database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-10-22 14:32:25 +03:00
Code Activity

Invent qsort_interruptible().

Browse Source 
Justin Pryzby reported that some scenarios could cause gathering
of extended statistics to spend many seconds in an un-cancelable
qsort() operation.  To fix, invent qsort_interruptible(), which is
just like qsort_arg() except that it will also do CHECK_FOR_INTERRUPTS
every so often.  This bloats the backend by a couple of kB, which
seems like a good investment.  (We considered just enabling
CHECK_FOR_INTERRUPTS in the existing qsort and qsort_arg functions,
but there are some callers for which that'd demonstrably be unsafe.
Opt-in seems like a better way.)

For now, just apply qsort_interruptible() in statistics collection.
There's probably more places where it could be useful, but we can
always change other call sites as we find problems.

Back-patch to v14.  Before that we didn't have extended stats on
expressions, so that the problem was less severe.  Also, this patch
depends on the sort_template infrastructure introduced in v14.

Tom Lane and Justin Pryzby

Discussion: https://postgr.es/m/20220509000108.GQ28830@telsasoft.com
This commit is contained in:
Tom Lane
2022-07-12 16:30:36 -04:00
parent 920072339f
commit e64cdab003
10 changed files with 80 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/backend/tsearch/ts_typanalyze.c
View File

@@ -44,8 +44,10 @@ static void prune_lexemes_hashtable(HTAB *lexemes_tab, int b_current);
static uint32 lexeme_hash(const void *key, Size keysize);
static int lexeme_match(const void *key1, const void *key2, Size keysize);
static int lexeme_compare(const void *key1, const void *key2);
static int trackitem_compare_frequencies_desc(const void *e1, const void *e2);
static int trackitem_compare_lexemes(const void *e1, const void *e2);
static int trackitem_compare_frequencies_desc(const void *e1, const void *e2,
void *arg);
static int trackitem_compare_lexemes(const void *e1, const void *e2,
void *arg);
/*
@@ -347,8 +349,8 @@ compute_tsvector_stats(VacAttrStats *stats,
*/
if (num_mcelem < track_len)
{
qsort(sort_table, track_len, sizeof(TrackItem *),
trackitem_compare_frequencies_desc);
qsort_interruptible(sort_table, track_len, sizeof(TrackItem *),
trackitem_compare_frequencies_desc, NULL);
/* reset minfreq to the smallest frequency we're keeping */
minfreq = sort_table[num_mcelem - 1]->frequency;
}
@@ -376,8 +378,8 @@ compute_tsvector_stats(VacAttrStats *stats,
* presorted we can employ binary search for that. See
* ts_selfuncs.c for a real usage scenario.
*/
qsort(sort_table, num_mcelem, sizeof(TrackItem *),
trackitem_compare_lexemes);
qsort_interruptible(sort_table, num_mcelem, sizeof(TrackItem *),
trackitem_compare_lexemes, NULL);
/* Must copy the target values into anl_context */
old_context = MemoryContextSwitchTo(stats->anl_context);
@@ -510,10 +512,10 @@ lexeme_compare(const void *key1, const void *key2)
}
/*
* qsort() comparator for sorting TrackItems on frequencies (descending sort)
* Comparator for sorting TrackItems on frequencies (descending sort)
*/
static int
trackitem_compare_frequencies_desc(const void *e1, const void *e2)
trackitem_compare_frequencies_desc(const void *e1, const void *e2, void *arg)
{
const TrackItem *const *t1 = (const TrackItem *const *) e1;
const TrackItem *const *t2 = (const TrackItem *const *) e2;
@@ -522,10 +524,10 @@ trackitem_compare_frequencies_desc(const void *e1, const void *e2)
}
/*
* qsort() comparator for sorting TrackItems on lexemes
* Comparator for sorting TrackItems on lexemes
*/
static int
trackitem_compare_lexemes(const void *e1, const void *e2)
trackitem_compare_lexemes(const void *e1, const void *e2, void *arg)
{
const TrackItem *const *t1 = (const TrackItem *const *) e1;
const TrackItem *const *t2 = (const TrackItem *const *) e2;