database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-10-15 05:46:52 +03:00
Code Activity

Transfer statistics during pg_upgrade.

Browse Source 
Add support to pg_dump for dumping stats, and use that during
pg_upgrade so that statistics are transferred during upgrade. In most
cases this removes the need for a costly re-analyze after upgrade.

Some statistics are not transferred, such as extended statistics or
statistics with a custom stakind.

Now pg_dump accepts the options --schema-only, --no-schema,
--data-only, --no-data, --statistics-only, and --no-statistics; which
allow all combinations of schema, data, and/or stats. The options are
named this way to preserve compatibility with the previous
--schema-only and --data-only options.

Statistics are in SECTION_DATA, unless the object itself is in
SECTION_POST_DATA.

The stats are represented as calls to pg_restore_relation_stats() and
pg_restore_attribute_stats().

Author: Corey Huinker, Jeff Davis
Reviewed-by: Jian He
Discussion: https://postgr.es/m/CADkLM=fzX7QX6r78fShWDjNN3Vcr4PVAnvXxQ4DiGy6V=0bCUA@mail.gmail.com
Discussion: https://postgr.es/m/CADkLM%3DcB0rF3p_FuWRTMSV0983ihTRpsH%2BOCpNyiqE7Wk0vUWA%40mail.gmail.com
This commit is contained in:
Jeff Davis
2025-02-20 01:29:06 -08:00
parent 7da344b9f8
commit 1fd1bd8710
22 changed files with 858 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

83
src/bin/pg_dump/pg_backup_archiver.c
View File

@@ -46,6 +46,9 @@
#define TEXT_DUMP_HEADER "--\n-- PostgreSQL database dump\n--\n\n"
#define TEXT_DUMPALL_HEADER "--\n-- PostgreSQL database cluster dump\n--\n\n"
#define TOC_PREFIX_NONE ""
#define TOC_PREFIX_DATA "Data for "
#define TOC_PREFIX_STATS "Statistics for "
static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt,
const pg_compress_specification compression_spec,
@@ -53,7 +56,7 @@ static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt,
SetupWorkerPtrType setupWorkerPtr,
DataDirSyncMethod sync_method);
static void _getObjectDescription(PQExpBuffer buf, const TocEntry *te);
static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData);
static void _printTocEntry(ArchiveHandle *AH, TocEntry *te, const char *pfx);
static char *sanitize_line(const char *str, bool want_hyphen);
static void _doSetFixedOutputState(ArchiveHandle *AH);
static void _doSetSessionAuth(ArchiveHandle *AH, const char *user);
@@ -149,6 +152,7 @@ InitDumpOptions(DumpOptions *opts)
opts->dumpSections = DUMP_UNSECTIONED;
opts->dumpSchema = true;
opts->dumpData = true;
opts->dumpStatistics = true;
}
/*
@@ -169,9 +173,10 @@ dumpOptionsFromRestoreOptions(RestoreOptions *ropt)
dopt->outputClean = ropt->dropSchema;
dopt->dumpData = ropt->dumpData;
dopt->dumpSchema = ropt->dumpSchema;
dopt->dumpSections = ropt->dumpSections;
dopt->dumpStatistics = ropt->dumpStatistics;
dopt->if_exists = ropt->if_exists;
dopt->column_inserts = ropt->column_inserts;
dopt->dumpSections = ropt->dumpSections;
dopt->aclsSkip = ropt->aclsSkip;
dopt->outputSuperuser = ropt->superuser;
dopt->outputCreateDB = ropt->createDB;
@@ -418,8 +423,8 @@ RestoreArchive(Archive *AHX)
}
/*
* Work out if we have an implied data-only restore. This can happen if
* the dump was data only or if the user has used a toc list to exclude
* Work out if we have an implied schema-less restore. This can happen if
* the dump excluded the schema or the user has used a toc list to exclude
* all of the schema data. All we do is look for schema entries - if none
* are found then we unset the dumpSchema flag.
*
@@ -428,20 +433,20 @@ RestoreArchive(Archive *AHX)
*/
if (ropt->dumpSchema)
{
int impliedDataOnly = 1;
bool no_schema_found = true;
for (te = AH->toc->next; te != AH->toc; te = te->next)
{
if ((te->reqs & REQ_SCHEMA) != 0)
{ /* It's schema, and it's wanted */
impliedDataOnly = 0;
{
no_schema_found = false;
break;
}
}
if (impliedDataOnly)
if (no_schema_found)
{
ropt->dumpSchema = false;
pg_log_info("implied data-only restore");
pg_log_info("implied no-schema restore");
}
}
@@ -739,7 +744,7 @@ RestoreArchive(Archive *AHX)
for (te = AH->toc->next; te != AH->toc; te = te->next)
{
if ((te->reqs & (REQ_SCHEMA | REQ_DATA)) == 0)
if ((te->reqs & (REQ_SCHEMA | REQ_DATA | REQ_STATS)) == 0)
continue; /* ignore if not to be dumped at all */
switch (_tocEntryRestorePass(te))
@@ -760,7 +765,7 @@ RestoreArchive(Archive *AHX)
{
for (te = AH->toc->next; te != AH->toc; te = te->next)
{
if ((te->reqs & (REQ_SCHEMA | REQ_DATA)) != 0 &&
if ((te->reqs & (REQ_SCHEMA | REQ_DATA | REQ_STATS)) != 0 &&
_tocEntryRestorePass(te) == RESTORE_PASS_ACL)
(void) restore_toc_entry(AH, te, false);
}
@@ -770,7 +775,7 @@ RestoreArchive(Archive *AHX)
{
for (te = AH->toc->next; te != AH->toc; te = te->next)
{
if ((te->reqs & (REQ_SCHEMA | REQ_DATA)) != 0 &&
if ((te->reqs & (REQ_SCHEMA | REQ_DATA | REQ_STATS)) != 0 &&
_tocEntryRestorePass(te) == RESTORE_PASS_POST_ACL)
(void) restore_toc_entry(AH, te, false);
}
@@ -869,7 +874,7 @@ restore_toc_entry(ArchiveHandle *AH, TocEntry *te, bool is_parallel)
pg_log_info("creating %s \"%s\"",
te->desc, te->tag);
_printTocEntry(AH, te, false);
_printTocEntry(AH, te, TOC_PREFIX_NONE);
defnDumped = true;
if (strcmp(te->desc, "TABLE") == 0)
@@ -938,7 +943,7 @@ restore_toc_entry(ArchiveHandle *AH, TocEntry *te, bool is_parallel)
*/
if (AH->PrintTocDataPtr != NULL)
{
_printTocEntry(AH, te, true);
_printTocEntry(AH, te, TOC_PREFIX_DATA);
if (strcmp(te->desc, "BLOBS") == 0 ||
strcmp(te->desc, "BLOB COMMENTS") == 0)
@@ -1036,15 +1041,21 @@ restore_toc_entry(ArchiveHandle *AH, TocEntry *te, bool is_parallel)
{
/* If we haven't already dumped the defn part, do so now */
pg_log_info("executing %s %s", te->desc, te->tag);
_printTocEntry(AH, te, false);
_printTocEntry(AH, te, TOC_PREFIX_NONE);
}
}
/*
* If it has a statistics component that we want, then process that
*/
if ((reqs & REQ_STATS) != 0)
_printTocEntry(AH, te, TOC_PREFIX_STATS);
/*
* If we emitted anything for this TOC entry, that counts as one action
* against the transaction-size limit. Commit if it's time to.
*/
if ((reqs & (REQ_SCHEMA | REQ_DATA)) != 0 && ropt->txn_size > 0)
if ((reqs & (REQ_SCHEMA | REQ_DATA | REQ_STATS)) != 0 && ropt->txn_size > 0)
{
if (++AH->txnCount >= ropt->txn_size)
{
@@ -1084,6 +1095,7 @@ NewRestoreOptions(void)
opts->compression_spec.level = 0;
opts->dumpSchema = true;
opts->dumpData = true;
opts->dumpStatistics = true;
return opts;
}
@@ -1329,7 +1341,7 @@ PrintTOCSummary(Archive *AHX)
te->reqs = _tocEntryRequired(te, curSection, AH);
/* Now, should we print it? */
if (ropt->verbose ||
(te->reqs & (REQ_SCHEMA | REQ_DATA)) != 0)
(te->reqs & (REQ_SCHEMA | REQ_DATA | REQ_STATS)) != 0)
{
char *sanitized_name;
char *sanitized_schema;
@@ -2582,7 +2594,7 @@ WriteToc(ArchiveHandle *AH)
tocCount = 0;
for (te = AH->toc->next; te != AH->toc; te = te->next)
{
if ((te->reqs & (REQ_SCHEMA | REQ_DATA | REQ_SPECIAL)) != 0)
if ((te->reqs & (REQ_SCHEMA | REQ_DATA | REQ_STATS | REQ_SPECIAL)) != 0)
tocCount++;
}
@@ -2592,7 +2604,7 @@ WriteToc(ArchiveHandle *AH)
for (te = AH->toc->next; te != AH->toc; te = te->next)
{
if ((te->reqs & (REQ_SCHEMA | REQ_DATA | REQ_SPECIAL)) == 0)
if ((te->reqs & (REQ_SCHEMA | REQ_DATA | REQ_STATS | REQ_SPECIAL)) == 0)
continue;
WriteInt(AH, te->dumpId);
@@ -2904,8 +2916,9 @@ StrictNamesCheck(RestoreOptions *ropt)
* Determine whether we want to restore this TOC entry.
*
* Returns 0 if entry should be skipped, or some combination of the
* REQ_SCHEMA and REQ_DATA bits if we want to restore schema and/or data
* portions of this TOC entry, or REQ_SPECIAL if it's a special entry.
* REQ_SCHEMA, REQ_DATA, and REQ_STATS bits if we want to restore schema, data
* and/or statistics portions of this TOC entry, or REQ_SPECIAL if it's a
* special entry.
*/
static int
_tocEntryRequired(TocEntry *te, teSection curSection, ArchiveHandle *AH)
@@ -2919,6 +2932,14 @@ _tocEntryRequired(TocEntry *te, teSection curSection, ArchiveHandle *AH)
strcmp(te->desc, "SEARCHPATH") == 0)
return REQ_SPECIAL;
if (strcmp(te->desc, "STATISTICS DATA") == 0)
{
if (!ropt->dumpStatistics)
return 0;
else
res = REQ_STATS;
}
/*
* DATABASE and DATABASE PROPERTIES also have a special rule: they are
* restored in createDB mode, and not restored otherwise, independently of
@@ -2963,6 +2984,10 @@ _tocEntryRequired(TocEntry *te, teSection curSection, ArchiveHandle *AH)
if (ropt->no_subscriptions && strcmp(te->desc, "SUBSCRIPTION") == 0)
return 0;
/* If it's statistics and we don't want statistics, maybe ignore it */
if (!ropt->dumpStatistics && strcmp(te->desc, "STATISTICS DATA") == 0)
return 0;
/* Ignore it if section is not to be dumped/restored */
switch (curSection)
{
@@ -2992,6 +3017,7 @@ _tocEntryRequired(TocEntry *te, teSection curSection, ArchiveHandle *AH)
*/
if (strcmp(te->desc, "ACL") == 0 ||
strcmp(te->desc, "COMMENT") == 0 ||
strcmp(te->desc, "STATISTICS DATA") == 0 ||
strcmp(te->desc, "SECURITY LABEL") == 0)
{
/* Database properties react to createDB, not selectivity options. */
@@ -3108,6 +3134,7 @@ _tocEntryRequired(TocEntry *te, teSection curSection, ArchiveHandle *AH)
}
}
/*
* Determine whether the TOC entry contains schema and/or data components,
* and mask off inapplicable REQ bits. If it had a dataDumper, assume
@@ -3173,12 +3200,12 @@ _tocEntryRequired(TocEntry *te, teSection curSection, ArchiveHandle *AH)
strncmp(te->tag, "LARGE OBJECT", 12) == 0) ||
(strcmp(te->desc, "SECURITY LABEL") == 0 &&
strncmp(te->tag, "LARGE OBJECT", 12) == 0))))
res = res & REQ_SCHEMA;
res = res & (REQ_SCHEMA | REQ_STATS);
}
/* Mask it if we don't want schema */
if (!ropt->dumpSchema)
res = res & REQ_DATA;
res = res & (REQ_DATA | REQ_STATS);
return res;
}
@@ -3730,7 +3757,7 @@ _getObjectDescription(PQExpBuffer buf, const TocEntry *te)
* will remain at default, until the matching ACL TOC entry is restored.
*/
static void
_printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData)
_printTocEntry(ArchiveHandle *AH, TocEntry *te, const char *pfx)
{
RestoreOptions *ropt = AH->public.ropt;
@@ -3749,16 +3776,10 @@ _printTocEntry(ArchiveHandle *AH, TocEntry *te, bool isData)
/* Emit header comment for item */
if (!AH->noTocComments)
{
const char *pfx;
char *sanitized_name;
char *sanitized_schema;
char *sanitized_owner;
if (isData)
pfx = "Data for ";
else
pfx = "";
ahprintf(AH, "--\n");
if (AH->public.verbose)
{
@@ -4325,7 +4346,7 @@ restore_toc_entries_parallel(ArchiveHandle *AH, ParallelState *pstate,
if (next_work_item != NULL)
{
/* If not to be restored, don't waste time launching a worker */
if ((next_work_item->reqs & (REQ_SCHEMA | REQ_DATA)) == 0)
if ((next_work_item->reqs & (REQ_SCHEMA | REQ_DATA | REQ_STATS)) == 0)
{
pg_log_info("skipping item %d %s %s",
next_work_item->dumpId,