You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
postgres/src/backend/utils/adt/pgstatfuncs.c

2386 lines
56 KiB

/*-------------------------------------------------------------------------
*
* pgstatfuncs.c
* Functions for accessing various forms of statistics data
*
* Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/utils/adt/pgstatfuncs.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/htup_details.h"
#include "access/xlog.h"
Prefetch data referenced by the WAL, take II. Introduce a new GUC recovery_prefetch. When enabled, look ahead in the WAL and try to initiate asynchronous reading of referenced data blocks that are not yet cached in our buffer pool. For now, this is done with posix_fadvise(), which has several caveats. Since not all OSes have that system call, "try" is provided so that it can be enabled where available. Better mechanisms for asynchronous I/O are possible in later work. Set to "try" for now for test coverage. Default setting to be finalized before release. The GUC wal_decode_buffer_size limits the distance we can look ahead in bytes of decoded data. The existing GUC maintenance_io_concurrency is used to limit the number of concurrent I/Os allowed, based on pessimistic heuristics used to infer that I/Os have begun and completed. We'll also not look more than maintenance_io_concurrency * 4 block references ahead. Reviewed-by: Julien Rouhaud <rjuju123@gmail.com> Reviewed-by: Tomas Vondra <tomas.vondra@2ndquadrant.com> Reviewed-by: Alvaro Herrera <alvherre@2ndquadrant.com> (earlier version) Reviewed-by: Andres Freund <andres@anarazel.de> (earlier version) Reviewed-by: Justin Pryzby <pryzby@telsasoft.com> (earlier version) Tested-by: Tomas Vondra <tomas.vondra@2ndquadrant.com> (earlier version) Tested-by: Jakub Wartak <Jakub.Wartak@tomtom.com> (earlier version) Tested-by: Dmitry Dolgov <9erthalion6@gmail.com> (earlier version) Tested-by: Sait Talha Nisanci <Sait.Nisanci@microsoft.com> (earlier version) Discussion: https://postgr.es/m/CA%2BhUKGJ4VJN8ttxScUFM8dOKX0BrBiboo5uz1cq%3DAovOddfHpA%40mail.gmail.com
3 years ago
#include "access/xlogprefetcher.h"
#include "catalog/pg_authid.h"
#include "catalog/pg_type.h"
#include "common/ip.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "postmaster/bgworker_internals.h"
#include "postmaster/postmaster.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "utils/acl.h"
#include "utils/builtins.h"
#include "utils/inet.h"
#include "utils/timestamp.h"
#define UINT32_ACCESS_ONCE(var) ((uint32)(*((volatile uint32 *)&(var))))
#define HAS_PGSTAT_PERMISSIONS(role) (has_privs_of_role(GetUserId(), ROLE_PG_READ_ALL_STATS) || has_privs_of_role(GetUserId(), role))
Datum
pg_stat_get_numscans(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->numscans);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_lastscan(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
PG_RETURN_NULL();
else
PG_RETURN_TIMESTAMPTZ(tabentry->lastscan);
}
Datum
pg_stat_get_tuples_returned(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->tuples_returned);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_tuples_fetched(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->tuples_fetched);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_tuples_inserted(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->tuples_inserted);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_tuples_updated(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->tuples_updated);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_tuples_deleted(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->tuples_deleted);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_tuples_hot_updated(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->tuples_hot_updated);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_live_tuples(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->n_live_tuples);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_dead_tuples(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->n_dead_tuples);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_mod_since_analyze(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->changes_since_analyze);
PG_RETURN_INT64(result);
}
Trigger autovacuum based on number of INSERTs Traditionally autovacuum has only ever invoked a worker based on the estimated number of dead tuples in a table and for anti-wraparound purposes. For the latter, with certain classes of tables such as insert-only tables, anti-wraparound vacuums could be the first vacuum that the table ever receives. This could often lead to autovacuum workers being busy for extended periods of time due to having to potentially freeze every page in the table. This could be particularly bad for very large tables. New clusters, or recently pg_restored clusters could suffer even more as many large tables may have the same relfrozenxid, which could result in large numbers of tables requiring an anti-wraparound vacuum all at once. Here we aim to reduce the work required by anti-wraparound and aggressive vacuums in general, by triggering autovacuum when the table has received enough INSERTs. This is controlled by adding two new GUCs and reloptions; autovacuum_vacuum_insert_threshold and autovacuum_vacuum_insert_scale_factor. These work exactly the same as the existing scale factor and threshold controls, only base themselves off the number of inserts since the last vacuum, rather than the number of dead tuples. New controls were added rather than reusing the existing controls, to allow these new vacuums to be tuned independently and perhaps even completely disabled altogether, which can be done by setting autovacuum_vacuum_insert_threshold to -1. We make no attempt to skip index cleanup operations on these vacuums as they may trigger for an insert-mostly table which continually doesn't have enough dead tuples to trigger an autovacuum for the purpose of removing those dead tuples. If we were to skip cleaning the indexes in this case, then it is possible for the index(es) to become bloated over time. There are additional benefits to triggering autovacuums based on inserts, as tables which never contain enough dead tuples to trigger an autovacuum are now more likely to receive a vacuum, which can mark more of the table as "allvisible" and encourage the query planner to make use of Index Only Scans. Currently, we still obey vacuum_freeze_min_age when triggering these new autovacuums based on INSERTs. For large insert-only tables, it may be beneficial to lower the table's autovacuum_freeze_min_age so that tuples are eligible to be frozen sooner. Here we've opted not to zero that for these types of vacuums, since the table may just be insert-mostly and we may otherwise freeze tuples that are still destined to be updated or removed in the near future. There was some debate to what exactly the new scale factor and threshold should default to. For now, these are set to 0.2 and 1000, respectively. There may be some motivation to adjust these before the release. Author: Laurenz Albe, Darafei Praliaskouski Reviewed-by: Alvaro Herrera, Masahiko Sawada, Chris Travers, Andres Freund, Justin Pryzby Discussion: https://postgr.es/m/CAC8Q8t%2Bj36G_bLF%3D%2B0iMo6jGNWnLnWb1tujXuJr-%2Bx8ZCCTqoQ%40mail.gmail.com
5 years ago
Datum
pg_stat_get_ins_since_vacuum(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->inserts_since_vacuum);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_blocks_fetched(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->blocks_fetched);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_blocks_hit(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->blocks_hit);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_last_vacuum_time(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
TimestampTz result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = tabentry->vacuum_timestamp;
if (result == 0)
PG_RETURN_NULL();
else
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_last_autovacuum_time(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
TimestampTz result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = tabentry->autovac_vacuum_timestamp;
if (result == 0)
PG_RETURN_NULL();
else
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_last_analyze_time(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
TimestampTz result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = tabentry->analyze_timestamp;
if (result == 0)
PG_RETURN_NULL();
else
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_last_autoanalyze_time(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
TimestampTz result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = tabentry->autovac_analyze_timestamp;
if (result == 0)
PG_RETURN_NULL();
else
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_vacuum_count(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->vacuum_count);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_autovacuum_count(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->autovac_vacuum_count);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_analyze_count(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->analyze_count);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_autoanalyze_count(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_StatTabEntry *tabentry;
if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->autovac_analyze_count);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_function_calls(PG_FUNCTION_ARGS)
{
Oid funcid = PG_GETARG_OID(0);
PgStat_StatFuncEntry *funcentry;
if ((funcentry = pgstat_fetch_stat_funcentry(funcid)) == NULL)
PG_RETURN_NULL();
PG_RETURN_INT64(funcentry->f_numcalls);
}
Datum
pg_stat_get_function_total_time(PG_FUNCTION_ARGS)
{
Oid funcid = PG_GETARG_OID(0);
PgStat_StatFuncEntry *funcentry;
if ((funcentry = pgstat_fetch_stat_funcentry(funcid)) == NULL)
PG_RETURN_NULL();
/* convert counter from microsec to millisec for display */
PG_RETURN_FLOAT8(((double) funcentry->f_total_time) / 1000.0);
}
Datum
pg_stat_get_function_self_time(PG_FUNCTION_ARGS)
{
Oid funcid = PG_GETARG_OID(0);
PgStat_StatFuncEntry *funcentry;
if ((funcentry = pgstat_fetch_stat_funcentry(funcid)) == NULL)
PG_RETURN_NULL();
/* convert counter from microsec to millisec for display */
PG_RETURN_FLOAT8(((double) funcentry->f_self_time) / 1000.0);
}
Datum
pg_stat_get_backend_idset(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
int *fctx;
/* stuff done only on the first call of the function */
if (SRF_IS_FIRSTCALL())
{
/* create a function context for cross-call persistence */
funcctx = SRF_FIRSTCALL_INIT();
fctx = MemoryContextAlloc(funcctx->multi_call_memory_ctx,
sizeof(int));
funcctx->user_fctx = fctx;
fctx[0] = 0;
}
/* stuff done on every call of the function */
funcctx = SRF_PERCALL_SETUP();
fctx = funcctx->user_fctx;
fctx[0] += 1;
/*
* We recheck pgstat_fetch_stat_numbackends() each time through, just in
* case the local status data has been refreshed since we started. It's
* plenty cheap enough if not. If a refresh does happen, we'll likely
* miss or duplicate some backend IDs, but we're content not to crash.
