1
0
mirror of https://github.com/postgres/postgres.git synced 2025-07-02 09:02:37 +03:00

Use an MVCC snapshot, rather than SnapshotNow, for catalog scans.

SnapshotNow scans have the undesirable property that, in the face of
concurrent updates, the scan can fail to see either the old or the new
versions of the row.  In many cases, we work around this by requiring
DDL operations to hold AccessExclusiveLock on the object being
modified; in some cases, the existing locking is inadequate and random
failures occur as a result.  This commit doesn't change anything
related to locking, but will hopefully pave the way to allowing lock
strength reductions in the future.

The major issue has held us back from making this change in the past
is that taking an MVCC snapshot is significantly more expensive than
using a static special snapshot such as SnapshotNow.  However, testing
of various worst-case scenarios reveals that this problem is not
severe except under fairly extreme workloads.  To mitigate those
problems, we avoid retaking the MVCC snapshot for each new scan;
instead, we take a new snapshot only when invalidation messages have
been processed.  The catcache machinery already requires that
invalidation messages be sent before releasing the related heavyweight
lock; else other backends might rely on locally-cached data rather
than scanning the catalog at all.  Thus, making snapshot reuse
dependent on the same guarantees shouldn't break anything that wasn't
already subtly broken.

Patch by me.  Review by Michael Paquier and Andres Freund.
This commit is contained in:
Robert Haas
2013-07-02 09:47:01 -04:00
parent 384f933046
commit 568d4138c6
69 changed files with 617 additions and 353 deletions

View File

@ -33,7 +33,10 @@
#include "catalog/pg_constraint.h"
#include "catalog/pg_conversion.h"
#include "catalog/pg_database.h"
#include "catalog/pg_db_role_setting.h"
#include "catalog/pg_default_acl.h"
#include "catalog/pg_depend.h"
#include "catalog/pg_description.h"
#include "catalog/pg_enum.h"
#include "catalog/pg_event_trigger.h"
#include "catalog/pg_foreign_data_wrapper.h"
@ -47,6 +50,10 @@
#include "catalog/pg_proc.h"
#include "catalog/pg_range.h"
#include "catalog/pg_rewrite.h"
#include "catalog/pg_seclabel.h"
#include "catalog/pg_shdepend.h"
#include "catalog/pg_shdescription.h"
#include "catalog/pg_shseclabel.h"
#include "catalog/pg_statistic.h"
#include "catalog/pg_tablespace.h"
#include "catalog/pg_ts_config.h"
@ -796,6 +803,10 @@ static CatCache *SysCache[
static int SysCacheSize = lengthof(cacheinfo);
static bool CacheInitialized = false;
static Oid SysCacheRelationOid[lengthof(cacheinfo)];
static int SysCacheRelationOidSize;
static int oid_compare(const void *a, const void *b);
/*
* InitCatalogCache - initialize the caches
@ -809,6 +820,8 @@ void
InitCatalogCache(void)
{
int cacheId;
int i,
j = 0;
Assert(!CacheInitialized);
@ -825,11 +838,23 @@ InitCatalogCache(void)
if (!PointerIsValid(SysCache[cacheId]))
elog(ERROR, "could not initialize cache %u (%d)",
cacheinfo[cacheId].reloid, cacheId);
SysCacheRelationOid[SysCacheRelationOidSize++] =
cacheinfo[cacheId].reloid;
/* see comments for RelationInvalidatesSnapshotsOnly */
Assert(!RelationInvalidatesSnapshotsOnly(cacheinfo[cacheId].reloid));
}
/* Sort and dedup OIDs. */
pg_qsort(SysCacheRelationOid, SysCacheRelationOidSize,
sizeof(Oid), oid_compare);
for (i = 1; i < SysCacheRelationOidSize; ++i)
if (SysCacheRelationOid[i] != SysCacheRelationOid[j])
SysCacheRelationOid[++j] = SysCacheRelationOid[i];
SysCacheRelationOidSize = j + 1;
CacheInitialized = true;
}
/*
* InitCatalogCachePhase2 - finish initializing the caches
*
@ -1113,3 +1138,73 @@ SearchSysCacheList(int cacheId, int nkeys,
return SearchCatCacheList(SysCache[cacheId], nkeys,
key1, key2, key3, key4);
}
/*
* Certain relations that do not have system caches send snapshot invalidation
* messages in lieu of catcache messages. This is for the benefit of
* GetCatalogSnapshot(), which can then reuse its existing MVCC snapshot
* for scanning one of those catalogs, rather than taking a new one, if no
* invalidation has been received.
*
* Relations that have syscaches need not (and must not) be listed here. The
* catcache invalidation messages will also flush the snapshot. If you add a
* syscache for one of these relations, remove it from this list.
*/
bool
RelationInvalidatesSnapshotsOnly(Oid relid)
{
switch (relid)
{
case DbRoleSettingRelationId:
case DependRelationId:
case SharedDependRelationId:
case DescriptionRelationId:
case SharedDescriptionRelationId:
case SecLabelRelationId:
case SharedSecLabelRelationId:
return true;
default:
break;
}
return false;
}
/*
* Test whether a relation has a system cache.
*/
bool
RelationHasSysCache(Oid relid)
{
int low = 0,
high = SysCacheRelationOidSize - 1;
while (low <= high)
{
int middle = low + (high - low) / 2;
if (SysCacheRelationOid[middle] == relid)
return true;
if (SysCacheRelationOid[middle] < relid)
low = middle + 1;
else
high = middle - 1;
}
return false;
}
/*
* OID comparator for pg_qsort
*/
static int
oid_compare(const void *a, const void *b)
{
Oid oa = *((Oid *) a);
Oid ob = *((Oid *) b);
if (oa == ob)
return 0;
return (oa > ob) ? 1 : -1;
}