Use HTAB for replication slot statistics.

Previously, we used to use the array of size max_replication_slots to
store stats for replication slots. But that had two problems in the cases
where a message for dropping a slot gets lost: 1) the stats for the new
slot are not recorded if the array is full and 2) writing beyond the end
of the array if the user reduces the max_replication_slots.

This commit uses HTAB for replication slot statistics, resolving both
problems. Now, pgstat_vacuum_stat() search for all the dead replication
slots in stats hashtable and tell the collector to remove them. To avoid
showing the stats for the already-dropped slots, pg_stat_replication_slots
view searches slot stats by the slot name taken from pg_replication_slots.

Also, we send a message for creating a slot at slot creation, initializing
the stats. This reduces the possibility that the stats are accumulated
into the old slot stats when a message for dropping a slot gets lost.

Reported-by: Andres Freund
Author: Sawada Masahiko, test case by Vignesh C
Reviewed-by: Amit Kapila, Vignesh C, Dilip Kumar
Discussion: https://postgr.es/m/20210319185247.ldebgpdaxsowiflw@alap3.anarazel.de

1 files changed, 6 insertions, 4 deletions

diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 5c5920b0b5f..1ce363e7d18 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -541,6 +541,7 @@ typedef struct PgStat_MsgReplSlot
 {
 	PgStat_MsgHdr m_hdr;
 	NameData	m_slotname;
+	bool		m_create;
 	bool		m_drop;
 	PgStat_Counter m_spill_txns;
 	PgStat_Counter m_spill_count;
@@ -917,7 +918,7 @@ typedef struct PgStat_SLRUStats
 /*
  * Replication slot statistics kept in the stats collector
  */
-typedef struct PgStat_ReplSlotStats
+typedef struct PgStat_StatReplSlotEntry
 {
 	NameData	slotname;
 	PgStat_Counter spill_txns;
@@ -929,7 +930,7 @@ typedef struct PgStat_ReplSlotStats
 	PgStat_Counter total_txns;
 	PgStat_Counter total_bytes;
 	TimestampTz stat_reset_timestamp;
-} PgStat_ReplSlotStats;
+} PgStat_StatReplSlotEntry;
 
 
 /*
@@ -1031,7 +1032,8 @@ extern void pgstat_report_recovery_conflict(int reason);
 extern void pgstat_report_deadlock(void);
 extern void pgstat_report_checksum_failures_in_db(Oid dboid, int failurecount);
 extern void pgstat_report_checksum_failure(void);
-extern void pgstat_report_replslot(const PgStat_ReplSlotStats *repSlotStat);
+extern void pgstat_report_replslot(const PgStat_StatReplSlotEntry *repSlotStat);
+extern void pgstat_report_replslot_create(const char *slotname);
 extern void pgstat_report_replslot_drop(const char *slotname);
 
 extern void pgstat_initialize(void);
@@ -1129,7 +1131,7 @@ extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 extern PgStat_GlobalStats *pgstat_fetch_global(void);
 extern PgStat_WalStats *pgstat_fetch_stat_wal(void);
 extern PgStat_SLRUStats *pgstat_fetch_slru(void);
-extern PgStat_ReplSlotStats *pgstat_fetch_replslot(int *nslots_p);
+extern PgStat_StatReplSlotEntry *pgstat_fetch_replslot(NameData slotname);
 extern PgStat_RecoveryPrefetchStats *pgstat_fetch_recoveryprefetch(void);
 
 extern void pgstat_count_slru_page_zeroed(int slru_idx);