* (Refreshing midway through such a query would be problematic usage
* anyway, since the backend IDs we've already returned might no longer
* refer to extant sessions.)
*/
if (fctx[0] <= pgstat_fetch_stat_numbackends())
{
/* do when there is more left to send */
LocalPgBackendStatus *local_beentry = pgstat_fetch_stat_local_beentry(fctx[0]);
SRF_RETURN_NEXT(funcctx, Int32GetDatum(local_beentry->backend_id));
}
else
{
/* do when there is no more left */
SRF_RETURN_DONE(funcctx);
}
}
/*
* Returns command progress information for the named command.
*/
Datum
pg_stat_get_progress_info(PG_FUNCTION_ARGS)
{
#define PG_STAT_GET_PROGRESS_COLS PGSTAT_NUM_PROGRESS_PARAM + 3
int num_backends = pgstat_fetch_stat_numbackends();
int curr_backend;
char *cmd = text_to_cstring(PG_GETARG_TEXT_PP(0));
ProgressCommandType cmdtype;
ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
/* Translate command name into command type code. */
if (pg_strcasecmp(cmd, "VACUUM") == 0)
cmdtype = PROGRESS_COMMAND_VACUUM;
else if (pg_strcasecmp(cmd, "ANALYZE") == 0)
cmdtype = PROGRESS_COMMAND_ANALYZE;
else if (pg_strcasecmp(cmd, "CLUSTER") == 0)
cmdtype = PROGRESS_COMMAND_CLUSTER;
else if (pg_strcasecmp(cmd, "CREATE INDEX") == 0)
cmdtype = PROGRESS_COMMAND_CREATE_INDEX;
else if (pg_strcasecmp(cmd, "BASEBACKUP") == 0)
cmdtype = PROGRESS_COMMAND_BASEBACKUP;
else if (pg_strcasecmp(cmd, "COPY") == 0)
cmdtype = PROGRESS_COMMAND_COPY;
else
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid command name: \"%s\"", cmd)));
InitMaterializedSRF(fcinfo, 0);
/* 1-based index */
for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
{
LocalPgBackendStatus *local_beentry;
PgBackendStatus *beentry;
Datum values[PG_STAT_GET_PROGRESS_COLS] = {0};
bool nulls[PG_STAT_GET_PROGRESS_COLS] = {0};
int i;
local_beentry = pgstat_fetch_stat_local_beentry(curr_backend);
beentry = &local_beentry->backendStatus;
/*
* Report values for only those backends which are running the given
* command.
*/
if (beentry->st_progress_command != cmdtype)
continue;
/* Value available to all callers */
values[0] = Int32GetDatum(beentry->st_procpid);
values[1] = ObjectIdGetDatum(beentry->st_databaseid);
/* show rest of the values including relid only to role members */
if (HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
{
values[2] = ObjectIdGetDatum(beentry->st_progress_command_target);
for (i = 0; i < PGSTAT_NUM_PROGRESS_PARAM; i++)
values[i + 3] = Int64GetDatum(beentry->st_progress_param[i]);
}
else
{
nulls[2] = true;
for (i = 0; i < PGSTAT_NUM_PROGRESS_PARAM; i++)
nulls[i + 3] = true;
}
Create routine able to set single-call SRFs for Materialize mode Set-returning functions that use the Materialize mode, creating a tuplestore to include all the tuples returned in a set rather than doing so in multiple calls, use roughly the same set of steps to prepare ReturnSetInfo for this job: - Check if ReturnSetInfo supports returning a tuplestore and if the materialize mode is enabled. - Create a tuplestore for all the tuples part of the returned set in the per-query memory context, stored in ReturnSetInfo->setResult. - Build a tuple descriptor mostly from get_call_result_type(), then stored in ReturnSetInfo->setDesc. Note that there are some cases where the SRF's tuple descriptor has to be the one specified by the function caller. This refactoring is done so as there are (well, should be) no behavior changes in any of the in-core functions refactored, and the centralized function that checks and sets up the function's ReturnSetInfo can be controlled with a set of bits32 options. Two of them prove to be necessary now: - SRF_SINGLE_USE_EXPECTED to use expectedDesc as tuple descriptor, as expected by the function's caller. - SRF_SINGLE_BLESS to validate the tuple descriptor for the SRF. The same initialization pattern is simplified in 28 places per my count as of src/backend/, shaving up to ~900 lines of code. These mostly come from the removal of the per-query initializations and the sanity checks now grouped in a single location. There are more locations that could be simplified in contrib/, that are left for a follow-up cleanup. fcc2817, 07daca5 and d61a361 have prepared the areas of the code related to this change, to ease this refactoring. Author: Melanie Plageman, Michael Paquier Reviewed-by: Álvaro Herrera, Justin Pryzby Discussion: https://postgr.es/m/CAAKRu_azyd1Z3W_r7Ou4sorTjRCs+PxeHw1CWJeXKofkE6TuZg@mail.gmail.com
3 years ago
tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
}
return (Datum) 0;
}
/*
* Returns activity of PG backends.
*/
Datum
pg_stat_get_activity(PG_FUNCTION_ARGS)
{
#define PG_STAT_GET_ACTIVITY_COLS 30
int num_backends = pgstat_fetch_stat_numbackends();
int curr_backend;
int pid = PG_ARGISNULL(0) ? -1 : PG_GETARG_INT32(0);
ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
InitMaterializedSRF(fcinfo, 0);
/* 1-based index */
for (curr_backend = 1; curr_backend <= num_backends; curr_backend++)
{
/* for each row */
Datum values[PG_STAT_GET_ACTIVITY_COLS] = {0};
bool nulls[PG_STAT_GET_ACTIVITY_COLS] = {0};
LocalPgBackendStatus *local_beentry;
PgBackendStatus *beentry;
PGPROC *proc;
const char *wait_event_type = NULL;
const char *wait_event = NULL;
/* Get the next one in the list */
local_beentry = pgstat_fetch_stat_local_beentry(curr_backend);
beentry = &local_beentry->backendStatus;
/* If looking for specific PID, ignore all the others */
if (pid != -1 && beentry->st_procpid != pid)
continue;
/* Values available to all callers */
if (beentry->st_databaseid != InvalidOid)
values[0] = ObjectIdGetDatum(beentry->st_databaseid);
else
nulls[0] = true;
values[1] = Int32GetDatum(beentry->st_procpid);
if (beentry->st_userid != InvalidOid)
values[2] = ObjectIdGetDatum(beentry->st_userid);
else
nulls[2] = true;
if (beentry->st_appname)
values[3] = CStringGetTextDatum(beentry->st_appname);
else
nulls[3] = true;
if (TransactionIdIsValid(local_beentry->backend_xid))
values[15] = TransactionIdGetDatum(local_beentry->backend_xid);
else
nulls[15] = true;
if (TransactionIdIsValid(local_beentry->backend_xmin))
values[16] = TransactionIdGetDatum(local_beentry->backend_xmin);
else
nulls[16] = true;
/* Values only available to role member or pg_read_all_stats */
if (HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
{
SockAddr zero_clientaddr;
char *clipped_activity;
switch (beentry->st_state)
{
case STATE_IDLE:
values[4] = CStringGetTextDatum("idle");
break;
case STATE_RUNNING:
values[4] = CStringGetTextDatum("active");
break;
case STATE_IDLEINTRANSACTION:
values[4] = CStringGetTextDatum("idle in transaction");
break;
case STATE_FASTPATH:
values[4] = CStringGetTextDatum("fastpath function call");
break;
case STATE_IDLEINTRANSACTION_ABORTED:
values[4] = CStringGetTextDatum("idle in transaction (aborted)");
break;
case STATE_DISABLED:
values[4] = CStringGetTextDatum("disabled");
break;
case STATE_UNDEFINED:
nulls[4] = true;
break;
}
clipped_activity = pgstat_clip_activity(beentry->st_activity_raw);
values[5] = CStringGetTextDatum(clipped_activity);
pfree(clipped_activity);
/* leader_pid */
nulls[28] = true;
proc = BackendPidGetProc(beentry->st_procpid);
if (proc == NULL && (beentry->st_backendType != B_BACKEND))
{
/*
* For an auxiliary process, retrieve process info from
* AuxiliaryProcs stored in shared-memory.
*/
proc = AuxiliaryPidGetProc(beentry->st_procpid);
}
/*
* If a PGPROC entry was retrieved, display wait events and lock
* group leader information if any. To avoid extra overhead, no
* extra lock is being held, so there is no guarantee of
* consistency across multiple rows.
*/
if (proc != NULL)
{
uint32 raw_wait_event;
PGPROC *leader;
raw_wait_event = UINT32_ACCESS_ONCE(proc->wait_event_info);
wait_event_type = pgstat_get_wait_event_type(raw_wait_event);
wait_event = pgstat_get_wait_event(raw_wait_event);
leader = proc->lockGroupLeader;
/*
* Show the leader only for active parallel workers. This
* leaves the field as NULL for the leader of a parallel
* group.
*/
if (leader && leader->pid != beentry->st_procpid)
{
values[28] = Int32GetDatum(leader->pid);
nulls[28] = false;
}
}
if (wait_event_type)
values[6] = CStringGetTextDatum(wait_event_type);
else
nulls[6] = true;
if (wait_event)
values[7] = CStringGetTextDatum(wait_event);
else
nulls[7] = true;
/*
* Don't expose transaction time for walsenders; it confuses
* monitoring, particularly because we don't keep the time up-to-
* date.
*/
if (beentry->st_xact_start_timestamp != 0 &&
beentry->st_backendType != B_WAL_SENDER)
values[8] = TimestampTzGetDatum(beentry->st_xact_start_timestamp);
else
nulls[8] = true;
if (beentry->st_activity_start_timestamp != 0)
values[9] = TimestampTzGetDatum(beentry->st_activity_start_timestamp);
else
nulls[9] = true;
if (beentry->st_proc_start_timestamp != 0)
values[10] = TimestampTzGetDatum(beentry->st_proc_start_timestamp);
else
nulls[10] = true;
if (beentry->st_state_start_timestamp != 0)
values[11] = TimestampTzGetDatum(beentry->st_state_start_timestamp);
else
nulls[11] = true;
/* A zeroed client addr means we don't know */
memset(&zero_clientaddr, 0, sizeof(zero_clientaddr));
if (memcmp(&(beentry->st_clientaddr), &zero_clientaddr,
sizeof(zero_clientaddr)) == 0)
{
nulls[12] = true;
nulls[13] = true;
nulls[14] = true;
}
else
{
if (beentry->st_clientaddr.addr.ss_family == AF_INET ||
beentry->st_clientaddr.addr.ss_family == AF_INET6)
{
char remote_host[NI_MAXHOST];
char remote_port[NI_MAXSERV];
int ret;
remote_host[0] = '\0';
remote_port[0] = '\0';
ret = pg_getnameinfo_all(&beentry->st_clientaddr.addr,
beentry->st_clientaddr.salen,
remote_host, sizeof(remote_host),
remote_port, sizeof(remote_port),
NI_NUMERICHOST | NI_NUMERICSERV);
if (ret == 0)
{
clean_ipv6_addr(beentry->st_clientaddr.addr.ss_family, remote_host);
values[12] = DirectFunctionCall1(inet_in,
CStringGetDatum(remote_host));
if (beentry->st_clienthostname &&
beentry->st_clienthostname[0])
values[13] = CStringGetTextDatum(beentry->st_clienthostname);
else
nulls[13] = true;
values[14] = Int32GetDatum(atoi(remote_port));
}
else
{
nulls[12] = true;
nulls[13] = true;
nulls[14] = true;
}
}
else if (beentry->st_clientaddr.addr.ss_family == AF_UNIX)
{
/*
* Unix sockets always reports NULL for host and -1 for
* port, so it's possible to tell the difference to
* connections we have no permissions to view, or with
* errors.
*/
nulls[12] = true;
nulls[13] = true;
values[14] = Int32GetDatum(-1);
}
else
{
/* Unknown address type, should never happen */
nulls[12] = true;
nulls[13] = true;
nulls[14] = true;
}
}
/* Add backend type */
if (beentry->st_backendType == B_BG_WORKER)
{
const char *bgw_type;
bgw_type = GetBackgroundWorkerTypeByPid(beentry->st_procpid);
if (bgw_type)
values[17] = CStringGetTextDatum(bgw_type);
else
nulls[17] = true;
}
else
values[17] =
CStringGetTextDatum(GetBackendTypeDesc(beentry->st_backendType));
/* SSL information */
if (beentry->st_ssl)
{
values[18] = BoolGetDatum(true); /* ssl */
values[19] = CStringGetTextDatum(beentry->st_sslstatus->ssl_version);
values[20] = CStringGetTextDatum(beentry->st_sslstatus->ssl_cipher);
values[21] = Int32GetDatum(beentry->st_sslstatus->ssl_bits);
if (beentry->st_sslstatus->ssl_client_dn[0])
values[22] = CStringGetTextDatum(beentry->st_sslstatus->ssl_client_dn);
else
nulls[22] = true;
if (beentry->st_sslstatus->ssl_client_serial[0])
values[23] = DirectFunctionCall3(numeric_in,
CStringGetDatum(beentry->st_sslstatus->ssl_client_serial),
ObjectIdGetDatum(InvalidOid),
Int32GetDatum(-1));
else
nulls[23] = true;
if (beentry->st_sslstatus->ssl_issuer_dn[0])
values[24] = CStringGetTextDatum(beentry->st_sslstatus->ssl_issuer_dn);
else
nulls[24] = true;
}
else
{
values[18] = BoolGetDatum(false); /* ssl */
nulls[19] = nulls[20] = nulls[21] = nulls[22] = nulls[23] = nulls[24] = true;
}
GSSAPI encryption support On both the frontend and backend, prepare for GSSAPI encryption support by moving common code for error handling into a separate file. Fix a TODO for handling multiple status messages in the process. Eliminate the OIDs, which have not been needed for some time. Add frontend and backend encryption support functions. Keep the context initiation for authentication-only separate on both the frontend and backend in order to avoid concerns about changing the requested flags to include encryption support. In postmaster, pull GSSAPI authorization checking into a shared function. Also share the initiator name between the encryption and non-encryption codepaths. For HBA, add "hostgssenc" and "hostnogssenc" entries that behave similarly to their SSL counterparts. "hostgssenc" requires either "gss", "trust", or "reject" for its authentication. Similarly, add a "gssencmode" parameter to libpq. Supported values are "disable", "require", and "prefer". Notably, negotiation will only be attempted if credentials can be acquired. Move credential acquisition into its own function to support this behavior. Add a simple pg_stat_gssapi view similar to pg_stat_ssl, for monitoring if GSSAPI authentication was used, what principal was used, and if encryption is being used on the connection. Finally, add documentation for everything new, and update existing documentation on connection security. Thanks to Michael Paquier for the Windows fixes. Author: Robbie Harwood, with changes to the read/write functions by me. Reviewed in various forms and at different times by: Michael Paquier, Andres Freund, David Steele. Discussion: https://www.postgresql.org/message-id/flat/jlg1tgq1ktm.fsf@thriss.redhat.com
6 years ago
/* GSSAPI information */
if (beentry->st_gss)
{
values[25] = BoolGetDatum(beentry->st_gssstatus->gss_auth); /* gss_auth */
values[26] = CStringGetTextDatum(beentry->st_gssstatus->gss_princ);
values[27] = BoolGetDatum(beentry->st_gssstatus->gss_enc); /* GSS Encryption in use */
GSSAPI encryption support On both the frontend and backend, prepare for GSSAPI encryption support by moving common code for error handling into a separate file. Fix a TODO for handling multiple status messages in the process. Eliminate the OIDs, which have not been needed for some time. Add frontend and backend encryption support functions. Keep the context initiation for authentication-only separate on both the frontend and backend in order to avoid concerns about changing the requested flags to include encryption support. In postmaster, pull GSSAPI authorization checking into a shared function. Also share the initiator name between the encryption and non-encryption codepaths. For HBA, add "hostgssenc" and "hostnogssenc" entries that behave similarly to their SSL counterparts. "hostgssenc" requires either "gss", "trust", or "reject" for its authentication. Similarly, add a "gssencmode" parameter to libpq. Supported values are "disable", "require", and "prefer". Notably, negotiation will only be attempted if credentials can be acquired. Move credential acquisition into its own function to support this behavior. Add a simple pg_stat_gssapi view similar to pg_stat_ssl, for monitoring if GSSAPI authentication was used, what principal was used, and if encryption is being used on the connection. Finally, add documentation for everything new, and update existing documentation on connection security. Thanks to Michael Paquier for the Windows fixes. Author: Robbie Harwood, with changes to the read/write functions by me. Reviewed in various forms and at different times by: Michael Paquier, Andres Freund, David Steele. Discussion: https://www.postgresql.org/message-id/flat/jlg1tgq1ktm.fsf@thriss.redhat.com
6 years ago
}
else
{
values[25] = BoolGetDatum(false); /* gss_auth */
nulls[26] = true; /* No GSS principal */
values[27] = BoolGetDatum(false); /* GSS Encryption not in
GSSAPI encryption support On both the frontend and backend, prepare for GSSAPI encryption support by moving common code for error handling into a separate file. Fix a TODO for handling multiple status messages in the process. Eliminate the OIDs, which have not been needed for some time. Add frontend and backend encryption support functions. Keep the context initiation for authentication-only separate on both the frontend and backend in order to avoid concerns about changing the requested flags to include encryption support. In postmaster, pull GSSAPI authorization checking into a shared function. Also share the initiator name between the encryption and non-encryption codepaths. For HBA, add "hostgssenc" and "hostnogssenc" entries that behave similarly to their SSL counterparts. "hostgssenc" requires either "gss", "trust", or "reject" for its authentication. Similarly, add a "gssencmode" parameter to libpq. Supported values are "disable", "require", and "prefer". Notably, negotiation will only be attempted if credentials can be acquired. Move credential acquisition into its own function to support this behavior. Add a simple pg_stat_gssapi view similar to pg_stat_ssl, for monitoring if GSSAPI authentication was used, what principal was used, and if encryption is being used on the connection. Finally, add documentation for everything new, and update existing documentation on connection security. Thanks to Michael Paquier for the Windows fixes. Author: Robbie Harwood, with changes to the read/write functions by me. Reviewed in various forms and at different times by: Michael Paquier, Andres Freund, David Steele. Discussion: https://www.postgresql.org/message-id/flat/jlg1tgq1ktm.fsf@thriss.redhat.com
6 years ago
* use */
}
if (beentry->st_query_id == 0)
nulls[29] = true;
else
values[29] = UInt64GetDatum(beentry->st_query_id);
}
else
{
/* No permissions to view data about this session */
values[5] = CStringGetTextDatum("<insufficient privilege>");
nulls[4] = true;
nulls[6] = true;
nulls[7] = true;
nulls[8] = true;
nulls[9] = true;
nulls[10] = true;
nulls[11] = true;
nulls[12] = true;
nulls[13] = true;
nulls[14] = true;
nulls[17] = true;
nulls[18] = true;
nulls[19] = true;
nulls[20] = true;
nulls[21] = true;
nulls[22] = true;
nulls[23] = true;
nulls[24] = true;
nulls[25] = true;
GSSAPI encryption support On both the frontend and backend, prepare for GSSAPI encryption support by moving common code for error handling into a separate file. Fix a TODO for handling multiple status messages in the process. Eliminate the OIDs, which have not been needed for some time. Add frontend and backend encryption support functions. Keep the context initiation for authentication-only separate on both the frontend and backend in order to avoid concerns about changing the requested flags to include encryption support. In postmaster, pull GSSAPI authorization checking into a shared function. Also share the initiator name between the encryption and non-encryption codepaths. For HBA, add "hostgssenc" and "hostnogssenc" entries that behave similarly to their SSL counterparts. "hostgssenc" requires either "gss", "trust", or "reject" for its authentication. Similarly, add a "gssencmode" parameter to libpq. Supported values are "disable", "require", and "prefer". Notably, negotiation will only be attempted if credentials can be acquired. Move credential acquisition into its own function to support this behavior. Add a simple pg_stat_gssapi view similar to pg_stat_ssl, for monitoring if GSSAPI authentication was used, what principal was used, and if encryption is being used on the connection. Finally, add documentation for everything new, and update existing documentation on connection security. Thanks to Michael Paquier for the Windows fixes. Author: Robbie Harwood, with changes to the read/write functions by me. Reviewed in various forms and at different times by: Michael Paquier, Andres Freund, David Steele. Discussion: https://www.postgresql.org/message-id/flat/jlg1tgq1ktm.fsf@thriss.redhat.com
6 years ago
nulls[26] = true;
nulls[27] = true;
nulls[28] = true;
nulls[29] = true;
}
Create routine able to set single-call SRFs for Materialize mode Set-returning functions that use the Materialize mode, creating a tuplestore to include all the tuples returned in a set rather than doing so in multiple calls, use roughly the same set of steps to prepare ReturnSetInfo for this job: - Check if ReturnSetInfo supports returning a tuplestore and if the materialize mode is enabled. - Create a tuplestore for all the tuples part of the returned set in the per-query memory context, stored in ReturnSetInfo->setResult. - Build a tuple descriptor mostly from get_call_result_type(), then stored in ReturnSetInfo->setDesc. Note that there are some cases where the SRF's tuple descriptor has to be the one specified by the function caller. This refactoring is done so as there are (well, should be) no behavior changes in any of the in-core functions refactored, and the centralized function that checks and sets up the function's ReturnSetInfo can be controlled with a set of bits32 options. Two of them prove to be necessary now: - SRF_SINGLE_USE_EXPECTED to use expectedDesc as tuple descriptor, as expected by the function's caller. - SRF_SINGLE_BLESS to validate the tuple descriptor for the SRF. The same initialization pattern is simplified in 28 places per my count as of src/backend/, shaving up to ~900 lines of code. These mostly come from the removal of the per-query initializations and the sanity checks now grouped in a single location. There are more locations that could be simplified in contrib/, that are left for a follow-up cleanup. fcc2817, 07daca5 and d61a361 have prepared the areas of the code related to this change, to ease this refactoring. Author: Melanie Plageman, Michael Paquier Reviewed-by: Álvaro Herrera, Justin Pryzby Discussion: https://postgr.es/m/CAAKRu_azyd1Z3W_r7Ou4sorTjRCs+PxeHw1CWJeXKofkE6TuZg@mail.gmail.com
3 years ago
tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
/* If only a single backend was requested, and we found it, break. */
if (pid != -1)
break;
}
return (Datum) 0;
}
Datum
pg_backend_pid(PG_FUNCTION_ARGS)
{
PG_RETURN_INT32(MyProcPid);
}
Datum
pg_stat_get_backend_pid(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
PgBackendStatus *beentry;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
PG_RETURN_NULL();
PG_RETURN_INT32(beentry->st_procpid);
}
Datum
pg_stat_get_backend_dbid(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
PgBackendStatus *beentry;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
PG_RETURN_NULL();
PG_RETURN_OID(beentry->st_databaseid);
}
Datum
pg_stat_get_backend_userid(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
PgBackendStatus *beentry;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
PG_RETURN_NULL();
PG_RETURN_OID(beentry->st_userid);
}
Datum
pg_stat_get_backend_activity(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
PgBackendStatus *beentry;
const char *activity;
char *clipped_activity;
text *ret;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
activity = "<backend information not available>";
else if (!HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
activity = "<insufficient privilege>";
else if (*(beentry->st_activity_raw) == '\0')
activity = "<command string not enabled>";
else
activity = beentry->st_activity_raw;
clipped_activity = pgstat_clip_activity(activity);
ret = cstring_to_text(activity);
pfree(clipped_activity);
PG_RETURN_TEXT_P(ret);
}
Datum
pg_stat_get_backend_wait_event_type(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
PgBackendStatus *beentry;
PGPROC *proc;
const char *wait_event_type = NULL;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
wait_event_type = "<backend information not available>";
else if (!HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
wait_event_type = "<insufficient privilege>";
else if ((proc = BackendPidGetProc(beentry->st_procpid)) != NULL)
wait_event_type = pgstat_get_wait_event_type(proc->wait_event_info);
if (!wait_event_type)
PG_RETURN_NULL();
PG_RETURN_TEXT_P(cstring_to_text(wait_event_type));
}
Datum
pg_stat_get_backend_wait_event(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
PgBackendStatus *beentry;
PGPROC *proc;
const char *wait_event = NULL;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
wait_event = "<backend information not available>";
else if (!HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
wait_event = "<insufficient privilege>";
else if ((proc = BackendPidGetProc(beentry->st_procpid)) != NULL)
wait_event = pgstat_get_wait_event(proc->wait_event_info);
if (!wait_event)
PG_RETURN_NULL();
PG_RETURN_TEXT_P(cstring_to_text(wait_event));
}
Datum
pg_stat_get_backend_activity_start(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
22 years ago
TimestampTz result;
PgBackendStatus *beentry;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
PG_RETURN_NULL();
else if (!HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
PG_RETURN_NULL();
result = beentry->st_activity_start_timestamp;
/*
* No time recorded for start of current query -- this is the case if the
* user hasn't enabled query-level stats collection.
*/
if (result == 0)
PG_RETURN_NULL();
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_backend_xact_start(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
TimestampTz result;
PgBackendStatus *beentry;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
PG_RETURN_NULL();
else if (!HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
PG_RETURN_NULL();
result = beentry->st_xact_start_timestamp;
if (result == 0) /* not in a transaction */
PG_RETURN_NULL();
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_backend_start(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
TimestampTz result;
PgBackendStatus *beentry;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
PG_RETURN_NULL();
else if (!HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
PG_RETURN_NULL();
result = beentry->st_proc_start_timestamp;
if (result == 0) /* probably can't happen? */
PG_RETURN_NULL();
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_backend_client_addr(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
PgBackendStatus *beentry;
SockAddr zero_clientaddr;
char remote_host[NI_MAXHOST];
int ret;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
PG_RETURN_NULL();
else if (!HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
PG_RETURN_NULL();
/* A zeroed client addr means we don't know */
memset(&zero_clientaddr, 0, sizeof(zero_clientaddr));
if (memcmp(&(beentry->st_clientaddr), &zero_clientaddr,
sizeof(zero_clientaddr)) == 0)
PG_RETURN_NULL();
switch (beentry->st_clientaddr.addr.ss_family)
{
case AF_INET:
case AF_INET6:
break;
default:
PG_RETURN_NULL();
}
remote_host[0] = '\0';
ret = pg_getnameinfo_all(&beentry->st_clientaddr.addr,
beentry->st_clientaddr.salen,
remote_host, sizeof(remote_host),
NULL, 0,
NI_NUMERICHOST | NI_NUMERICSERV);
if (ret != 0)
PG_RETURN_NULL();
clean_ipv6_addr(beentry->st_clientaddr.addr.ss_family, remote_host);
PG_RETURN_DATUM(DirectFunctionCall1(inet_in,
CStringGetDatum(remote_host)));
}
Datum
pg_stat_get_backend_client_port(PG_FUNCTION_ARGS)
{
int32 beid = PG_GETARG_INT32(0);
PgBackendStatus *beentry;
SockAddr zero_clientaddr;
char remote_port[NI_MAXSERV];
int ret;
if ((beentry = pgstat_fetch_stat_beentry(beid)) == NULL)
PG_RETURN_NULL();
else if (!HAS_PGSTAT_PERMISSIONS(beentry->st_userid))
PG_RETURN_NULL();
/* A zeroed client addr means we don't know */
memset(&zero_clientaddr, 0, sizeof(zero_clientaddr));
if (memcmp(&(beentry->st_clientaddr), &zero_clientaddr,
sizeof(zero_clientaddr)) == 0)
PG_RETURN_NULL();
switch (beentry->st_clientaddr.addr.ss_family)
{
case AF_INET:
case AF_INET6:
break;
case AF_UNIX:
PG_RETURN_INT32(-1);
default:
PG_RETURN_NULL();
}
remote_port[0] = '\0';
ret = pg_getnameinfo_all(&beentry->st_clientaddr.addr,
beentry->st_clientaddr.salen,
NULL, 0,
remote_port, sizeof(remote_port),
NI_NUMERICHOST | NI_NUMERICSERV);
if (ret != 0)
PG_RETURN_NULL();
PG_RETURN_DATUM(DirectFunctionCall1(int4in,
CStringGetDatum(remote_port)));
}
Datum
pg_stat_get_db_numbackends(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int32 result;
int tot_backends = pgstat_fetch_stat_numbackends();
int beid;
result = 0;
for (beid = 1; beid <= tot_backends; beid++)
{
LocalPgBackendStatus *local_beentry = pgstat_fetch_stat_local_beentry(beid);
if (local_beentry->backendStatus.st_databaseid == dbid)
result++;
}
PG_RETURN_INT32(result);
}
Datum
pg_stat_get_db_xact_commit(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_xact_commit);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_xact_rollback(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_xact_rollback);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_blocks_fetched(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_blocks_fetched);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_blocks_hit(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_blocks_hit);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_tuples_returned(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_tuples_returned);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_tuples_fetched(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_tuples_fetched);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_tuples_inserted(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_tuples_inserted);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_tuples_updated(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_tuples_updated);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_tuples_deleted(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_tuples_deleted);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_stat_reset_time(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
TimestampTz result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = dbentry->stat_reset_timestamp;
if (result == 0)
PG_RETURN_NULL();
else
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_db_temp_files(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = dbentry->n_temp_files;
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_temp_bytes(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = dbentry->n_temp_bytes;
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_conflict_tablespace(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_conflict_tablespace);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_conflict_lock(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_conflict_lock);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_conflict_snapshot(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_conflict_snapshot);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_conflict_bufferpin(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_conflict_bufferpin);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_conflict_startup_deadlock(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_conflict_startup_deadlock);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_conflict_all(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_conflict_tablespace +
dbentry->n_conflict_lock +
dbentry->n_conflict_snapshot +
dbentry->n_conflict_bufferpin +
dbentry->n_conflict_startup_deadlock);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_deadlocks(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_deadlocks);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_checksum_failures(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result;
PgStat_StatDBEntry *dbentry;
if (!DataChecksumsEnabled())
PG_RETURN_NULL();
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = (int64) (dbentry->n_checksum_failures);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_checksum_last_failure(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
TimestampTz result;
PgStat_StatDBEntry *dbentry;
if (!DataChecksumsEnabled())
PG_RETURN_NULL();
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = dbentry->last_checksum_failure;
if (result == 0)
PG_RETURN_NULL();
else
PG_RETURN_TIMESTAMPTZ(result);
}
Datum
pg_stat_get_db_blk_read_time(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
double result;
PgStat_StatDBEntry *dbentry;
/* convert counter from microsec to millisec for display */
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = ((double) dbentry->n_block_read_time) / 1000.0;
PG_RETURN_FLOAT8(result);
}
Datum
pg_stat_get_db_blk_write_time(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
double result;
PgStat_StatDBEntry *dbentry;
/* convert counter from microsec to millisec for display */
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
result = 0;
else
result = ((double) dbentry->n_block_write_time) / 1000.0;
PG_RETURN_FLOAT8(result);
}
Datum
pg_stat_get_db_session_time(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
double result = 0.0;
PgStat_StatDBEntry *dbentry;
/* convert counter from microsec to millisec for display */
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) != NULL)
result = ((double) dbentry->total_session_time) / 1000.0;
PG_RETURN_FLOAT8(result);
}
Datum
pg_stat_get_db_active_time(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
double result = 0.0;
PgStat_StatDBEntry *dbentry;
/* convert counter from microsec to millisec for display */
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) != NULL)
result = ((double) dbentry->total_active_time) / 1000.0;
PG_RETURN_FLOAT8(result);
}
Datum
pg_stat_get_db_idle_in_transaction_time(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
double result = 0.0;
PgStat_StatDBEntry *dbentry;
/* convert counter from microsec to millisec for display */
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) != NULL)
result = ((double) dbentry->total_idle_in_xact_time) / 1000.0;
PG_RETURN_FLOAT8(result);
}
Datum
pg_stat_get_db_sessions(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result = 0;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) != NULL)
result = (int64) (dbentry->n_sessions);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_sessions_abandoned(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result = 0;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) != NULL)
result = (int64) (dbentry->n_sessions_abandoned);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_sessions_fatal(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result = 0;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) != NULL)
result = (int64) (dbentry->n_sessions_fatal);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_db_sessions_killed(PG_FUNCTION_ARGS)
{
Oid dbid = PG_GETARG_OID(0);
int64 result = 0;
PgStat_StatDBEntry *dbentry;
if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) != NULL)
result = (int64) (dbentry->n_sessions_killed);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_bgwriter_timed_checkpoints(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->timed_checkpoints);
}
Datum
pg_stat_get_bgwriter_requested_checkpoints(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->requested_checkpoints);
}
Datum
pg_stat_get_bgwriter_buf_written_checkpoints(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->buf_written_checkpoints);
}
Datum
pg_stat_get_bgwriter_buf_written_clean(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_bgwriter()->buf_written_clean);
}
Datum
pg_stat_get_bgwriter_maxwritten_clean(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_bgwriter()->maxwritten_clean);
}
Datum
pg_stat_get_checkpoint_write_time(PG_FUNCTION_ARGS)
{
/* time is already in msec, just convert to double for presentation */
PG_RETURN_FLOAT8((double)
pgstat_fetch_stat_checkpointer()->checkpoint_write_time);
}
Datum
pg_stat_get_checkpoint_sync_time(PG_FUNCTION_ARGS)
{
/* time is already in msec, just convert to double for presentation */
PG_RETURN_FLOAT8((double)
pgstat_fetch_stat_checkpointer()->checkpoint_sync_time);
}
Datum
pg_stat_get_bgwriter_stat_reset_time(PG_FUNCTION_ARGS)
{
PG_RETURN_TIMESTAMPTZ(pgstat_fetch_stat_bgwriter()->stat_reset_timestamp);
}
Datum
pg_stat_get_buf_written_backend(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->buf_written_backend);
}
Datum
pg_stat_get_buf_fsync_backend(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_checkpointer()->buf_fsync_backend);
}
Datum
pg_stat_get_buf_alloc(PG_FUNCTION_ARGS)
{
PG_RETURN_INT64(pgstat_fetch_stat_bgwriter()->buf_alloc);
}
/*
* Returns statistics of WAL activity
*/
Datum
pg_stat_get_wal(PG_FUNCTION_ARGS)
{
#define PG_STAT_GET_WAL_COLS 9
TupleDesc tupdesc;
Datum values[PG_STAT_GET_WAL_COLS] = {0};
bool nulls[PG_STAT_GET_WAL_COLS] = {0};
char buf[256];
PgStat_WalStats *wal_stats;
/* Initialise attributes information in the tuple descriptor */
tupdesc = CreateTemplateTupleDesc(PG_STAT_GET_WAL_COLS);
TupleDescInitEntry(tupdesc, (AttrNumber) 1, "wal_records",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 2, "wal_fpi",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 3, "wal_bytes",
NUMERICOID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 4, "wal_buffers_full",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 5, "wal_write",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 6, "wal_sync",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 7, "wal_write_time",
FLOAT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 8, "wal_sync_time",
FLOAT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 9, "stats_reset",
TIMESTAMPTZOID, -1, 0);
BlessTupleDesc(tupdesc);
/* Get statistics about WAL activity */
wal_stats = pgstat_fetch_stat_wal();
/* Fill values and NULLs */
values[0] = Int64GetDatum(wal_stats->wal_records);
values[1] = Int64GetDatum(wal_stats->wal_fpi);
/* Convert to numeric. */
snprintf(buf, sizeof buf, UINT64_FORMAT, wal_stats->wal_bytes);
values[2] = DirectFunctionCall3(numeric_in,
CStringGetDatum(buf),
ObjectIdGetDatum(0),
Int32GetDatum(-1));
values[3] = Int64GetDatum(wal_stats->wal_buffers_full);
values[4] = Int64GetDatum(wal_stats->wal_write);
values[5] = Int64GetDatum(wal_stats->wal_sync);
/* Convert counters from microsec to millisec for display */
values[6] = Float8GetDatum(((double) wal_stats->wal_write_time) / 1000.0);
values[7] = Float8GetDatum(((double) wal_stats->wal_sync_time) / 1000.0);
values[8] = TimestampTzGetDatum(wal_stats->stat_reset_timestamp);
/* Returns the record as Datum */
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
}
/*
* Returns statistics of SLRU caches.
*/
Datum
pg_stat_get_slru(PG_FUNCTION_ARGS)
{
#define PG_STAT_GET_SLRU_COLS 9
ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
int i;
PgStat_SLRUStats *stats;
InitMaterializedSRF(fcinfo, 0);
/* request SLRU stats from the cumulative stats system */
stats = pgstat_fetch_slru();
for (i = 0;; i++)
{
/* for each row */
Datum values[PG_STAT_GET_SLRU_COLS] = {0};
bool nulls[PG_STAT_GET_SLRU_COLS] = {0};
PgStat_SLRUStats stat;
const char *name;
name = pgstat_get_slru_name(i);
if (!name)
break;
stat = stats[i];
values[0] = PointerGetDatum(cstring_to_text(name));
values[1] = Int64GetDatum(stat.blocks_zeroed);
values[2] = Int64GetDatum(stat.blocks_hit);
values[3] = Int64GetDatum(stat.blocks_read);
values[4] = Int64GetDatum(stat.blocks_written);
values[5] = Int64GetDatum(stat.blocks_exists);
values[6] = Int64GetDatum(stat.flush);
values[7] = Int64GetDatum(stat.truncate);
values[8] = TimestampTzGetDatum(stat.stat_reset_timestamp);
Create routine able to set single-call SRFs for Materialize mode Set-returning functions that use the Materialize mode, creating a tuplestore to include all the tuples returned in a set rather than doing so in multiple calls, use roughly the same set of steps to prepare ReturnSetInfo for this job: - Check if ReturnSetInfo supports returning a tuplestore and if the materialize mode is enabled. - Create a tuplestore for all the tuples part of the returned set in the per-query memory context, stored in ReturnSetInfo->setResult. - Build a tuple descriptor mostly from get_call_result_type(), then stored in ReturnSetInfo->setDesc. Note that there are some cases where the SRF's tuple descriptor has to be the one specified by the function caller. This refactoring is done so as there are (well, should be) no behavior changes in any of the in-core functions refactored, and the centralized function that checks and sets up the function's ReturnSetInfo can be controlled with a set of bits32 options. Two of them prove to be necessary now: - SRF_SINGLE_USE_EXPECTED to use expectedDesc as tuple descriptor, as expected by the function's caller. - SRF_SINGLE_BLESS to validate the tuple descriptor for the SRF. The same initialization pattern is simplified in 28 places per my count as of src/backend/, shaving up to ~900 lines of code. These mostly come from the removal of the per-query initializations and the sanity checks now grouped in a single location. There are more locations that could be simplified in contrib/, that are left for a follow-up cleanup. fcc2817, 07daca5 and d61a361 have prepared the areas of the code related to this change, to ease this refactoring. Author: Melanie Plageman, Michael Paquier Reviewed-by: Álvaro Herrera, Justin Pryzby Discussion: https://postgr.es/m/CAAKRu_azyd1Z3W_r7Ou4sorTjRCs+PxeHw1CWJeXKofkE6TuZg@mail.gmail.com
3 years ago
tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
}
return (Datum) 0;
}
Datum
pg_stat_get_xact_numscans(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->t_counts.t_numscans);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_tuples_returned(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->t_counts.t_tuples_returned);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_tuples_fetched(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->t_counts.t_tuples_fetched);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_tuples_inserted(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
PgStat_TableXactStatus *trans;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
{
result = tabentry->t_counts.t_tuples_inserted;
/* live subtransactions' counts aren't in t_tuples_inserted yet */
for (trans = tabentry->trans; trans != NULL; trans = trans->upper)
result += trans->tuples_inserted;
}
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_tuples_updated(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
PgStat_TableXactStatus *trans;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
{
result = tabentry->t_counts.t_tuples_updated;
/* live subtransactions' counts aren't in t_tuples_updated yet */
for (trans = tabentry->trans; trans != NULL; trans = trans->upper)
result += trans->tuples_updated;
}
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_tuples_deleted(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
PgStat_TableXactStatus *trans;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
{
result = tabentry->t_counts.t_tuples_deleted;
/* live subtransactions' counts aren't in t_tuples_deleted yet */
for (trans = tabentry->trans; trans != NULL; trans = trans->upper)
result += trans->tuples_deleted;
}
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_tuples_hot_updated(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->t_counts.t_tuples_hot_updated);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_blocks_fetched(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->t_counts.t_blocks_fetched);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_blocks_hit(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 result;
PgStat_TableStatus *tabentry;
if ((tabentry = find_tabstat_entry(relid)) == NULL)
result = 0;
else
result = (int64) (tabentry->t_counts.t_blocks_hit);
PG_RETURN_INT64(result);
}
Datum
pg_stat_get_xact_function_calls(PG_FUNCTION_ARGS)
{
Oid funcid = PG_GETARG_OID(0);
PgStat_BackendFunctionEntry *funcentry;
if ((funcentry = find_funcstat_entry(funcid)) == NULL)
PG_RETURN_NULL();
PG_RETURN_INT64(funcentry->f_counts.f_numcalls);
}
Datum
pg_stat_get_xact_function_total_time(PG_FUNCTION_ARGS)
{
Oid funcid = PG_GETARG_OID(0);
PgStat_BackendFunctionEntry *funcentry;
if ((funcentry = find_funcstat_entry(funcid)) == NULL)
PG_RETURN_NULL();
PG_RETURN_FLOAT8(INSTR_TIME_GET_MILLISEC(funcentry->f_counts.f_total_time));
}
Datum
pg_stat_get_xact_function_self_time(PG_FUNCTION_ARGS)
{
Oid funcid = PG_GETARG_OID(0);
PgStat_BackendFunctionEntry *funcentry;
if ((funcentry = find_funcstat_entry(funcid)) == NULL)
PG_RETURN_NULL();
PG_RETURN_FLOAT8(INSTR_TIME_GET_MILLISEC(funcentry->f_counts.f_self_time));
}
/* Get the timestamp of the current statistics snapshot */
Datum
pg_stat_get_snapshot_timestamp(PG_FUNCTION_ARGS)
{
pgstat: store statistics in shared memory. Previously the statistics collector received statistics updates via UDP and shared statistics data by writing them out to temporary files regularly. These files can reach tens of megabytes and are written out up to twice a second. This has repeatedly prevented us from adding additional useful statistics. Now statistics are stored in shared memory. Statistics for variable-numbered objects are stored in a dshash hashtable (backed by dynamic shared memory). Fixed-numbered stats are stored in plain shared memory. The header for pgstat.c contains an overview of the architecture. The stats collector is not needed anymore, remove it. By utilizing the transactional statistics drop infrastructure introduced in a prior commit statistics entries cannot "leak" anymore. Previously leaked statistics were dropped by pgstat_vacuum_stat(), called from [auto-]vacuum. On systems with many small relations pgstat_vacuum_stat() could be quite expensive. Now that replicas drop statistics entries for dropped objects, it is not necessary anymore to reset stats when starting from a cleanly shut down replica. Subsequent commits will perform some further code cleanup, adapt docs and add tests. Bumps PGSTAT_FILE_FORMAT_ID. Author: Kyotaro Horiguchi <horikyota.ntt@gmail.com> Author: Andres Freund <andres@anarazel.de> Author: Melanie Plageman <melanieplageman@gmail.com> Reviewed-By: Andres Freund <andres@anarazel.de> Reviewed-By: Thomas Munro <thomas.munro@gmail.com> Reviewed-By: Justin Pryzby <pryzby@telsasoft.com> Reviewed-By: "David G. Johnston" <david.g.johnston@gmail.com> Reviewed-By: Tomas Vondra <tomas.vondra@2ndquadrant.com> (in a much earlier version) Reviewed-By: Arthur Zakirov <a.zakirov@postgrespro.ru> (in a much earlier version) Reviewed-By: Antonin Houska <ah@cybertec.at> (in a much earlier version) Discussion: https://postgr.es/m/20220303021600.hs34ghqcw6zcokdh@alap3.anarazel.de Discussion: https://postgr.es/m/20220308205351.2xcn6k4x5yivcxyd@alap3.anarazel.de Discussion: https://postgr.es/m/20210319235115.y3wz7hpnnrshdyv6@alap3.anarazel.de
3 years ago
bool have_snapshot;
TimestampTz ts;
ts = pgstat_get_stat_snapshot_timestamp(&have_snapshot);
if (!have_snapshot)
PG_RETURN_NULL();
PG_RETURN_TIMESTAMPTZ(ts);
}
/* Discard the active statistics snapshot */
Datum
pg_stat_clear_snapshot(PG_FUNCTION_ARGS)
{
pgstat_clear_snapshot();
PG_RETURN_VOID();
}
/* Force statistics to be reported at the next occasion */
Datum
pg_stat_force_next_flush(PG_FUNCTION_ARGS)
{
pgstat_force_next_flush();
PG_RETURN_VOID();
}
/* Reset all counters for the current database */
Datum
pg_stat_reset(PG_FUNCTION_ARGS)
{
pgstat_reset_counters();
PG_RETURN_VOID();
}
/* Reset some shared cluster-wide counters */
Datum
pg_stat_reset_shared(PG_FUNCTION_ARGS)
{
char *target = text_to_cstring(PG_GETARG_TEXT_PP(0));
if (strcmp(target, "archiver") == 0)
pgstat_reset_of_kind(PGSTAT_KIND_ARCHIVER);
else if (strcmp(target, "bgwriter") == 0)
{
/*
* Historically checkpointer was part of bgwriter, continue to reset
* both for now.
*/
pgstat_reset_of_kind(PGSTAT_KIND_BGWRITER);
pgstat_reset_of_kind(PGSTAT_KIND_CHECKPOINTER);
}
Prefetch data referenced by the WAL, take II. Introduce a new GUC recovery_prefetch. When enabled, look ahead in the WAL and try to initiate asynchronous reading of referenced data blocks that are not yet cached in our buffer pool. For now, this is done with posix_fadvise(), which has several caveats. Since not all OSes have that system call, "try" is provided so that it can be enabled where available. Better mechanisms for asynchronous I/O are possible in later work. Set to "try" for now for test coverage. Default setting to be finalized before release. The GUC wal_decode_buffer_size limits the distance we can look ahead in bytes of decoded data. The existing GUC maintenance_io_concurrency is used to limit the number of concurrent I/Os allowed, based on pessimistic heuristics used to infer that I/Os have begun and completed. We'll also not look more than maintenance_io_concurrency * 4 block references ahead. Reviewed-by: Julien Rouhaud <rjuju123@gmail.com> Reviewed-by: Tomas Vondra <tomas.vondra@2ndquadrant.com> Reviewed-by: Alvaro Herrera <alvherre@2ndquadrant.com> (earlier version) Reviewed-by: Andres Freund <andres@anarazel.de> (earlier version) Reviewed-by: Justin Pryzby <pryzby@telsasoft.com> (earlier version) Tested-by: Tomas Vondra <tomas.vondra@2ndquadrant.com> (earlier version) Tested-by: Jakub Wartak <Jakub.Wartak@tomtom.com> (earlier version) Tested-by: Dmitry Dolgov <9erthalion6@gmail.com> (earlier version) Tested-by: Sait Talha Nisanci <Sait.Nisanci@microsoft.com> (earlier version) Discussion: https://postgr.es/m/CA%2BhUKGJ4VJN8ttxScUFM8dOKX0BrBiboo5uz1cq%3DAovOddfHpA%40mail.gmail.com
3 years ago
else if (strcmp(target, "recovery_prefetch") == 0)
XLogPrefetchResetStats();
else if (strcmp(target, "wal") == 0)
pgstat_reset_of_kind(PGSTAT_KIND_WAL);
else
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("unrecognized reset target: \"%s\"", target),
Prefetch data referenced by the WAL, take II. Introduce a new GUC recovery_prefetch. When enabled, look ahead in the WAL and try to initiate asynchronous reading of referenced data blocks that are not yet cached in our buffer pool. For now, this is done with posix_fadvise(), which has several caveats. Since not all OSes have that system call, "try" is provided so that it can be enabled where available. Better mechanisms for asynchronous I/O are possible in later work. Set to "try" for now for test coverage. Default setting to be finalized before release. The GUC wal_decode_buffer_size limits the distance we can look ahead in bytes of decoded data. The existing GUC maintenance_io_concurrency is used to limit the number of concurrent I/Os allowed, based on pessimistic heuristics used to infer that I/Os have begun and completed. We'll also not look more than maintenance_io_concurrency * 4 block references ahead. Reviewed-by: Julien Rouhaud <rjuju123@gmail.com> Reviewed-by: Tomas Vondra <tomas.vondra@2ndquadrant.com> Reviewed-by: Alvaro Herrera <alvherre@2ndquadrant.com> (earlier version) Reviewed-by: Andres Freund <andres@anarazel.de> (earlier version) Reviewed-by: Justin Pryzby <pryzby@telsasoft.com> (earlier version) Tested-by: Tomas Vondra <tomas.vondra@2ndquadrant.com> (earlier version) Tested-by: Jakub Wartak <Jakub.Wartak@tomtom.com> (earlier version) Tested-by: Dmitry Dolgov <9erthalion6@gmail.com> (earlier version) Tested-by: Sait Talha Nisanci <Sait.Nisanci@microsoft.com> (earlier version) Discussion: https://postgr.es/m/CA%2BhUKGJ4VJN8ttxScUFM8dOKX0BrBiboo5uz1cq%3DAovOddfHpA%40mail.gmail.com
3 years ago
errhint("Target must be \"archiver\", \"bgwriter\", \"recovery_prefetch\", or \"wal\".")));
PG_RETURN_VOID();
}
/* Reset a single counter in the current database */
Datum
pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
{
Oid taboid = PG_GETARG_OID(0);
pgstat_reset(PGSTAT_KIND_RELATION, MyDatabaseId, taboid);
PG_RETURN_VOID();
}
Datum
pg_stat_reset_single_function_counters(PG_FUNCTION_ARGS)
{
Oid funcoid = PG_GETARG_OID(0);
pgstat_reset(PGSTAT_KIND_FUNCTION, MyDatabaseId, funcoid);
PG_RETURN_VOID();
}
/* Reset SLRU counters (a specific one or all of them). */
Datum
pg_stat_reset_slru(PG_FUNCTION_ARGS)
{
char *target = NULL;
if (PG_ARGISNULL(0))
pgstat_reset_of_kind(PGSTAT_KIND_SLRU);
else
{
target = text_to_cstring(PG_GETARG_TEXT_PP(0));
pgstat_reset_slru(target);
}
PG_RETURN_VOID();
}
/* Reset replication slots stats (a specific one or all of them). */
Datum
pg_stat_reset_replication_slot(PG_FUNCTION_ARGS)
{
char *target = NULL;
if (PG_ARGISNULL(0))
pgstat_reset_of_kind(PGSTAT_KIND_REPLSLOT);
else
{
target = text_to_cstring(PG_GETARG_TEXT_PP(0));
pgstat_reset_replslot(target);
}
PG_RETURN_VOID();
}
/* Reset subscription stats (a specific one or all of them) */
Datum
pg_stat_reset_subscription_stats(PG_FUNCTION_ARGS)
{
Oid subid;
if (PG_ARGISNULL(0))
{
/* Clear all subscription stats */
pgstat_reset_of_kind(PGSTAT_KIND_SUBSCRIPTION);
}
else
{
subid = PG_GETARG_OID(0);
if (!OidIsValid(subid))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid subscription OID %u", subid)));
pgstat_reset(PGSTAT_KIND_SUBSCRIPTION, InvalidOid, subid);
}
PG_RETURN_VOID();
}
Datum
pg_stat_get_archiver(PG_FUNCTION_ARGS)
{
TupleDesc tupdesc;
Datum values[7] = {0};
bool nulls[7] = {0};
PgStat_ArchiverStats *archiver_stats;
/* Initialise attributes information in the tuple descriptor */
Remove WITH OIDS support, change oid catalog column visibility. Previously tables declared WITH OIDS, including a significant fraction of the catalog tables, stored the oid column not as a normal column, but as part of the tuple header. This special column was not shown by default, which was somewhat odd, as it's often (consider e.g. pg_class.oid) one of the more important parts of a row. Neither pg_dump nor COPY included the contents of the oid column by default. The fact that the oid column was not an ordinary column necessitated a significant amount of special case code to support oid columns. That already was painful for the existing, but upcoming work aiming to make table storage pluggable, would have required expanding and duplicating that "specialness" significantly. WITH OIDS has been deprecated since 2005 (commit ff02d0a05280e0). Remove it. Removing includes: - CREATE TABLE and ALTER TABLE syntax for declaring the table to be WITH OIDS has been removed (WITH (oids[ = true]) will error out) - pg_dump does not support dumping tables declared WITH OIDS and will issue a warning when dumping one (and ignore the oid column). - restoring an pg_dump archive with pg_restore will warn when restoring a table with oid contents (and ignore the oid column) - COPY will refuse to load binary dump that includes oids. - pg_upgrade will error out when encountering tables declared WITH OIDS, they have to be altered to remove the oid column first. - Functionality to access the oid of the last inserted row (like plpgsql's RESULT_OID, spi's SPI_lastoid, ...) has been removed. The syntax for declaring a table WITHOUT OIDS (or WITH (oids = false) for CREATE TABLE) is still supported. While that requires a bit of support code, it seems unnecessary to break applications / dumps that do not use oids, and are explicit about not using them. The biggest user of WITH OID columns was postgres' catalog. This commit changes all 'magic' oid columns to be columns that are normally declared and stored. To reduce unnecessary query breakage all the newly added columns are still named 'oid', even if a table's column naming scheme would indicate 'reloid' or such. This obviously requires adapting a lot code, mostly replacing oid access via HeapTupleGetOid() with access to the underlying Form_pg_*->oid column. The bootstrap process now assigns oids for all oid columns in genbki.pl that do not have an explicit value (starting at the largest oid previously used), only oids assigned later by oids will be above FirstBootstrapObjectId. As the oid column now is a normal column the special bootstrap syntax for oids has been removed. Oids are not automatically assigned during insertion anymore, all backend code explicitly assigns oids with GetNewOidWithIndex(). For the rare case that insertions into the catalog via SQL are called for the new pg_nextoid() function can be used (which only works on catalog tables). The fact that oid columns on system tables are now normal columns means that they will be included in the set of columns expanded by * (i.e. SELECT * FROM pg_class will now include the table's oid, previously it did not). It'd not technically be hard to hide oid column by default, but that'd mean confusing behavior would either have to be carried forward forever, or it'd cause breakage down the line. While it's not unlikely that further adjustments are needed, the scope/invasiveness of the patch makes it worthwhile to get merge this now. It's painful to maintain externally, too complicated to commit after the code code freeze, and a dependency of a number of other patches. Catversion bump, for obvious reasons. Author: Andres Freund, with contributions by John Naylor Discussion: https://postgr.es/m/20180930034810.ywp2c7awz7opzcfr@alap3.anarazel.de
7 years ago
tupdesc = CreateTemplateTupleDesc(7);
TupleDescInitEntry(tupdesc, (AttrNumber) 1, "archived_count",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 2, "last_archived_wal",
TEXTOID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 3, "last_archived_time",
TIMESTAMPTZOID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 4, "failed_count",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 5, "last_failed_wal",
TEXTOID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 6, "last_failed_time",
TIMESTAMPTZOID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 7, "stats_reset",
TIMESTAMPTZOID, -1, 0);
BlessTupleDesc(tupdesc);
/* Get statistics about the archiver process */
archiver_stats = pgstat_fetch_stat_archiver();
/* Fill values and NULLs */
values[0] = Int64GetDatum(archiver_stats->archived_count);
if (*(archiver_stats->last_archived_wal) == '\0')
nulls[1] = true;
else
values[1] = CStringGetTextDatum(archiver_stats->last_archived_wal);
if (archiver_stats->last_archived_timestamp == 0)
nulls[2] = true;
else
values[2] = TimestampTzGetDatum(archiver_stats->last_archived_timestamp);
values[3] = Int64GetDatum(archiver_stats->failed_count);
if (*(archiver_stats->last_failed_wal) == '\0')
nulls[4] = true;
else
values[4] = CStringGetTextDatum(archiver_stats->last_failed_wal);
if (archiver_stats->last_failed_timestamp == 0)
nulls[5] = true;
else
values[5] = TimestampTzGetDatum(archiver_stats->last_failed_timestamp);
if (archiver_stats->stat_reset_timestamp == 0)
nulls[6] = true;
else
values[6] = TimestampTzGetDatum(archiver_stats->stat_reset_timestamp);
/* Returns the record as Datum */
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
}
/*
* Get the statistics for the replication slot. If the slot statistics is not
* available, return all-zeroes stats.
*/
Datum
pg_stat_get_replication_slot(PG_FUNCTION_ARGS)
{
#define PG_STAT_GET_REPLICATION_SLOT_COLS 10
text *slotname_text = PG_GETARG_TEXT_P(0);
NameData slotname;
TupleDesc tupdesc;
Datum values[PG_STAT_GET_REPLICATION_SLOT_COLS] = {0};
bool nulls[PG_STAT_GET_REPLICATION_SLOT_COLS] = {0};
PgStat_StatReplSlotEntry *slotent;
PgStat_StatReplSlotEntry allzero;
/* Initialise attributes information in the tuple descriptor */
tupdesc = CreateTemplateTupleDesc(PG_STAT_GET_REPLICATION_SLOT_COLS);
TupleDescInitEntry(tupdesc, (AttrNumber) 1, "slot_name",
TEXTOID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 2, "spill_txns",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 3, "spill_count",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 4, "spill_bytes",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 5, "stream_txns",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 6, "stream_count",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 7, "stream_bytes",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 8, "total_txns",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 9, "total_bytes",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 10, "stats_reset",
TIMESTAMPTZOID, -1, 0);
BlessTupleDesc(tupdesc);
namestrcpy(&slotname, text_to_cstring(slotname_text));
slotent = pgstat_fetch_replslot(slotname);
if (!slotent)
{
/*
* If the slot is not found, initialise its stats. This is possible if
* the create slot message is lost.
*/
memset(&allzero, 0, sizeof(PgStat_StatReplSlotEntry));
slotent = &allzero;
}
values[0] = CStringGetTextDatum(NameStr(slotname));
values[1] = Int64GetDatum(slotent->spill_txns);
values[2] = Int64GetDatum(slotent->spill_count);
values[3] = Int64GetDatum(slotent->spill_bytes);
values[4] = Int64GetDatum(slotent->stream_txns);
values[5] = Int64GetDatum(slotent->stream_count);
values[6] = Int64GetDatum(slotent->stream_bytes);
values[7] = Int64GetDatum(slotent->total_txns);
values[8] = Int64GetDatum(slotent->total_bytes);
if (slotent->stat_reset_timestamp == 0)
nulls[9] = true;
else
values[9] = TimestampTzGetDatum(slotent->stat_reset_timestamp);
/* Returns the record as Datum */
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
}
/*
* Get the subscription statistics for the given subscription. If the
* subscription statistics is not available, return all-zeros stats.
*/
Datum
pg_stat_get_subscription_stats(PG_FUNCTION_ARGS)
{
#define PG_STAT_GET_SUBSCRIPTION_STATS_COLS 4
Oid subid = PG_GETARG_OID(0);
TupleDesc tupdesc;
Datum values[PG_STAT_GET_SUBSCRIPTION_STATS_COLS] = {0};
bool nulls[PG_STAT_GET_SUBSCRIPTION_STATS_COLS] = {0};
PgStat_StatSubEntry *subentry;
PgStat_StatSubEntry allzero;
/* Get subscription stats */
subentry = pgstat_fetch_stat_subscription(subid);
/* Initialise attributes information in the tuple descriptor */
tupdesc = CreateTemplateTupleDesc(PG_STAT_GET_SUBSCRIPTION_STATS_COLS);
TupleDescInitEntry(tupdesc, (AttrNumber) 1, "subid",
OIDOID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 2, "apply_error_count",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 3, "sync_error_count",
INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, (AttrNumber) 4, "stats_reset",
TIMESTAMPTZOID, -1, 0);
BlessTupleDesc(tupdesc);
if (!subentry)
{
/* If the subscription is not found, initialise its stats */
memset(&allzero, 0, sizeof(PgStat_StatSubEntry));
subentry = &allzero;
}
/* subid */
values[0] = ObjectIdGetDatum(subid);
/* apply_error_count */
values[1] = Int64GetDatum(subentry->apply_error_count);
/* sync_error_count */
values[2] = Int64GetDatum(subentry->sync_error_count);
/* stats_reset */
if (subentry->stat_reset_timestamp == 0)
nulls[3] = true;
else
values[3] = TimestampTzGetDatum(subentry->stat_reset_timestamp);
/* Returns the record as Datum */
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
}
/*
* Checks for presence of stats for object with provided kind, database oid,
* object oid.
*
* This is useful for tests, but not really anything else. Therefore not
* documented.
*/
Datum
pg_stat_have_stats(PG_FUNCTION_ARGS)
{
char *stats_type = text_to_cstring(PG_GETARG_TEXT_P(0));
Oid dboid = PG_GETARG_OID(1);
Oid objoid = PG_GETARG_OID(2);
PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objoid));
}