From 94ad63093e8dfa1986397320deb987ec53bf8784 Mon Sep 17 00:00:00 2001 From: TatsuyaKawata Date: Sun, 7 Dec 2025 00:08:42 +0900 Subject: [PATCH v1] Add sampling statistics to autoanalyze log output --- contrib/file_fdw/file_fdw.c | 34 ++++++++++---- contrib/postgres_fdw/postgres_fdw.c | 31 +++++++++---- src/backend/commands/analyze.c | 72 +++++++++++++++++++++-------- src/include/foreign/fdwapi.h | 6 ++- 4 files changed, 105 insertions(+), 38 deletions(-) diff --git a/contrib/file_fdw/file_fdw.c b/contrib/file_fdw/file_fdw.c index e9cda3c47d1..81328c84205 100644 --- a/contrib/file_fdw/file_fdw.c +++ b/contrib/file_fdw/file_fdw.c @@ -171,7 +171,11 @@ static void estimate_costs(PlannerInfo *root, RelOptInfo *baserel, Cost *startup_cost, Cost *total_cost); static int file_acquire_sample_rows(Relation onerel, int elevel, HeapTuple *rows, int targrows, - double *totalrows, double *totaldeadrows); + double *totalrows, double *totaldeadrows, + BlockNumber *totalpages, + BlockNumber *scannedpages, + double *liverows, + double *deadrows); /* @@ -1185,7 +1189,11 @@ estimate_costs(PlannerInfo *root, RelOptInfo *baserel, static int file_acquire_sample_rows(Relation onerel, int elevel, HeapTuple *rows, int targrows, - double *totalrows, double *totaldeadrows) + double *totalrows, double *totaldeadrows, + BlockNumber *totalpages, + BlockNumber *scannedpages, + double *liverows, + double *deadrows) { int numrows = 0; double rowstoskip = -1; /* -1 means not set yet */ @@ -1327,14 +1335,20 @@ file_acquire_sample_rows(Relation onerel, int elevel, pfree(values); pfree(nulls); - /* - * Emit some interesting relation info - */ - ereport(elevel, - (errmsg("\"%s\": file contains %.0f rows; " - "%d rows in sample", - RelationGetRelationName(onerel), - *totalrows, numrows))); + /* Populate sampling statistics output parameters */ + /* Estimate page count from row count (assume ~100 rows per page) */ + if (*totalrows > 0) + { + *totalpages = (BlockNumber) ceil(*totalrows / 100.0); + *scannedpages = *totalpages; /* file is scanned entirely */ + } + else + { + *totalpages = 0; + *scannedpages = 0; + } + *liverows = *totalrows; /* all rows in file are "live" */ + *deadrows = 0; /* files don't have dead rows */ return numrows; } diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 06b52c65300..c04b9855cf7 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -504,7 +504,11 @@ static void process_query_params(ExprContext *econtext, static int postgresAcquireSampleRowsFunc(Relation relation, int elevel, HeapTuple *rows, int targrows, double *totalrows, - double *totaldeadrows); + double *totaldeadrows, + BlockNumber *totalpages, + BlockNumber *scannedpages, + double *liverows, + double *deadrows); static void analyze_row_processor(PGresult *res, int row, PgFdwAnalyzeState *astate); static void produce_tuple_asynchronously(AsyncRequest *areq, bool fetch); @@ -5008,7 +5012,11 @@ static int postgresAcquireSampleRowsFunc(Relation relation, int elevel, HeapTuple *rows, int targrows, double *totalrows, - double *totaldeadrows) + double *totaldeadrows, + BlockNumber *totalpages, + BlockNumber *scannedpages, + double *liverows, + double *deadrows) { PgFdwAnalyzeState astate; ForeignTable *table; @@ -5019,6 +5027,7 @@ postgresAcquireSampleRowsFunc(Relation relation, int elevel, PgFdwSamplingMethod method = ANALYZE_SAMPLE_AUTO; /* auto is default */ double sample_frac = -1.0; double reltuples = -1.0; + BlockNumber relpages = 0; unsigned int