn;
}
}
diff --git a/src/backend/storage/ipc/standby.c b/src/backend/storage/ipc/standby.c
index 6a9bf84..75c367c 100644
--- a/src/backend/storage/ipc/standby.c
+++ b/src/backend/storage/ipc/standby.c
@@ -952,7 +952,8 @@ LogStandbySnapshot(void)
* The definitions of RunningTransactionsData and xl_xact_running_xacts
* are similar. We keep them separate because xl_xact_running_xacts
* is a contiguous chunk of memory and never exists fully until it is
- * assembled in WAL.
+ * assembled in WAL. Progress of WAL activity is not updated when
+ * this record is logged.
*/
static XLogRecPtr
LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
@@ -976,7 +977,9 @@ LogCurrentRunningXacts(RunningTransactions CurrRunningXacts)
XLogRegisterData((char *) CurrRunningXacts->xids,
(xlrec.xcnt + xlrec.subxcnt) * sizeof(TransactionId));
- recptr = XLogInsert(RM_STANDBY_ID, XLOG_RUNNING_XACTS);
+ recptr = XLogInsertExtended(RM_STANDBY_ID,
+ XLOG_RUNNING_XACTS,
+ XLOG_INSERT_NO_PROGRESS);
if (CurrRunningXacts->subxid_overflow)
elog(trace_recovery(DEBUG2),
@@ -1024,7 +1027,8 @@ LogAccessExclusiveLocks(int nlocks, xl_standby_lock *locks)
XLogRegisterData((char *) &xlrec, offsetof(xl_standby_locks, locks));
XLogRegisterData((char *) locks, nlocks * sizeof(xl_standby_lock));
- (void) XLogInsert(RM_STANDBY_ID, XLOG_STANDBY_LOCK);
+ (void) XLogInsertExtended(RM_STANDBY_ID, XLOG_STANDBY_LOCK,
+ XLOG_INSERT_NO_PROGRESS);
}
/*
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index ecd30ce..7844844 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -210,7 +210,9 @@ extern CheckpointStatsData CheckpointStats;
struct XLogRecData;
-extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata, XLogRecPtr fpw_lsn);
+extern XLogRecPtr XLogInsertRecord(struct XLogRecData *rdata,
+ XLogRecPtr fpw_lsn,
+ uint8 flags);
extern void XLogFlush(XLogRecPtr RecPtr);
extern bool XLogBackgroundFlush(void);
extern bool XLogNeedsFlush(XLogRecPtr RecPtr);
@@ -261,6 +263,8 @@ extern void GetFullPageWriteInfo(XLogRecPtr *RedoRecPtr_p, bool *doPageWrites_p)
extern XLogRecPtr GetRedoRecPtr(void);
extern XLogRecPtr GetInsertRecPtr(void);
extern XLogRecPtr GetFlushRecPtr(void);
+extern XLogRecPtr GetProgressRecPtr(void);
+extern XLogRecPtr GetLastCheckpointRecPtr(void);
extern void GetNextXidAndEpoch(TransactionId *xid, uint32 *epoch);
extern void RemovePromoteSignalFiles(void);
diff --git a/src/include/access/xloginsert.h b/src/include/access/xloginsert.h
index cc0177e..6ff0176 100644
--- a/src/include/access/xloginsert.h
+++ b/src/include/access/xloginsert.h
@@ -38,10 +38,15 @@
#define REGBUF_KEEP_DATA 0x10/* include data even if a full-page image is
* taken */
+/* flags for XLogInsertExtended */
+#define XLOG_INSERT_NO_PROGRESS 0x01 /* do not update progress LSN
+ * when inserting record */
+
/* prototypes for public functions in xloginsert.c: */
extern void XLogBeginInsert(void);
extern void XLogIncludeOrigin(void);
extern XLogRecPtr XLogInsert(RmgrId rmid, uint8 info);
+extern XLogRecPtr XLogInsertExtended(RmgrId rmid, uint8 info, uint8 flags);
extern void XLogEnsureRecordSpace(int nbuffers, int ndatas);
extern void XLogRegisterData(char *data, int len);
extern void XLogRegisterBuffer(uint8 block_id, Buffer buffer, uint8 flags);
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
