public inbox for [email protected]
help / color / mirror / Atom feed[PATCH v3 1/2] In-place table persistence change
3+ messages / 3 participants
[nested] [flat]
* [PATCH v3 1/2] In-place table persistence change
@ 2020-11-11 12:51 Kyotaro Horiguchi <[email protected]>
0 siblings, 0 replies; 3+ messages in thread
From: Kyotaro Horiguchi @ 2020-11-11 12:51 UTC (permalink / raw)
Even though ALTER TABLE SET LOGGED/UNLOGGED does not require data
rewriting, currently it runs heap rewrite which causes large amount of
file I/O. This patch makes the command run without heap rewrite.
Addition to that, SET LOGGED while wal_level > minimal emits WAL using
XLOG_FPI instead of massive number of HEAP_INSERT's, which should be
smaller.
Also this allows for the cleanup of files left behind in the crash of
the transaction that created it.
---
src/backend/access/rmgrdesc/smgrdesc.c | 23 ++
src/backend/access/transam/README | 10 +
src/backend/catalog/storage.c | 420 +++++++++++++++++++++++--
src/backend/commands/tablecmds.c | 246 ++++++++++++---
src/backend/storage/buffer/bufmgr.c | 88 ++++++
src/backend/storage/file/reinit.c | 162 ++++++----
src/backend/storage/smgr/md.c | 4 +-
src/backend/storage/smgr/smgr.c | 6 +
src/common/relpath.c | 3 +-
src/include/catalog/storage.h | 2 +
src/include/catalog/storage_xlog.h | 22 +-
src/include/common/relpath.h | 5 +-
src/include/storage/bufmgr.h | 2 +
src/include/storage/smgr.h | 1 +
14 files changed, 854 insertions(+), 140 deletions(-)
diff --git a/src/backend/access/rmgrdesc/smgrdesc.c b/src/backend/access/rmgrdesc/smgrdesc.c
index 7755553d57..2c109b8ca4 100644
--- a/src/backend/access/rmgrdesc/smgrdesc.c
+++ b/src/backend/access/rmgrdesc/smgrdesc.c
@@ -40,6 +40,23 @@ smgr_desc(StringInfo buf, XLogReaderState *record)
xlrec->blkno, xlrec->flags);
pfree(path);
}
+ else if (info == XLOG_SMGR_UNLINK)
+ {
+ xl_smgr_unlink *xlrec = (xl_smgr_unlink *) rec;
+ char *path = relpathperm(xlrec->rnode, xlrec->forkNum);
+
+ appendStringInfoString(buf, path);
+ pfree(path);
+ }
+ else if (info == XLOG_SMGR_BUFPERSISTENCE)
+ {
+ xl_smgr_bufpersistence *xlrec = (xl_smgr_bufpersistence *) rec;
+ char *path = relpathperm(xlrec->rnode, MAIN_FORKNUM);
+
+ appendStringInfoString(buf, path);
+ appendStringInfo(buf, " persistence %d", xlrec->persistence);
+ pfree(path);
+ }
}
const char *
@@ -55,6 +72,12 @@ smgr_identify(uint8 info)
case XLOG_SMGR_TRUNCATE:
id = "TRUNCATE";
break;
+ case XLOG_SMGR_UNLINK:
+ id = "UNLINK";
+ break;
+ case XLOG_SMGR_BUFPERSISTENCE:
+ id = "BUFPERSISTENCE";
+ break;
}
return id;
diff --git a/src/backend/access/transam/README b/src/backend/access/transam/README
index 1edc8180c1..51616b2458 100644
--- a/src/backend/access/transam/README
+++ b/src/backend/access/transam/README
@@ -724,6 +724,16 @@ we must panic and abort recovery. The DBA will have to manually clean up
then restart recovery. This is part of the reason for not writing a WAL
entry until we've successfully done the original action.
+The INITTMP fork file
+--------------------------------
+
+An INITTMP fork is created when new relation file is created to mark
+the relfilenode needs to be cleaned up at recovery time. The file is
+removed at transaction end but is left when the process crashes before
+the transaction ends. In contrast to 4 above, failure to remove an
+INITTMP file will lead to data loss, in which case the server will
+shut down.
+
Skipping WAL for New RelFileNode
--------------------------------
diff --git a/src/backend/catalog/storage.c b/src/backend/catalog/storage.c
index cba7a9ada0..bd9680583b 100644
--- a/src/backend/catalog/storage.c
+++ b/src/backend/catalog/storage.c
@@ -19,6 +19,7 @@
#include "postgres.h"
+#include "access/amapi.h"
#include "access/parallel.h"
#include "access/visibilitymap.h"
#include "access/xact.h"
@@ -27,6 +28,7 @@
#include "access/xlogutils.h"
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
+#include "common/hashfn.h"
#include "miscadmin.h"
#include "storage/freespace.h"
#include "storage/smgr.h"
@@ -57,9 +59,16 @@ int wal_skip_threshold = 2048; /* in kilobytes */
* but I'm being paranoid.
*/
+#define PDOP_DELETE (0)
+#define PDOP_UNLINK_FORK (1 << 0)
+#define PDOP_SET_PERSISTENCE (1 << 1)
+
typedef struct PendingRelDelete
{
RelFileNode relnode; /* relation that may need to be deleted */
+ int op; /* operation mask */
+ bool bufpersistence; /* buffer persistence to set */
+ int unlink_forknum; /* forknum to unlink */
BackendId backend; /* InvalidBackendId if not a temp rel */
bool atCommit; /* T=delete at commit; F=delete at abort */
int nestLevel; /* xact nesting level of request */
@@ -75,6 +84,24 @@ typedef struct PendingRelSync
static PendingRelDelete *pendingDeletes = NULL; /* head of linked list */
HTAB *pendingSyncHash = NULL;
+typedef struct SRelHashEntry
+{
+ SMgrRelation srel;
+ char status; /* for simplehash use */
+} SRelHashEntry;
+
+/* define hashtable for workarea for pending deletes */
+#define SH_PREFIX srelhash
+#define SH_ELEMENT_TYPE SRelHashEntry
+#define SH_KEY_TYPE SMgrRelation
+#define SH_KEY srel
+#define SH_HASH_KEY(tb, key) \
+ hash_bytes((unsigned char *)&key, sizeof(SMgrRelation))
+#define SH_EQUAL(tb, a, b) (memcmp(&a, &b, sizeof(SMgrRelation)) == 0)
+#define SH_SCOPE static inline
+#define SH_DEFINE
+#define SH_DECLARE
+#include "lib/simplehash.h"
/*
* AddPendingSync
@@ -143,7 +170,17 @@ RelationCreateStorage(RelFileNode rnode, char relpersistence)
return NULL; /* placate compiler */
}
+ /*
+ * We are going to create a new storage file. If server crashes before the
+ * current transaction ends the file needs to be cleaned up but there's no
+ * clue to the orphan files. The inittmp fork works as the sentinel to
+ * identify that situation.
+ */
srel = smgropen(rnode, backend);
+ smgrcreate(srel, INITTMP_FORKNUM, false);
+ log_smgrcreate(&rnode, INITTMP_FORKNUM);
+ smgrimmedsync(srel, INITTMP_FORKNUM);
+
smgrcreate(srel, MAIN_FORKNUM, false);
if (needs_wal)
@@ -153,12 +190,25 @@ RelationCreateStorage(RelFileNode rnode, char relpersistence)
pending = (PendingRelDelete *)
MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
pending->relnode = rnode;
+ pending->op = PDOP_DELETE;
pending->backend = backend;
pending->atCommit = false; /* delete if abort */
pending->nestLevel = GetCurrentTransactionNestLevel();
pending->next = pendingDeletes;
pendingDeletes = pending;
+ /* drop inittmp fork at commit */
+ pending = (PendingRelDelete *)
+ MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
+ pending->relnode = rnode;
+ pending->op = PDOP_UNLINK_FORK;
+ pending->unlink_forknum = INITTMP_FORKNUM;
+ pending->backend = backend;
+ pending->atCommit = true;
+ pending->nestLevel = GetCurrentTransactionNestLevel();
+ pending->next = pendingDeletes;
+ pendingDeletes = pending;
+
if (relpersistence == RELPERSISTENCE_PERMANENT && !XLogIsNeeded())
{
Assert(backend == InvalidBackendId);
@@ -168,6 +218,215 @@ RelationCreateStorage(RelFileNode rnode, char relpersistence)
return srel;
}
+/*
+ * RelationCreateInitFork
+ * Create physical storage for the init fork of a relation.
+ *
+ * Create the init fork for the relation.
+ *
+ * This function is transactional. The creation is WAL-logged, and if the
+ * transaction aborts later on, the init fork will be removed.
+ */
+void
+RelationCreateInitFork(Relation rel)
+{
+ RelFileNode rnode = rel->rd_node;
+ PendingRelDelete *pending;
+ SMgrRelation srel;
+ PendingRelDelete *prev;
+ PendingRelDelete *next;
+ bool create = true;
+
+ /* switch buffer persistence */
+ SetRelationBuffersPersistence(rel->rd_smgr, false, false);
+
+ /*
+ * If we have entries for init-fork operation of this relation, that means
+ * that we have already registered pending sync entries to drop preexisting
+ * init fork since before the current transaction started. This function
+ * reverts that change just by removing the entries.
+ */
+ prev = NULL;
+ for (pending = pendingDeletes; pending != NULL; pending = next)
+ {
+ next = pending->next;
+ if (RelFileNodeEquals(rnode, pending->relnode) &&
+ pending->op != PDOP_DELETE)
+ {
+ if (prev)
+ prev->next = next;
+ else
+ pendingDeletes = next;
+ pfree(pending);
+
+ create = false;
+ }
+ else
+ {
+ /* unrelated entry, don't touch it */
+ prev = pending;
+ }
+ }
+
+ if (!create)
+ return;
+
+ /*
+ * We are going to create the init fork. If server crashes before the
+ * current transaction ends the init fork left alone corrupts data while
+ * recovery. The inittmp fork works as the sentinel to identify that
+ * situation.
+ */
+ srel = smgropen(rnode, InvalidBackendId);
+ smgrcreate(srel, INITTMP_FORKNUM, false);
+ log_smgrcreate(&rnode, INITTMP_FORKNUM);
+ smgrimmedsync(srel, INITTMP_FORKNUM);
+
+ /* We don't have existing init fork, create it. */
+ smgrcreate(srel, INIT_FORKNUM, false);
+
+ /*
+ * index-init fork needs further initialization. ambuildempty shoud do
+ * WAL-log and file sync by itself but otherwise we do that by myself.
+ */
+ if (rel->rd_rel->relkind == RELKIND_INDEX)
+ rel->rd_indam->ambuildempty(rel);
+ else
+ {
+ log_smgrcreate(&rnode, INIT_FORKNUM);
+ smgrimmedsync(srel, INIT_FORKNUM);
+ }
+
+ /* drop this init fork file at abort and revert persistence */
+ pending = (PendingRelDelete *)
+ MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
+ pending->relnode = rnode;
+ pending->op = PDOP_UNLINK_FORK | PDOP_SET_PERSISTENCE;
+ pending->unlink_forknum = INIT_FORKNUM;
+ pending->bufpersistence = true;
+ pending->backend = InvalidBackendId;
+ pending->atCommit = false;
+ pending->nestLevel = GetCurrentTransactionNestLevel();
+ pending->next = pendingDeletes;
+ pendingDeletes = pending;
+
+ /* drop inittmp fork at abort */
+ pending = (PendingRelDelete *)
+ MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
+ pending->relnode = rnode;
+ pending->op = PDOP_UNLINK_FORK;
+ pending->unlink_forknum = INITTMP_FORKNUM;
+ pending->backend = InvalidBackendId;
+ pending->atCommit = false;
+ pending->nestLevel = GetCurrentTransactionNestLevel();
+ pending->next = pendingDeletes;
+ pendingDeletes = pending;
+
+ /* drop inittmp fork at commit */
+ pending = (PendingRelDelete *)
+ MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
+ pending->relnode = rnode;
+ pending->op = PDOP_UNLINK_FORK;
+ pending->unlink_forknum = INITTMP_FORKNUM;
+ pending->backend = InvalidBackendId;
+ pending->atCommit = true;
+ pending->nestLevel = GetCurrentTransactionNestLevel();
+ pending->next = pendingDeletes;
+ pendingDeletes = pending;
+}
+
+/*
+ * RelationDropInitFork
+ * Delete physical storage for the init fork of a relation.
+ *
+ * Register pending-delete of the init fork. The real deletion is performed by
+ * smgrDoPendingDeletes at commit.
+ *
+ * This function is transactional. If the transaction aborts later on, the
+ * deletion doesn't happen.
+ */
+void
+RelationDropInitFork(Relation rel)
+{
+ RelFileNode rnode = rel->rd_node;
+ PendingRelDelete *pending;
+ PendingRelDelete *prev;
+ PendingRelDelete *next;
+ bool inxact_created = false;
+
+ /* switch buffer persistence */
+ SetRelationBuffersPersistence(rel->rd_smgr, true, false);
+
+ /*
+ * If we have entries for init-fork operation of this relation, that means
+ * that we have created the init fork in the current transaction. We
+ * immediately remove the init and inittmp forks immediately in that case.
+ * Otherwise just reister pending-delete for the existing init fork.
+ */
+ prev = NULL;
+ for (pending = pendingDeletes; pending != NULL; pending = next)
+ {
+ next = pending->next;
+ if (RelFileNodeEquals(rnode, pending->relnode) &&
+ pending->op != PDOP_DELETE)
+ {
+ /* unlink list entry */
+ if (prev)
+ prev->next = next;
+ else
+ pendingDeletes = next;
+ pfree(pending);
+
+ inxact_created = true;
+ }
+ else
+ {
+ /* unrelated entry, don't touch it */
+ prev = pending;
+ }
+ }
+
+ if (inxact_created)
+ {
+ SMgrRelation srel = smgropen(rnode, InvalidBackendId);
+
+ /*
+ * INIT/INITTMP forks never be loaded to shared buffer so no point in
+ * dropping buffers for these files.
+ */
+ log_smgrunlink(&rnode, INIT_FORKNUM);
+ smgrunlink(srel, INIT_FORKNUM, false);
+ log_smgrunlink(&rnode, INITTMP_FORKNUM);
+ smgrunlink(srel, INITTMP_FORKNUM, false);
+ smgrclose(srel);
+ return;
+ }
+
+ /* register drop of this init fork file at commit */
+ pending = (PendingRelDelete *)
+ MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
+ pending->relnode = rnode;
+ pending->op = PDOP_UNLINK_FORK;
+ pending->unlink_forknum = INIT_FORKNUM;
+ pending->backend = InvalidBackendId;
+ pending->atCommit = true;
+ pending->nestLevel = GetCurrentTransactionNestLevel();
+ pending->next = pendingDeletes;
+ pendingDeletes = pending;
+
+ /* revert buffer-persistence changes at abort */
+ pending = (PendingRelDelete *)
+ MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
+ pending->relnode = rnode;
+ pending->op = PDOP_SET_PERSISTENCE;
+ pending->bufpersistence = false;
+ pending->backend = InvalidBackendId;
+ pending->atCommit = true;
+ pending->nestLevel = GetCurrentTransactionNestLevel();
+ pending->next = pendingDeletes;
+ pendingDeletes = pending;
+}
+
/*
* Perform XLogInsert of an XLOG_SMGR_CREATE record to WAL.
*/
@@ -187,6 +446,44 @@ log_smgrcreate(const RelFileNode *rnode, ForkNumber forkNum)
XLogInsert(RM_SMGR_ID, XLOG_SMGR_CREATE | XLR_SPECIAL_REL_UPDATE);
}
+/*
+ * Perform XLogInsert of an XLOG_SMGR_UNLINK record to WAL.
+ */
+void
+log_smgrunlink(const RelFileNode *rnode, ForkNumber forkNum)
+{
+ xl_smgr_unlink xlrec;
+
+ /*
+ * Make an XLOG entry reporting the file unlink.
+ */
+ xlrec.rnode = *rnode;
+ xlrec.forkNum = forkNum;
+
+ XLogBeginInsert();
+ XLogRegisterData((char *) &xlrec, sizeof(xlrec));
+ XLogInsert(RM_SMGR_ID, XLOG_SMGR_UNLINK | XLR_SPECIAL_REL_UPDATE);
+}
+
+/*
+ * Perform XLogInsert of an XLOG_SMGR_BUFPERSISTENCE record to WAL.
+ */
+void
+log_smgrbufpersistence(const RelFileNode *rnode, bool persistence)
+{
+ xl_smgr_bufpersistence xlrec;
+
+ /*
+ * Make an XLOG entry reporting the change of buffer persistence.
+ */
+ xlrec.rnode = *rnode;
+ xlrec.persistence = persistence;
+
+ XLogBeginInsert();
+ XLogRegisterData((char *) &xlrec, sizeof(xlrec));
+ XLogInsert(RM_SMGR_ID, XLOG_SMGR_BUFPERSISTENCE | XLR_SPECIAL_REL_UPDATE);
+}
+
/*
* RelationDropStorage
* Schedule unlinking of physical storage at transaction commit.
@@ -200,6 +497,7 @@ RelationDropStorage(Relation rel)
pending = (PendingRelDelete *)
MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
pending->relnode = rel->rd_node;
+ pending->op = PDOP_DELETE;
pending->backend = rel->rd_backend;
pending->atCommit = true; /* delete if commit */
pending->nestLevel = GetCurrentTransactionNestLevel();
@@ -602,59 +900,97 @@ smgrDoPendingDeletes(bool isCommit)
int nrels = 0,
maxrels = 0;
SMgrRelation *srels = NULL;
+ srelhash_hash *close_srels = NULL;
+ bool found;
+
prev = NULL;
for (pending = pendingDeletes; pending != NULL; pending = next)
{
+ SMgrRelation srel;
+
next = pending->next;
if (pending->nestLevel < nestLevel)
{
/* outer-level entries should not be processed yet */
prev = pending;
+ continue;
}
+
+ /* unlink list entry first, so we don't retry on failure */
+ if (prev)
+ prev->next = next;
else
+ pendingDeletes = next;
+
+ if (pending->atCommit != isCommit)
{
- /* unlink list entry first, so we don't retry on failure */
- if (prev)
- prev->next = next;
- else
- pendingDeletes = next;
- /* do deletion if called for */
- if (pending->atCommit == isCommit)
- {
- SMgrRelation srel;
-
- srel = smgropen(pending->relnode, pending->backend);
-
- /* allocate the initial array, or extend it, if needed */
- if (maxrels == 0)
- {
- maxrels = 8;
- srels = palloc(sizeof(SMgrRelation) * maxrels);
- }
- else if (maxrels <= nrels)
- {
- maxrels *= 2;
- srels = repalloc(srels, sizeof(SMgrRelation) * maxrels);
- }
-
- srels[nrels++] = srel;
- }
/* must explicitly free the list entry */
pfree(pending);
/* prev does not change */
+ continue;
+ }
+
+ if (close_srels == NULL)
+ close_srels = srelhash_create(CurrentMemoryContext, 32, NULL);
+
+ srel = smgropen(pending->relnode, pending->backend);
+
+ /* Uniquify the smgr relations */
+ srelhash_insert(close_srels, srel, &found);
+
+ if (pending->op != PDOP_DELETE)
+ {
+ if (pending->op & PDOP_UNLINK_FORK)
+ {
+ /* other forks needs to drop buffers */
+ Assert(pending->unlink_forknum == INIT_FORKNUM ||
+ pending->unlink_forknum == INITTMP_FORKNUM);
+
+ log_smgrunlink(&pending->relnode, pending->unlink_forknum);
+ smgrunlink(srel, pending->unlink_forknum, false);
+
+ }
+
+ if (pending->op & PDOP_SET_PERSISTENCE)
+ SetRelationBuffersPersistence(srel, pending->bufpersistence,
+ false);
+ }
+ else
+ {
+ /* allocate the initial array, or extend it, if needed */
+ if (maxrels == 0)
+ {
+ maxrels = 8;
+ srels = palloc(sizeof(SMgrRelation) * maxrels);
+ }
+ else if (maxrels <= nrels)
+ {
+ maxrels *= 2;
+ srels = repalloc(srels, sizeof(SMgrRelation) * maxrels);
+ }
+
+ srels[nrels++] = srel;
}
}
if (nrels > 0)
{
smgrdounlinkall(srels, nrels, false);
-
- for (int i = 0; i < nrels; i++)
- smgrclose(srels[i]);
-
pfree(srels);
}
+
+ if (close_srels)
+ {
+ srelhash_iterator i;
+ SRelHashEntry *ent;
+
+ /* close smgr relatoins */
+ srelhash_start_iterate(close_srels, &i);
+ while ((ent = srelhash_iterate(close_srels, &i)) != NULL)
+ smgrclose(ent->srel);
+ srelhash_destroy(close_srels);
+ }
}
/*
@@ -824,7 +1160,8 @@ smgrGetPendingDeletes(bool forCommit, RelFileNode **ptr)
for (pending = pendingDeletes; pending != NULL; pending = pending->next)
{
if (pending->nestLevel >= nestLevel && pending->atCommit == forCommit
- && pending->backend == InvalidBackendId)
+ && pending->backend == InvalidBackendId
+ && pending->op == PDOP_DELETE)
nrels++;
}
if (nrels == 0)
@@ -837,7 +1174,8 @@ smgrGetPendingDeletes(bool forCommit, RelFileNode **ptr)
for (pending = pendingDeletes; pending != NULL; pending = pending->next)
{
if (pending->nestLevel >= nestLevel && pending->atCommit == forCommit
- && pending->backend == InvalidBackendId)
+ && pending->backend == InvalidBackendId &&
+ pending->op == PDOP_DELETE)
{
*rptr = pending->relnode;
rptr++;
@@ -917,6 +1255,15 @@ smgr_redo(XLogReaderState *record)
reln = smgropen(xlrec->rnode, InvalidBackendId);
smgrcreate(reln, xlrec->forkNum, true);
}
+ else if (info == XLOG_SMGR_UNLINK)
+ {
+ xl_smgr_unlink *xlrec = (xl_smgr_unlink *) XLogRecGetData(record);
+ SMgrRelation reln;
+
+ reln = smgropen(xlrec->rnode, InvalidBackendId);
+ smgrunlink(reln, xlrec->forkNum, true);
+ smgrclose(reln);
+ }
else if (info == XLOG_SMGR_TRUNCATE)
{
xl_smgr_truncate *xlrec = (xl_smgr_truncate *) XLogRecGetData(record);
@@ -1005,6 +1352,15 @@ smgr_redo(XLogReaderState *record)
FreeFakeRelcacheEntry(rel);
}
+ else if (info == XLOG_SMGR_BUFPERSISTENCE)
+ {
+ xl_smgr_bufpersistence *xlrec =
+ (xl_smgr_bufpersistence *) XLogRecGetData(record);
+ SMgrRelation reln;
+
+ reln = smgropen(xlrec->rnode, InvalidBackendId);
+ SetRelationBuffersPersistence(reln, xlrec->persistence, true);
+ }
else
elog(PANIC, "smgr_redo: unknown op code %u", info);
}
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 993da56d43..37a15d31ee 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -50,6 +50,7 @@
#include "commands/defrem.h"
#include "commands/event_trigger.h"
#include "commands/policy.h"
+#include "commands/progress.h"
#include "commands/sequence.h"
#include "commands/tablecmds.h"
#include "commands/tablespace.h"
@@ -4917,6 +4918,170 @@ ATParseTransformCmd(List **wqueue, AlteredTableInfo *tab, Relation rel,
return newcmd;
}
+/*
+ * RelationChangePersistence: do in-place persistence change of a relation
+ */
+static void
+RelationChangePersistence(AlteredTableInfo *tab, char persistence,
+ LOCKMODE lockmode)
+{
+ Relation rel;
+ Relation classRel;
+ HeapTuple tuple,
+ newtuple;
+ Datum new_val[Natts_pg_class];
+ bool new_null[Natts_pg_class],
+ new_repl[Natts_pg_class];
+ int i;
+ List *relids;
+ ListCell *lc_oid;
+
+ Assert(tab->rewrite == AT_REWRITE_ALTER_PERSISTENCE);
+ Assert(lockmode == AccessExclusiveLock);
+
+ /*
+ * Under the following condition, we need to call ATRewriteTable, which
+ * cannot be false in the AT_REWRITE_ALTER_PERSISTENCE case.
+ */
+ Assert(tab->constraints == NULL && tab->partition_constraint == NULL &&
+ tab->newvals == NULL && !tab->verify_new_notnull);
+
+ rel = table_open(tab->relid, lockmode);
+
+ Assert(rel->rd_rel->relpersistence != persistence);
+
+ elog(DEBUG1, "perform im-place persistnce change");
+
+ RelationOpenSmgr(rel);
+
+ /*
+ * First we collect all relations that we need to change persistence.
+ */
+
+ /* Collect OIDs of indexes and toast relations */
+ relids = RelationGetIndexList(rel);
+ relids = lcons_oid(rel->rd_id, relids);
+
+ /* Add toast relation if any */
+ if (OidIsValid(rel->rd_rel->reltoastrelid))
+ {
+ List *toastidx;
+ Relation toastrel = table_open(rel->rd_rel->reltoastrelid, lockmode);
+
+ RelationOpenSmgr(toastrel);
+ relids = lappend_oid(relids, rel->rd_rel->reltoastrelid);
+ toastidx = RelationGetIndexList(toastrel);
+ relids = list_concat(relids, toastidx);
+ pfree(toastidx);
+ table_close(toastrel, NoLock);
+ }
+
+ table_close(rel, NoLock);
+
+ /* Make changes in storage */
+ classRel = table_open(RelationRelationId, RowExclusiveLock);
+
+ foreach (lc_oid, relids)
+ {
+ Oid reloid = lfirst_oid(lc_oid);
+ Relation r = relation_open(reloid, lockmode);
+
+ /*
+ * Some access methods do not accept in-place persistence change. For
+ * example, GiST uses page LSNs to figure out whether a block has
+ * changed, where UNLOGGED GiST indexes use fake LSNs that are
+ * incompatible with real LSNs used for LOGGED ones.
+ *
+ * XXXX: We don't bother allowing in-place persistence change for index
+ * methods other than btree for now.
+ */
+ if (r->rd_rel->relkind == RELKIND_INDEX &&
+ r->rd_rel->relam != BTREE_AM_OID)
+ {
+ int reindex_flags;
+
+ /* reindex doesn't allow concurrent use of the index */
+ table_close(r, NoLock);
+
+ reindex_flags =
+ REINDEX_REL_SUPPRESS_INDEX_USE |
+ REINDEX_REL_CHECK_CONSTRAINTS;
+
+ /* Set the same persistence with the parent relation. */
+ if (persistence == RELPERSISTENCE_UNLOGGED)
+ reindex_flags |= REINDEX_REL_FORCE_INDEXES_UNLOGGED;
+ else
+ reindex_flags |= REINDEX_REL_FORCE_INDEXES_PERMANENT;
+
+ reindex_index(reloid, reindex_flags, persistence, 0);
+
+ continue;
+ }
+
+ RelationOpenSmgr(r);
+
+ /* Create or drop init fork */
+ if (persistence == RELPERSISTENCE_UNLOGGED)
+ RelationCreateInitFork(r);
+ else
+ RelationDropInitFork(r);
+
+ /*
+ * When this relation gets WAL-logged, immediately sync all files but
+ * initfork to establish the initial state on storage. Buffers have
+ * already flushed out by RelationCreate(Drop)InitFork called just
+ * above. Initfork should have been synced as needed.
+ */
+ if (persistence == RELPERSISTENCE_PERMANENT)
+ {
+ for (i = 0 ; i < INIT_FORKNUM ; i++)
+ {
+ if (smgrexists(r->rd_smgr, i))
+ smgrimmedsync(r->rd_smgr, i);
+ }
+ }
+
+ /* Update catalog */
+ tuple = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(reloid));
+ if (!HeapTupleIsValid(tuple))
+ elog(ERROR, "cache lookup failed for relation %u", reloid);
+
+ memset(new_val, 0, sizeof(new_val));
+ memset(new_null, false, sizeof(new_null));
+ memset(new_repl, false, sizeof(new_repl));
+
+ new_val[Anum_pg_class_relpersistence - 1] = CharGetDatum(persistence);
+ new_null[Anum_pg_class_relpersistence - 1] = false;
+ new_repl[Anum_pg_class_relpersistence - 1] = true;
+
+ newtuple = heap_modify_tuple(tuple, RelationGetDescr(classRel),
+ new_val, new_null, new_repl);
+
+ CatalogTupleUpdate(classRel, &newtuple->t_self, newtuple);
+ heap_freetuple(newtuple);
+
+ /*
+ * While wal_level >= replica, switching to LOGGED requires the
+ * relation content to be WAL-logged to recover the table.
+ */
+ if (persistence == RELPERSISTENCE_PERMANENT && XLogIsNeeded())
+ {
+ ForkNumber fork;
+
+ for (fork = 0; fork < INIT_FORKNUM ; fork++)
+ {
+ if (smgrexists(r->rd_smgr, fork))
+ log_newpage_range(r, fork,
+ 0, smgrnblocks(r->rd_smgr, fork), false);
+ }
+ }
+
+ table_close(r, NoLock);
+ }
+
+ table_close(classRel, NoLock);
+}
+
/*
* ATRewriteTables: ALTER TABLE phase 3
*/
@@ -5037,45 +5202,52 @@ ATRewriteTables(AlterTableStmt *parsetree, List **wqueue, LOCKMODE lockmode,
tab->relid,
tab->rewrite);
- /*
- * Create transient table that will receive the modified data.
- *
- * Ensure it is marked correctly as logged or unlogged. We have
- * to do this here so that buffers for the new relfilenode will
- * have the right persistence set, and at the same time ensure
- * that the original filenode's buffers will get read in with the
- * correct setting (i.e. the original one). Otherwise a rollback
- * after the rewrite would possibly result with buffers for the
- * original filenode having the wrong persistence setting.
- *
- * NB: This relies on swap_relation_files() also swapping the
- * persistence. That wouldn't work for pg_class, but that can't be
- * unlogged anyway.
- */
- OIDNewHeap = make_new_heap(tab->relid, NewTableSpace, persistence,
- lockmode);
+ if (tab->rewrite == AT_REWRITE_ALTER_PERSISTENCE)
+ RelationChangePersistence(tab, persistence, lockmode);
+ else
+ {
+ /*
+ * Create transient table that will receive the modified data.
+ *
+ * Ensure it is marked correctly as logged or unlogged. We
+ * have to do this here so that buffers for the new relfilenode
+ * will have the right persistence set, and at the same time
+ * ensure that the original filenode's buffers will get read in
+ * with the correct setting (i.e. the original one). Otherwise
+ * a rollback after the rewrite would possibly result with
+ * buffers for the original filenode having the wrong
+ * persistence setting.
+ *
+ * NB: This relies on swap_relation_files() also swapping the
+ * persistence. That wouldn't work for pg_class, but that can't
+ * be unlogged anyway.
+ */
+ OIDNewHeap = make_new_heap(tab->relid, NewTableSpace, persistence,
+ lockmode);
- /*
- * Copy the heap data into the new table with the desired
- * modifications, and test the current data within the table
- * against new constraints generated by ALTER TABLE commands.
- */
- ATRewriteTable(tab, OIDNewHeap, lockmode);
+ /*
+ * Copy the heap data into the new table with the desired
+ * modifications, and test the current data within the table
+ * against new constraints generated by ALTER TABLE commands.
+ */
+ ATRewriteTable(tab, OIDNewHeap, lockmode);
- /*
- * Swap the physical files of the old and new heaps, then rebuild
- * indexes and discard the old heap. We can use RecentXmin for
- * the table's new relfrozenxid because we rewrote all the tuples
- * in ATRewriteTable, so no older Xid remains in the table. Also,
- * we never try to swap toast tables by content, since we have no
- * interest in letting this code work on system catalogs.
- */
- finish_heap_swap(tab->relid, OIDNewHeap,
- false, false, true,
- !OidIsValid(tab->newTableSpace),
- RecentXmin,
- ReadNextMultiXactId(),
- persistence);
+ /*
+ * Swap the physical files of the old and new heaps, then
+ * rebuild indexes and discard the old heap. We can use
+ * RecentXmin for the table's new relfrozenxid because we
+ * rewrote all the tuples in ATRewriteTable, so no older Xid
+ * remains in the table. Also, we never try to swap toast
+ * tables by content, since we have no interest in letting this
+ * code work on system catalogs.
+ */
+ finish_heap_swap(tab->relid, OIDNewHeap,
+ false, false, true,
+ !OidIsValid(tab->newTableSpace),
+ RecentXmin,
+ ReadNextMultiXactId(),
+ persistence);
+ }
}
else
{
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index 71b5852224..b730b4417c 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -37,6 +37,7 @@
#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/storage.h"
+#include "catalog/storage_xlog.h"
#include "executor/instrument.h"
#include "lib/binaryheap.h"
#include "miscadmin.h"
@@ -3032,6 +3033,93 @@ DropRelFileNodeBuffers(RelFileNodeBackend rnode, ForkNumber *forkNum,
}
}
+/* ---------------------------------------------------------------------
+ * SetRelFileNodeBuffersPersistence
+ *
+ * This function changes the persistence of all buffer pages of a relation
+ * then writes all dirty pages of the relation out to disk when switching
+ * to PERMANENT. (or more accurately, out to kernel disk buffers),
+ * ensuring that the kernel has an up-to-date view of the relation.
+ *
+ * Generally, the caller should be holding AccessExclusiveLock on the
+ * target relation to ensure that no other backend is busy dirtying
+ * more blocks of the relation; the effects can't be expected to last
+ * after the lock is released.
+ *
+ * XXX currently it sequentially searches the buffer pool, should be
+ * changed to more clever ways of searching. This routine is not
+ * used in any performance-critical code paths, so it's not worth
+ * adding additional overhead to normal paths to make it go faster;
+ * but see also DropRelFileNodeBuffers.
+ * --------------------------------------------------------------------
+ */
+void
+SetRelationBuffersPersistence(SMgrRelation srel, bool permanent, bool isRedo)
+{
+ int i;
+ RelFileNodeBackend rnode = srel->smgr_rnode;
+
+ Assert (!RelFileNodeBackendIsTemp(rnode));
+
+ if (!isRedo)
+ log_smgrbufpersistence(&srel->smgr_rnode.node, permanent);
+
+ ResourceOwnerEnlargeBuffers(CurrentResourceOwner);
+
+ for (i = 0; i < NBuffers; i++)
+ {
+ BufferDesc *bufHdr = GetBufferDescriptor(i);
+ uint32 buf_state;
+
+ if (!RelFileNodeEquals(bufHdr->tag.rnode, rnode.node))
+ continue;
+
+ ReservePrivateRefCountEntry();
+
+ buf_state = LockBufHdr(bufHdr);
+
+ if (!RelFileNodeEquals(bufHdr->tag.rnode, rnode.node))
+ {
+ UnlockBufHdr(bufHdr, buf_state);
+ continue;
+ }
+
+ if (permanent)
+ {
+ /* Init fork is being dropped, drop buffers for it. */
+ if (bufHdr->tag.forkNum == INIT_FORKNUM)
+ {
+ InvalidateBuffer(bufHdr);
+ continue;
+ }
+
+ buf_state |= BM_PERMANENT;
+ pg_atomic_write_u32(&bufHdr->state, buf_state);
+
+ /* we flush this buffer when switching to PERMANENT */
+ if ((buf_state & (BM_VALID | BM_DIRTY)) == (BM_VALID | BM_DIRTY))
+ {
+ PinBuffer_Locked(bufHdr);
+ LWLockAcquire(BufferDescriptorGetContentLock(bufHdr),
+ LW_SHARED);
+ FlushBuffer(bufHdr, srel);
+ LWLockRelease(BufferDescriptorGetContentLock(bufHdr));
+ UnpinBuffer(bufHdr, true);
+ }
+ else
+ UnlockBufHdr(bufHdr, buf_state);
+ }
+ else
+ {
+ /* init fork is always BM_PERMANENT. See BufferAlloc */
+ if (bufHdr->tag.forkNum != INIT_FORKNUM)
+ buf_state &= ~BM_PERMANENT;
+
+ UnlockBufHdr(bufHdr, buf_state);
+ }
+ }
+}
+
/* ---------------------------------------------------------------------
* DropRelFileNodesAllBuffers
*
diff --git a/src/backend/storage/file/reinit.c b/src/backend/storage/file/reinit.c
index 40c758d789..adcb54b0fa 100644
--- a/src/backend/storage/file/reinit.c
+++ b/src/backend/storage/file/reinit.c
@@ -31,7 +31,8 @@ static void ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname,
typedef struct
{
Oid reloid; /* hash key */
-} unlogged_relation_entry;
+ bool dirty; /* to be removed */
+} relfile_entry;
/*
* Reset unlogged relations from before the last restart.
@@ -151,6 +152,8 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
DIR *dbspace_dir;
struct dirent *de;
char rm_path[MAXPGPATH * 2];
+ HTAB *hash;
+ HASHCTL ctl;
/* Caller must specify at least one operation. */
Assert((op & (UNLOGGED_RELATION_CLEANUP | UNLOGGED_RELATION_INIT)) != 0);
@@ -160,88 +163,86 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
* the files with init forks. Then, we go through again and nuke
* everything with the same OID except the init fork.
*/
+
+ /*
+ * It's possible that someone could create a ton of unlogged relations
+ * in the same database & tablespace, so we'd better use a hash table
+ * rather than an array or linked list to keep track of which files
+ * need to be reset. Otherwise, this cleanup operation would be
+ * O(n^2).
+ */
+ memset(&ctl, 0, sizeof(ctl));
+ ctl.keysize = sizeof(Oid);
+ ctl.entrysize = sizeof(relfile_entry);
+ hash = hash_create("inittmp hash", 32, &ctl, HASH_ELEM | HASH_BLOBS);
+
+ /* Collect inttmp forks in the directory. */
+ dbspace_dir = AllocateDir(dbspacedirname);
+ while ((de = ReadDir(dbspace_dir, dbspacedirname)) != NULL)
+ {
+ int oidchars;
+ ForkNumber forkNum;
+
+ /* Skip anything that doesn't look like a relation data file. */
+ if (!parse_filename_for_nontemp_relation(de->d_name, &oidchars,
+ &forkNum))
+ continue;
+
+ /* Record init and inittmp forks */
+ if (forkNum == INIT_FORKNUM || forkNum == INITTMP_FORKNUM)
+ {
+ Oid key;
+ relfile_entry *ent;
+ bool found;
+
+ /*
+ * Record the relfilenode. If it has INITTMP fork, the all files
+ * needs to be cleaned up. Otherwise the relfilenode is cleaned up
+ * according to the unloggedness.
+ */
+ key = atooid(de->d_name);
+ ent = hash_search(hash, &key, HASH_ENTER, &found);
+
+ if (!found)
+ ent->dirty = false;
+
+ if (forkNum == INITTMP_FORKNUM)
+ ent->dirty = true;
+ }
+ }
+
+ /* Done with the first pass. */
+ FreeDir(dbspace_dir);
+
if ((op & UNLOGGED_RELATION_CLEANUP) != 0)
{
- HTAB *hash;
- HASHCTL ctl;
-
- /*
- * It's possible that someone could create a ton of unlogged relations
- * in the same database & tablespace, so we'd better use a hash table
- * rather than an array or linked list to keep track of which files
- * need to be reset. Otherwise, this cleanup operation would be
- * O(n^2).
- */
- ctl.keysize = sizeof(Oid);
- ctl.entrysize = sizeof(unlogged_relation_entry);
- ctl.hcxt = CurrentMemoryContext;
- hash = hash_create("unlogged relation OIDs", 32, &ctl,
- HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
-
- /* Scan the directory. */
- dbspace_dir = AllocateDir(dbspacedirname);
- while ((de = ReadDir(dbspace_dir, dbspacedirname)) != NULL)
- {
- ForkNumber forkNum;
- int oidchars;
- unlogged_relation_entry ent;
-
- /* Skip anything that doesn't look like a relation data file. */
- if (!parse_filename_for_nontemp_relation(de->d_name, &oidchars,
- &forkNum))
- continue;
-
- /* Also skip it unless this is the init fork. */
- if (forkNum != INIT_FORKNUM)
- continue;
-
- /*
- * Put the OID portion of the name into the hash table, if it
- * isn't already.
- */
- ent.reloid = atooid(de->d_name);
- (void) hash_search(hash, &ent, HASH_ENTER, NULL);
- }
-
- /* Done with the first pass. */
- FreeDir(dbspace_dir);
-
- /*
- * If we didn't find any init forks, there's no point in continuing;
- * we can bail out now.
- */
- if (hash_get_num_entries(hash) == 0)
- {
- hash_destroy(hash);
- return;
- }
-
/*
* Now, make a second pass and remove anything that matches.
*/
dbspace_dir = AllocateDir(dbspacedirname);
while ((de = ReadDir(dbspace_dir, dbspacedirname)) != NULL)
{
- ForkNumber forkNum;
- int oidchars;
- unlogged_relation_entry ent;
+ ForkNumber forkNum;
+ int oidchars;
+ Oid key;
+ relfile_entry *ent;
/* Skip anything that doesn't look like a relation data file. */
if (!parse_filename_for_nontemp_relation(de->d_name, &oidchars,
&forkNum))
continue;
- /* We never remove the init fork. */
- if (forkNum == INIT_FORKNUM)
- continue;
-
/*
* See whether the OID portion of the name shows up in the hash
* table. If so, nuke it!
*/
- ent.reloid = atooid(de->d_name);
- if (hash_search(hash, &ent, HASH_FIND, NULL))
+ key = atooid(de->d_name);
+ ent = hash_search(hash, &key, HASH_FIND, NULL);
+
+ /* we don't remove clean init file */
+ if (ent && (ent->dirty || forkNum != INIT_FORKNUM))
{
+ /* so, nuke it! */
snprintf(rm_path, sizeof(rm_path), "%s/%s",
dbspacedirname, de->d_name);
if (unlink(rm_path) < 0)
@@ -256,7 +257,6 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
/* Cleanup is complete. */
FreeDir(dbspace_dir);
- hash_destroy(hash);
}
/*
@@ -277,12 +277,42 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
char oidbuf[OIDCHARS + 1];
char srcpath[MAXPGPATH * 2];
char dstpath[MAXPGPATH];
+ Oid key;
+ relfile_entry *ent;
/* Skip anything that doesn't look like a relation data file. */
if (!parse_filename_for_nontemp_relation(de->d_name, &oidchars,
&forkNum))
continue;
+ /*
+ * See whether the OID portion of the name shows up in the hash
+ * table.
+ */
+ key = atooid(de->d_name);
+ ent = hash_search(hash, &key, HASH_FIND, NULL);
+
+ /* we don't remove clean init file */
+ if (ent && (ent->dirty || forkNum != INIT_FORKNUM))
+ {
+ /*
+ * The file is dirty. It shoudl have been removed once at
+ * cleanup time but recovery can create them again. Remove
+ * them.
+ */
+ snprintf(rm_path, sizeof(rm_path), "%s/%s",
+ dbspacedirname, de->d_name);
+ if (unlink(rm_path) < 0)
+ ereport(ERROR,
+ (errcode_for_file_access(),
+ errmsg("could not remove file \"%s\": %m",
+ rm_path)));
+ else
+ elog(DEBUG2, "unlinked file \"%s\"", rm_path);
+
+ continue;
+ }
+
/* Also skip it unless this is the init fork. */
if (forkNum != INIT_FORKNUM)
continue;
@@ -351,6 +381,8 @@ ResetUnloggedRelationsInDbspaceDir(const char *dbspacedirname, int op)
*/
fsync_fname(dbspacedirname, true);
}
+
+ hash_destroy(hash);
}
/*
diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 0643d714fb..416fd859e6 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -338,8 +338,10 @@ mdunlinkfork(RelFileNodeBackend rnode, ForkNumber forkNum, bool isRedo)
if (ret == 0 || errno != ENOENT)
{
ret = unlink(path);
+
+ /* failure of removing inittmp fork leads to a data loss. */
if (ret < 0 && errno != ENOENT)
- ereport(WARNING,
+ ereport((forkNum != INITTMP_FORKNUM ? WARNING : ERROR),
(errcode_for_file_access(),
errmsg("could not remove file \"%s\": %m", path)));
}
diff --git a/src/backend/storage/smgr/smgr.c b/src/backend/storage/smgr/smgr.c
index 0f31ff3822..4102d3d59c 100644
--- a/src/backend/storage/smgr/smgr.c
+++ b/src/backend/storage/smgr/smgr.c
@@ -644,6 +644,12 @@ smgrimmedsync(SMgrRelation reln, ForkNumber forknum)
smgrsw[reln->smgr_which].smgr_immedsync(reln, forknum);
}
+void
+smgrunlink(SMgrRelation reln, ForkNumber forknum, bool isRedo)
+{
+ smgrsw[reln->smgr_which].smgr_unlink(reln->smgr_rnode, forknum, isRedo);
+}
+
/*
* AtEOXact_SMgr
*
diff --git a/src/common/relpath.c b/src/common/relpath.c
index 1f5c426ec0..2954cd9c24 100644
--- a/src/common/relpath.c
+++ b/src/common/relpath.c
@@ -34,7 +34,8 @@ const char *const forkNames[] = {
"main", /* MAIN_FORKNUM */
"fsm", /* FSM_FORKNUM */
"vm", /* VISIBILITYMAP_FORKNUM */
- "init" /* INIT_FORKNUM */
+ "init", /* INIT_FORKNUM */
+ "itmp" /* INITTMP_FORKNUM */
};
StaticAssertDecl(lengthof(forkNames) == (MAX_FORKNUM + 1),
diff --git a/src/include/catalog/storage.h b/src/include/catalog/storage.h
index 0ab32b44e9..382623159c 100644
--- a/src/include/catalog/storage.h
+++ b/src/include/catalog/storage.h
@@ -23,6 +23,8 @@
extern int wal_skip_threshold;
extern SMgrRelation RelationCreateStorage(RelFileNode rnode, char relpersistence);
+extern void RelationCreateInitFork(Relation rel);
+extern void RelationDropInitFork(Relation rel);
extern void RelationDropStorage(Relation rel);
extern void RelationPreserveStorage(RelFileNode rnode, bool atCommit);
extern void RelationPreTruncate(Relation rel);
diff --git a/src/include/catalog/storage_xlog.h b/src/include/catalog/storage_xlog.h
index f0814f1458..0fd0832a8b 100644
--- a/src/include/catalog/storage_xlog.h
+++ b/src/include/catalog/storage_xlog.h
@@ -22,13 +22,17 @@
/*
* Declarations for smgr-related XLOG records
*
- * Note: we log file creation and truncation here, but logging of deletion
- * actions is handled by xact.c, because it is part of transaction commit.
+ * Note: we log file creation, truncation, deletion and persistence change
+ * here. logging of deletion actions is mainly handled by xact.c, because it is
+ * part of transaction commit, but we log deletions happens outside of a
+ * transaction.
*/
/* XLOG gives us high 4 bits */
#define XLOG_SMGR_CREATE 0x10
#define XLOG_SMGR_TRUNCATE 0x20
+#define XLOG_SMGR_UNLINK 0x30
+#define XLOG_SMGR_BUFPERSISTENCE 0x40
typedef struct xl_smgr_create
{
@@ -36,6 +40,18 @@ typedef struct xl_smgr_create
ForkNumber forkNum;
} xl_smgr_create;
+typedef struct xl_smgr_unlink
+{
+ RelFileNode rnode;
+ ForkNumber forkNum;
+} xl_smgr_unlink;
+
+typedef struct xl_smgr_bufpersistence
+{
+ RelFileNode rnode;
+ bool persistence;
+} xl_smgr_bufpersistence;
+
/* flags for xl_smgr_truncate */
#define SMGR_TRUNCATE_HEAP 0x0001
#define SMGR_TRUNCATE_VM 0x0002
@@ -51,6 +67,8 @@ typedef struct xl_smgr_truncate
} xl_smgr_truncate;
extern void log_smgrcreate(const RelFileNode *rnode, ForkNumber forkNum);
+extern void log_smgrunlink(const RelFileNode *rnode, ForkNumber forkNum);
+extern void log_smgrbufpersistence(const RelFileNode *rnode, bool persistence);
extern void smgr_redo(XLogReaderState *record);
extern void smgr_desc(StringInfo buf, XLogReaderState *record);
diff --git a/src/include/common/relpath.h b/src/include/common/relpath.h
index a44be11ca0..4305bdbe96 100644
--- a/src/include/common/relpath.h
+++ b/src/include/common/relpath.h
@@ -43,7 +43,8 @@ typedef enum ForkNumber
MAIN_FORKNUM = 0,
FSM_FORKNUM,
VISIBILITYMAP_FORKNUM,
- INIT_FORKNUM
+ INIT_FORKNUM,
+ INITTMP_FORKNUM
/*
* NOTE: if you add a new fork, change MAX_FORKNUM and possibly
@@ -52,7 +53,7 @@ typedef enum ForkNumber
*/
} ForkNumber;
-#define MAX_FORKNUM INIT_FORKNUM
+#define MAX_FORKNUM INITTMP_FORKNUM
#define FORKNAMECHARS 4 /* max chars for a fork name */
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index ff6cd0fc54..d9752a8317 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -205,6 +205,8 @@ extern void FlushRelationsAllBuffers(struct SMgrRelationData **smgrs, int nrels)
extern void FlushDatabaseBuffers(Oid dbid);
extern void DropRelFileNodeBuffers(RelFileNodeBackend rnode, ForkNumber *forkNum,
int nforks, BlockNumber *firstDelBlock);
+extern void SetRelationBuffersPersistence(struct SMgrRelationData *srel,
+ bool permanent, bool isRedo);
extern void DropRelFileNodesAllBuffers(RelFileNodeBackend *rnodes, int nnodes);
extern void DropDatabaseBuffers(Oid dbid);
diff --git a/src/include/storage/smgr.h b/src/include/storage/smgr.h
index ebf4a199dc..8be17d9afc 100644
--- a/src/include/storage/smgr.h
+++ b/src/include/storage/smgr.h
@@ -86,6 +86,7 @@ extern void smgrclose(SMgrRelation reln);
extern void smgrcloseall(void);
extern void smgrclosenode(RelFileNodeBackend rnode);
extern void smgrcreate(SMgrRelation reln, ForkNumber forknum, bool isRedo);
+extern void smgrunlink(SMgrRelation reln, ForkNumber forknum, bool isRedo);
extern void smgrdosyncall(SMgrRelation *rels, int nrels);
extern void smgrdounlinkall(SMgrRelation *rels, int nrels, bool isRedo);
extern void smgrextend(SMgrRelation reln, ForkNumber forknum,
--
2.27.0
----Next_Part(Fri_Jan__8_14_47_05_2021_579)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
filename="v3-0002-New-command-ALTER-TABLE-ALL-IN-TABLESPACE-SET-LOG.patch"
^ permalink raw reply [nested|flat] 3+ messages in thread
* Difference in dump from original and restored database due to NOT NULL constraints on children
@ 2024-11-14 10:56 Ashutosh Bapat <[email protected]>
2024-11-14 12:38 ` Re: Difference in dump from original and restored database due to NOT NULL constraints on children Alvaro Herrera <[email protected]>
0 siblings, 1 reply; 3+ messages in thread
From: Ashutosh Bapat @ 2024-11-14 10:56 UTC (permalink / raw)
To: Alvaro Herrera <[email protected]>; pgsql-hackers
Hi Alvaro,
Because of the test I am developing under discussion at [1], I noticed
that the DDLs dumped for inheritance children with NOT NULL
constraints defer between original database and database restored from
a dump of original database. I investigated those differences, but can
not decide whether they are expected and whether they are intentional
or not. Look something related to
14e87ffa5c543b5f30ead7413084c25f7735039f.
I have attached four files. Original dumps from source (src_dump.sql)
and restored databases (dest_dump.plain.sql). Dumps adjusted for known
differences (src_dump.sql_adjusted and
dest_dump.plain.sql_adjusted respectively)
as per AdjustDump.pm module added by 0001 patch attached to [1].
Are these differences safe? Are they intentional?
--
Best Wishes,
Ashutosh Bapat
Attachments:
[application/octet-stream] dest_dump.plain.sql_adjusted (491.2K, ../../CAExHW5tbdgAKDfqjDJ-7Fk6PJtHg8D4zUF6FQ4H2Pq8zK38Nyw@mail.gmail.com/2-dest_dump.plain.sql_adjusted)
download
[application/sql] src_dump.sql (497.9K, ../../CAExHW5tbdgAKDfqjDJ-7Fk6PJtHg8D4zUF6FQ4H2Pq8zK38Nyw@mail.gmail.com/3-src_dump.sql)
download
[application/octet-stream] src_dump.sql_adjusted (491.1K, ../../CAExHW5tbdgAKDfqjDJ-7Fk6PJtHg8D4zUF6FQ4H2Pq8zK38Nyw@mail.gmail.com/4-src_dump.sql_adjusted)
download
[application/sql] dest_dump.plain.sql (497.9K, ../../CAExHW5tbdgAKDfqjDJ-7Fk6PJtHg8D4zUF6FQ4H2Pq8zK38Nyw@mail.gmail.com/5-dest_dump.plain.sql)
download
^ permalink raw reply [nested|flat] 3+ messages in thread
* Re: Difference in dump from original and restored database due to NOT NULL constraints on children
2024-11-14 10:56 Difference in dump from original and restored database due to NOT NULL constraints on children Ashutosh Bapat <[email protected]>
@ 2024-11-14 12:38 ` Alvaro Herrera <[email protected]>
0 siblings, 0 replies; 3+ messages in thread
From: Alvaro Herrera @ 2024-11-14 12:38 UTC (permalink / raw)
To: Ashutosh Bapat <[email protected]>; +Cc: pgsql-hackers
Hello Ashutosh,
On 2024-Nov-14, Ashutosh Bapat wrote:
> Because of the test I am developing under discussion at [1], I noticed
> that the DDLs dumped for inheritance children with NOT NULL
> constraints defer between original database and database restored from
> a dump of original database. I investigated those differences, but can
> not decide whether they are expected and whether they are intentional
> or not. Look something related to
> 14e87ffa5c543b5f30ead7413084c25f7735039f.
It does and it is, thanks.
So there are two differences:
1.
CREATE TABLE generated_stored_tests.gtest1 (
a integer NOT NULL,
b integer GENERATED ALWAYS AS ((a * 2)) STORED
);
CREATE TABLE generated_stored_tests.gtestxx_4 (
- a integer,
- b integer NOT NULL
+ a integer NOT NULL,
+ b integer
)
INHERITS (generated_stored_tests.gtest1);
In this case, I think it's wrong to add NOT NULL to gtestxx_4.a because
the constraint was not local originally and it should be acquired by the
inheritance. I'm not sure about gtestxx_4.b ... the GENERATED
constraint should induce a not-null if I recall correctly, so an
explicit not-null marking in the child might not be necessary. But I'll
have a look.
2.
CREATE TABLE public.notnull_tbl4 (
a integer NOT NULL
);
CREATE TABLE public.notnull_tbl4_cld2 (
)
INHERITS (public.notnull_tbl4);
-ALTER TABLE ONLY public.notnull_tbl4_cld2 ALTER COLUMN a SET NOT NULL;
+ALTER TABLE ONLY public.notnull_tbl4_cld2 ADD CONSTRAINT notnull_tbl4_a_not_null NOT NULL a;
CREATE TABLE public.notnull_tbl4_cld3 (
)
INHERITS (public.notnull_tbl4);
-ALTER TABLE ONLY public.notnull_tbl4_cld3 ADD CONSTRAINT a_nn NOT NULL a;
+ALTER TABLE ONLY public.notnull_tbl4_cld3 ADD CONSTRAINT notnull_tbl4_a_not_null NOT NULL a;
For notnull_tbl4_cld2 we try to set the column not-null, but it's
already not-null due to inheritance ... so why are we doing that?
Weird. These lines should just go away in both dumps.
In notnull_tbl4_cld3's case we have the same, but we also want to set a
constraint name, but the constraint already exists, so that doesn't
work, and that's the reason why the next dump uses the standard name.
Maybe we could dump the name change as ALTER TABLE RENAME CONSTRAINT in
that case instead, _if_ we can obtain the original name (should be
doable, because we can see it's a nonstandard name.)
--
Álvaro Herrera 48°01'N 7°57'E — https://www.EnterpriseDB.com/
^ permalink raw reply [nested|flat] 3+ messages in thread
end of thread, other threads:[~2024-11-14 12:38 UTC | newest]
Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-11-11 12:51 [PATCH v3 1/2] In-place table persistence change Kyotaro Horiguchi <[email protected]>
2024-11-14 10:56 Difference in dump from original and restored database due to NOT NULL constraints on children Ashutosh Bapat <[email protected]>
2024-11-14 12:38 ` Re: Difference in dump from original and restored database due to NOT NULL constraints on children Alvaro Herrera <[email protected]>
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox