Add infrastructure to track WAL usage.

This allows gathering the WAL generation statistics for each statement
execution.  The three statistics that we collect are the number of WAL
records, the number of full page writes and the amount of WAL bytes
generated.

This helps the users who have write-intensive workload to see the impact
of I/O due to WAL.  This further enables us to see approximately what
percentage of overall WAL is due to full page writes.

In the future, we can extend this functionality to allow us to compute the
the exact amount of WAL data due to full page writes.

This patch in itself is just an infrastructure to compute WAL usage data.
The upcoming patches will expose this data via explain, auto_explain,
pg_stat_statements and verbose (auto)vacuum output.

Author: Kirill Bychik, Julien Rouhaud
Reviewed-by: Dilip Kumar, Fujii Masao and Amit Kapila
Discussion: https://postgr.es/m/CAB-hujrP8ZfUkvL5OYETipQwA=e3n7oqHFU=4ZLxWS_Cza3kQQ@mail.gmail.com

2 files changed, 17 insertions, 2 deletions

diff --git a/src/include/executor/execParallel.h b/src/include/executor/execParallel.h
index 17d07cf020c..5a39a5b29c4 100644
--- a/src/include/executor/execParallel.h
+++ b/src/include/executor/execParallel.h
@@ -26,6 +26,7 @@ typedef struct ParallelExecutorInfo
 	PlanState  *planstate;		/* plan subtree we're running in parallel */
 	ParallelContext *pcxt;		/* parallel context we're using */
 	BufferUsage *buffer_usage;	/* points to bufusage area in DSM */
+	WalUsage   *wal_usage;		/* walusage area in DSM */
 	SharedExecutorInstrumentation *instrumentation; /* optional */
 	struct SharedJitInstrumentation *jit_instrumentation;	/* optional */
 	dsa_area   *area;			/* points to DSA area in DSM */
diff --git a/src/include/executor/instrument.h b/src/include/executor/instrument.h
index 3825a5ac1f3..64439c6819c 100644
--- a/src/include/executor/instrument.h
+++ b/src/include/executor/instrument.h
@@ -32,12 +32,20 @@ typedef struct BufferUsage
 	instr_time	blk_write_time; /* time spent writing */
 } BufferUsage;
 
+typedef struct WalUsage
+{
+	long		wal_records;	/* # of WAL records produced */
+	long		wal_num_fpw;	/* # of WAL full page image writes produced */
+	uint64		wal_bytes;		/* size of WAL records produced */
+} WalUsage;
+
 /* Flag bits included in InstrAlloc's instrument_options bitmask */
 typedef enum InstrumentOption
 {
 	INSTRUMENT_TIMER = 1 << 0,	/* needs timer (and row counts) */
 	INSTRUMENT_BUFFERS = 1 << 1,	/* needs buffer usage */
 	INSTRUMENT_ROWS = 1 << 2,	/* needs row count */
+	INSTRUMENT_WAL = 1 << 3,	/* needs WAL usage */
 	INSTRUMENT_ALL = PG_INT32_MAX
 } InstrumentOption;
 
@@ -46,6 +54,7 @@ typedef struct Instrumentation
 	/* Parameters set at node creation: */
 	bool		need_timer;		/* true if we need timer data */
 	bool		need_bufusage;	/* true if we need buffer usage data */
+	bool		need_walusage;	/* true if we need WAL usage data */
 	/* Info about current plan cycle: */
 	bool		running;		/* true if we've completed first tuple */
 	instr_time	starttime;		/* start time of current iteration of node */
@@ -53,6 +62,7 @@ typedef struct Instrumentation
 	double		firsttuple;		/* time for first tuple of this cycle */
 	double		tuplecount;		/* # of tuples emitted so far this cycle */
 	BufferUsage bufusage_start; /* buffer usage at start */
+	WalUsage	walusage_start; /* WAL usage at start */
 	/* Accumulated statistics across all completed cycles: */
 	double		startup;		/* total startup time (in seconds) */
 	double		total;			/* total time (in seconds) */
@@ -62,6 +72,7 @@ typedef struct Instrumentation
 	double		nfiltered1;		/* # of tuples removed by scanqual or joinqual */
 	double		nfiltered2;		/* # of tuples removed by "other" quals */
 	BufferUsage bufusage;		/* total buffer usage */
+	WalUsage	walusage;		/* total WAL usage */
 } Instrumentation;
 
 typedef struct WorkerInstrumentation
@@ -71,6 +82,7 @@ typedef struct WorkerInstrumentation
 } WorkerInstrumentation;
 
 extern PGDLLIMPORT BufferUsage pgBufferUsage;
+extern PGDLLIMPORT WalUsage pgWalUsage;
 
 extern Instrumentation *InstrAlloc(int n, int instrument_options);
 extern void InstrInit(Instrumentation *instr, int instrument_options);
@@ -79,9 +91,11 @@ extern void InstrStopNode(Instrumentation *instr, double nTuples);
 extern void InstrEndLoop(Instrumentation *instr);
 extern void InstrAggNode(Instrumentation *dst, Instrumentation *add);
 extern void InstrStartParallelQuery(void);
-extern void InstrEndParallelQuery(BufferUsage *result);
-extern void InstrAccumParallelQuery(BufferUsage *result);
+extern void InstrEndParallelQuery(BufferUsage *bufusage, WalUsage *walusage);
+extern void InstrAccumParallelQuery(BufferUsage *bufusage, WalUsage *walusage);
 extern void BufferUsageAccumDiff(BufferUsage *dst,
 								 const BufferUsage *add, const BufferUsage *sub);
+extern void WalUsageAccumDiff(WalUsage *dst, const WalUsage *add,
+							  const WalUsage *sub);
 
 #endif							/* INSTRUMENT_H */