public inbox for [email protected]
help / color / mirror / Atom feedFrom: Kyotaro Horiguchi <[email protected]>
Subject: [PATCH 5/7] Add infrastructure to WAL-logging skip feature
Date: Tue, 2 Apr 2019 18:05:10 +0900
We used to optimize WAL-logging for truncation of in-transaction
crated tables in minimal mode by just signaling by
HEAP_INSERT_SKIP_WAL option on heap operations. This mechanism can
emit WAL records that results in corrupt state for certain series of
in-transaction operations. This patch provides infrastructure to track
pending at-commit fsyncs for a relation and in-transaction
truncations. table_relation_register_walskip() should be used to start
tracking before batch operations like COPY and CLUSTER, and use
BufferNeedsWAL() instead of RelationNeedsWAL() at the places related
to WAL-logging about heap-modifying operations, then remove
call to table_finish_bulk_insert() and the tableam intaface.
---
src/backend/access/transam/xact.c | 12 +-
src/backend/catalog/storage.c | 612 +++++++++++++++++++++++++++++++++---
src/backend/commands/tablecmds.c | 6 +-
src/backend/storage/buffer/bufmgr.c | 39 ++-
src/backend/utils/cache/relcache.c | 3 +
src/include/catalog/storage.h | 17 +-
src/include/storage/bufmgr.h | 2 +
src/include/utils/rel.h | 7 +
8 files changed, 631 insertions(+), 67 deletions(-)
diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c
index e9ed92b70b..33a83dc784 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -2102,6 +2102,9 @@ CommitTransaction(void)
/* close large objects before lower-level cleanup */
AtEOXact_LargeObject(true);
+ /* Flush updates to relations that we didn't WAL-logged */
+ smgrFinishBulkInsert(true);
+
/*
* Mark serializable transaction as complete for predicate locking
* purposes. This should be done as late as we can put it and still allow
@@ -2334,6 +2337,9 @@ PrepareTransaction(void)
/* close large objects before lower-level cleanup */
AtEOXact_LargeObject(true);
+ /* Flush updates to relations that we didn't WAL-logged */
+ smgrFinishBulkInsert(true);
+
/*
* Mark serializable transaction as complete for predicate locking
* purposes. This should be done as late as we can put it and still allow
@@ -2659,6 +2665,7 @@ AbortTransaction(void)
AtAbort_Notify();
AtEOXact_RelationMap(false, is_parallel_worker);
AtAbort_Twophase();
+ smgrFinishBulkInsert(false); /* abandon pending syncs */
/*
* Advertise the fact that we aborted in pg_xact (assuming that we got as
@@ -4792,8 +4799,7 @@ CommitSubTransaction(void)
AtEOSubXact_RelationCache(true, s->subTransactionId,
s->parent->subTransactionId);
AtEOSubXact_Inval(true);
- AtSubCommit_smgr();
-
+ AtSubCommit_smgr(s->subTransactionId, s->parent->subTransactionId);
/*
* The only lock we actually release here is the subtransaction XID lock.
*/
@@ -4970,7 +4976,7 @@ AbortSubTransaction(void)
ResourceOwnerRelease(s->curTransactionOwner,
RESOURCE_RELEASE_AFTER_LOCKS,
false, false);
- AtSubAbort_smgr();
+ AtSubAbort_smgr(s->subTransactionId, s->parent->subTransactionId);
AtEOXact_GUC(false, s->gucNestLevel);
AtEOSubXact_SPI(false, s->subTransactionId);
diff --git a/src/backend/catalog/storage.c b/src/backend/catalog/storage.c
index 72242b2476..4cd112f86c 100644
--- a/src/backend/catalog/storage.c
+++ b/src/backend/catalog/storage.c
@@ -21,6 +21,7 @@
#include "miscadmin.h"
+#include "access/tableam.h"
#include "access/visibilitymap.h"
#include "access/xact.h"
#include "access/xlog.h"
@@ -29,10 +30,18 @@
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
#include "storage/freespace.h"
-#include "storage/smgr.h"
+#include "utils/hsearch.h"
#include "utils/memutils.h"
#include "utils/rel.h"
+ /* #define STORAGEDEBUG */ /* turns DEBUG elogs on */
+
+#ifdef STORAGEDEBUG
+#define STORAGE_elog(...) elog(__VA_ARGS__)
+#else
+#define STORAGE_elog(...)
+#endif
+
/*
* We keep a list of all relations (represented as RelFileNode values)
* that have been created or deleted in the current transaction. When
@@ -64,6 +73,61 @@ typedef struct PendingRelDelete
static PendingRelDelete *pendingDeletes = NULL; /* head of linked list */
+/*
+ * We also track relation files (RelFileNode values) that have been created
+ * in the same transaction, and that have been modified without WAL-logging
+ * the action (an optimization possible with wal_level=minimal). When we are
+ * about to skip WAL-logging, a RelWalSkip entry is created, and
+ * 'skip_wal_min_blk' is set to the current size of the relation. Any
+ * operations on blocks < skip_wal_min_blk need to be WAL-logged as usual, but
+ * for operations on higher blocks, WAL-logging is skipped.
+
+ *
+ * NB: after WAL-logging has been skipped for a block, we must not WAL-log
+ * any subsequent actions on the same block either. Replaying the WAL record
+ * of the subsequent action might fail otherwise, as the "before" state of
+ * the block might not match, as the earlier actions were not WAL-logged.
+ * Likewise, after we have WAL-logged an operation for a block, we must
+ * WAL-log any subsequent operations on the same page as well. Replaying
+ * a possible full-page-image from the earlier WAL record would otherwise
+ * revert the page to the old state, even if we sync the relation at end
+ * of transaction.
+ *
+ * If a relation is truncated (without creating a new relfilenode), and we
+ * emit a WAL record of the truncation, we can't skip WAL-logging for any
+ * of the truncated blocks anymore, as replaying the truncation record will
+ * destroy all the data inserted after that. But if we have already decided
+ * to skip WAL-logging changes to a relation, and the relation is truncated,
+ * we don't need to WAL-log the truncation either.
+ *
+ * This mechanism is currently only used by heaps. Indexes are always
+ * WAL-logged. Also, this only applies for wal_level=minimal; with higher
+ * WAL levels we need the WAL for PITR/replication anyway.
+ */
+typedef struct RelWalSkip
+{
+ RelFileNode relnode; /* relation created in same xact */
+ bool forks[MAX_FORKNUM + 1]; /* target forknums */
+ BlockNumber skip_wal_min_blk; /* WAL-logging skipped for blocks >=
+ * skip_wal_min_blk */
+ BlockNumber wal_log_min_blk; /* The minimum blk number that requires
+ * WAL-logging even if skipped by the
+ * above*/
+ SubTransactionId create_sxid; /* subxid where this entry is created */
+ SubTransactionId invalidate_sxid; /* subxid where this entry is
+ * invalidated */
+ const TableAmRoutine *tableam; /* Table access routine */
+} RelWalSkip;
+
+/* Relations that need to be fsync'd at commit */
+static HTAB *walSkipHash = NULL;
+
+static RelWalSkip *getWalSkipEntry(Relation rel, bool create);
+static RelWalSkip *getWalSkipEntryRNode(RelFileNode *node,
+ bool create);
+static void smgrProcessWALSkipInval(bool isCommit, SubTransactionId mySubid,
+ SubTransactionId parentSubid);
+
/*
* RelationCreateStorage
* Create physical storage for a relation.
@@ -261,31 +325,59 @@ RelationTruncate(Relation rel, BlockNumber nblocks)
*/
if (RelationNeedsWAL(rel))
{
- /*
- * Make an XLOG entry reporting the file truncation.
- */
- XLogRecPtr lsn;
- xl_smgr_truncate xlrec;
+ RelWalSkip *walskip;
- xlrec.blkno = nblocks;
- xlrec.rnode = rel->rd_node;
- xlrec.flags = SMGR_TRUNCATE_ALL;
-
- XLogBeginInsert();
- XLogRegisterData((char *) &xlrec, sizeof(xlrec));
-
- lsn = XLogInsert(RM_SMGR_ID,
- XLOG_SMGR_TRUNCATE | XLR_SPECIAL_REL_UPDATE);
+ /* get pending sync entry, create if not yet */
+ walskip = getWalSkipEntry(rel, true);
/*
- * Flush, because otherwise the truncation of the main relation might
- * hit the disk before the WAL record, and the truncation of the FSM
- * or visibility map. If we crashed during that window, we'd be left
- * with a truncated heap, but the FSM or visibility map would still
- * contain entries for the non-existent heap pages.
+ * walskip is null here if rel doesn't support WAL-logging skip,
+ * otherwise check for WAL-skipping status.
*/
- if (fsm || vm)
- XLogFlush(lsn);
+ if (walskip == NULL ||
+ walskip->skip_wal_min_blk == InvalidBlockNumber ||
+ walskip->skip_wal_min_blk < nblocks)
+ {
+ /*
+ * If WAL-skipping is enabled, this is the first time truncation
+ * of this relation in this transaction or truncation that leaves
+ * pages that need at-commit fsync. Make an XLOG entry reporting
+ * the file truncation.
+ */
+ XLogRecPtr lsn;
+ xl_smgr_truncate xlrec;
+
+ xlrec.blkno = nblocks;
+ xlrec.rnode = rel->rd_node;
+ xlrec.flags = SMGR_TRUNCATE_ALL;
+
+ XLogBeginInsert();
+ XLogRegisterData((char *) &xlrec, sizeof(xlrec));
+
+ lsn = XLogInsert(RM_SMGR_ID,
+ XLOG_SMGR_TRUNCATE | XLR_SPECIAL_REL_UPDATE);
+
+ STORAGE_elog(DEBUG2,
+ "WAL-logged truncation of rel %u/%u/%u to %u blocks",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, nblocks);
+ /*
+ * Flush, because otherwise the truncation of the main relation
+ * might hit the disk before the WAL record, and the truncation of
+ * the FSM or visibility map. If we crashed during that window,
+ * we'd be left with a truncated heap, but the FSM or visibility
+ * map would still contain entries for the non-existent heap
+ * pages.
+ */
+ if (fsm || vm)
+ XLogFlush(lsn);
+
+ if (walskip)
+ {
+ /* no longer skip WAL-logging for the blocks */
+ walskip->wal_log_min_blk = nblocks;
+ }
+ }
}
/* Do the real work */
@@ -296,8 +388,7 @@ RelationTruncate(Relation rel, BlockNumber nblocks)
* Copy a fork's data, block by block.
*/
void
-RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
- ForkNumber forkNum, char relpersistence)
+RelationCopyStorage(Relation srcrel, SMgrRelation dst, ForkNumber forkNum)
{
PGAlignedBlock buf;
Page page;
@@ -305,6 +396,8 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
bool copying_initfork;
BlockNumber nblocks;
BlockNumber blkno;
+ SMgrRelation src = srcrel->rd_smgr;
+ char relpersistence = srcrel->rd_rel->relpersistence;
page = (Page) buf.data;
@@ -316,12 +409,33 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
copying_initfork = relpersistence == RELPERSISTENCE_UNLOGGED &&
forkNum == INIT_FORKNUM;
- /*
- * We need to log the copied data in WAL iff WAL archiving/streaming is
- * enabled AND it's a permanent relation.
- */
- use_wal = XLogIsNeeded() &&
- (relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork);
+ if (relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork)
+ {
+ /*
+ * We need to log the copied data in WAL iff WAL archiving/streaming
+ * is enabled AND it's a permanent relation.
+ */
+ if (XLogIsNeeded())
+ use_wal = true;
+
+ /*
+ * If the rel is WAL-logged, must fsync before commit. We use
+ * heap_sync to ensure that the toast table gets fsync'd too. (For a
+ * temp or unlogged rel we don't care since the data will be gone
+ * after a crash anyway.)
+ *
+ * It's obvious that we must do this when not WAL-logging the
+ * copy. It's less obvious that we have to do it even if we did
+ * WAL-log the copied pages. The reason is that since we're copying
+ * outside shared buffers, a CHECKPOINT occurring during the copy has
+ * no way to flush the previously written data to disk (indeed it
+ * won't know the new rel even exists). A crash later on would replay
+ * WAL from the checkpoint, therefore it wouldn't replay our earlier
+ * WAL entries. If we do not fsync those pages here, they might still
+ * not be on disk when the crash occurs.
+ */
+ RecordPendingSync(srcrel, dst, forkNum);
+ }
nblocks = smgrnblocks(src, forkNum);
@@ -358,24 +472,321 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
*/
smgrextend(dst, forkNum, blkno, buf.data, true);
}
+}
+
+/*
+ * Do changes to given heap page need to be WAL-logged?
+ *
+ * This takes into account any previous RecordPendingSync() requests.
+ *
+ * Note that it is required to check this before creating any WAL records for
+ * heap pages - it is not merely an optimization! WAL-logging a record, when
+ * we have already skipped a previous WAL record for the same page could lead
+ * to failure at WAL replay, as the "before" state expected by the record
+ * might not match what's on disk. Also, if the heap was truncated earlier, we
+ * must WAL-log any changes to the once-truncated blocks, because replaying
+ * the truncation record will destroy them.
+ */
+bool
+BufferNeedsWAL(Relation rel, Buffer buf)
+{
+ BlockNumber blkno = InvalidBlockNumber;
+ RelWalSkip *walskip;
+
+ if (!RelationNeedsWAL(rel))
+ return false;
+
+ /* fetch existing pending sync entry */
+ walskip = getWalSkipEntry(rel, false);
/*
- * If the rel is WAL-logged, must fsync before commit. We use heap_sync
- * to ensure that the toast table gets fsync'd too. (For a temp or
- * unlogged rel we don't care since the data will be gone after a crash
- * anyway.)
- *
- * It's obvious that we must do this when not WAL-logging the copy. It's
- * less obvious that we have to do it even if we did WAL-log the copied
- * pages. The reason is that since we're copying outside shared buffers, a
- * CHECKPOINT occurring during the copy has no way to flush the previously
- * written data to disk (indeed it won't know the new rel even exists). A
- * crash later on would replay WAL from the checkpoint, therefore it
- * wouldn't replay our earlier WAL entries. If we do not fsync those pages
- * here, they might still not be on disk when the crash occurs.
+ * no point in doing further work if we know that we don't skip
+ * WAL-logging.
*/
- if (relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork)
- smgrimmedsync(dst, forkNum);
+ if (!walskip)
+ {
+ STORAGE_elog(DEBUG2,
+ "not skipping WAL-logging for rel %u/%u/%u block %u",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, BufferGetBlockNumber(buf));
+ return true;
+ }
+
+ Assert(BufferIsValid(buf));
+
+ blkno = BufferGetBlockNumber(buf);
+
+ /*
+ * We don't skip WAL-logging for pages that once done.
+ */
+ if (walskip->skip_wal_min_blk == InvalidBlockNumber ||
+ walskip->skip_wal_min_blk > blkno)
+ {
+ STORAGE_elog(DEBUG2, "not skipping WAL-logging for rel %u/%u/%u block %u, because skip_wal_min_blk is %u",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, blkno, walskip->skip_wal_min_blk);
+ return true;
+ }
+
+ /*
+ * we don't skip WAL-logging for blocks that have got WAL-logged
+ * truncation
+ */
+ if (walskip->wal_log_min_blk != InvalidBlockNumber &&
+ walskip->wal_log_min_blk <= blkno)
+ {
+ STORAGE_elog(DEBUG2, "not skipping WAL-logging for rel %u/%u/%u block %u, because wal_log_min_blk is %u",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, blkno, walskip->wal_log_min_blk);
+ return true;
+ }
+
+ STORAGE_elog(DEBUG2, "skipping WAL-logging for rel %u/%u/%u block %u",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, blkno);
+
+ return false;
+}
+
+bool
+BlockNeedsWAL(Relation rel, BlockNumber blkno)
+{
+ RelWalSkip *walskip;
+
+ if (!RelationNeedsWAL(rel))
+ return false;
+
+ /* fetch exising pending sync entry */
+ walskip = getWalSkipEntry(rel, false);
+
+ /*
+ * no point in doing further work if we know that we don't skip
+ * WAL-logging.
+ */
+ if (!walskip)
+ return true;
+
+ /*
+ * We don't skip WAL-logging for pages that once done.
+ */
+ if (walskip->skip_wal_min_blk == InvalidBlockNumber ||
+ walskip->skip_wal_min_blk > blkno)
+ {
+ STORAGE_elog(DEBUG2, "not skipping WAL-logging for rel %u/%u/%u block %u, because skip_wal_min_blk is %u",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, blkno, walskip->skip_wal_min_blk);
+ return true;
+ }
+
+ /*
+ * we don't skip WAL-logging for blocks that have got WAL-logged
+ * truncation
+ */
+ if (walskip->wal_log_min_blk != InvalidBlockNumber &&
+ walskip->wal_log_min_blk <= blkno)
+ {
+ STORAGE_elog(DEBUG2, "not skipping WAL-logging for rel %u/%u/%u block %u, because wal_log_min_blk is %u",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, blkno, walskip->wal_log_min_blk);
+
+ return true;
+ }
+
+ STORAGE_elog(DEBUG2, "skipping WAL-logging for rel %u/%u/%u block %u",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, blkno);
+
+ return false;
+}
+
+/*
+ * Remember that the given relation doesn't need WAL-logging for the blocks
+ * after the current block size and for the blocks that are going to be synced
+ * at commit.
+ */
+void
+RecordWALSkipping(Relation rel)
+{
+ RelWalSkip *walskip;
+
+ Assert(RelationNeedsWAL(rel));
+
+ /* get pending sync entry, create if not yet */
+ walskip = getWalSkipEntry(rel, true);
+
+ if (walskip == NULL)
+ return;
+
+ /*
+ * Record only the first registration.
+ */
+ if (walskip->skip_wal_min_blk != InvalidBlockNumber)
+ {
+ STORAGE_elog(DEBUG2, "WAL skipping for rel %u/%u/%u was already registered at block %u (new %u)",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, walskip->skip_wal_min_blk,
+ RelationGetNumberOfBlocks(rel));
+ return;
+ }
+
+ STORAGE_elog(DEBUG2, "registering new WAL skipping rel %u/%u/%u at block %u",
+ rel->rd_node.spcNode, rel->rd_node.dbNode,
+ rel->rd_node.relNode, RelationGetNumberOfBlocks(rel));
+
+ walskip->skip_wal_min_blk = RelationGetNumberOfBlocks(rel);
+}
+
+/*
+ * Record commit-time file sync. This shouldn't be used mixing with
+ * RecordWALSkipping.
+ */
+void
+RecordPendingSync(Relation rel, SMgrRelation targetsrel, ForkNumber forknum)
+{
+ RelWalSkip *walskip;
+
+ Assert(RelationNeedsWAL(rel));
+
+ /* check for support for this feature */
+ if (rel->rd_tableam == NULL ||
+ rel->rd_tableam->relation_register_walskip == NULL)
+ return;
+
+ walskip = getWalSkipEntryRNode(&targetsrel->smgr_rnode.node, true);
+ walskip->forks[forknum] = true;
+ walskip->skip_wal_min_blk = 0;
+ walskip->tableam = rel->rd_tableam;
+
+ STORAGE_elog(DEBUG2,
+ "registering new pending sync for rel %u/%u/%u at block %u",
+ walskip->relnode.spcNode, walskip->relnode.dbNode,
+ walskip->relnode.relNode, 0);
+}
+
+/*
+ * RelationInvalidateWALSkip() -- invalidate WAL-skip entry
+ */
+void
+RelationInvalidateWALSkip(Relation rel)
+{
+ RelWalSkip *walskip;
+
+ /* we know we don't have one */
+ if (rel->rd_nowalskip)
+ return;
+
+ walskip = getWalSkipEntry(rel, false);
+
+ if (!walskip)
+ return;
+
+ /*
+ * The state is reset at subtransaction commit/abort. No invalidation
+ * request must not come for the same relation in the same subtransaction.
+ */
+ Assert(walskip->invalidate_sxid == InvalidSubTransactionId);
+
+ walskip->invalidate_sxid = GetCurrentSubTransactionId();
+
+ STORAGE_elog(DEBUG2,
+ "WAL skip of rel %u/%u/%u invalidated by sxid %d",
+ walskip->relnode.spcNode, walskip->relnode.dbNode,
+ walskip->relnode.relNode, walskip->invalidate_sxid);
+}
+
+/*
+ * getWalSkipEntry: get WAL skip entry.
+ *
+ * Returns WAL skip entry for the relation. The entry tracks WAL-skipping
+ * blocks for the relation. The WAL-skipped blocks need fsync at commit time.
+ * Creates one if needed when create is true. If rel doesn't support this
+ * feature, returns true even if create is true.
+ */
+static inline RelWalSkip *
+getWalSkipEntry(Relation rel, bool create)
+{
+ RelWalSkip *walskip_entry = NULL;
+
+ if (rel->rd_walskip)
+ return rel->rd_walskip;
+
+ /* we know we don't have pending sync entry */
+ if (!create && rel->rd_nowalskip)
+ return NULL;
+
+ /* check for support for this feature */
+ if (rel->rd_tableam == NULL ||
+ rel->rd_tableam->relation_register_walskip == NULL)
+ {
+ rel->rd_nowalskip = true;
+ return NULL;
+ }
+
+ walskip_entry = getWalSkipEntryRNode(&rel->rd_node, create);
+
+ if (!walskip_entry)
+ {
+ /* prevent further hash lookup */
+ rel->rd_nowalskip = true;
+ return NULL;
+ }
+
+ walskip_entry->forks[MAIN_FORKNUM] = true;
+ walskip_entry->tableam = rel->rd_tableam;
+
+ /* hold shortcut in Relation */
+ rel->rd_nowalskip = false;
+ rel->rd_walskip = walskip_entry;
+
+ return walskip_entry;
+}
+
+/*
+ * getWalSkipEntryRNode: get WAL skip entry by rnode
+ *
+ * Returns a WAL skip entry for the RelFileNode.
+ */
+static RelWalSkip *
+getWalSkipEntryRNode(RelFileNode *rnode, bool create)
+{
+ RelWalSkip *walskip_entry = NULL;
+ bool found;
+
+ if (!walSkipHash)
+ {
+ /* First time through: initialize the hash table */
+ HASHCTL ctl;
+
+ if (!create)
+ return NULL;
+
+ MemSet(&ctl, 0, sizeof(ctl));
+ ctl.keysize = sizeof(RelFileNode);
+ ctl.entrysize = sizeof(RelWalSkip);
+ ctl.hash = tag_hash;
+ walSkipHash = hash_create("pending relation sync table", 5,
+ &ctl, HASH_ELEM | HASH_FUNCTION);
+ }
+
+ walskip_entry = (RelWalSkip *)
+ hash_search(walSkipHash, (void *) rnode,
+ create ? HASH_ENTER: HASH_FIND, &found);
+
+ if (!walskip_entry)
+ return NULL;
+
+ /* new entry created */
+ if (!found)
+ {
+ memset(&walskip_entry->forks, 0, sizeof(walskip_entry->forks));
+ walskip_entry->wal_log_min_blk = InvalidBlockNumber;
+ walskip_entry->skip_wal_min_blk = InvalidBlockNumber;
+ walskip_entry->create_sxid = GetCurrentSubTransactionId();
+ walskip_entry->invalidate_sxid = InvalidSubTransactionId;
+ walskip_entry->tableam = NULL;
+ }
+
+ return walskip_entry;
}
/*
@@ -506,6 +917,107 @@ smgrGetPendingDeletes(bool forCommit, RelFileNode **ptr)
return nrels;
}
+/*
+ * Finish bulk insert of files.
+ */
+void
+smgrFinishBulkInsert(bool isCommit)
+{
+ if (!walSkipHash)
+ return;
+
+ if (isCommit)
+ {
+ HASH_SEQ_STATUS status;
+ RelWalSkip *walskip;
+
+ hash_seq_init(&status, walSkipHash);
+
+ while ((walskip = hash_seq_search(&status)) != NULL)
+ {
+ /*
+ * On commit, process valid entreis. Rollback doesn't need sync on
+ * all changes during the transaction.
+ */
+ if (walskip->skip_wal_min_blk != InvalidBlockNumber &&
+ walskip->invalidate_sxid == InvalidSubTransactionId)
+ {
+ int f;
+
+ FlushRelationBuffersWithoutRelCache(walskip->relnode, false);
+
+ /*
+ * We mustn't create an entry when the table AM doesn't
+ * support WAL-skipping.
+ */
+ Assert (walskip->tableam->finish_bulk_insert);
+
+ /* flush all requested forks */
+ for (f = MAIN_FORKNUM ; f <= MAX_FORKNUM ; f++)
+ {
+ if (walskip->forks[f])
+ {
+ walskip->tableam->finish_bulk_insert(walskip->relnode, f);
+ STORAGE_elog(DEBUG2, "finishing bulk insert to rel %u/%u/%u fork %d",
+ walskip->relnode.spcNode,
+ walskip->relnode.dbNode,
+ walskip->relnode.relNode, f);
+ }
+ }
+ }
+ }
+ }
+
+ hash_destroy(walSkipHash);
+ walSkipHash = NULL;
+}
+
+/*
+ * Process pending invalidation of WAL skip happened in the subtransaction
+ */
+void
+smgrProcessWALSkipInval(bool isCommit, SubTransactionId mySubid,
+ SubTransactionId parentSubid)
+{
+ HASH_SEQ_STATUS status;
+ RelWalSkip *walskip;
+
+ if (!walSkipHash)
+ return;
+
+ /* We expect that we don't have walSkipHash in almost all cases */
+ hash_seq_init(&status, walSkipHash);
+
+ while ((walskip = hash_seq_search(&status)) != NULL)
+ {
+ if (walskip->create_sxid == mySubid)
+ {
+ /*
+ * The entry was created in this subxact. Remove it on abort, or
+ * on commit after invalidation.
+ */
+ if (!isCommit || walskip->invalidate_sxid == mySubid)
+ hash_search(walSkipHash, &walskip->relnode,
+ HASH_REMOVE, NULL);
+ /* Treat committing valid entry as creation by the parent. */
+ else if (walskip->invalidate_sxid == InvalidSubTransactionId)
+ walskip->create_sxid = parentSubid;
+ }
+ else if (walskip->invalidate_sxid == mySubid)
+ {
+ /*
+ * This entry was created elsewhere then invalidated by this
+ * subxact. Treat commit as invalidation by the parent. Otherwise
+ * cancel invalidation.
+ */
+ if (isCommit)
+ walskip->invalidate_sxid = parentSubid;
+ else
+ walskip->invalidate_sxid = InvalidSubTransactionId;
+ }
+ }
+}
+
/*
* PostPrepare_smgr -- Clean up after a successful PREPARE
*
@@ -535,7 +1047,7 @@ PostPrepare_smgr(void)
* Reassign all items in the pending-deletes list to the parent transaction.
*/
void
-AtSubCommit_smgr(void)
+AtSubCommit_smgr(SubTransactionId mySubid, SubTransactionId parentSubid)
{
int nestLevel = GetCurrentTransactionNestLevel();
PendingRelDelete *pending;
@@ -545,6 +1057,9 @@ AtSubCommit_smgr(void)
if (pending->nestLevel >= nestLevel)
pending->nestLevel = nestLevel - 1;
}
+
+ /* Remove invalidated WAL skip in this subtransaction */
+ smgrProcessWALSkipInval(true, mySubid, parentSubid);
}
/*
@@ -555,9 +1070,12 @@ AtSubCommit_smgr(void)
* subtransaction will not commit.
*/
void
-AtSubAbort_smgr(void)
+AtSubAbort_smgr(SubTransactionId mySubid, SubTransactionId parentSubid)
{
smgrDoPendingDeletes(false);
+
+ /* Remove invalidated WAL skip in this subtransaction */
+ smgrProcessWALSkipInval(false, mySubid, parentSubid);
}
void
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 654179297c..8908b77d98 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -11983,8 +11983,7 @@ index_copy_data(Relation rel, RelFileNode newrnode)
RelationCreateStorage(newrnode, rel->rd_rel->relpersistence);
/* copy main fork */
- RelationCopyStorage(rel->rd_smgr, dstrel, MAIN_FORKNUM,
- rel->rd_rel->relpersistence);
+ RelationCopyStorage(rel, dstrel, MAIN_FORKNUM);
/* copy those extra forks that exist */
for (ForkNumber forkNum = MAIN_FORKNUM + 1;
@@ -12002,8 +12001,7 @@ index_copy_data(Relation rel, RelFileNode newrnode)
(rel->rd_rel->relpersistence == RELPERSISTENCE_UNLOGGED &&
forkNum == INIT_FORKNUM))
log_smgrcreate(&newrnode, forkNum);
- RelationCopyStorage(rel->rd_smgr, dstrel, forkNum,
- rel->rd_rel->relpersistence);
+ RelationCopyStorage(rel, dstrel, forkNum);
}
}
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index 273e2f385f..f00826712a 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -451,6 +451,7 @@ static BufferDesc *BufferAlloc(SMgrRelation smgr,
BufferAccessStrategy strategy,
bool *foundPtr);
static void FlushBuffer(BufferDesc *buf, SMgrRelation reln);
+static void FlushRelationBuffers_common(SMgrRelation smgr, bool islocal);
static void AtProcExit_Buffers(int code, Datum arg);
static void CheckForBufferLeaks(void);
static int rnode_comparator(const void *p1, const void *p2);
@@ -3153,20 +3154,40 @@ PrintPinnedBufs(void)
void
FlushRelationBuffers(Relation rel)
{
- int i;
- BufferDesc *bufHdr;
-
/* Open rel at the smgr level if not already done */
RelationOpenSmgr(rel);
- if (RelationUsesLocalBuffers(rel))
+ FlushRelationBuffers_common(rel->rd_smgr, RelationUsesLocalBuffers(rel));
+}
+
+/*
+ * Like FlushRelationBuffers(), but the relation is specified by RelFileNode
+ */
+void
+FlushRelationBuffersWithoutRelCache(RelFileNode rnode, bool islocal)
+{
+ FlushRelationBuffers_common(smgropen(rnode, InvalidBackendId), islocal);
+}
+
+/*
+ * Code shared between functions FlushRelationBuffers() and
+ * FlushRelationBuffersWithoutRelCache().
+ */
+static void
+FlushRelationBuffers_common(SMgrRelation smgr, bool islocal)
+{
+ RelFileNode rnode = smgr->smgr_rnode.node;
+ int i;
+ BufferDesc *bufHdr;
+
+ if (islocal)
{
for (i = 0; i < NLocBuffer; i++)
{
uint32 buf_state;
bufHdr = GetLocalBufferDescriptor(i);
- if (RelFileNodeEquals(bufHdr->tag.rnode, rel->rd_node) &&
+ if (RelFileNodeEquals(bufHdr->tag.rnode, rnode) &&
((buf_state = pg_atomic_read_u32(&bufHdr->state)) &
(BM_VALID | BM_DIRTY)) == (BM_VALID | BM_DIRTY))
{
@@ -3183,7 +3204,7 @@ FlushRelationBuffers(Relation rel)
PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);
- smgrwrite(rel->rd_smgr,
+ smgrwrite(smgr,
bufHdr->tag.forkNum,
bufHdr->tag.blockNum,
localpage,
@@ -3213,18 +3234,18 @@ FlushRelationBuffers(Relation rel)
* As in DropRelFileNodeBuffers, an unlocked precheck should be safe
* and saves some cycles.
*/
- if (!RelFileNodeEquals(bufHdr->tag.rnode, rel->rd_node))
+ if (!RelFileNodeEquals(bufHdr->tag.rnode, rnode))
continue;
ReservePrivateRefCountEntry();
buf_state = LockBufHdr(bufHdr);
- if (RelFileNodeEquals(bufHdr->tag.rnode, rel->rd_node) &&
+ if (RelFileNodeEquals(bufHdr->tag.rnode, rnode) &&
(buf_state & (BM_VALID | BM_DIRTY)) == (BM_VALID | BM_DIRTY))
{
PinBuffer_Locked(bufHdr);
LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED);
- FlushBuffer(bufHdr, rel->rd_smgr);
+ FlushBuffer(bufHdr, smgr);
LWLockRelease(BufferDescriptorGetContentLock(bufHdr));
UnpinBuffer(bufHdr, true);
}
diff --git a/src/backend/utils/cache/relcache.c b/src/backend/utils/cache/relcache.c
index 64f3c2e887..f06d55a8fe 100644
--- a/src/backend/utils/cache/relcache.c
+++ b/src/backend/utils/cache/relcache.c
@@ -75,6 +75,7 @@
#include "partitioning/partdesc.h"
#include "rewrite/rewriteDefine.h"
#include "rewrite/rowsecurity.h"
+#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "storage/smgr.h"
#include "utils/array.h"
@@ -5644,6 +5645,8 @@ load_relcache_init_file(bool shared)
rel->rd_newRelfilenodeSubid = InvalidSubTransactionId;
rel->rd_amcache = NULL;
MemSet(&rel->pgstat_info, 0, sizeof(rel->pgstat_info));
+ rel->rd_nowalskip = false;
+ rel->rd_walskip = NULL;
/*
* Recompute lock and physical addressing info. This is needed in
diff --git a/src/include/catalog/storage.h b/src/include/catalog/storage.h
index 882dc65c89..83fee7dbfe 100644
--- a/src/include/catalog/storage.h
+++ b/src/include/catalog/storage.h
@@ -23,8 +23,14 @@ extern void RelationCreateStorage(RelFileNode rnode, char relpersistence);
extern void RelationDropStorage(Relation rel);
extern void RelationPreserveStorage(RelFileNode rnode, bool atCommit);
extern void RelationTruncate(Relation rel, BlockNumber nblocks);
-extern void RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
- ForkNumber forkNum, char relpersistence);
+extern void RelationCopyStorage(Relation srcrel, SMgrRelation dst,
+ ForkNumber forkNum);
+extern bool BufferNeedsWAL(Relation rel, Buffer buf);
+extern bool BlockNeedsWAL(Relation rel, BlockNumber blkno);
+extern void RecordWALSkipping(Relation rel);
+extern void RecordPendingSync(Relation rel, SMgrRelation srel,
+ ForkNumber forknum);
+extern void RelationInvalidateWALSkip(Relation rel);
/*
* These functions used to be in storage/smgr/smgr.c, which explains the
@@ -32,8 +38,11 @@ extern void RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
*/
extern void smgrDoPendingDeletes(bool isCommit);
extern int smgrGetPendingDeletes(bool forCommit, RelFileNode **ptr);
-extern void AtSubCommit_smgr(void);
-extern void AtSubAbort_smgr(void);
+extern void smgrFinishBulkInsert(bool isCommit);
+extern void AtSubCommit_smgr(SubTransactionId mySubid,
+ SubTransactionId parentSubid);
+extern void AtSubAbort_smgr(SubTransactionId mySubid,
+ SubTransactionId parentSubid);
extern void PostPrepare_smgr(void);
#endif /* STORAGE_H */
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index c5826f691d..8a9ea041dd 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -189,6 +189,8 @@ extern BlockNumber RelationGetNumberOfBlocksInFork(Relation relation,
ForkNumber forkNum);
extern void FlushOneBuffer(Buffer buffer);
extern void FlushRelationBuffers(Relation rel);
+extern void FlushRelationBuffersWithoutRelCache(RelFileNode rnode,
+ bool islocal);
extern void FlushDatabaseBuffers(Oid dbid);
extern void DropRelFileNodeBuffers(RelFileNodeBackend rnode,
ForkNumber forkNum, BlockNumber firstDelBlock);
diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h
index 54028515a7..b2b46322b2 100644
--- a/src/include/utils/rel.h
+++ b/src/include/utils/rel.h
@@ -198,6 +198,13 @@ typedef struct RelationData
/* use "struct" here to avoid needing to include pgstat.h: */
struct PgStat_TableStatus *pgstat_info; /* statistics collection area */
+
+ /*
+ * rd_nowalskip is true if this relation is known not to skip WAL.
+ * Otherwise we need to ask smgr for an entry if rd_walskip is NULL.
+ */
+ bool rd_nowalskip;
+ struct RelWalSkip *rd_walskip;
} RelationData;
--
2.16.3
----Next_Part(Tue_Apr_02_19_54_06_2019_801)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
filename="v10-0006-Fix-WAL-skipping-feature.patch"
view thread (42+ messages) latest in thread
reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: [email protected]
Cc: [email protected]
Subject: Re: [PATCH 5/7] Add infrastructure to WAL-logging skip feature
In-Reply-To: <no-message-id-1883182@localhost>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox