database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-28 23:42:10 +03:00
Code Activity

Add infrastructure to track WAL usage.

Browse Source 
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
This commit is contained in:
Amit Kapila
2020-04-04 10:02:08 +05:30
parent 0588ee63aa
commit df3b181499
10 changed files with 182 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
src/backend/executor/instrument.c
View File

@ -19,8 +19,11 @@
BufferUsage pgBufferUsage;
static BufferUsage save_pgBufferUsage;
WalUsage pgWalUsage;
static WalUsage save_pgWalUsage;
static void BufferUsageAdd(BufferUsage *dst, const BufferUsage *add);
static void WalUsageAdd(WalUsage *dst, WalUsage *add);
/* Allocate new instrumentation structure(s) */
@ -31,15 +34,17 @@ InstrAlloc(int n, int instrument_options)
/* initialize all fields to zeroes, then modify as needed */
instr = palloc0(n * sizeof(Instrumentation));
if (instrument_options & (INSTRUMENT_BUFFERS | INSTRUMENT_TIMER))
if (instrument_options & (INSTRUMENT_BUFFERS | INSTRUMENT_TIMER | INSTRUMENT_WAL))
{
bool need_buffers = (instrument_options & INSTRUMENT_BUFFERS) != 0;
bool need_wal = (instrument_options & INSTRUMENT_WAL) != 0;
bool need_timer = (instrument_options & INSTRUMENT_TIMER) != 0;
int i;
for (i = 0; i < n; i++)
{
instr[i].need_bufusage = need_buffers;
instr[i].need_walusage = need_wal;
instr[i].need_timer = need_timer;
}
}
@ -53,6 +58,7 @@ InstrInit(Instrumentation *instr, int instrument_options)
{
memset(instr, 0, sizeof(Instrumentation));
instr->need_bufusage = (instrument_options & INSTRUMENT_BUFFERS) != 0;
instr->need_walusage = (instrument_options & INSTRUMENT_WAL) != 0;
instr->need_timer = (instrument_options & INSTRUMENT_TIMER) != 0;
}
@ -67,6 +73,9 @@ InstrStartNode(Instrumentation *instr)
/* save buffer usage totals at node entry, if needed */
if (instr->need_bufusage)
instr->bufusage_start = pgBufferUsage;
if (instr->need_walusage)
instr->walusage_start = pgWalUsage;
}
/* Exit from a plan node */
@ -95,6 +104,10 @@ InstrStopNode(Instrumentation *instr, double nTuples)
BufferUsageAccumDiff(&instr->bufusage,
&pgBufferUsage, &instr->bufusage_start);
if (instr->need_walusage)
WalUsageAccumDiff(&instr->walusage,
&pgWalUsage, &instr->walusage_start);
/* Is this the first tuple of this cycle? */
if (!instr->running)
{
@ -158,6 +171,9 @@ InstrAggNode(Instrumentation *dst, Instrumentation *add)
/* Add delta of buffer usage since entry to node's totals */
if (dst->need_bufusage)
BufferUsageAdd(&dst->bufusage, &add->bufusage);
if (dst->need_walusage)
WalUsageAdd(&dst->walusage, &add->walusage);
}
/* note current values during parallel executor startup */
@ -165,21 +181,29 @@ void
InstrStartParallelQuery(void)
{
save_pgBufferUsage = pgBufferUsage;
save_pgWalUsage = pgWalUsage;
}
/* report usage after parallel executor shutdown */
void
InstrEndParallelQuery(BufferUsage *result)
InstrEndParallelQuery(BufferUsage *bufusage, WalUsage *walusage)
{
memset(result, 0, sizeof(BufferUsage));
BufferUsageAccumDiff(result, &pgBufferUsage, &save_pgBufferUsage);
if (bufusage)
{
memset(bufusage, 0, sizeof(BufferUsage));
BufferUsageAccumDiff(bufusage, &pgBufferUsage, &save_pgBufferUsage);
}
memset(walusage, 0, sizeof(WalUsage));
WalUsageAccumDiff(walusage, &pgWalUsage, &save_pgWalUsage);
}
/* accumulate work done by workers in leader's stats */
void
InstrAccumParallelQuery(BufferUsage *result)
InstrAccumParallelQuery(BufferUsage *bufusage, WalUsage *walusage)
{
BufferUsageAdd(&pgBufferUsage, result);
if (bufusage)
BufferUsageAdd(&pgBufferUsage, bufusage);
WalUsageAdd(&pgWalUsage, walusage);
}
/* dst += add */
@ -221,3 +245,20 @@ BufferUsageAccumDiff(BufferUsage *dst,
INSTR_TIME_ACCUM_DIFF(dst->blk_write_time,
add->blk_write_time, sub->blk_write_time);
}
/* helper functions for WAL usage accumulation */
static void
WalUsageAdd(WalUsage *dst, WalUsage *add)
{
dst->wal_bytes += add->wal_bytes;
dst->wal_records += add->wal_records;
dst->wal_num_fpw += add->wal_num_fpw;
}
void
WalUsageAccumDiff(WalUsage *dst, const WalUsage *add, const WalUsage *sub)
{
dst->wal_bytes += add->wal_bytes - sub->wal_bytes;
dst->wal_records += add->wal_records - sub->wal_records;
dst->wal_num_fpw += add->wal_num_fpw - sub->wal_num_fpw;
}