From 6db9eb6f11629e3610eaaa2901f847f3238bfb3f Mon Sep 17 00:00:00 2001 From: Jakub Wartak Date: Fri, 8 May 2026 09:19:49 +0200 Subject: [PATCH v10f 3/3] Lower pg_stat_io_histogram shared memory use by using array with indirect offsets. We use pgstat_track_io_*() family of functions to derive the length of static array that is allocated in shared memory region during startup. As the number of valid combinations of backend types vs I/O object/context/operations is coming from semi-runtime pgstat_io_get_sum_tracked() function, it cannot be preprocessed, so we would need to come up with #define PGSTAT_IO_HIST_BUCKET_SLOTS somehow. In order to do that - and avoid that C limitations (lack of constexpr) - we could precalculate (in the build system) the size of static array and generate .h include that would be included by pgstat.h, however it appears that would be it hardly cross-portable and hardly cross-compilable. Instead of doing that, we dynamically allocate shared memory for IO historgrams during startup. --- src/backend/utils/activity/pgstat.c | 42 +++++- src/backend/utils/activity/pgstat_io.c | 165 +++++++++++++++++++--- src/backend/utils/activity/pgstat_shmem.c | 15 ++ src/backend/utils/adt/pgstatfuncs.c | 20 ++- src/include/pgstat.h | 26 +++- 5 files changed, 241 insertions(+), 27 deletions(-) diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c index 7c597932671..0bd59992f4e 100644 --- a/src/backend/utils/activity/pgstat.c +++ b/src/backend/utils/activity/pgstat.c @@ -443,7 +443,13 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE] .snapshot_ctl_off = offsetof(PgStat_Snapshot, io), .shared_ctl_off = offsetof(PgStat_ShmemControl, io), .shared_data_off = offsetof(PgStatShared_IO, stats), - .shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats), + + /* + * Do not write everything using this .shared_data_len, as the IO + * histogram backing store is handled by special-case (as it is + * dynamic) in pgstat_write_statsfile() / pgstat_read_statsfile(). + */ + .shared_data_len = offsetof(PgStat_IO, hist_time_buckets_slot_count), .init_backend_cb = pgstat_io_init_backend_cb, .flush_static_cb = pgstat_io_flush_cb, @@ -1685,6 +1691,21 @@ pgstat_write_statsfile(void) fputc(PGSTAT_FILE_ENTRY_FIXED, fpout); pgstat_write_chunk_s(fpout, &kind); pgstat_write_chunk(fpout, ptr, info->shared_data_len); + + /* + * PGSTAT_KIND_IO has a dynamically-sized histogram that lives outside + * the shared_data_len region. This assumes that PGSTAT_FILE_FORMAT_ID + * would be bumped each time that pgstat_track_io*() logic is altered. + */ + if (kind == PGSTAT_KIND_IO) + { + PgStat_IO *io = pgStatLocal.snapshot.io; + + pgstat_write_chunk(fpout, io->hist_time_buckets_slots, + (size_t) io->hist_time_buckets_slot_count * + PGSTAT_IO_HIST_BUCKETS * + sizeof(uint64)); + } } /* @@ -1930,6 +1951,25 @@ pgstat_read_statsfile(void) goto error; } + /* + * PGSTAT_KIND_IO has also semi-dynamic histogram array + * appended after the main chunk. By now, the + * StatsShmemInit() prepared the memory. + */ + if (kind == PGSTAT_KIND_IO) + { + PgStat_IO *io = &shmem->io.stats; + + if (!pgstat_read_chunk(fpin, io->hist_time_buckets_slots, + (size_t) io->hist_time_buckets_slot_count * + PGSTAT_IO_HIST_BUCKETS * + sizeof(uint64))) + { + elog(WARNING, "could not read pgstat_io histogram backing store"); + goto error; + } + } + break; } case PGSTAT_FILE_ENTRY_HASH: diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c index 1696f278a77..3cc965638e8 100644 --- a/src/backend/utils/activity/pgstat_io.c +++ b/src/backend/utils/activity/pgstat_io.c @@ -20,6 +20,7 @@ #include "executor/instrument.h" #include "port/pg_bitutils.h" #include "storage/bufmgr.h" +#include "storage/shmem.h" #include "utils/memutils.h" #include "utils/pgstat_internal.h" @@ -210,6 +211,8 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op, { int offset; + Assert(track_io_timing || track_wal_io_timing); + /* * calculate the bucket_index based on latency in nanoseconds * (uint64) @@ -217,6 +220,10 @@ pgstat_count_io_op_time(IOObject io_object, IOContext io_context, IOOp io_op, bucket_index = get_bucket_index(INSTR_TIME_GET_NANOSEC(io_time)); offset = PendingIOStats.pending_hist_time_buckets_offsets[io_object][io_context][io_op]; + + /* does offset points to valid slot? */ + Assert(offset >= 0 && offset < PendingIOStats.pending_hist_time_buckets_size); + PendingIOStats.pending_hist_time_buckets[offset][bucket_index]++; } @@ -258,6 +265,7 @@ pgstat_io_flush_cb(bool nowait) { LWLock *bktype_lock; PgStat_BktypeIO *bktype_shstats; + PgStat_IO *bk_io; if (!have_iostats) return false; @@ -265,6 +273,7 @@ pgstat_io_flush_cb(bool nowait) bktype_lock = &pgStatLocal.shmem->io.locks[MyBackendType]; bktype_shstats = &pgStatLocal.shmem->io.stats.stats[MyBackendType]; + bk_io = &pgStatLocal.shmem->io.stats; if (!nowait) LWLockAcquire(bktype_lock, LW_EXCLUSIVE); @@ -297,16 +306,23 @@ pgstat_io_flush_cb(bool nowait) * offsets to save memory) into shared memory. */ if (PendingIOStats.pending_hist_time_buckets != NULL) - for (int b = 0; b < PGSTAT_IO_HIST_BUCKETS; b++) - { - int pending_off = PendingIOStats.pending_hist_time_buckets_offsets[io_object][io_context][io_op]; + { + int bktype_shstats_off = bktype_shstats->hist_time_buckets_offsets[io_object][io_context][io_op]; + int pending_off = PendingIOStats.pending_hist_time_buckets_offsets[io_object][io_context][io_op]; - if (pending_off != -1) - { - bktype_shstats->hist_time_buckets[io_object][io_context][io_op][b] += - PendingIOStats.pending_hist_time_buckets[pending_off][b]; - } - } + Assert(track_io_timing || track_wal_io_timing); + + /* + * -1 means here that such mapping doesn't have a slot + * (based on pgstat_track_io_*()). + */ + if (bktype_shstats_off == -1 || pending_off == -1) + continue; + + for (int b = 0; b < PGSTAT_IO_HIST_BUCKETS; b++) + bk_io->hist_time_buckets_slots[bktype_shstats_off][b] += + PendingIOStats.pending_hist_time_buckets[pending_off][b]; + } } } } @@ -415,7 +431,7 @@ pgstat_io_init_backend_cb(void) { if (pgstat_tracks_io_op(MyBackendType, io_object, io_context, io_op)) { - Assert(io_histograms_used <= PendingIOStats.pending_hist_time_buckets_size); + Assert(io_histograms_used < PendingIOStats.pending_hist_time_buckets_size); PendingIOStats.pending_hist_time_buckets_offsets[io_object][io_context][io_op] = io_histograms_used++; @@ -428,12 +444,12 @@ pgstat_io_init_backend_cb(void) } else PendingIOStats.pending_hist_time_buckets = NULL; - } void pgstat_io_init_shmem_cb(void *stats) { + int histogram_slots = 0; PgStatShared_IO *stat_shmem = (PgStatShared_IO *) stats; for (int i = 0; i < BACKEND_NUM_TYPES; i++) @@ -441,26 +457,79 @@ pgstat_io_init_shmem_cb(void *stats) /* this might end up being lazily allocated in pgstat_io_snapshot_cb() */ pgStatLocal.snapshot.io = NULL; + + /* + * Establish indirect mapping from + * PgStat_BktypeIO.hist_time_buckets_offsets[][][] to + * PgStat_IO.hist_time_buckets_slots[x] + */ + for (int i = 0; i < BACKEND_NUM_TYPES; i++) + { + for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++) + { + for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++) + { + for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++) + { + if (pgstat_tracks_io_op(i, io_object, io_context, io_op)) + { + stat_shmem->stats.stats[i].hist_time_buckets_offsets[io_object][io_context][io_op] = + histogram_slots++; + } + else + stat_shmem->stats.stats[i].hist_time_buckets_offsets[io_object][io_context][io_op] = + -1; + } + } + } + } + + /* + * Sanity check: the offset table we just produced must use exactly the + * number of slots StatsShmemInit() reserved. Both come from the same + * pgstat_tracks_io_*() rules, so a mismatch would indicate a bug. + */ + Assert(histogram_slots == stat_shmem->stats.hist_time_buckets_slot_count); } void pgstat_io_reset_all_cb(TimestampTz ts) { + PgStat_IO *io_stats = &pgStatLocal.shmem->io.stats; + for (int i = 0; i < BACKEND_NUM_TYPES; i++) { LWLock *bktype_lock = &pgStatLocal.shmem->io.locks[i]; - PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stats.stats[i]; + PgStat_BktypeIO *bktype_shstats = &io_stats->stats[i]; LWLockAcquire(bktype_lock, LW_EXCLUSIVE); /* * Use the lock in the first BackendType's PgStat_BktypeIO to protect - * the reset timestamp as well. + * the reset timestamp. */ if (i == 0) - pgStatLocal.shmem->io.stats.stat_reset_timestamp = ts; + io_stats->stat_reset_timestamp = ts; + + /* Reset this BackendType's histogram slots */ + for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++) + { + for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++) + { + for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++) + { + int off = bktype_shstats->hist_time_buckets_offsets[io_object][io_context][io_op]; + + if (off == -1) + continue; + memset(io_stats->hist_time_buckets_slots[off], 0, + sizeof(io_stats->hist_time_buckets_slots[off])); + } + } + } - memset(bktype_shstats, 0, sizeof(*bktype_shstats)); + /* Avoid resetting our indirect mapping offsets */ + memset(bktype_shstats, 0, offsetof(PgStat_BktypeIO, hist_time_buckets_offsets)); LWLockRelease(bktype_lock); } } @@ -468,14 +537,30 @@ pgstat_io_reset_all_cb(TimestampTz ts) void pgstat_io_snapshot_cb(void) { + PgStat_IO *shmem_io = &pgStatLocal.shmem->io.stats; + if (unlikely(pgStatLocal.snapshot.io == NULL)) + { + int n = shmem_io->hist_time_buckets_slot_count; + pgStatLocal.snapshot.io = MemoryContextAllocZero(TopMemoryContext, sizeof(PgStat_IO)); + /* + * Allocated on demand in private (TopMemoryContext) memory and points + * to the same indirect offsets. + */ + pgStatLocal.snapshot.io->hist_time_buckets_slot_count = n; + pgStatLocal.snapshot.io->hist_time_buckets_slots = + MemoryContextAllocZero(TopMemoryContext, + (size_t) n * PGSTAT_IO_HIST_BUCKETS * + sizeof(uint64)); + } + for (int i = 0; i < BACKEND_NUM_TYPES; i++) { LWLock *bktype_lock = &pgStatLocal.shmem->io.locks[i]; - PgStat_BktypeIO *bktype_shstats = &pgStatLocal.shmem->io.stats.stats[i]; + PgStat_BktypeIO *bktype_shstats = &shmem_io->stats[i]; PgStat_BktypeIO *bktype_snap = &pgStatLocal.snapshot.io->stats[i]; LWLockAcquire(bktype_lock, LW_SHARED); @@ -486,17 +571,35 @@ pgstat_io_snapshot_cb(void) */ if (i == 0) pgStatLocal.snapshot.io->stat_reset_timestamp = - pgStatLocal.shmem->io.stats.stat_reset_timestamp; + shmem_io->stat_reset_timestamp; /* using struct assignment due to better type safety */ *bktype_snap = *bktype_shstats; + + /* Copy this BackendType's histogram slots */ + for (int io_object = 0; io_object < IOOBJECT_NUM_TYPES; io_object++) + { + for (int io_context = 0; io_context < IOCONTEXT_NUM_TYPES; io_context++) + { + for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++) + { + int off = bktype_shstats->hist_time_buckets_offsets[io_object][io_context][io_op]; + + if (off == -1) + continue; + memcpy(pgStatLocal.snapshot.io->hist_time_buckets_slots[off], + shmem_io->hist_time_buckets_slots[off], + sizeof(shmem_io->hist_time_buckets_slots[off])); + } + } + } + LWLockRelease(bktype_lock); } } /* * IO statistics are not collected for all BackendTypes. -* * The following BackendTypes do not participate in the cumulative stats * subsystem or do not perform IO on which we currently track: * - Dead-end backend because it is not connected to shared memory and @@ -720,3 +823,29 @@ pgstat_tracks_io_op(BackendType bktype, IOObject io_object, return true; } + +/* + * Total number of tuple of really usable combinations (BackendType, IOObject, + * IOContext, IOOp) that we consider trackable. + */ +int +pgstat_io_get_sum_tracked(void) +{ + int sum = 0; + + for (int i = 0; i < BACKEND_NUM_TYPES; i++) + sum += pgstat_bktype_count_potentially_used(i); + + return sum; +} + +/* + * Returns number of bytes for shared memory required by + * PgStat_IO.hist_time_buckets_slots, + */ +Size +pgstat_io_histogram_shmem_size(void) +{ + return mul_size(pgstat_io_get_sum_tracked(), + PGSTAT_IO_HIST_BUCKETS * sizeof(uint64)); +} diff --git a/src/backend/utils/activity/pgstat_shmem.c b/src/backend/utils/activity/pgstat_shmem.c index b8f354c818a..bb25be106be 100644 --- a/src/backend/utils/activity/pgstat_shmem.c +++ b/src/backend/utils/activity/pgstat_shmem.c @@ -139,6 +139,12 @@ StatsShmemSize(void) sz = MAXALIGN(sizeof(PgStat_ShmemControl)); sz = add_size(sz, pgstat_dsa_init_size()); + /* + * Dynamic allocation for PgStat_IO.hist_time_buckets_slots. Sized from + * the rules in pgstat_tracks_io_*() + */ + sz = add_size(sz, MAXALIGN(pgstat_io_histogram_shmem_size())); + /* Add shared memory for all the custom fixed-numbered statistics */ for (PgStat_Kind kind = PGSTAT_KIND_CUSTOM_MIN; kind <= PGSTAT_KIND_CUSTOM_MAX; kind++) { @@ -194,6 +200,15 @@ StatsShmemInit(void *arg) LWTRANCHE_PGSTATS_DSA, NULL); dsa_pin(dsa); + /* + * Prepare PgStat_IO.hist_time_buckets_slot* stuff before calling + * pgstat_io_init_shmem_cb(). The additional memory for this was requested + * in the StatsShmemSize() above. + */ + ctl->io.stats.hist_time_buckets_slot_count = pgstat_io_get_sum_tracked(); + ctl->io.stats.hist_time_buckets_slots = (uint64 (*)[PGSTAT_IO_HIST_BUCKETS]) p; + p += MAXALIGN(pgstat_io_histogram_shmem_size()); + /* * To ensure dshash is created in "plain" shared memory, temporarily limit * size of dsa to the initial size of the dsa. diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 04eab7b3bcd..f106ca9cd3e 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -1667,6 +1667,7 @@ typedef enum hist_io_stat_col */ static void pg_stat_io_histogram_build_tuples(ReturnSetInfo *rsinfo, + PgStat_IO *backends_io_stats, PgStat_BktypeIO *bktype_stats, BackendType bktype, TimestampTz stat_reset_timestamp) @@ -1695,6 +1696,16 @@ pg_stat_io_histogram_build_tuples(ReturnSetInfo *rsinfo, for (int io_op = 0; io_op < IOOP_NUM_TYPES; io_op++) { const char *op_name = pgstat_get_io_op_name(io_op); + int bktype_hist_time_bucket_off; + + /* + * The offset is the same for every histogram bucket of this + * io_obj/io_context/io_op combination. + */ + bktype_hist_time_bucket_off = bktype_stats->hist_time_buckets_offsets[io_obj][io_context][io_op]; + if (bktype_hist_time_bucket_off == -1) + continue; + Assert(bktype_hist_time_bucket_off < backends_io_stats->hist_time_buckets_slot_count); for (int bucket = 0; bucket < PGSTAT_IO_HIST_BUCKETS; bucket++) { @@ -1703,6 +1714,7 @@ pg_stat_io_histogram_build_tuples(ReturnSetInfo *rsinfo, RangeBound lower, upper; RangeType *range; + uint64 bktype_bucket; values[HIST_IO_COL_BACKEND_TYPE] = bktype_desc; values[HIST_IO_COL_OBJECT] = CStringGetTextDatum(obj_name); @@ -1731,9 +1743,9 @@ pg_stat_io_histogram_build_tuples(ReturnSetInfo *rsinfo, range = make_range(typcache, &lower, &upper, false, NULL); values[HIST_IO_COL_BUCKET_US] = RangeTypePGetDatum(range); - /* bucket count */ - values[HIST_IO_COL_COUNT] = Int64GetDatum( - bktype_stats->hist_time_buckets[io_obj][io_context][io_op][bucket]); + /* get bucket count, access indirectly */ + bktype_bucket = backends_io_stats->hist_time_buckets_slots[bktype_hist_time_bucket_off][bucket]; + values[HIST_IO_COL_COUNT] = Int64GetDatum(bktype_bucket); if (stat_reset_timestamp != 0) values[HIST_IO_COL_RESET_TIME] = TimestampTzGetDatum(stat_reset_timestamp); @@ -1779,7 +1791,7 @@ pg_stat_get_io_histogram(PG_FUNCTION_ARGS) continue; /* save tuples with data from this PgStat_BktypeIO */ - pg_stat_io_histogram_build_tuples(rsinfo, bktype_stats, bktype, + pg_stat_io_histogram_build_tuples(rsinfo, backends_io_stats, bktype_stats, bktype, backends_io_stats->stat_reset_timestamp); } diff --git a/src/include/pgstat.h b/src/include/pgstat.h index 984914e69b8..de90f1fb5b0 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -20,7 +20,6 @@ #include "utils/backend_status.h" /* for backward compatibility */ /* IWYU pragma: export */ #include "utils/pgstat_kind.h" - /* avoid including access/transam.h */ typedef struct FullTransactionId FullTransactionId; @@ -218,7 +217,7 @@ typedef struct PgStat_TableXactStatus * ------------------------------------------------------------ */ -#define PGSTAT_FILE_FORMAT_ID 0x01A5BCBC +#define PGSTAT_FILE_FORMAT_ID 0x01A5BCBD typedef struct PgStat_ArchiverStats { @@ -342,7 +341,14 @@ typedef struct PgStat_BktypeIO uint64 bytes[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES]; PgStat_Counter counts[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES]; PgStat_Counter times[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES]; - uint64 hist_time_buckets[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES][PGSTAT_IO_HIST_BUCKETS]; + + /* + * Indirect offset to PgStat_IO (parent + * structure).hist_time_buckets_slots. This needs to be the last field due + * to the use of memset(.., offsetof(hist_time_buckets_offsets)) in + * pgstat_io_reset_all_cb(). + */ + int hist_time_buckets_offsets[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES]; } PgStat_BktypeIO; typedef struct PgStat_PendingIO @@ -358,7 +364,7 @@ typedef struct PgStat_PendingIO * memory. */ uint64 (*pending_hist_time_buckets)[PGSTAT_IO_HIST_BUCKETS]; - uint64 pending_hist_time_buckets_offsets[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES]; + int pending_hist_time_buckets_offsets[IOOBJECT_NUM_TYPES][IOCONTEXT_NUM_TYPES][IOOP_NUM_TYPES]; /* * Cache how much histograms we have allocated to avoid repetably calling @@ -374,6 +380,16 @@ typedef struct PgStat_IO { TimestampTz stat_reset_timestamp; PgStat_BktypeIO stats[BACKEND_NUM_TYPES]; + + /* + * The IO histogram memory is sized at postmaster start from the rules in + * pgstat_tracks_io_*() and persisted by additinal code to handle this + * dynamic (shared) memory pointer in pgstat_write_statsfile() / + * pgstat_read_statsfile(), so they nes are not part of the serialization + * to disk by common code. + */ + int hist_time_buckets_slot_count; + uint64 (*hist_time_buckets_slots)[PGSTAT_IO_HIST_BUCKETS]; } PgStat_IO; typedef struct PgStat_LockEntry @@ -654,6 +670,8 @@ extern PgStat_CheckpointerStats *pgstat_fetch_stat_checkpointer(void); extern bool pgstat_bktype_io_stats_valid(PgStat_BktypeIO *backend_io, BackendType bktype); extern int pgstat_bktype_count_potentially_used(BackendType bktype); +extern int pgstat_io_get_sum_tracked(void); +extern Size pgstat_io_histogram_shmem_size(void); extern void pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op, uint32 cnt, uint64 bytes); extern instr_time pgstat_prepare_io_time(bool track_io_guc); -- 2.43.0