cursor_number; StringInfoData sql; PGresult *res; @@ -5127,6 +5136,12 @@ postgresAcquireSampleRowsFunc(Relation relation, int elevel, reltuples = postgresGetAnalyzeInfoForForeignTable(relation, &can_tablesample); + /* Estimate number of pages from tuple count */ + if (reltuples > 0) + relpages = (BlockNumber) ceil(reltuples / 100.0); /* assume ~100 tuples per page */ + else + relpages = 0; + /* * Make sure we're not choosing TABLESAMPLE when the remote relation * does not support that. But only do this for "auto" - if the user @@ -5286,13 +5301,11 @@ postgresAcquireSampleRowsFunc(Relation relation, int elevel, else *totalrows = reltuples; - /* - * Emit some interesting relation info - */ - ereport(elevel, - (errmsg("\"%s\": table contains %.0f rows, %d rows in sample", - RelationGetRelationName(relation), - *totalrows, astate.numrows))); + /* Populate sampling statistics output parameters */ + *totalpages = relpages; + *scannedpages = relpages; /* use estimate for foreign tables */ + *liverows = astate.samplerows; /* total rows collected during sampling */ + *deadrows = 0; /* foreign tables don't track dead rows the same way */ return astate.numrows; } diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 25089fae3e0..15a67401d6a 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -86,11 +86,18 @@ static VacAttrStats *examine_attribute(Relation onerel, int attnum, Node *index_expr); static int acquire_sample_rows(Relation onerel, int elevel, HeapTuple *rows, int targrows, - double *totalrows, double *totaldeadrows); + double *totalrows, double *totaldeadrows, + BlockNumber *totalpages, + BlockNumber *scannedpages, + double *liverows, double *deadrows); static int compare_rows(const void *a, const void *b, void *arg); static int acquire_inherited_sample_rows(Relation onerel, int elevel, HeapTuple *rows, int targrows, - double *totalrows, double *totaldeadrows); + double *totalrows, double *totaldeadrows, + BlockNumber *totalpages, + BlockNumber *scannedpages, + double *sampleliverows, + double *sampledeadrows); static void update_attstats(Oid relid, bool inh, int natts, VacAttrStats **vacattrstats); static Datum std_fetch_func(VacAttrStatsP stats, int rownum, bool *isNull); @@ -296,6 +303,10 @@ do_analyze_rel(Relation onerel, const VacuumParams params, double totalrows, totaldeadrows; HeapTuple *rows; + BlockNumber totalpages = 0; + BlockNumber scannedpages = 0; + double sampleliverows = 0; + double sampledeadrows = 0; PGRUsage ru0; TimestampTz starttime = 0; MemoryContext caller_context; @@ -529,11 +540,15 @@ do_analyze_rel(Relation onerel, const VacuumParams params, if (inh) numrows = acquire_inherited_sample_rows(onerel, elevel, rows, targrows, - &totalrows, &totaldeadrows); + &totalrows, &totaldeadrows, + &totalpages, &scannedpages, + &sampleliverows, &sampledeadrows); else numrows = (*acquirefunc) (onerel, elevel, rows, targrows, - &totalrows, &totaldeadrows); + &totalrows, &totaldeadrows, + &totalpages, &scannedpages, + &sampleliverows, &sampledeadrows); /* * Compute the statistics. Temporary results during the calculations for @@ -838,6 +853,13 @@ do_analyze_rel(Relation onerel, const VacuumParams params, walusage.wal_fpi_bytes, walusage.wal_buffers_full); appendStringInfo(&buf, _("system usage: %s"), pg_rusage_show(&ru0)); + appendStringInfo(&buf, + _("\nsampling: scanned %u of %u pages, " + "containing %.0f live rows and %.0f dead rows; " + "%d rows in sample, %.0f estimated total rows"), + scannedpages, totalpages, + sampleliverows, sampledeadrows, + numrows, totalrows); ereport(verbose ? INFO : LOG, (errmsg_internal("%s", buf.data))); @@ -1198,7 +1220,9 @@ block_sampling_read_stream_next(ReadStream *stream, static int acquire_sample_rows(Relation onerel, int elevel, HeapTuple *rows, int targrows, - double *totalrows, double *totaldeadrows) + double *totalrows, double *totaldeadrows, + BlockNumber *totalpages, BlockNumber *scannedpages, + double *sampleliverows, double *sampledeadrows) { int numrows = 0; /* # rows now in reservoir */ double samplerows = 0; /* total # rows collected */ @@ -1339,17 +1363,11 @@ acquire_sample_rows(Relation onerel, int elevel, *totaldeadrows = 0.0; } - /* - * Emit some interesting relation info - */ - ereport(elevel, - (errmsg("\"%s\": scanned %d of %u pages, " - "containing %.0f live rows and %.0f dead rows; " - "%d rows in sample, %.0f estimated total rows", - RelationGetRelationName(onerel), - bs.m, totalblocks, - liverows, deadrows, - numrows, *totalrows))); + /* Populate sampling statistics output parameters */ + *totalpages = totalblocks; + *scannedpages = bs.m; + *sampleliverows = liverows; + *sampledeadrows = deadrows; return numrows; } @@ -1390,7 +1408,9 @@ compare_rows(const void *a, const void *b, void *arg) static int acquire_inherited_sample_rows(Relation onerel, int elevel, HeapTuple *rows, int targrows, - double *totalrows, double *totaldeadrows) + double *totalrows, double *totaldeadrows, + BlockNumber *totalpages, BlockNumber *scannedpages, + double *sampleliverows, double *sampledeadrows) { List *tableOIDs; Relation *rels; @@ -1402,10 +1422,18 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, i; ListCell *lc; bool has_child; + BlockNumber child_totalpages; + BlockNumber child_scannedpages; + double child_liverows; + double child_deadrows; /* Initialize output parameters to zero now, in case we exit early */ *totalrows = 0; *totaldeadrows = 0; + *totalpages = 0; + *scannedpages = 0; + *sampleliverows = 0; + *sampledeadrows = 0; /* * Find all members of inheritance set. We only need AccessShareLock on @@ -1582,7 +1610,9 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, /* Fetch a random sample of the child's rows */ childrows = (*acquirefunc) (childrel, elevel, rows + numrows, childtargrows, - &trows, &tdrows); + &trows, &tdrows, + &child_totalpages, &child_scannedpages, + &child_liverows, &child_deadrows); /* We may need to convert from child's rowtype to parent's */ if (childrows > 0 && @@ -1613,6 +1643,12 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, numrows += childrows; *totalrows += trows; *totaldeadrows += tdrows; + + /* Accumulate sampling statistics */ + *totalpages += child_totalpages; + *scannedpages += child_scannedpages; + *sampleliverows += child_liverows; + *sampledeadrows += child_deadrows; } } diff --git a/src/include/foreign/fdwapi.h b/src/include/foreign/fdwapi.h index fcd7e7027f3..ed45c2a3f68 100644 --- a/src/include/foreign/fdwapi.h +++ b/src/include/foreign/fdwapi.h @@ -151,7 +151,11 @@ typedef void (*ExplainDirectModify_function) (ForeignScanState *node, typedef int (*AcquireSampleRowsFunc) (Relation relation, int elevel, HeapTuple *rows, int targrows, double *totalrows, - double *totaldeadrows); + double *totaldeadrows, + BlockNumber *totalpages, + BlockNumber *scannedpages, + double *liverows, + double *deadrows); typedef bool (*AnalyzeForeignTable_function) (Relation relation, AcquireSampleRowsFunc *func, -- 2.34.1