* - Add a pgstat config column to pg_database, so this
* entire thing can be enabled/disabled on a per db basis.
*
- * Copyright (c) 2001-2012, PostgreSQL Global Development Group
+ * Copyright (c) 2001-2017, PostgreSQL Global Development Group
*
* src/backend/postmaster/pgstat.c
* ----------
#include <arpa/inet.h>
#include <signal.h>
#include <time.h>
+#ifdef HAVE_SYS_SELECT_H
+#include <sys/select.h>
+#endif
#include "pgstat.h"
#include "access/heapam.h"
+#include "access/htup_details.h"
#include "access/transam.h"
#include "access/twophase_rmgr.h"
#include "access/xact.h"
#include "catalog/pg_database.h"
#include "catalog/pg_proc.h"
-#include "libpq/ip.h"
+#include "common/ip.h"
#include "libpq/libpq.h"
#include "libpq/pqsignal.h"
#include "mb/pg_wchar.h"
#include "postmaster/autovacuum.h"
#include "postmaster/fork_process.h"
#include "postmaster/postmaster.h"
+#include "replication/walsender.h"
#include "storage/backendid.h"
+#include "storage/dsm.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/latch.h"
+#include "storage/lmgr.h"
#include "storage/pg_shmem.h"
#include "storage/procsignal.h"
+#include "storage/sinvaladt.h"
#include "utils/ascii.h"
#include "utils/guc.h"
#include "utils/memutils.h"
#include "utils/ps_status.h"
#include "utils/rel.h"
+#include "utils/snapmgr.h"
#include "utils/timestamp.h"
#include "utils/tqual.h"
-/* ----------
- * Paths for the statistics files (relative to installation's $PGDATA).
- * ----------
- */
-#define PGSTAT_STAT_PERMANENT_FILENAME "global/pgstat.stat"
-#define PGSTAT_STAT_PERMANENT_TMPFILE "global/pgstat.tmp"
-
/* ----------
* Timer definitions.
* ----------
*/
-#define PGSTAT_STAT_INTERVAL 500 /* Minimum time between stats file
- * updates; in milliseconds. */
+#define PGSTAT_STAT_INTERVAL 500 /* Minimum time between stats file
+ * updates; in milliseconds. */
-#define PGSTAT_RETRY_DELAY 10 /* How long to wait between checks for
- * a new file; in milliseconds. */
+#define PGSTAT_RETRY_DELAY 10 /* How long to wait between checks for a
+ * new file; in milliseconds. */
#define PGSTAT_MAX_WAIT_TIME 10000 /* Maximum time to wait for a stats
* file update; in milliseconds. */
-#define PGSTAT_INQ_INTERVAL 640 /* How often to ping the collector for
- * a new file; in milliseconds. */
+#define PGSTAT_INQ_INTERVAL 640 /* How often to ping the collector for a
+ * new file; in milliseconds. */
-#define PGSTAT_RESTART_INTERVAL 60 /* How often to attempt to restart a
- * failed statistics collector; in
- * seconds. */
+#define PGSTAT_RESTART_INTERVAL 60 /* How often to attempt to restart a
+ * failed statistics collector; in
+ * seconds. */
#define PGSTAT_POLL_LOOP_COUNT (PGSTAT_MAX_WAIT_TIME / PGSTAT_RETRY_DELAY)
#define PGSTAT_INQ_LOOP_COUNT (PGSTAT_INQ_INTERVAL / PGSTAT_RETRY_DELAY)
+/* Minimum receive buffer size for the collector's socket. */
+#define PGSTAT_MIN_RCVBUF (100 * 1024)
+
/* ----------
* The initial size hints for the hash tables used in the collector.
#define PGSTAT_FUNCTION_HASH_SIZE 512
+/* ----------
+ * Total number of backends including auxiliary
+ *
+ * We reserve a slot for each possible BackendId, plus one for each
+ * possible auxiliary process type. (This scheme assumes there is not
+ * more than one of any auxiliary process type at a time.) MaxBackends
+ * includes autovacuum workers and background workers as well.
+ * ----------
+ */
+#define NumBackendStatSlots (MaxBackends + NUM_AUXPROCTYPES)
+
+
/* ----------
* GUC parameters
* ----------
* Built from GUC parameter
* ----------
*/
+char *pgstat_stat_directory = NULL;
char *pgstat_stat_filename = NULL;
char *pgstat_stat_tmpname = NULL;
*/
NON_EXEC_STATIC pgsocket pgStatSock = PGINVALID_SOCKET;
-static Latch pgStatLatch;
-
static struct sockaddr_storage pgStatAddr;
static time_t last_pgstat_start_time;
static TabStatusArray *pgStatTabList = NULL;
+/*
+ * pgStatTabHash entry: map from relation OID to PgStat_TableStatus pointer
+ */
+typedef struct TabStatHashEntry
+{
+ Oid t_id;
+ PgStat_TableStatus *tsa_entry;
+} TabStatHashEntry;
+
+/*
+ * Hash table for O(1) t_id -> tsa_entry lookup
+ */
+static HTAB *pgStatTabHash = NULL;
+
/*
* Backends store per-function info that's waiting to be sent to the collector
* in this hash table (indexed by function OID).
{
int nest_level; /* subtransaction nest level */
struct PgStat_SubXactStatus *prev; /* higher-level subxact if any */
- PgStat_TableXactStatus *first; /* head of list for this subxact */
+ PgStat_TableXactStatus *first; /* head of list for this subxact */
} PgStat_SubXactStatus;
static PgStat_SubXactStatus *pgStatXactStack = NULL;
/* Record that's written to 2PC state file when pgstat state is persisted */
typedef struct TwoPhasePgStatRecord
{
- PgStat_Counter tuples_inserted; /* tuples inserted in xact */
- PgStat_Counter tuples_updated; /* tuples updated in xact */
- PgStat_Counter tuples_deleted; /* tuples deleted in xact */
+ PgStat_Counter tuples_inserted; /* tuples inserted in xact */
+ PgStat_Counter tuples_updated; /* tuples updated in xact */
+ PgStat_Counter tuples_deleted; /* tuples deleted in xact */
+ PgStat_Counter inserted_pre_trunc; /* tuples inserted prior to truncate */
+ PgStat_Counter updated_pre_trunc; /* tuples updated prior to truncate */
+ PgStat_Counter deleted_pre_trunc; /* tuples deleted prior to truncate */
Oid t_id; /* table's OID */
bool t_shared; /* is it a shared catalog? */
+ bool t_truncated; /* was the relation truncated? */
} TwoPhasePgStatRecord;
/*
*/
static MemoryContext pgStatLocalContext = NULL;
static HTAB *pgStatDBHash = NULL;
-static PgBackendStatus *localBackendStatusTable = NULL;
+
+/* Status for backends including auxiliary */
+static LocalPgBackendStatus *localBackendStatusTable = NULL;
+
+/* Total number of backends including auxiliary */
static int localNumBackends = 0;
/*
* Contains statistics that are not collected per database
* or per table.
*/
+static PgStat_ArchiverStats archiverStats;
static PgStat_GlobalStats globalStats;
-/* Last time the collector successfully wrote the stats file */
-static TimestampTz last_statwrite;
-
-/* Latest statistics request time from backends */
-static TimestampTz last_statrequest;
+/*
+ * List of OIDs of databases we need to write out. If an entry is InvalidOid,
+ * it means to write only the shared-catalog stats ("DB 0"); otherwise, we
+ * will write both that DB's data and the shared stats.
+ */
+static List *pending_write_requests = NIL;
+/* Signal handler flags */
static volatile bool need_exit = false;
static volatile bool got_SIGHUP = false;
static pid_t pgstat_forkexec(void);
#endif
-NON_EXEC_STATIC void PgstatCollectorMain(int argc, char *argv[]);
+NON_EXEC_STATIC void PgstatCollectorMain(int argc, char *argv[]) pg_attribute_noreturn();
static void pgstat_exit(SIGNAL_ARGS);
static void pgstat_beshutdown_hook(int code, Datum arg);
static void pgstat_sighup_handler(SIGNAL_ARGS);
static PgStat_StatDBEntry *pgstat_get_db_entry(Oid databaseid, bool create);
static PgStat_StatTabEntry *pgstat_get_tab_entry(PgStat_StatDBEntry *dbentry,
Oid tableoid, bool create);
-static void pgstat_write_statsfile(bool permanent);
-static HTAB *pgstat_read_statsfile(Oid onlydb, bool permanent);
+static void pgstat_write_statsfiles(bool permanent, bool allDbs);
+static void pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry, bool permanent);
+static HTAB *pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep);
+static void pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash, bool permanent);
static void backend_read_statsfile(void);
static void pgstat_read_current_status(void);
+static bool pgstat_write_statsfile_needed(void);
+static bool pgstat_db_requested(Oid databaseid);
+
static void pgstat_send_tabstat(PgStat_MsgTabstat *tsmsg);
static void pgstat_send_funcstats(void);
static HTAB *pgstat_collect_oids(Oid catalogid);
static void pgstat_setup_memcxt(void);
+static const char *pgstat_get_wait_activity(WaitEventActivity w);
+static const char *pgstat_get_wait_client(WaitEventClient w);
+static const char *pgstat_get_wait_ipc(WaitEventIPC w);
+static const char *pgstat_get_wait_timeout(WaitEventTimeout w);
+static const char *pgstat_get_wait_io(WaitEventIO w);
+
static void pgstat_setheader(PgStat_MsgHdr *hdr, StatMsgType mtype);
static void pgstat_send(void *msg, int len);
static void pgstat_recv_autovac(PgStat_MsgAutovacStart *msg, int len);
static void pgstat_recv_vacuum(PgStat_MsgVacuum *msg, int len);
static void pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len);
+static void pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len);
static void pgstat_recv_bgwriter(PgStat_MsgBgWriter *msg, int len);
static void pgstat_recv_funcstat(PgStat_MsgFuncstat *msg, int len);
static void pgstat_recv_funcpurge(PgStat_MsgFuncpurge *msg, int len);
static void pgstat_recv_deadlock(PgStat_MsgDeadlock *msg, int len);
static void pgstat_recv_tempfile(PgStat_MsgTempFile *msg, int len);
-
/* ------------------------------------------------------------
* Public functions called from postmaster follow
* ------------------------------------------------------------
#define TESTBYTEVAL ((char) 199)
+ /*
+ * This static assertion verifies that we didn't mess up the calculations
+ * involved in selecting maximum payload sizes for our UDP messages.
+ * Because the only consequence of overrunning PGSTAT_MAX_MSG_SIZE would
+ * be silent performance loss from fragmentation, it seems worth having a
+ * compile-time cross-check that we didn't.
+ */
+ StaticAssertStmt(sizeof(PgStat_Msg) <= PGSTAT_MAX_MSG_SIZE,
+ "maximum stats message size exceeds PGSTAT_MAX_MSG_SIZE");
+
/*
* Create the UDP socket for sending and receiving statistic messages
*/
hints.ai_flags = AI_PASSIVE;
- hints.ai_family = PF_UNSPEC;
+ hints.ai_family = AF_UNSPEC;
hints.ai_socktype = SOCK_DGRAM;
hints.ai_protocol = 0;
hints.ai_addrlen = 0;
* On some platforms, pg_getaddrinfo_all() may return multiple addresses
* only one of which will actually work (eg, both IPv6 and IPv4 addresses
* when kernel will reject IPv6). Worse, the failure may occur at the
- * bind() or perhaps even connect() stage. So we must loop through the
+ * bind() or perhaps even connect() stage. So we must loop through the
* results till we find a working combination. We will generate LOG
* messages, but no error, for bogus combinations.
*/
if (++tries > 1)
ereport(LOG,
- (errmsg("trying another address for the statistics collector")));
+ (errmsg("trying another address for the statistics collector")));
/*
* Create the socket.
{
ereport(LOG,
(errcode_for_socket_access(),
- errmsg("could not create socket for statistics collector: %m")));
+ errmsg("could not create socket for statistics collector: %m")));
continue;
}
{
ereport(LOG,
(errcode_for_socket_access(),
- errmsg("could not bind socket for statistics collector: %m")));
+ errmsg("could not bind socket for statistics collector: %m")));
closesocket(pgStatSock);
pgStatSock = PGINVALID_SOCKET;
continue;
}
alen = sizeof(pgStatAddr);
- if (getsockname(pgStatSock, (struct sockaddr *) & pgStatAddr, &alen) < 0)
+ if (getsockname(pgStatSock, (struct sockaddr *) &pgStatAddr, &alen) < 0)
{
ereport(LOG,
(errcode_for_socket_access(),
* provides a kernel-level check that only packets from this same
* address will be received.
*/
- if (connect(pgStatSock, (struct sockaddr *) & pgStatAddr, alen) < 0)
+ if (connect(pgStatSock, (struct sockaddr *) &pgStatAddr, alen) < 0)
{
ereport(LOG,
(errcode_for_socket_access(),
- errmsg("could not connect socket for statistics collector: %m")));
+ errmsg("could not connect socket for statistics collector: %m")));
closesocket(pgStatSock);
pgStatSock = PGINVALID_SOCKET;
continue;
goto startup_failed;
}
+ /*
+ * Try to ensure that the socket's receive buffer is at least
+ * PGSTAT_MIN_RCVBUF bytes, so that it won't easily overflow and lose
+ * data. Use of UDP protocol means that we are willing to lose data under
+ * heavy load, but we don't want it to happen just because of ridiculously
+ * small default buffer sizes (such as 8KB on older Windows versions).
+ */
+ {
+ int old_rcvbuf;
+ int new_rcvbuf;
+ ACCEPT_TYPE_ARG3 rcvbufsize = sizeof(old_rcvbuf);
+
+ if (getsockopt(pgStatSock, SOL_SOCKET, SO_RCVBUF,
+ (char *) &old_rcvbuf, &rcvbufsize) < 0)
+ {
+ elog(LOG, "getsockopt(SO_RCVBUF) failed: %m");
+ /* if we can't get existing size, always try to set it */
+ old_rcvbuf = 0;
+ }
+
+ new_rcvbuf = PGSTAT_MIN_RCVBUF;
+ if (old_rcvbuf < new_rcvbuf)
+ {
+ if (setsockopt(pgStatSock, SOL_SOCKET, SO_RCVBUF,
+ (char *) &new_rcvbuf, sizeof(new_rcvbuf)) < 0)
+ elog(LOG, "setsockopt(SO_RCVBUF) failed: %m");
+ }
+ }
+
pg_freeaddrinfo_all(hints.ai_family, addrs);
return;
startup_failed:
ereport(LOG,
- (errmsg("disabling statistics collector for lack of working socket")));
+ (errmsg("disabling statistics collector for lack of working socket")));
if (addrs)
pg_freeaddrinfo_all(hints.ai_family, addrs);
SetConfigOption("track_counts", "off", PGC_INTERNAL, PGC_S_OVERRIDE);
}
+/*
+ * subroutine for pgstat_reset_all
+ */
+static void
+pgstat_reset_remove_files(const char *directory)
+{
+ DIR *dir;
+ struct dirent *entry;
+ char fname[MAXPGPATH * 2];
+
+ dir = AllocateDir(directory);
+ while ((entry = ReadDir(dir, directory)) != NULL)
+ {
+ int nchars;
+ Oid tmp_oid;
+
+ /*
+ * Skip directory entries that don't match the file names we write.
+ * See get_dbstat_filename for the database-specific pattern.
+ */
+ if (strncmp(entry->d_name, "global.", 7) == 0)
+ nchars = 7;
+ else
+ {
+ nchars = 0;
+ (void) sscanf(entry->d_name, "db_%u.%n",
+ &tmp_oid, &nchars);
+ if (nchars <= 0)
+ continue;
+ /* %u allows leading whitespace, so reject that */
+ if (strchr("0123456789", entry->d_name[3]) == NULL)
+ continue;
+ }
+
+ if (strcmp(entry->d_name + nchars, "tmp") != 0 &&
+ strcmp(entry->d_name + nchars, "stat") != 0)
+ continue;
+
+ snprintf(fname, sizeof(fname), "%s/%s", directory,
+ entry->d_name);
+ unlink(fname);
+ }
+ FreeDir(dir);
+}
+
/*
* pgstat_reset_all() -
*
- * Remove the stats file. This is currently used only if WAL
+ * Remove the stats files. This is currently used only if WAL
* recovery is needed after a crash.
*/
void
pgstat_reset_all(void)
{
- unlink(pgstat_stat_filename);
- unlink(PGSTAT_STAT_PERMANENT_FILENAME);
+ pgstat_reset_remove_files(pgstat_stat_directory);
+ pgstat_reset_remove_files(PGSTAT_STAT_PERMANENT_DIRECTORY);
}
#ifdef EXEC_BACKEND
return postmaster_forkexec(ac, av);
}
-#endif /* EXEC_BACKEND */
+#endif /* EXEC_BACKEND */
/*
/*
* Do nothing if too soon since last collector start. This is a safety
* valve to protect against continuous respawn attempts if the collector
- * is dying immediately at launch. Note that since we will be re-called
+ * is dying immediately at launch. Note that since we will be re-called
* from the postmaster main loop, we will get another chance later.
*/
curtime = time(NULL);
#ifndef EXEC_BACKEND
case 0:
/* in postmaster child ... */
+ InitPostmasterChild();
+
/* Close the postmaster's sockets */
ClosePostmasterPorts(false);
- /* Lose the postmaster's on-exit routines */
- on_exit_reset();
-
/* Drop our connection to postmaster's shared memory, as well */
+ dsm_detach_all();
PGSharedMemoryDetach();
PgstatCollectorMain(0, NULL);
/* ----------
* pgstat_report_stat() -
*
- * Called from tcop/postgres.c to send the so far collected per-table
- * and function usage statistics to the collector. Note that this is
- * called only when not within a transaction, so it is fair to use
+ * Must be called by processes that performs DML: tcop/postgres.c, logical
+ * receiver processes, SPI worker, etc. to send the so far collected
+ * per-table and function usage statistics to the collector. Note that this
+ * is called only when not within a transaction, so it is fair to use
* transaction stop time as an approximation of current time.
* ----------
*/
int i;
/* Don't expend a clock check if nothing to do */
- if ((pgStatTabList == NULL || pgStatTabList->tsa_used == 0)
- && !have_function_stats)
+ if ((pgStatTabList == NULL || pgStatTabList->tsa_used == 0) &&
+ pgStatXactCommit == 0 && pgStatXactRollback == 0 &&
+ !have_function_stats)
return;
/*
return;
last_report = now;
+ /*
+ * Destroy pgStatTabHash before we start invalidating PgStat_TableEntry
+ * entries it points to. (Should we fail partway through the loop below,
+ * it's okay to have removed the hashtable already --- the only
+ * consequence is we'd get multiple entries for the same table in the
+ * pgStatTabList, and that's safe.)
+ */
+ if (pgStatTabHash)
+ hash_destroy(pgStatTabHash);
+ pgStatTabHash = NULL;
+
/*
* Scan through the TabStatusArray struct(s) to find tables that actually
* have counts, and build messages to send. We have to separate shared
}
/*
- * Send partial messages. If force is true, make sure that any pending
- * xact commit/abort gets counted, even if no table stats to send.
+ * Send partial messages. Make sure that any pending xact commit/abort
+ * gets counted, even if there are no table stats to send.
*/
if (regular_msg.m_nentries > 0 ||
- (force && (pgStatXactCommit > 0 || pgStatXactRollback > 0)))
+ pgStatXactCommit > 0 || pgStatXactRollback > 0)
pgstat_send_tabstat(®ular_msg);
if (shared_msg.m_nentries > 0)
pgstat_send_tabstat(&shared_msg);
if (msg.m_nentries >= PGSTAT_NUM_TABPURGE)
{
len = offsetof(PgStat_MsgTabpurge, m_tableid[0])
- +msg.m_nentries * sizeof(Oid);
+ + msg.m_nentries * sizeof(Oid);
pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE);
msg.m_databaseid = MyDatabaseId;
if (msg.m_nentries > 0)
{
len = offsetof(PgStat_MsgTabpurge, m_tableid[0])
- +msg.m_nentries * sizeof(Oid);
+ + msg.m_nentries * sizeof(Oid);
pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE);
msg.m_databaseid = MyDatabaseId;
if (f_msg.m_nentries >= PGSTAT_NUM_FUNCPURGE)
{
len = offsetof(PgStat_MsgFuncpurge, m_functionid[0])
- +f_msg.m_nentries * sizeof(Oid);
+ + f_msg.m_nentries * sizeof(Oid);
pgstat_send(&f_msg, len);
if (f_msg.m_nentries > 0)
{
len = offsetof(PgStat_MsgFuncpurge, m_functionid[0])
- +f_msg.m_nentries * sizeof(Oid);
+ + f_msg.m_nentries * sizeof(Oid);
pgstat_send(&f_msg, len);
}
*
* Collect the OIDs of all objects listed in the specified system catalog
* into a temporary hash table. Caller should hash_destroy the result
- * when done with it. (However, we make the table in CurrentMemoryContext
+ * when done with it. (However, we make the table in CurrentMemoryContext
* so that it will be freed properly in event of an error.)
* ----------
*/
Relation rel;
HeapScanDesc scan;
HeapTuple tup;
+ Snapshot snapshot;
memset(&hash_ctl, 0, sizeof(hash_ctl));
hash_ctl.keysize = sizeof(Oid);
hash_ctl.entrysize = sizeof(Oid);
- hash_ctl.hash = oid_hash;
hash_ctl.hcxt = CurrentMemoryContext;
htab = hash_create("Temporary table of OIDs",
PGSTAT_TAB_HASH_SIZE,
&hash_ctl,
- HASH_ELEM | HASH_FUNCTION | HASH_CONTEXT);
+ HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
rel = heap_open(catalogid, AccessShareLock);
- scan = heap_beginscan(rel, SnapshotNow, 0, NULL);
+ snapshot = RegisterSnapshot(GetLatestSnapshot());
+ scan = heap_beginscan(rel, snapshot, 0, NULL);
while ((tup = heap_getnext(scan, ForwardScanDirection)) != NULL)
{
Oid thisoid = HeapTupleGetOid(tup);
(void) hash_search(htab, (void *) &thisoid, HASH_ENTER, NULL);
}
heap_endscan(scan);
+ UnregisterSnapshot(snapshot);
heap_close(rel, AccessShareLock);
return htab;
msg.m_tableid[0] = relid;
msg.m_nentries = 1;
- len = offsetof(PgStat_MsgTabpurge, m_tableid[0]) +sizeof(Oid);
+ len = offsetof(PgStat_MsgTabpurge, m_tableid[0]) + sizeof(Oid);
pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE);
msg.m_databaseid = MyDatabaseId;
pgstat_send(&msg, len);
}
-#endif /* NOT_USED */
+#endif /* NOT_USED */
/* ----------
* pgstat_reset_counters() -
*
* Tell the statistics collector to reset counters for our database.
+ *
+ * Permission checking for this function is managed through the normal
+ * GRANT system.
* ----------
*/
void
if (pgStatSock == PGINVALID_SOCKET)
return;
- if (!superuser())
- ereport(ERROR,
- (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
- errmsg("must be superuser to reset statistics counters")));
-
pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETCOUNTER);
msg.m_databaseid = MyDatabaseId;
pgstat_send(&msg, sizeof(msg));
* pgstat_reset_shared_counters() -
*
* Tell the statistics collector to reset cluster-wide shared counters.
+ *
+ * Permission checking for this function is managed through the normal
+ * GRANT system.
* ----------
*/
void
if (pgStatSock == PGINVALID_SOCKET)
return;
- if (!superuser())
- ereport(ERROR,
- (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
- errmsg("must be superuser to reset statistics counters")));
-
- if (strcmp(target, "bgwriter") == 0)
+ if (strcmp(target, "archiver") == 0)
+ msg.m_resettarget = RESET_ARCHIVER;
+ else if (strcmp(target, "bgwriter") == 0)
msg.m_resettarget = RESET_BGWRITER;
else
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("unrecognized reset target: \"%s\"", target),
- errhint("Target must be \"bgwriter\".")));
+ errhint("Target must be \"archiver\" or \"bgwriter\".")));
pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETSHAREDCOUNTER);
pgstat_send(&msg, sizeof(msg));
* pgstat_reset_single_counter() -
*
* Tell the statistics collector to reset a single counter.
+ *
+ * Permission checking for this function is managed through the normal
+ * GRANT system.
* ----------
*/
void
if (pgStatSock == PGINVALID_SOCKET)
return;
- if (!superuser())
- ereport(ERROR,
- (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
- errmsg("must be superuser to reset statistics counters")));
-
pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETSINGLECOUNTER);
msg.m_databaseid = MyDatabaseId;
msg.m_resettype = type;
* ---------
*/
void
-pgstat_report_vacuum(Oid tableoid, bool shared, PgStat_Counter tuples)
+pgstat_report_vacuum(Oid tableoid, bool shared,
+ PgStat_Counter livetuples, PgStat_Counter deadtuples)
{
PgStat_MsgVacuum msg;
msg.m_tableoid = tableoid;
msg.m_autovacuum = IsAutoVacuumWorkerProcess();
msg.m_vacuumtime = GetCurrentTimestamp();
- msg.m_tuples = tuples;
+ msg.m_live_tuples = livetuples;
+ msg.m_dead_tuples = deadtuples;
pgstat_send(&msg, sizeof(msg));
}
* pgstat_report_analyze() -
*
* Tell the collector about the table we just analyzed.
+ *
+ * Caller must provide new live- and dead-tuples estimates, as well as a
+ * flag indicating whether to reset the changes_since_analyze counter.
* --------
*/
void
pgstat_report_analyze(Relation rel,
- PgStat_Counter livetuples, PgStat_Counter deadtuples)
+ PgStat_Counter livetuples, PgStat_Counter deadtuples,
+ bool resetcounter)
{
PgStat_MsgAnalyze msg;
* have counted such rows as live or dead respectively. Because we will
* report our counts of such rows at transaction end, we should subtract
* off these counts from what we send to the collector now, else they'll
- * be double-counted after commit. (This approach also ensures that the
+ * be double-counted after commit. (This approach also ensures that the
* collector ends up with the right numbers if we abort instead of
* committing.)
*/
msg.m_databaseid = rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId;
msg.m_tableoid = RelationGetRelid(rel);
msg.m_autovacuum = IsAutoVacuumWorkerProcess();
+ msg.m_resetcounter = resetcounter;
msg.m_analyzetime = GetCurrentTimestamp();
msg.m_live_tuples = livetuples;
msg.m_dead_tuples = deadtuples;
* pgstat_send_inquiry() -
*
* Notify collector that we need fresh data.
- * ts specifies the minimum acceptable timestamp for the stats file.
* ----------
*/
static void
-pgstat_send_inquiry(TimestampTz ts)
+pgstat_send_inquiry(TimestampTz clock_time, TimestampTz cutoff_time, Oid databaseid)
{
PgStat_MsgInquiry msg;
pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_INQUIRY);
- msg.inquiry_time = ts;
+ msg.clock_time = clock_time;
+ msg.cutoff_time = cutoff_time;
+ msg.databaseid = databaseid;
pgstat_send(&msg, sizeof(msg));
}
memset(&hash_ctl, 0, sizeof(hash_ctl));
hash_ctl.keysize = sizeof(Oid);
hash_ctl.entrysize = sizeof(PgStat_BackendFunctionEntry);
- hash_ctl.hash = oid_hash;
pgStatFunctions = hash_create("Function stat entries",
PGSTAT_FUNCTION_HASH_SIZE,
&hash_ctl,
- HASH_ELEM | HASH_FUNCTION);
+ HASH_ELEM | HASH_BLOBS);
}
/* Get the stats entry for this function, create if necessary */
/* We only count stats for things that have storage */
if (!(relkind == RELKIND_RELATION ||
+ relkind == RELKIND_MATVIEW ||
relkind == RELKIND_INDEX ||
relkind == RELKIND_TOASTVALUE ||
relkind == RELKIND_SEQUENCE))
static PgStat_TableStatus *
get_tabstat_entry(Oid rel_id, bool isshared)
{
+ TabStatHashEntry *hash_entry;
PgStat_TableStatus *entry;
TabStatusArray *tsa;
- TabStatusArray *prev_tsa;
- int i;
+ bool found;
/*
- * Search the already-used tabstat slots for this relation.
+ * Create hash table if we don't have it already.
*/
- prev_tsa = NULL;
- for (tsa = pgStatTabList; tsa != NULL; prev_tsa = tsa, tsa = tsa->tsa_next)
+ if (pgStatTabHash == NULL)
{
- for (i = 0; i < tsa->tsa_used; i++)
- {
- entry = &tsa->tsa_entries[i];
- if (entry->t_id == rel_id)
- return entry;
- }
+ HASHCTL ctl;
- if (tsa->tsa_used < TABSTAT_QUANTUM)
- {
- /*
- * It must not be present, but we found a free slot instead. Fine,
- * let's use this one. We assume the entry was already zeroed,
- * either at creation or after last use.
- */
- entry = &tsa->tsa_entries[tsa->tsa_used++];
- entry->t_id = rel_id;
- entry->t_shared = isshared;
- return entry;
- }
+ memset(&ctl, 0, sizeof(ctl));
+ ctl.keysize = sizeof(Oid);
+ ctl.entrysize = sizeof(TabStatHashEntry);
+
+ pgStatTabHash = hash_create("pgstat TabStatusArray lookup hash table",
+ TABSTAT_QUANTUM,
+ &ctl,
+ HASH_ELEM | HASH_BLOBS);
}
/*
- * We ran out of tabstat slots, so allocate more. Be sure they're zeroed.
+ * Find an entry or create a new one.
*/
- tsa = (TabStatusArray *) MemoryContextAllocZero(TopMemoryContext,
- sizeof(TabStatusArray));
- if (prev_tsa)
- prev_tsa->tsa_next = tsa;
- else
- pgStatTabList = tsa;
+ hash_entry = hash_search(pgStatTabHash, &rel_id, HASH_ENTER, &found);
+ if (!found)
+ {
+ /* initialize new entry with null pointer */
+ hash_entry->tsa_entry = NULL;
+ }
+
+ /*
+ * If entry is already valid, we're done.
+ */
+ if (hash_entry->tsa_entry)
+ return hash_entry->tsa_entry;
/*
- * Use the first entry of the new TabStatusArray.
+ * Locate the first pgStatTabList entry with free space, making a new list
+ * entry if needed. Note that we could get an OOM failure here, but if so
+ * we have left the hashtable and the list in a consistent state.
+ */
+ if (pgStatTabList == NULL)
+ {
+ /* Set up first pgStatTabList entry */
+ pgStatTabList = (TabStatusArray *)
+ MemoryContextAllocZero(TopMemoryContext,
+ sizeof(TabStatusArray));
+ }
+
+ tsa = pgStatTabList;
+ while (tsa->tsa_used >= TABSTAT_QUANTUM)
+ {
+ if (tsa->tsa_next == NULL)
+ tsa->tsa_next = (TabStatusArray *)
+ MemoryContextAllocZero(TopMemoryContext,
+ sizeof(TabStatusArray));
+ tsa = tsa->tsa_next;
+ }
+
+ /*
+ * Allocate a PgStat_TableStatus entry within this list entry. We assume
+ * the entry was already zeroed, either at creation or after last use.
*/
entry = &tsa->tsa_entries[tsa->tsa_used++];
entry->t_id = rel_id;
entry->t_shared = isshared;
+
+ /*
+ * Now we can fill the entry in pgStatTabHash.
+ */
+ hash_entry->tsa_entry = entry;
+
return entry;
}
* find_tabstat_entry - find any existing PgStat_TableStatus entry for rel
*
* If no entry, return NULL, don't create a new one
+ *
+ * Note: if we got an error in the most recent execution of pgstat_report_stat,
+ * it's possible that an entry exists but there's no hashtable entry for it.
+ * That's okay, we'll treat this case as "doesn't exist".
*/
PgStat_TableStatus *
find_tabstat_entry(Oid rel_id)
{
- PgStat_TableStatus *entry;
- TabStatusArray *tsa;
- int i;
+ TabStatHashEntry *hash_entry;
- for (tsa = pgStatTabList; tsa != NULL; tsa = tsa->tsa_next)
- {
- for (i = 0; i < tsa->tsa_used; i++)
- {
- entry = &tsa->tsa_entries[i];
- if (entry->t_id == rel_id)
- return entry;
- }
- }
+ /* If hashtable doesn't exist, there are no entries at all */
+ if (!pgStatTabHash)
+ return NULL;
- /* Not present */
- return NULL;
+ hash_entry = hash_search(pgStatTabHash, &rel_id, HASH_FIND, NULL);
+ if (!hash_entry)
+ return NULL;
+
+ /* Note that this step could also return NULL, but that's correct */
+ return hash_entry->tsa_entry;
}
/*
* pgstat_count_heap_insert - count a tuple insertion of n tuples
*/
void
-pgstat_count_heap_insert(Relation rel, int n)
+pgstat_count_heap_insert(Relation rel, PgStat_Counter n)
{
PgStat_TableStatus *pgstat_info = rel->pgstat_info;
}
}
+/*
+ * pgstat_truncate_save_counters
+ *
+ * Whenever a table is truncated, we save its i/u/d counters so that they can
+ * be cleared, and if the (sub)xact that executed the truncate later aborts,
+ * the counters can be restored to the saved (pre-truncate) values. Note we do
+ * this on the first truncate in any particular subxact level only.
+ */
+static void
+pgstat_truncate_save_counters(PgStat_TableXactStatus *trans)
+{
+ if (!trans->truncated)
+ {
+ trans->inserted_pre_trunc = trans->tuples_inserted;
+ trans->updated_pre_trunc = trans->tuples_updated;
+ trans->deleted_pre_trunc = trans->tuples_deleted;
+ trans->truncated = true;
+ }
+}
+
+/*
+ * pgstat_truncate_restore_counters - restore counters when a truncate aborts
+ */
+static void
+pgstat_truncate_restore_counters(PgStat_TableXactStatus *trans)
+{
+ if (trans->truncated)
+ {
+ trans->tuples_inserted = trans->inserted_pre_trunc;
+ trans->tuples_updated = trans->updated_pre_trunc;
+ trans->tuples_deleted = trans->deleted_pre_trunc;
+ }
+}
+
+/*
+ * pgstat_count_truncate - update tuple counters due to truncate
+ */
+void
+pgstat_count_truncate(Relation rel)
+{
+ PgStat_TableStatus *pgstat_info = rel->pgstat_info;
+
+ if (pgstat_info != NULL)
+ {
+ /* We have to log the effect at the proper transactional level */
+ int nest_level = GetCurrentTransactionNestLevel();
+
+ if (pgstat_info->trans == NULL ||
+ pgstat_info->trans->nest_level != nest_level)
+ add_tabstat_xact_level(pgstat_info, nest_level);
+
+ pgstat_truncate_save_counters(pgstat_info->trans);
+ pgstat_info->trans->tuples_inserted = 0;
+ pgstat_info->trans->tuples_updated = 0;
+ pgstat_info->trans->tuples_deleted = 0;
+ }
+}
+
/*
* pgstat_update_heap_dead_tuples - update dead-tuples count
*
Assert(trans->upper == NULL);
tabstat = trans->parent;
Assert(tabstat->trans == trans);
+ /* restore pre-truncate stats (if any) in case of aborted xact */
+ if (!isCommit)
+ pgstat_truncate_restore_counters(trans);
/* count attempted actions regardless of commit/abort */
tabstat->t_counts.t_tuples_inserted += trans->tuples_inserted;
tabstat->t_counts.t_tuples_updated += trans->tuples_updated;
tabstat->t_counts.t_tuples_deleted += trans->tuples_deleted;
if (isCommit)
{
+ tabstat->t_counts.t_truncated = trans->truncated;
+ if (trans->truncated)
+ {
+ /* forget live/dead stats seen by backend thus far */
+ tabstat->t_counts.t_delta_live_tuples = 0;
+ tabstat->t_counts.t_delta_dead_tuples = 0;
+ }
/* insert adds a live tuple, delete removes one */
tabstat->t_counts.t_delta_live_tuples +=
trans->tuples_inserted - trans->tuples_deleted;
{
if (trans->upper && trans->upper->nest_level == nestDepth - 1)
{
- trans->upper->tuples_inserted += trans->tuples_inserted;
- trans->upper->tuples_updated += trans->tuples_updated;
- trans->upper->tuples_deleted += trans->tuples_deleted;
+ if (trans->truncated)
+ {
+ /* propagate the truncate status one level up */
+ pgstat_truncate_save_counters(trans->upper);
+ /* replace upper xact stats with ours */
+ trans->upper->tuples_inserted = trans->tuples_inserted;
+ trans->upper->tuples_updated = trans->tuples_updated;
+ trans->upper->tuples_deleted = trans->tuples_deleted;
+ }
+ else
+ {
+ trans->upper->tuples_inserted += trans->tuples_inserted;
+ trans->upper->tuples_updated += trans->tuples_updated;
+ trans->upper->tuples_deleted += trans->tuples_deleted;
+ }
tabstat->trans = trans->upper;
pfree(trans);
}
* subtransaction
*/
+ /* first restore values obliterated by truncate */
+ pgstat_truncate_restore_counters(trans);
/* count attempted actions regardless of commit/abort */
tabstat->t_counts.t_tuples_inserted += trans->tuples_inserted;
tabstat->t_counts.t_tuples_updated += trans->tuples_updated;
record.tuples_inserted = trans->tuples_inserted;
record.tuples_updated = trans->tuples_updated;
record.tuples_deleted = trans->tuples_deleted;
+ record.inserted_pre_trunc = trans->inserted_pre_trunc;
+ record.updated_pre_trunc = trans->updated_pre_trunc;
+ record.deleted_pre_trunc = trans->deleted_pre_trunc;
record.t_id = tabstat->t_id;
record.t_shared = tabstat->t_shared;
+ record.t_truncated = trans->truncated;
RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
&record, sizeof(TwoPhasePgStatRecord));
* Clean up after successful PREPARE.
*
* All we need do here is unlink the transaction stats state from the
- * nontransactional state. The nontransactional action counts will be
+ * nontransactional state. The nontransactional action counts will be
* reported to the stats collector immediately, while the effects on live
* and dead tuple counts are preserved in the 2PC state file.
*
pgstat_info->t_counts.t_tuples_inserted += rec->tuples_inserted;
pgstat_info->t_counts.t_tuples_updated += rec->tuples_updated;
pgstat_info->t_counts.t_tuples_deleted += rec->tuples_deleted;
+ pgstat_info->t_counts.t_truncated = rec->t_truncated;
+ if (rec->t_truncated)
+ {
+ /* forget live/dead stats seen by backend thus far */
+ pgstat_info->t_counts.t_delta_live_tuples = 0;
+ pgstat_info->t_counts.t_delta_dead_tuples = 0;
+ }
pgstat_info->t_counts.t_delta_live_tuples +=
rec->tuples_inserted - rec->tuples_deleted;
pgstat_info->t_counts.t_delta_dead_tuples +=
pgstat_info = get_tabstat_entry(rec->t_id, rec->t_shared);
/* Same math as in AtEOXact_PgStat, abort case */
+ if (rec->t_truncated)
+ {
+ rec->tuples_inserted = rec->inserted_pre_trunc;
+ rec->tuples_updated = rec->updated_pre_trunc;
+ rec->tuples_deleted = rec->deleted_pre_trunc;
+ }
pgstat_info->t_counts.t_tuples_inserted += rec->tuples_inserted;
pgstat_info->t_counts.t_tuples_updated += rec->tuples_updated;
pgstat_info->t_counts.t_tuples_deleted += rec->tuples_deleted;
{
pgstat_read_current_status();
+ if (beid < 1 || beid > localNumBackends)
+ return NULL;
+
+ return &localBackendStatusTable[beid - 1].backendStatus;
+}
+
+
+/* ----------
+ * pgstat_fetch_stat_local_beentry() -
+ *
+ * Like pgstat_fetch_stat_beentry() but with locally computed additions (like
+ * xid and xmin values of the backend)
+ *
+ * NB: caller is responsible for a check if the user is permitted to see
+ * this info (especially the querystring).
+ * ----------
+ */
+LocalPgBackendStatus *
+pgstat_fetch_stat_local_beentry(int beid)
+{
+ pgstat_read_current_status();
+
if (beid < 1 || beid > localNumBackends)
return NULL;
return localNumBackends;
}
+/*
+ * ---------
+ * pgstat_fetch_stat_archiver() -
+ *
+ * Support function for the SQL-callable pgstat* functions. Returns
+ * a pointer to the archiver statistics struct.
+ * ---------
+ */
+PgStat_ArchiverStats *
+pgstat_fetch_stat_archiver(void)
+{
+ backend_read_statsfile();
+
+ return &archiverStats;
+}
+
+
/*
* ---------
* pgstat_fetch_global() -
static PgBackendStatus *BackendStatusArray = NULL;
static PgBackendStatus *MyBEEntry = NULL;
-static char *BackendClientHostnameBuffer = NULL;
static char *BackendAppnameBuffer = NULL;
+static char *BackendClientHostnameBuffer = NULL;
static char *BackendActivityBuffer = NULL;
static Size BackendActivityBufferSize = 0;
+#ifdef USE_SSL
+static PgBackendSSLStatus *BackendSslStatusBuffer = NULL;
+#endif
/*
{
Size size;
- size = mul_size(sizeof(PgBackendStatus), MaxBackends);
+ /* BackendStatusArray: */
+ size = mul_size(sizeof(PgBackendStatus), NumBackendStatSlots);
+ /* BackendAppnameBuffer: */
size = add_size(size,
- mul_size(NAMEDATALEN, MaxBackends));
+ mul_size(NAMEDATALEN, NumBackendStatSlots));
+ /* BackendClientHostnameBuffer: */
size = add_size(size,
- mul_size(pgstat_track_activity_query_size, MaxBackends));
+ mul_size(NAMEDATALEN, NumBackendStatSlots));
+ /* BackendActivityBuffer: */
size = add_size(size,
- mul_size(NAMEDATALEN, MaxBackends));
+ mul_size(pgstat_track_activity_query_size, NumBackendStatSlots));
+#ifdef USE_SSL
+ /* BackendSslStatusBuffer: */
+ size = add_size(size,
+ mul_size(sizeof(PgBackendSSLStatus), NumBackendStatSlots));
+#endif
return size;
}
char *buffer;
/* Create or attach to the shared array */
- size = mul_size(sizeof(PgBackendStatus), MaxBackends);
+ size = mul_size(sizeof(PgBackendStatus), NumBackendStatSlots);
BackendStatusArray = (PgBackendStatus *)
ShmemInitStruct("Backend Status Array", size, &found);
/* Initialize st_appname pointers. */
buffer = BackendAppnameBuffer;
- for (i = 0; i < MaxBackends; i++)
+ for (i = 0; i < NumBackendStatSlots; i++)
{
BackendStatusArray[i].st_appname = buffer;
buffer += NAMEDATALEN;
/* Initialize st_clienthostname pointers. */
buffer = BackendClientHostnameBuffer;
- for (i = 0; i < MaxBackends; i++)
+ for (i = 0; i < NumBackendStatSlots; i++)
{
BackendStatusArray[i].st_clienthostname = buffer;
buffer += NAMEDATALEN;
/* Create or attach to the shared activity buffer */
BackendActivityBufferSize = mul_size(pgstat_track_activity_query_size,
- MaxBackends);
+ NumBackendStatSlots);
BackendActivityBuffer = (char *)
ShmemInitStruct("Backend Activity Buffer",
BackendActivityBufferSize,
/* Initialize st_activity pointers. */
buffer = BackendActivityBuffer;
- for (i = 0; i < MaxBackends; i++)
+ for (i = 0; i < NumBackendStatSlots; i++)
{
- BackendStatusArray[i].st_activity = buffer;
+ BackendStatusArray[i].st_activity_raw = buffer;
buffer += pgstat_track_activity_query_size;
}
}
+
+#ifdef USE_SSL
+ /* Create or attach to the shared SSL status buffer */
+ size = mul_size(sizeof(PgBackendSSLStatus), NumBackendStatSlots);
+ BackendSslStatusBuffer = (PgBackendSSLStatus *)
+ ShmemInitStruct("Backend SSL Status Buffer", size, &found);
+
+ if (!found)
+ {
+ PgBackendSSLStatus *ptr;
+
+ MemSet(BackendSslStatusBuffer, 0, size);
+
+ /* Initialize st_sslstatus pointers. */
+ ptr = BackendSslStatusBuffer;
+ for (i = 0; i < NumBackendStatSlots; i++)
+ {
+ BackendStatusArray[i].st_sslstatus = ptr;
+ ptr++;
+ }
+ }
+#endif
}
* pgstat_initialize() -
*
* Initialize pgstats state, and set up our on-proc-exit hook.
- * Called from InitPostgres. MyBackendId must be set,
+ * Called from InitPostgres and AuxiliaryProcessMain. For auxiliary process,
+ * MyBackendId is invalid. Otherwise, MyBackendId must be set,
* but we must not have started any transaction yet (since the
* exit hook must run after the last transaction exit).
* NOTE: MyDatabaseId isn't set yet; so the shutdown hook has to be careful.
pgstat_initialize(void)
{
/* Initialize MyBEEntry */
- Assert(MyBackendId >= 1 && MyBackendId <= MaxBackends);
- MyBEEntry = &BackendStatusArray[MyBackendId - 1];
+ if (MyBackendId != InvalidBackendId)
+ {
+ Assert(MyBackendId >= 1 && MyBackendId <= MaxBackends);
+ MyBEEntry = &BackendStatusArray[MyBackendId - 1];
+ }
+ else
+ {
+ /* Must be an auxiliary process */
+ Assert(MyAuxProcType != NotAnAuxProcess);
+
+ /*
+ * Assign the MyBEEntry for an auxiliary process. Since it doesn't
+ * have a BackendId, the slot is statically allocated based on the
+ * auxiliary process type (MyAuxProcType). Backends use slots indexed
+ * in the range from 1 to MaxBackends (inclusive), so we use
+ * MaxBackends + AuxBackendType + 1 as the index of the slot for an
+ * auxiliary process.
+ */
+ MyBEEntry = &BackendStatusArray[MaxBackends + MyAuxProcType];
+ }
/* Set up a process-exit hook to clean up */
on_shmem_exit(pgstat_beshutdown_hook, 0);
*
* Initialize this backend's entry in the PgBackendStatus array.
* Called from InitPostgres.
- * MyDatabaseId, session userid, and application_name must be set
- * (hence, this cannot be combined with pgstat_initialize).
+ *
+ * Apart from auxiliary processes, MyBackendId, MyDatabaseId,
+ * session userid, and application_name must be set for a
+ * backend (hence, this cannot be combined with pgstat_initialize).
* ----------
*/
void
pgstat_bestart(void)
{
TimestampTz proc_start_timestamp;
- Oid userid;
SockAddr clientaddr;
volatile PgBackendStatus *beentry;
proc_start_timestamp = MyProcPort->SessionStartTime;
else
proc_start_timestamp = GetCurrentTimestamp();
- userid = GetSessionUserId();
/*
* We may not have a MyProcPort (eg, if this is the autovacuum process).
* cute.
*/
beentry = MyBEEntry;
+
+ /* pgstats state must be initialized from pgstat_initialize() */
+ Assert(beentry != NULL);
+
+ if (MyBackendId != InvalidBackendId)
+ {
+ if (IsAutoVacuumLauncherProcess())
+ {
+ /* Autovacuum Launcher */
+ beentry->st_backendType = B_AUTOVAC_LAUNCHER;
+ }
+ else if (IsAutoVacuumWorkerProcess())
+ {
+ /* Autovacuum Worker */
+ beentry->st_backendType = B_AUTOVAC_WORKER;
+ }
+ else if (am_walsender)
+ {
+ /* Wal sender */
+ beentry->st_backendType = B_WAL_SENDER;
+ }
+ else if (IsBackgroundWorker)
+ {
+ /* bgworker */
+ beentry->st_backendType = B_BG_WORKER;
+ }
+ else
+ {
+ /* client-backend */
+ beentry->st_backendType = B_BACKEND;
+ }
+ }
+ else
+ {
+ /* Must be an auxiliary process */
+ Assert(MyAuxProcType != NotAnAuxProcess);
+ switch (MyAuxProcType)
+ {
+ case StartupProcess:
+ beentry->st_backendType = B_STARTUP;
+ break;
+ case BgWriterProcess:
+ beentry->st_backendType = B_BG_WRITER;
+ break;
+ case CheckpointerProcess:
+ beentry->st_backendType = B_CHECKPOINTER;
+ break;
+ case WalWriterProcess:
+ beentry->st_backendType = B_WAL_WRITER;
+ break;
+ case WalReceiverProcess:
+ beentry->st_backendType = B_WAL_RECEIVER;
+ break;
+ default:
+ elog(FATAL, "unrecognized process type: %d",
+ (int) MyAuxProcType);
+ proc_exit(1);
+ }
+ }
+
do
{
- beentry->st_changecount++;
+ pgstat_increment_changecount_before(beentry);
} while ((beentry->st_changecount & 1) == 0);
beentry->st_procpid = MyProcPid;
beentry->st_state_start_timestamp = 0;
beentry->st_xact_start_timestamp = 0;
beentry->st_databaseid = MyDatabaseId;
- beentry->st_userid = userid;
+
+ /* We have userid for client-backends, wal-sender and bgworker processes */
+ if (beentry->st_backendType == B_BACKEND
+ || beentry->st_backendType == B_WAL_SENDER
+ || beentry->st_backendType == B_BG_WORKER)
+ beentry->st_userid = GetSessionUserId();
+ else
+ beentry->st_userid = InvalidOid;
+
beentry->st_clientaddr = clientaddr;
- beentry->st_clienthostname[0] = '\0';
- beentry->st_waiting = false;
+ if (MyProcPort && MyProcPort->remote_hostname)
+ strlcpy(beentry->st_clienthostname, MyProcPort->remote_hostname,
+ NAMEDATALEN);
+ else
+ beentry->st_clienthostname[0] = '\0';
+#ifdef USE_SSL
+ if (MyProcPort && MyProcPort->ssl != NULL)
+ {
+ beentry->st_ssl = true;
+ beentry->st_sslstatus->ssl_bits = be_tls_get_cipher_bits(MyProcPort);
+ beentry->st_sslstatus->ssl_compression = be_tls_get_compression(MyProcPort);
+ be_tls_get_version(MyProcPort, beentry->st_sslstatus->ssl_version, NAMEDATALEN);
+ be_tls_get_cipher(MyProcPort, beentry->st_sslstatus->ssl_cipher, NAMEDATALEN);
+ be_tls_get_peerdn_name(MyProcPort, beentry->st_sslstatus->ssl_clientdn, NAMEDATALEN);
+ }
+ else
+ {
+ beentry->st_ssl = false;
+ }
+#else
+ beentry->st_ssl = false;
+#endif
beentry->st_state = STATE_UNDEFINED;
beentry->st_appname[0] = '\0';
- beentry->st_activity[0] = '\0';
+ beentry->st_activity_raw[0] = '\0';
/* Also make sure the last byte in each string area is always 0 */
beentry->st_clienthostname[NAMEDATALEN - 1] = '\0';
beentry->st_appname[NAMEDATALEN - 1] = '\0';
- beentry->st_activity[pgstat_track_activity_query_size - 1] = '\0';
+ beentry->st_activity_raw[pgstat_track_activity_query_size - 1] = '\0';
+ beentry->st_progress_command = PROGRESS_COMMAND_INVALID;
+ beentry->st_progress_command_target = InvalidOid;
- beentry->st_changecount++;
- Assert((beentry->st_changecount & 1) == 0);
+ /*
+ * we don't zero st_progress_param here to save cycles; nobody should
+ * examine it until st_progress_command has been set to something other
+ * than PROGRESS_COMMAND_INVALID
+ */
- if (MyProcPort && MyProcPort->remote_hostname)
- strlcpy(beentry->st_clienthostname, MyProcPort->remote_hostname, NAMEDATALEN);
+ pgstat_increment_changecount_after(beentry);
/* Update app name to current GUC setting */
if (application_name)
* before and after. We use a volatile pointer here to ensure the
* compiler doesn't try to get cute.
*/
- beentry->st_changecount++;
+ pgstat_increment_changecount_before(beentry);
beentry->st_procpid = 0; /* mark invalid */
- beentry->st_changecount++;
- Assert((beentry->st_changecount & 1) == 0);
+ pgstat_increment_changecount_after(beentry);
}
* pgstat_report_activity() -
*
* Called from tcop/postgres.c to report what the backend is actually doing
- * (usually "<IDLE>" or the start of the query to be executed).
+ * (but note cmd_str can be NULL for certain cases).
*
* All updates of the status entry follow the protocol of bumping
* st_changecount before and after. We use a volatile pointer here to
if (!beentry)
return;
- /*
- * To minimize the time spent modifying the entry, fetch all the needed
- * data first.
- */
- current_timestamp = GetCurrentTimestamp();
-
- if (!pgstat_track_activities && beentry->st_state != STATE_DISABLED)
+ if (!pgstat_track_activities)
{
- /*
- * Track activities is disabled, but we have a non-disabled state set.
- * That means the status changed - so as our last update, tell the
- * collector that we disabled it and will no longer update.
- */
- beentry->st_changecount++;
- beentry->st_state = STATE_DISABLED;
- beentry->st_state_start_timestamp = current_timestamp;
- beentry->st_changecount++;
- Assert((beentry->st_changecount & 1) == 0);
+ if (beentry->st_state != STATE_DISABLED)
+ {
+ volatile PGPROC *proc = MyProc;
+
+ /*
+ * track_activities is disabled, but we last reported a
+ * non-disabled state. As our final update, change the state and
+ * clear fields we will not be updating anymore.
+ */
+ pgstat_increment_changecount_before(beentry);
+ beentry->st_state = STATE_DISABLED;
+ beentry->st_state_start_timestamp = 0;
+ beentry->st_activity_raw[0] = '\0';
+ beentry->st_activity_start_timestamp = 0;
+ /* st_xact_start_timestamp and wait_event_info are also disabled */
+ beentry->st_xact_start_timestamp = 0;
+ proc->wait_event_info = 0;
+ pgstat_increment_changecount_after(beentry);
+ }
return;
}
/*
- * Fetch more data before we start modifying the entry
+ * To minimize the time spent modifying the entry, fetch all the needed
+ * data first.
*/
start_timestamp = GetCurrentStatementStartTimestamp();
if (cmd_str != NULL)
{
- len = pg_mbcliplen(cmd_str, strlen(cmd_str),
- pgstat_track_activity_query_size - 1);
+ /*
+ * Compute length of to-be-stored string unaware of multi-byte
+ * characters. For speed reasons that'll get corrected on read, rather
+ * than computed every write.
+ */
+ len = Min(strlen(cmd_str), pgstat_track_activity_query_size - 1);
}
+ current_timestamp = GetCurrentTimestamp();
/*
* Now update the status entry
*/
- beentry->st_changecount++;
+ pgstat_increment_changecount_before(beentry);
beentry->st_state = state;
beentry->st_state_start_timestamp = current_timestamp;
if (cmd_str != NULL)
{
- memcpy((char *) beentry->st_activity, cmd_str, len);
- beentry->st_activity[len] = '\0';
+ memcpy((char *) beentry->st_activity_raw, cmd_str, len);
+ beentry->st_activity_raw[len] = '\0';
beentry->st_activity_start_timestamp = start_timestamp;
}
- beentry->st_changecount++;
- Assert((beentry->st_changecount & 1) == 0);
+ pgstat_increment_changecount_after(beentry);
+}
+
+/*-----------
+ * pgstat_progress_start_command() -
+ *
+ * Set st_progress_command (and st_progress_command_target) in own backend
+ * entry. Also, zero-initialize st_progress_param array.
+ *-----------
+ */
+void
+pgstat_progress_start_command(ProgressCommandType cmdtype, Oid relid)
+{
+ volatile PgBackendStatus *beentry = MyBEEntry;
+
+ if (!beentry || !pgstat_track_activities)
+ return;
+
+ pgstat_increment_changecount_before(beentry);
+ beentry->st_progress_command = cmdtype;
+ beentry->st_progress_command_target = relid;
+ MemSet(&beentry->st_progress_param, 0, sizeof(beentry->st_progress_param));
+ pgstat_increment_changecount_after(beentry);
+}
+
+/*-----------
+ * pgstat_progress_update_param() -
+ *
+ * Update index'th member in st_progress_param[] of own backend entry.
+ *-----------
+ */
+void
+pgstat_progress_update_param(int index, int64 val)
+{
+ volatile PgBackendStatus *beentry = MyBEEntry;
+
+ Assert(index >= 0 && index < PGSTAT_NUM_PROGRESS_PARAM);
+
+ if (!beentry || !pgstat_track_activities)
+ return;
+
+ pgstat_increment_changecount_before(beentry);
+ beentry->st_progress_param[index] = val;
+ pgstat_increment_changecount_after(beentry);
+}
+
+/*-----------
+ * pgstat_progress_update_multi_param() -
+ *
+ * Update multiple members in st_progress_param[] of own backend entry.
+ * This is atomic; readers won't see intermediate states.
+ *-----------
+ */
+void
+pgstat_progress_update_multi_param(int nparam, const int *index,
+ const int64 *val)
+{
+ volatile PgBackendStatus *beentry = MyBEEntry;
+ int i;
+
+ if (!beentry || !pgstat_track_activities || nparam == 0)
+ return;
+
+ pgstat_increment_changecount_before(beentry);
+
+ for (i = 0; i < nparam; ++i)
+ {
+ Assert(index[i] >= 0 && index[i] < PGSTAT_NUM_PROGRESS_PARAM);
+
+ beentry->st_progress_param[index[i]] = val[i];
+ }
+
+ pgstat_increment_changecount_after(beentry);
+}
+
+/*-----------
+ * pgstat_progress_end_command() -
+ *
+ * Reset st_progress_command (and st_progress_command_target) in own backend
+ * entry. This signals the end of the command.
+ *-----------
+ */
+void
+pgstat_progress_end_command(void)
+{
+ volatile PgBackendStatus *beentry = MyBEEntry;
+
+ if (!beentry)
+ return;
+ if (!pgstat_track_activities
+ && beentry->st_progress_command == PROGRESS_COMMAND_INVALID)
+ return;
+
+ pgstat_increment_changecount_before(beentry);
+ beentry->st_progress_command = PROGRESS_COMMAND_INVALID;
+ beentry->st_progress_command_target = InvalidOid;
+ pgstat_increment_changecount_after(beentry);
}
/* ----------
* st_changecount before and after. We use a volatile pointer here to
* ensure the compiler doesn't try to get cute.
*/
- beentry->st_changecount++;
+ pgstat_increment_changecount_before(beentry);
memcpy((char *) beentry->st_appname, appname, len);
beentry->st_appname[len] = '\0';
- beentry->st_changecount++;
- Assert((beentry->st_changecount & 1) == 0);
+ pgstat_increment_changecount_after(beentry);
}
/*
* st_changecount before and after. We use a volatile pointer here to
* ensure the compiler doesn't try to get cute.
*/
- beentry->st_changecount++;
+ pgstat_increment_changecount_before(beentry);
beentry->st_xact_start_timestamp = tstamp;
- beentry->st_changecount++;
- Assert((beentry->st_changecount & 1) == 0);
-}
-
-/* ----------
- * pgstat_report_waiting() -
- *
- * Called from lock manager to report beginning or end of a lock wait.
- *
- * NB: this *must* be able to survive being called before MyBEEntry has been
- * initialized.
- * ----------
- */
-void
-pgstat_report_waiting(bool waiting)
-{
- volatile PgBackendStatus *beentry = MyBEEntry;
-
- if (!pgstat_track_activities || !beentry)
- return;
-
- /*
- * Since this is a single-byte field in a struct that only this process
- * may modify, there seems no need to bother with the st_changecount
- * protocol. The update must appear atomic in any case.
- */
- beentry->st_waiting = waiting;
+ pgstat_increment_changecount_after(beentry);
}
-
/* ----------
* pgstat_read_current_status() -
*
pgstat_read_current_status(void)
{
volatile PgBackendStatus *beentry;
- PgBackendStatus *localtable;
- PgBackendStatus *localentry;
+ LocalPgBackendStatus *localtable;
+ LocalPgBackendStatus *localentry;
char *localappname,
*localactivity;
+#ifdef USE_SSL
+ PgBackendSSLStatus *localsslstatus;
+#endif
int i;
Assert(!pgStatRunningInCollector);
pgstat_setup_memcxt();
- localtable = (PgBackendStatus *)
+ localtable = (LocalPgBackendStatus *)
MemoryContextAlloc(pgStatLocalContext,
- sizeof(PgBackendStatus) * MaxBackends);
+ sizeof(LocalPgBackendStatus) * NumBackendStatSlots);
localappname = (char *)
MemoryContextAlloc(pgStatLocalContext,
- NAMEDATALEN * MaxBackends);
+ NAMEDATALEN * NumBackendStatSlots);
localactivity = (char *)
MemoryContextAlloc(pgStatLocalContext,
- pgstat_track_activity_query_size * MaxBackends);
+ pgstat_track_activity_query_size * NumBackendStatSlots);
+#ifdef USE_SSL
+ localsslstatus = (PgBackendSSLStatus *)
+ MemoryContextAlloc(pgStatLocalContext,
+ sizeof(PgBackendSSLStatus) * NumBackendStatSlots);
+#endif
+
localNumBackends = 0;
beentry = BackendStatusArray;
localentry = localtable;
- for (i = 1; i <= MaxBackends; i++)
+ for (i = 1; i <= NumBackendStatSlots; i++)
{
/*
* Follow the protocol of retrying if st_changecount changes while we
*/
for (;;)
{
- int save_changecount = beentry->st_changecount;
+ int before_changecount;
+ int after_changecount;
- localentry->st_procpid = beentry->st_procpid;
- if (localentry->st_procpid > 0)
+ pgstat_save_changecount_before(beentry, before_changecount);
+
+ localentry->backendStatus.st_procpid = beentry->st_procpid;
+ if (localentry->backendStatus.st_procpid > 0)
{
- memcpy(localentry, (char *) beentry, sizeof(PgBackendStatus));
+ memcpy(&localentry->backendStatus, (char *) beentry, sizeof(PgBackendStatus));
/*
* strcpy is safe even if the string is modified concurrently,
* because there's always a \0 at the end of the buffer.
*/
strcpy(localappname, (char *) beentry->st_appname);
- localentry->st_appname = localappname;
- strcpy(localactivity, (char *) beentry->st_activity);
- localentry->st_activity = localactivity;
+ localentry->backendStatus.st_appname = localappname;
+ strcpy(localactivity, (char *) beentry->st_activity_raw);
+ localentry->backendStatus.st_activity_raw = localactivity;
+ localentry->backendStatus.st_ssl = beentry->st_ssl;
+#ifdef USE_SSL
+ if (beentry->st_ssl)
+ {
+ memcpy(localsslstatus, beentry->st_sslstatus, sizeof(PgBackendSSLStatus));
+ localentry->backendStatus.st_sslstatus = localsslstatus;
+ }
+#endif
}
- if (save_changecount == beentry->st_changecount &&
- (save_changecount & 1) == 0)
+ pgstat_save_changecount_after(beentry, after_changecount);
+ if (before_changecount == after_changecount &&
+ (before_changecount & 1) == 0)
break;
/* Make sure we can break out of loop if stuck... */
beentry++;
/* Only valid entries get included into the local array */
- if (localentry->st_procpid > 0)
+ if (localentry->backendStatus.st_procpid > 0)
{
+ BackendIdGetTransactionIds(i,
+ &localentry->backend_xid,
+ &localentry->backend_xmin);
+
localentry++;
localappname += NAMEDATALEN;
localactivity += pgstat_track_activity_query_size;
+#ifdef USE_SSL
+ localsslstatus++;
+#endif
localNumBackends++;
}
}
localBackendStatusTable = localtable;
}
+/* ----------
+ * pgstat_get_wait_event_type() -
+ *
+ * Return a string representing the current wait event type, backend is
+ * waiting on.
+ */
+const char *
+pgstat_get_wait_event_type(uint32 wait_event_info)
+{
+ uint32 classId;
+ const char *event_type;
+
+ /* report process as not waiting. */
+ if (wait_event_info == 0)
+ return NULL;
+
+ classId = wait_event_info & 0xFF000000;
+
+ switch (classId)
+ {
+ case PG_WAIT_LWLOCK:
+ event_type = "LWLock";
+ break;
+ case PG_WAIT_LOCK:
+ event_type = "Lock";
+ break;
+ case PG_WAIT_BUFFER_PIN:
+ event_type = "BufferPin";
+ break;
+ case PG_WAIT_ACTIVITY:
+ event_type = "Activity";
+ break;
+ case PG_WAIT_CLIENT:
+ event_type = "Client";
+ break;
+ case PG_WAIT_EXTENSION:
+ event_type = "Extension";
+ break;
+ case PG_WAIT_IPC:
+ event_type = "IPC";
+ break;
+ case PG_WAIT_TIMEOUT:
+ event_type = "Timeout";
+ break;
+ case PG_WAIT_IO:
+ event_type = "IO";
+ break;
+ default:
+ event_type = "???";
+ break;
+ }
+
+ return event_type;
+}
+
+/* ----------
+ * pgstat_get_wait_event() -
+ *
+ * Return a string representing the current wait event, backend is
+ * waiting on.
+ */
+const char *
+pgstat_get_wait_event(uint32 wait_event_info)
+{
+ uint32 classId;
+ uint16 eventId;
+ const char *event_name;
+
+ /* report process as not waiting. */
+ if (wait_event_info == 0)
+ return NULL;
+
+ classId = wait_event_info & 0xFF000000;
+ eventId = wait_event_info & 0x0000FFFF;
+
+ switch (classId)
+ {
+ case PG_WAIT_LWLOCK:
+ event_name = GetLWLockIdentifier(classId, eventId);
+ break;
+ case PG_WAIT_LOCK:
+ event_name = GetLockNameFromTagType(eventId);
+ break;
+ case PG_WAIT_BUFFER_PIN:
+ event_name = "BufferPin";
+ break;
+ case PG_WAIT_ACTIVITY:
+ {
+ WaitEventActivity w = (WaitEventActivity) wait_event_info;
+
+ event_name = pgstat_get_wait_activity(w);
+ break;
+ }
+ case PG_WAIT_CLIENT:
+ {
+ WaitEventClient w = (WaitEventClient) wait_event_info;
+
+ event_name = pgstat_get_wait_client(w);
+ break;
+ }
+ case PG_WAIT_EXTENSION:
+ event_name = "Extension";
+ break;
+ case PG_WAIT_IPC:
+ {
+ WaitEventIPC w = (WaitEventIPC) wait_event_info;
+
+ event_name = pgstat_get_wait_ipc(w);
+ break;
+ }
+ case PG_WAIT_TIMEOUT:
+ {
+ WaitEventTimeout w = (WaitEventTimeout) wait_event_info;
+
+ event_name = pgstat_get_wait_timeout(w);
+ break;
+ }
+ case PG_WAIT_IO:
+ {
+ WaitEventIO w = (WaitEventIO) wait_event_info;
+
+ event_name = pgstat_get_wait_io(w);
+ break;
+ }
+ default:
+ event_name = "unknown wait event";
+ break;
+ }
+
+ return event_name;
+}
+
+/* ----------
+ * pgstat_get_wait_activity() -
+ *
+ * Convert WaitEventActivity to string.
+ * ----------
+ */
+static const char *
+pgstat_get_wait_activity(WaitEventActivity w)
+{
+ const char *event_name = "unknown wait event";
+
+ switch (w)
+ {
+ case WAIT_EVENT_ARCHIVER_MAIN:
+ event_name = "ArchiverMain";
+ break;
+ case WAIT_EVENT_AUTOVACUUM_MAIN:
+ event_name = "AutoVacuumMain";
+ break;
+ case WAIT_EVENT_BGWRITER_HIBERNATE:
+ event_name = "BgWriterHibernate";
+ break;
+ case WAIT_EVENT_BGWRITER_MAIN:
+ event_name = "BgWriterMain";
+ break;
+ case WAIT_EVENT_CHECKPOINTER_MAIN:
+ event_name = "CheckpointerMain";
+ break;
+ case WAIT_EVENT_LOGICAL_LAUNCHER_MAIN:
+ event_name = "LogicalLauncherMain";
+ break;
+ case WAIT_EVENT_LOGICAL_APPLY_MAIN:
+ event_name = "LogicalApplyMain";
+ break;
+ case WAIT_EVENT_PGSTAT_MAIN:
+ event_name = "PgStatMain";
+ break;
+ case WAIT_EVENT_RECOVERY_WAL_ALL:
+ event_name = "RecoveryWalAll";
+ break;
+ case WAIT_EVENT_RECOVERY_WAL_STREAM:
+ event_name = "RecoveryWalStream";
+ break;
+ case WAIT_EVENT_SYSLOGGER_MAIN:
+ event_name = "SysLoggerMain";
+ break;
+ case WAIT_EVENT_WAL_RECEIVER_MAIN:
+ event_name = "WalReceiverMain";
+ break;
+ case WAIT_EVENT_WAL_SENDER_MAIN:
+ event_name = "WalSenderMain";
+ break;
+ case WAIT_EVENT_WAL_WRITER_MAIN:
+ event_name = "WalWriterMain";
+ break;
+ /* no default case, so that compiler will warn */
+ }
+
+ return event_name;
+}
+
+/* ----------
+ * pgstat_get_wait_client() -
+ *
+ * Convert WaitEventClient to string.
+ * ----------
+ */
+static const char *
+pgstat_get_wait_client(WaitEventClient w)
+{
+ const char *event_name = "unknown wait event";
+
+ switch (w)
+ {
+ case WAIT_EVENT_CLIENT_READ:
+ event_name = "ClientRead";
+ break;
+ case WAIT_EVENT_CLIENT_WRITE:
+ event_name = "ClientWrite";
+ break;
+ case WAIT_EVENT_LIBPQWALRECEIVER_CONNECT:
+ event_name = "LibPQWalReceiverConnect";
+ break;
+ case WAIT_EVENT_LIBPQWALRECEIVER_RECEIVE:
+ event_name = "LibPQWalReceiverReceive";
+ break;
+ case WAIT_EVENT_SSL_OPEN_SERVER:
+ event_name = "SSLOpenServer";
+ break;
+ case WAIT_EVENT_WAL_RECEIVER_WAIT_START:
+ event_name = "WalReceiverWaitStart";
+ break;
+ case WAIT_EVENT_WAL_SENDER_WAIT_WAL:
+ event_name = "WalSenderWaitForWAL";
+ break;
+ case WAIT_EVENT_WAL_SENDER_WRITE_DATA:
+ event_name = "WalSenderWriteData";
+ break;
+ /* no default case, so that compiler will warn */
+ }
+
+ return event_name;
+}
+
+/* ----------
+ * pgstat_get_wait_ipc() -
+ *
+ * Convert WaitEventIPC to string.
+ * ----------
+ */
+static const char *
+pgstat_get_wait_ipc(WaitEventIPC w)
+{
+ const char *event_name = "unknown wait event";
+
+ switch (w)
+ {
+ case WAIT_EVENT_BGWORKER_SHUTDOWN:
+ event_name = "BgWorkerShutdown";
+ break;
+ case WAIT_EVENT_BGWORKER_STARTUP:
+ event_name = "BgWorkerStartup";
+ break;
+ case WAIT_EVENT_BTREE_PAGE:
+ event_name = "BtreePage";
+ break;
+ case WAIT_EVENT_EXECUTE_GATHER:
+ event_name = "ExecuteGather";
+ break;
+ case WAIT_EVENT_LOGICAL_SYNC_DATA:
+ event_name = "LogicalSyncData";
+ break;
+ case WAIT_EVENT_LOGICAL_SYNC_STATE_CHANGE:
+ event_name = "LogicalSyncStateChange";
+ break;
+ case WAIT_EVENT_MQ_INTERNAL:
+ event_name = "MessageQueueInternal";
+ break;
+ case WAIT_EVENT_MQ_PUT_MESSAGE:
+ event_name = "MessageQueuePutMessage";
+ break;
+ case WAIT_EVENT_MQ_RECEIVE:
+ event_name = "MessageQueueReceive";
+ break;
+ case WAIT_EVENT_MQ_SEND:
+ event_name = "MessageQueueSend";
+ break;
+ case WAIT_EVENT_PARALLEL_FINISH:
+ event_name = "ParallelFinish";
+ break;
+ case WAIT_EVENT_PARALLEL_BITMAP_SCAN:
+ event_name = "ParallelBitmapScan";
+ break;
+ case WAIT_EVENT_PROCARRAY_GROUP_UPDATE:
+ event_name = "ProcArrayGroupUpdate";
+ break;
+ case WAIT_EVENT_CLOG_GROUP_UPDATE:
+ event_name = "ClogGroupUpdate";
+ break;
+ case WAIT_EVENT_REPLICATION_ORIGIN_DROP:
+ event_name = "ReplicationOriginDrop";
+ break;
+ case WAIT_EVENT_REPLICATION_SLOT_DROP:
+ event_name = "ReplicationSlotDrop";
+ break;
+ case WAIT_EVENT_SAFE_SNAPSHOT:
+ event_name = "SafeSnapshot";
+ break;
+ case WAIT_EVENT_SYNC_REP:
+ event_name = "SyncRep";
+ break;
+ /* no default case, so that compiler will warn */
+ }
+
+ return event_name;
+}
+
+/* ----------
+ * pgstat_get_wait_timeout() -
+ *
+ * Convert WaitEventTimeout to string.
+ * ----------
+ */
+static const char *
+pgstat_get_wait_timeout(WaitEventTimeout w)
+{
+ const char *event_name = "unknown wait event";
+
+ switch (w)
+ {
+ case WAIT_EVENT_BASE_BACKUP_THROTTLE:
+ event_name = "BaseBackupThrottle";
+ break;
+ case WAIT_EVENT_PG_SLEEP:
+ event_name = "PgSleep";
+ break;
+ case WAIT_EVENT_RECOVERY_APPLY_DELAY:
+ event_name = "RecoveryApplyDelay";
+ break;
+ /* no default case, so that compiler will warn */
+ }
+
+ return event_name;
+}
+
+/* ----------
+ * pgstat_get_wait_io() -
+ *
+ * Convert WaitEventIO to string.
+ * ----------
+ */
+static const char *
+pgstat_get_wait_io(WaitEventIO w)
+{
+ const char *event_name = "unknown wait event";
+
+ switch (w)
+ {
+ case WAIT_EVENT_BUFFILE_READ:
+ event_name = "BufFileRead";
+ break;
+ case WAIT_EVENT_BUFFILE_WRITE:
+ event_name = "BufFileWrite";
+ break;
+ case WAIT_EVENT_CONTROL_FILE_READ:
+ event_name = "ControlFileRead";
+ break;
+ case WAIT_EVENT_CONTROL_FILE_SYNC:
+ event_name = "ControlFileSync";
+ break;
+ case WAIT_EVENT_CONTROL_FILE_SYNC_UPDATE:
+ event_name = "ControlFileSyncUpdate";
+ break;
+ case WAIT_EVENT_CONTROL_FILE_WRITE:
+ event_name = "ControlFileWrite";
+ break;
+ case WAIT_EVENT_CONTROL_FILE_WRITE_UPDATE:
+ event_name = "ControlFileWriteUpdate";
+ break;
+ case WAIT_EVENT_COPY_FILE_READ:
+ event_name = "CopyFileRead";
+ break;
+ case WAIT_EVENT_COPY_FILE_WRITE:
+ event_name = "CopyFileWrite";
+ break;
+ case WAIT_EVENT_DATA_FILE_EXTEND:
+ event_name = "DataFileExtend";
+ break;
+ case WAIT_EVENT_DATA_FILE_FLUSH:
+ event_name = "DataFileFlush";
+ break;
+ case WAIT_EVENT_DATA_FILE_IMMEDIATE_SYNC:
+ event_name = "DataFileImmediateSync";
+ break;
+ case WAIT_EVENT_DATA_FILE_PREFETCH:
+ event_name = "DataFilePrefetch";
+ break;
+ case WAIT_EVENT_DATA_FILE_READ:
+ event_name = "DataFileRead";
+ break;
+ case WAIT_EVENT_DATA_FILE_SYNC:
+ event_name = "DataFileSync";
+ break;
+ case WAIT_EVENT_DATA_FILE_TRUNCATE:
+ event_name = "DataFileTruncate";
+ break;
+ case WAIT_EVENT_DATA_FILE_WRITE:
+ event_name = "DataFileWrite";
+ break;
+ case WAIT_EVENT_DSM_FILL_ZERO_WRITE:
+ event_name = "DSMFillZeroWrite";
+ break;
+ case WAIT_EVENT_LOCK_FILE_ADDTODATADIR_READ:
+ event_name = "LockFileAddToDataDirRead";
+ break;
+ case WAIT_EVENT_LOCK_FILE_ADDTODATADIR_SYNC:
+ event_name = "LockFileAddToDataDirSync";
+ break;
+ case WAIT_EVENT_LOCK_FILE_ADDTODATADIR_WRITE:
+ event_name = "LockFileAddToDataDirWrite";
+ break;
+ case WAIT_EVENT_LOCK_FILE_CREATE_READ:
+ event_name = "LockFileCreateRead";
+ break;
+ case WAIT_EVENT_LOCK_FILE_CREATE_SYNC:
+ event_name = "LockFileCreateSync";
+ break;
+ case WAIT_EVENT_LOCK_FILE_CREATE_WRITE:
+ event_name = "LockFileCreateWRITE";
+ break;
+ case WAIT_EVENT_LOCK_FILE_RECHECKDATADIR_READ:
+ event_name = "LockFileReCheckDataDirRead";
+ break;
+ case WAIT_EVENT_LOGICAL_REWRITE_CHECKPOINT_SYNC:
+ event_name = "LogicalRewriteCheckpointSync";
+ break;
+ case WAIT_EVENT_LOGICAL_REWRITE_MAPPING_SYNC:
+ event_name = "LogicalRewriteMappingSync";
+ break;
+ case WAIT_EVENT_LOGICAL_REWRITE_MAPPING_WRITE:
+ event_name = "LogicalRewriteMappingWrite";
+ break;
+ case WAIT_EVENT_LOGICAL_REWRITE_SYNC:
+ event_name = "LogicalRewriteSync";
+ break;
+ case WAIT_EVENT_LOGICAL_REWRITE_TRUNCATE:
+ event_name = "LogicalRewriteTruncate";
+ break;
+ case WAIT_EVENT_LOGICAL_REWRITE_WRITE:
+ event_name = "LogicalRewriteWrite";
+ break;
+ case WAIT_EVENT_RELATION_MAP_READ:
+ event_name = "RelationMapRead";
+ break;
+ case WAIT_EVENT_RELATION_MAP_SYNC:
+ event_name = "RelationMapSync";
+ break;
+ case WAIT_EVENT_RELATION_MAP_WRITE:
+ event_name = "RelationMapWrite";
+ break;
+ case WAIT_EVENT_REORDER_BUFFER_READ:
+ event_name = "ReorderBufferRead";
+ break;
+ case WAIT_EVENT_REORDER_BUFFER_WRITE:
+ event_name = "ReorderBufferWrite";
+ break;
+ case WAIT_EVENT_REORDER_LOGICAL_MAPPING_READ:
+ event_name = "ReorderLogicalMappingRead";
+ break;
+ case WAIT_EVENT_REPLICATION_SLOT_READ:
+ event_name = "ReplicationSlotRead";
+ break;
+ case WAIT_EVENT_REPLICATION_SLOT_RESTORE_SYNC:
+ event_name = "ReplicationSlotRestoreSync";
+ break;
+ case WAIT_EVENT_REPLICATION_SLOT_SYNC:
+ event_name = "ReplicationSlotSync";
+ break;
+ case WAIT_EVENT_REPLICATION_SLOT_WRITE:
+ event_name = "ReplicationSlotWrite";
+ break;
+ case WAIT_EVENT_SLRU_FLUSH_SYNC:
+ event_name = "SLRUFlushSync";
+ break;
+ case WAIT_EVENT_SLRU_READ:
+ event_name = "SLRURead";
+ break;
+ case WAIT_EVENT_SLRU_SYNC:
+ event_name = "SLRUSync";
+ break;
+ case WAIT_EVENT_SLRU_WRITE:
+ event_name = "SLRUWrite";
+ break;
+ case WAIT_EVENT_SNAPBUILD_READ:
+ event_name = "SnapbuildRead";
+ break;
+ case WAIT_EVENT_SNAPBUILD_SYNC:
+ event_name = "SnapbuildSync";
+ break;
+ case WAIT_EVENT_SNAPBUILD_WRITE:
+ event_name = "SnapbuildWrite";
+ break;
+ case WAIT_EVENT_TIMELINE_HISTORY_FILE_SYNC:
+ event_name = "TimelineHistoryFileSync";
+ break;
+ case WAIT_EVENT_TIMELINE_HISTORY_FILE_WRITE:
+ event_name = "TimelineHistoryFileWrite";
+ break;
+ case WAIT_EVENT_TIMELINE_HISTORY_READ:
+ event_name = "TimelineHistoryRead";
+ break;
+ case WAIT_EVENT_TIMELINE_HISTORY_SYNC:
+ event_name = "TimelineHistorySync";
+ break;
+ case WAIT_EVENT_TIMELINE_HISTORY_WRITE:
+ event_name = "TimelineHistoryWrite";
+ break;
+ case WAIT_EVENT_TWOPHASE_FILE_READ:
+ event_name = "TwophaseFileRead";
+ break;
+ case WAIT_EVENT_TWOPHASE_FILE_SYNC:
+ event_name = "TwophaseFileSync";
+ break;
+ case WAIT_EVENT_TWOPHASE_FILE_WRITE:
+ event_name = "TwophaseFileWrite";
+ break;
+ case WAIT_EVENT_WALSENDER_TIMELINE_HISTORY_READ:
+ event_name = "WALSenderTimelineHistoryRead";
+ break;
+ case WAIT_EVENT_WAL_BOOTSTRAP_SYNC:
+ event_name = "WALBootstrapSync";
+ break;
+ case WAIT_EVENT_WAL_BOOTSTRAP_WRITE:
+ event_name = "WALBootstrapWrite";
+ break;
+ case WAIT_EVENT_WAL_COPY_READ:
+ event_name = "WALCopyRead";
+ break;
+ case WAIT_EVENT_WAL_COPY_SYNC:
+ event_name = "WALCopySync";
+ break;
+ case WAIT_EVENT_WAL_COPY_WRITE:
+ event_name = "WALCopyWrite";
+ break;
+ case WAIT_EVENT_WAL_INIT_SYNC:
+ event_name = "WALInitSync";
+ break;
+ case WAIT_EVENT_WAL_INIT_WRITE:
+ event_name = "WALInitWrite";
+ break;
+ case WAIT_EVENT_WAL_READ:
+ event_name = "WALRead";
+ break;
+ case WAIT_EVENT_WAL_SYNC_METHOD_ASSIGN:
+ event_name = "WALSyncMethodAssign";
+ break;
+ case WAIT_EVENT_WAL_WRITE:
+ event_name = "WALWrite";
+ break;
+
+ /* no default case, so that compiler will warn */
+ }
+
+ return event_name;
+}
+
/* ----------
* pgstat_get_backend_current_activity() -
*
* Return a string representing the current activity of the backend with
- * the specified PID. This looks directly at the BackendStatusArray,
+ * the specified PID. This looks directly at the BackendStatusArray,
* and so will provide current information regardless of the age of our
* transaction's snapshot of the status array.
*
* It is the caller's responsibility to invoke this only for backends whose
- * state is expected to remain stable while the result is in use. The
+ * state is expected to remain stable while the result is in use. The
* only current use is in deadlock reporting, where we can expect that
* the target backend is blocked on a lock. (There are corner cases
* where the target's wait could get aborted while we are looking at it,
for (;;)
{
- int save_changecount = vbeentry->st_changecount;
+ int before_changecount;
+ int after_changecount;
+
+ pgstat_save_changecount_before(vbeentry, before_changecount);
found = (vbeentry->st_procpid == pid);
- if (save_changecount == vbeentry->st_changecount &&
- (save_changecount & 1) == 0)
+ pgstat_save_changecount_after(vbeentry, after_changecount);
+
+ if (before_changecount == after_changecount &&
+ (before_changecount & 1) == 0)
break;
/* Make sure we can break out of loop if stuck... */
/* Now it is safe to use the non-volatile pointer */
if (checkUser && !superuser() && beentry->st_userid != GetUserId())
return "<insufficient privilege>";
- else if (*(beentry->st_activity) == '\0')
+ else if (*(beentry->st_activity_raw) == '\0')
return "<command string not enabled>";
else
- return beentry->st_activity;
+ {
+ /* this'll leak a bit of memory, but that seems acceptable */
+ return pgstat_clip_activity(beentry->st_activity_raw);
+ }
}
beentry++;
if (beentry->st_procpid == pid)
{
/* Read pointer just once, so it can't change after validation */
- const char *activity = beentry->st_activity;
+ const char *activity = beentry->st_activity_raw;
const char *activity_last;
/*
/*
* Copy only ASCII-safe characters so we don't run into encoding
- * problems when reporting the message; and be sure not to run
- * off the end of memory.
+ * problems when reporting the message; and be sure not to run off
+ * the end of memory. As only ASCII characters are reported, it
+ * doesn't seem necessary to perform multibyte aware clipping.
*/
ascii_safe_strlcpy(buffer, activity,
Min(buflen, pgstat_track_activity_query_size));
return NULL;
}
+const char *
+pgstat_get_backend_desc(BackendType backendType)
+{
+ const char *backendDesc = "unknown process type";
+
+ switch (backendType)
+ {
+ case B_AUTOVAC_LAUNCHER:
+ backendDesc = "autovacuum launcher";
+ break;
+ case B_AUTOVAC_WORKER:
+ backendDesc = "autovacuum worker";
+ break;
+ case B_BACKEND:
+ backendDesc = "client backend";
+ break;
+ case B_BG_WORKER:
+ backendDesc = "background worker";
+ break;
+ case B_BG_WRITER:
+ backendDesc = "background writer";
+ break;
+ case B_CHECKPOINTER:
+ backendDesc = "checkpointer";
+ break;
+ case B_STARTUP:
+ backendDesc = "startup";
+ break;
+ case B_WAL_RECEIVER:
+ backendDesc = "walreceiver";
+ break;
+ case B_WAL_SENDER:
+ backendDesc = "walsender";
+ break;
+ case B_WAL_WRITER:
+ backendDesc = "walwriter";
+ break;
+ }
+
+ return backendDesc;
+}
/* ------------------------------------------------------------
* Local support functions follow
#endif
}
+/* ----------
+ * pgstat_send_archiver() -
+ *
+ * Tell the collector about the WAL file that we successfully
+ * archived or failed to archive.
+ * ----------
+ */
+void
+pgstat_send_archiver(const char *xlog, bool failed)
+{
+ PgStat_MsgArchiver msg;
+
+ /*
+ * Prepare and send the message
+ */
+ pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_ARCHIVER);
+ msg.m_failed = failed;
+ StrNCpy(msg.m_xlog, xlog, sizeof(msg.m_xlog));
+ msg.m_timestamp = GetCurrentTimestamp();
+ pgstat_send(&msg, sizeof(msg));
+}
+
/* ----------
* pgstat_send_bgwriter() -
*
/* ----------
* PgstatCollectorMain() -
*
- * Start up the statistics collector process. This is the body of the
+ * Start up the statistics collector process. This is the body of the
* postmaster child process.
*
* The argc/argv parameters are valid only in EXEC_BACKEND case.
PgStat_Msg msg;
int wr;
- IsUnderPostmaster = true; /* we are a postmaster subprocess now */
-
- MyProcPid = getpid(); /* reset MyProcPid */
-
- MyStartTime = time(NULL); /* record Start Time for logging */
-
- /*
- * If possible, make this process a group leader, so that the postmaster
- * can signal any child processes too. (pgstat probably never has any
- * child processes, but for consistency we make all postmaster child
- * processes do this.)
- */
-#ifdef HAVE_SETSID
- if (setsid() < 0)
- elog(FATAL, "setsid() failed: %m");
-#endif
-
- /* Initialize private latch for use by signal handlers */
- InitLatch(&pgStatLatch);
-
/*
* Ignore all signals usually bound to some action in the postmaster,
* except SIGHUP and SIGQUIT. Note we don't need a SIGUSR1 handler to
- * support latch operations, because pgStatLatch is local not shared.
+ * support latch operations, because we only use a local latch.
*/
pqsignal(SIGHUP, pgstat_sighup_handler);
pqsignal(SIGINT, SIG_IGN);
/*
* Identify myself via ps
*/
- init_ps_display("stats collector process", "", "", "");
-
- /*
- * Arrange to write the initial status file right away
- */
- last_statrequest = GetCurrentTimestamp();
- last_statwrite = last_statrequest - 1;
+ init_ps_display("stats collector", "", "", "");
/*
- * Read in an existing statistics stats file or initialize the stats to
- * zero.
+ * Read in existing stats files or initialize the stats to zero.
*/
pgStatRunningInCollector = true;
- pgStatDBHash = pgstat_read_statsfile(InvalidOid, true);
+ pgStatDBHash = pgstat_read_statsfiles(InvalidOid, true, true);
/*
* Loop to process messages until we get SIGQUIT or detect ungraceful
* every message; instead, do that only after a recv() fails to obtain a
* message. (This effectively means that if backends are sending us stuff
* like mad, we won't notice postmaster death until things slack off a
- * bit; which seems fine.) To do that, we have an inner loop that
+ * bit; which seems fine.) To do that, we have an inner loop that
* iterates as long as recv() succeeds. We do recognize got_SIGHUP inside
* the inner loop, which means that such interrupts will get serviced but
* the latch won't get cleared until next time there is a break in the
for (;;)
{
/* Clear any already-pending wakeups */
- ResetLatch(&pgStatLatch);
+ ResetLatch(MyLatch);
/*
* Quit if we get SIGQUIT from the postmaster.
}
/*
- * Write the stats file if a new request has arrived that is not
- * satisfied by existing file.
+ * Write the stats file(s) if a new request has arrived that is
+ * not satisfied by existing file(s).
*/
- if (last_statwrite < last_statrequest)
- pgstat_write_statsfile(false);
+ if (pgstat_write_statsfile_needed())
+ pgstat_write_statsfiles(false, false);
/*
* Try to receive and process a message. This will not block,
* since the socket is set to non-blocking mode.
+ *
+ * XXX On Windows, we have to force pgwin32_recv to cooperate,
+ * despite the previous use of pg_set_noblock() on the socket.
+ * This is extremely broken and should be fixed someday.
*/
+#ifdef WIN32
+ pgwin32_noblock = 1;
+#endif
+
len = recv(pgStatSock, (char *) &msg,
sizeof(PgStat_Msg), 0);
+
+#ifdef WIN32
+ pgwin32_noblock = 0;
+#endif
+
if (len < 0)
{
if (errno == EAGAIN || errno == EWOULDBLOCK || errno == EINTR)
case PGSTAT_MTYPE_RESETSHAREDCOUNTER:
pgstat_recv_resetsharedcounter(
- (PgStat_MsgResetsharedcounter *) &msg,
+ (PgStat_MsgResetsharedcounter *) &msg,
len);
break;
case PGSTAT_MTYPE_RESETSINGLECOUNTER:
pgstat_recv_resetsinglecounter(
- (PgStat_MsgResetsinglecounter *) &msg,
+ (PgStat_MsgResetsinglecounter *) &msg,
len);
break;
pgstat_recv_analyze((PgStat_MsgAnalyze *) &msg, len);
break;
+ case PGSTAT_MTYPE_ARCHIVER:
+ pgstat_recv_archiver((PgStat_MsgArchiver *) &msg, len);
+ break;
+
case PGSTAT_MTYPE_BGWRITER:
pgstat_recv_bgwriter((PgStat_MsgBgWriter *) &msg, len);
break;
} /* end of inner message-processing loop */
/* Sleep until there's something to do */
- wr = WaitLatchOrSocket(&pgStatLatch,
+#ifndef WIN32
+ wr = WaitLatchOrSocket(MyLatch,
WL_LATCH_SET | WL_POSTMASTER_DEATH | WL_SOCKET_READABLE,
+ pgStatSock, -1L,
+ WAIT_EVENT_PGSTAT_MAIN);
+#else
+
+ /*
+ * Windows, at least in its Windows Server 2003 R2 incarnation,
+ * sometimes loses FD_READ events. Waking up and retrying the recv()
+ * fixes that, so don't sleep indefinitely. This is a crock of the
+ * first water, but until somebody wants to debug exactly what's
+ * happening there, this is the best we can do. The two-second
+ * timeout matches our pre-9.2 behavior, and needs to be short enough
+ * to not provoke "using stale statistics" complaints from
+ * backend_read_statsfile.
+ */
+ wr = WaitLatchOrSocket(MyLatch,
+ WL_LATCH_SET | WL_POSTMASTER_DEATH | WL_SOCKET_READABLE | WL_TIMEOUT,
pgStatSock,
- -1L);
+ 2 * 1000L /* msec */ ,
+ WAIT_EVENT_PGSTAT_MAIN);
+#endif
/*
* Emergency bailout if postmaster has died. This is to avoid the
/*
* Save the final stats to reuse at next startup.
*/
- pgstat_write_statsfile(true);
+ pgstat_write_statsfiles(true, true);
exit(0);
}
int save_errno = errno;
need_exit = true;
- SetLatch(&pgStatLatch);
+ SetLatch(MyLatch);
errno = save_errno;
}
int save_errno = errno;
got_SIGHUP = true;
- SetLatch(&pgStatLatch);
+ SetLatch(MyLatch);
errno = save_errno;
}
+/*
+ * Subroutine to clear stats in a database entry
+ *
+ * Tables and functions hashes are initialized to empty.
+ */
+static void
+reset_dbentry_counters(PgStat_StatDBEntry *dbentry)
+{
+ HASHCTL hash_ctl;
+
+ dbentry->n_xact_commit = 0;
+ dbentry->n_xact_rollback = 0;
+ dbentry->n_blocks_fetched = 0;
+ dbentry->n_blocks_hit = 0;
+ dbentry->n_tuples_returned = 0;
+ dbentry->n_tuples_fetched = 0;
+ dbentry->n_tuples_inserted = 0;
+ dbentry->n_tuples_updated = 0;
+ dbentry->n_tuples_deleted = 0;
+ dbentry->last_autovac_time = 0;
+ dbentry->n_conflict_tablespace = 0;
+ dbentry->n_conflict_lock = 0;
+ dbentry->n_conflict_snapshot = 0;
+ dbentry->n_conflict_bufferpin = 0;
+ dbentry->n_conflict_startup_deadlock = 0;
+ dbentry->n_temp_files = 0;
+ dbentry->n_temp_bytes = 0;
+ dbentry->n_deadlocks = 0;
+ dbentry->n_block_read_time = 0;
+ dbentry->n_block_write_time = 0;
+
+ dbentry->stat_reset_timestamp = GetCurrentTimestamp();
+ dbentry->stats_timestamp = 0;
+
+ memset(&hash_ctl, 0, sizeof(hash_ctl));
+ hash_ctl.keysize = sizeof(Oid);
+ hash_ctl.entrysize = sizeof(PgStat_StatTabEntry);
+ dbentry->tables = hash_create("Per-database table",
+ PGSTAT_TAB_HASH_SIZE,
+ &hash_ctl,
+ HASH_ELEM | HASH_BLOBS);
+
+ hash_ctl.keysize = sizeof(Oid);
+ hash_ctl.entrysize = sizeof(PgStat_StatFuncEntry);
+ dbentry->functions = hash_create("Per-database function",
+ PGSTAT_FUNCTION_HASH_SIZE,
+ &hash_ctl,
+ HASH_ELEM | HASH_BLOBS);
+}
/*
* Lookup the hash table entry for the specified database. If no hash
if (!create && !found)
return NULL;
- /* If not found, initialize the new one. */
+ /*
+ * If not found, initialize the new one. This creates empty hash tables
+ * for tables and functions, too.
+ */
if (!found)
- {
- HASHCTL hash_ctl;
-
- result->tables = NULL;
- result->functions = NULL;
- result->n_xact_commit = 0;
- result->n_xact_rollback = 0;
- result->n_blocks_fetched = 0;
- result->n_blocks_hit = 0;
- result->n_tuples_returned = 0;
- result->n_tuples_fetched = 0;
- result->n_tuples_inserted = 0;
- result->n_tuples_updated = 0;
- result->n_tuples_deleted = 0;
- result->last_autovac_time = 0;
- result->n_conflict_tablespace = 0;
- result->n_conflict_lock = 0;
- result->n_conflict_snapshot = 0;
- result->n_conflict_bufferpin = 0;
- result->n_conflict_startup_deadlock = 0;
- result->n_temp_files = 0;
- result->n_temp_bytes = 0;
- result->n_deadlocks = 0;
- result->n_block_read_time = 0;
- result->n_block_write_time = 0;
-
- result->stat_reset_timestamp = GetCurrentTimestamp();
-
- memset(&hash_ctl, 0, sizeof(hash_ctl));
- hash_ctl.keysize = sizeof(Oid);
- hash_ctl.entrysize = sizeof(PgStat_StatTabEntry);
- hash_ctl.hash = oid_hash;
- result->tables = hash_create("Per-database table",
- PGSTAT_TAB_HASH_SIZE,
- &hash_ctl,
- HASH_ELEM | HASH_FUNCTION);
-
- hash_ctl.keysize = sizeof(Oid);
- hash_ctl.entrysize = sizeof(PgStat_StatFuncEntry);
- hash_ctl.hash = oid_hash;
- result->functions = hash_create("Per-database function",
- PGSTAT_FUNCTION_HASH_SIZE,
- &hash_ctl,
- HASH_ELEM | HASH_FUNCTION);
- }
+ reset_dbentry_counters(result);
return result;
}
/* ----------
- * pgstat_write_statsfile() -
+ * pgstat_write_statsfiles() -
+ * Write the global statistics file, as well as requested DB files.
*
- * Tell the news.
- * If writing to the permanent file (happens when the collector is
- * shutting down only), remove the temporary file so that backends
- * starting up under a new postmaster can't read the old data before
- * the new collector is ready.
+ * 'permanent' specifies writing to the permanent files not temporary ones.
+ * When true (happens only when the collector is shutting down), also remove
+ * the temporary files so that backends starting up under a new postmaster
+ * can't read old data before the new collector is ready.
+ *
+ * When 'allDbs' is false, only the requested databases (listed in
+ * pending_write_requests) will be written; otherwise, all databases
+ * will be written.
* ----------
*/
static void
-pgstat_write_statsfile(bool permanent)
+pgstat_write_statsfiles(bool permanent, bool allDbs)
{
HASH_SEQ_STATUS hstat;
- HASH_SEQ_STATUS tstat;
- HASH_SEQ_STATUS fstat;
PgStat_StatDBEntry *dbentry;
- PgStat_StatTabEntry *tabentry;
- PgStat_StatFuncEntry *funcentry;
FILE *fpout;
int32 format_id;
const char *tmpfile = permanent ? PGSTAT_STAT_PERMANENT_TMPFILE : pgstat_stat_tmpname;
const char *statfile = permanent ? PGSTAT_STAT_PERMANENT_FILENAME : pgstat_stat_filename;
int rc;
+ elog(DEBUG2, "writing stats file \"%s\"", statfile);
+
/*
* Open the statistics temp file to write out the current values.
*/
rc = fwrite(&globalStats, sizeof(globalStats), 1, fpout);
(void) rc; /* we'll check for error with ferror */
+ /*
+ * Write archiver stats struct
+ */
+ rc = fwrite(&archiverStats, sizeof(archiverStats), 1, fpout);
+ (void) rc; /* we'll check for error with ferror */
+
/*
* Walk through the database table.
*/
while ((dbentry = (PgStat_StatDBEntry *) hash_seq_search(&hstat)) != NULL)
{
/*
- * Write out the DB entry including the number of live backends. We
- * don't write the tables or functions pointers, since they're of no
- * use to any other process.
- */
- fputc('D', fpout);
- rc = fwrite(dbentry, offsetof(PgStat_StatDBEntry, tables), 1, fpout);
- (void) rc; /* we'll check for error with ferror */
-
- /*
- * Walk through the database's access stats per table.
+ * Write out the table and function stats for this DB into the
+ * appropriate per-DB stat file, if required.
*/
- hash_seq_init(&tstat, dbentry->tables);
- while ((tabentry = (PgStat_StatTabEntry *) hash_seq_search(&tstat)) != NULL)
+ if (allDbs || pgstat_db_requested(dbentry->databaseid))
{
- fputc('T', fpout);
- rc = fwrite(tabentry, sizeof(PgStat_StatTabEntry), 1, fpout);
- (void) rc; /* we'll check for error with ferror */
- }
+ /* Make DB's timestamp consistent with the global stats */
+ dbentry->stats_timestamp = globalStats.stats_timestamp;
- /*
- * Walk through the database's function stats table.
- */
- hash_seq_init(&fstat, dbentry->functions);
- while ((funcentry = (PgStat_StatFuncEntry *) hash_seq_search(&fstat)) != NULL)
- {
- fputc('F', fpout);
- rc = fwrite(funcentry, sizeof(PgStat_StatFuncEntry), 1, fpout);
- (void) rc; /* we'll check for error with ferror */
+ pgstat_write_db_statsfile(dbentry, permanent);
}
/*
- * Mark the end of this DB
+ * Write out the DB entry. We don't write the tables or functions
+ * pointers, since they're of no use to any other process.
*/
- fputc('d', fpout);
+ fputc('D', fpout);
+ rc = fwrite(dbentry, offsetof(PgStat_StatDBEntry, tables), 1, fpout);
+ (void) rc; /* we'll check for error with ferror */
}
/*
{
ereport(LOG,
(errcode_for_file_access(),
- errmsg("could not write temporary statistics file \"%s\": %m",
- tmpfile)));
+ errmsg("could not write temporary statistics file \"%s\": %m",
+ tmpfile)));
FreeFile(fpout);
unlink(tmpfile);
}
{
ereport(LOG,
(errcode_for_file_access(),
- errmsg("could not close temporary statistics file \"%s\": %m",
- tmpfile)));
+ errmsg("could not close temporary statistics file \"%s\": %m",
+ tmpfile)));
unlink(tmpfile);
}
else if (rename(tmpfile, statfile) < 0)
tmpfile, statfile)));
unlink(tmpfile);
}
- else
+
+ if (permanent)
+ unlink(pgstat_stat_filename);
+
+ /*
+ * Now throw away the list of requests. Note that requests sent after we
+ * started the write are still waiting on the network socket.
+ */
+ list_free(pending_write_requests);
+ pending_write_requests = NIL;
+}
+
+/*
+ * return the filename for a DB stat file; filename is the output buffer,
+ * of length len.
+ */
+static void
+get_dbstat_filename(bool permanent, bool tempname, Oid databaseid,
+ char *filename, int len)
+{
+ int printed;
+
+ /* NB -- pgstat_reset_remove_files knows about the pattern this uses */
+ printed = snprintf(filename, len, "%s/db_%u.%s",
+ permanent ? PGSTAT_STAT_PERMANENT_DIRECTORY :
+ pgstat_stat_directory,
+ databaseid,
+ tempname ? "tmp" : "stat");
+ if (printed > len)
+ elog(ERROR, "overlength pgstat path");
+}
+
+/* ----------
+ * pgstat_write_db_statsfile() -
+ * Write the stat file for a single database.
+ *
+ * If writing to the permanent file (happens when the collector is
+ * shutting down only), remove the temporary file so that backends
+ * starting up under a new postmaster can't read the old data before
+ * the new collector is ready.
+ * ----------
+ */
+static void
+pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry, bool permanent)
+{
+ HASH_SEQ_STATUS tstat;
+ HASH_SEQ_STATUS fstat;
+ PgStat_StatTabEntry *tabentry;
+ PgStat_StatFuncEntry *funcentry;
+ FILE *fpout;
+ int32 format_id;
+ Oid dbid = dbentry->databaseid;
+ int rc;
+ char tmpfile[MAXPGPATH];
+ char statfile[MAXPGPATH];
+
+ get_dbstat_filename(permanent, true, dbid, tmpfile, MAXPGPATH);
+ get_dbstat_filename(permanent, false, dbid, statfile, MAXPGPATH);
+
+ elog(DEBUG2, "writing stats file \"%s\"", statfile);
+
+ /*
+ * Open the statistics temp file to write out the current values.
+ */
+ fpout = AllocateFile(tmpfile, PG_BINARY_W);
+ if (fpout == NULL)
{
- /*
- * Successful write, so update last_statwrite.
- */
- last_statwrite = globalStats.stats_timestamp;
+ ereport(LOG,
+ (errcode_for_file_access(),
+ errmsg("could not open temporary statistics file \"%s\": %m",
+ tmpfile)));
+ return;
+ }
- /*
- * If there is clock skew between backends and the collector, we could
- * receive a stats request time that's in the future. If so, complain
- * and reset last_statrequest. Resetting ensures that no inquiry
- * message can cause more than one stats file write to occur.
- */
- if (last_statrequest > last_statwrite)
- {
- char *reqtime;
- char *mytime;
+ /*
+ * Write the file header --- currently just a format ID.
+ */
+ format_id = PGSTAT_FILE_FORMAT_ID;
+ rc = fwrite(&format_id, sizeof(format_id), 1, fpout);
+ (void) rc; /* we'll check for error with ferror */
- /* Copy because timestamptz_to_str returns a static buffer */
- reqtime = pstrdup(timestamptz_to_str(last_statrequest));
- mytime = pstrdup(timestamptz_to_str(last_statwrite));
- elog(LOG, "last_statrequest %s is later than collector's time %s",
- reqtime, mytime);
- pfree(reqtime);
- pfree(mytime);
+ /*
+ * Walk through the database's access stats per table.
+ */
+ hash_seq_init(&tstat, dbentry->tables);
+ while ((tabentry = (PgStat_StatTabEntry *) hash_seq_search(&tstat)) != NULL)
+ {
+ fputc('T', fpout);
+ rc = fwrite(tabentry, sizeof(PgStat_StatTabEntry), 1, fpout);
+ (void) rc; /* we'll check for error with ferror */
+ }
- last_statrequest = last_statwrite;
- }
+ /*
+ * Walk through the database's function stats table.
+ */
+ hash_seq_init(&fstat, dbentry->functions);
+ while ((funcentry = (PgStat_StatFuncEntry *) hash_seq_search(&fstat)) != NULL)
+ {
+ fputc('F', fpout);
+ rc = fwrite(funcentry, sizeof(PgStat_StatFuncEntry), 1, fpout);
+ (void) rc; /* we'll check for error with ferror */
+ }
+
+ /*
+ * No more output to be done. Close the temp file and replace the old
+ * pgstat.stat with it. The ferror() check replaces testing for error
+ * after each individual fputc or fwrite above.
+ */
+ fputc('E', fpout);
+
+ if (ferror(fpout))
+ {
+ ereport(LOG,
+ (errcode_for_file_access(),
+ errmsg("could not write temporary statistics file \"%s\": %m",
+ tmpfile)));
+ FreeFile(fpout);
+ unlink(tmpfile);
+ }
+ else if (FreeFile(fpout) < 0)
+ {
+ ereport(LOG,
+ (errcode_for_file_access(),
+ errmsg("could not close temporary statistics file \"%s\": %m",
+ tmpfile)));
+ unlink(tmpfile);
+ }
+ else if (rename(tmpfile, statfile) < 0)
+ {
+ ereport(LOG,
+ (errcode_for_file_access(),
+ errmsg("could not rename temporary statistics file \"%s\" to \"%s\": %m",
+ tmpfile, statfile)));
+ unlink(tmpfile);
}
if (permanent)
- unlink(pgstat_stat_filename);
-}
+ {
+ get_dbstat_filename(false, false, dbid, statfile, MAXPGPATH);
+ elog(DEBUG2, "removing temporary stats file \"%s\"", statfile);
+ unlink(statfile);
+ }
+}
/* ----------
- * pgstat_read_statsfile() -
+ * pgstat_read_statsfiles() -
+ *
+ * Reads in some existing statistics collector files and returns the
+ * databases hash table that is the top level of the data.
*
- * Reads in an existing statistics collector file and initializes the
- * databases' hash table (whose entries point to the tables' hash tables).
+ * If 'onlydb' is not InvalidOid, it means we only want data for that DB
+ * plus the shared catalogs ("DB 0"). We'll still populate the DB hash
+ * table for all databases, but we don't bother even creating table/function
+ * hash tables for other databases.
+ *
+ * 'permanent' specifies reading from the permanent files not temporary ones.
+ * When true (happens only when the collector is starting up), remove the
+ * files after reading; the in-memory status is now authoritative, and the
+ * files would be out of date in case somebody else reads them.
+ *
+ * If a 'deep' read is requested, table/function stats are read, otherwise
+ * the table/function hash tables remain empty.
* ----------
*/
static HTAB *
-pgstat_read_statsfile(Oid onlydb, bool permanent)
+pgstat_read_statsfiles(Oid onlydb, bool permanent, bool deep)
{
PgStat_StatDBEntry *dbentry;
PgStat_StatDBEntry dbbuf;
- PgStat_StatTabEntry *tabentry;
- PgStat_StatTabEntry tabbuf;
- PgStat_StatFuncEntry funcbuf;
- PgStat_StatFuncEntry *funcentry;
HASHCTL hash_ctl;
HTAB *dbhash;
- HTAB *tabhash = NULL;
- HTAB *funchash = NULL;
FILE *fpin;
int32 format_id;
bool found;
memset(&hash_ctl, 0, sizeof(hash_ctl));
hash_ctl.keysize = sizeof(Oid);
hash_ctl.entrysize = sizeof(PgStat_StatDBEntry);
- hash_ctl.hash = oid_hash;
hash_ctl.hcxt = pgStatLocalContext;
dbhash = hash_create("Databases hash", PGSTAT_DB_HASH_SIZE, &hash_ctl,
- HASH_ELEM | HASH_FUNCTION | HASH_CONTEXT);
+ HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
/*
- * Clear out global statistics so they start from zero in case we can't
- * load an existing statsfile.
+ * Clear out global and archiver statistics so they start from zero in
+ * case we can't load an existing statsfile.
*/
memset(&globalStats, 0, sizeof(globalStats));
+ memset(&archiverStats, 0, sizeof(archiverStats));
/*
* Set the current timestamp (will be kept only in case we can't load an
- * existing statsfile.
+ * existing statsfile).
*/
globalStats.stat_reset_timestamp = GetCurrentTimestamp();
+ archiverStats.stat_reset_timestamp = globalStats.stat_reset_timestamp;
/*
- * Try to open the status file. If it doesn't exist, the backends simply
+ * Try to open the stats file. If it doesn't exist, the backends simply
* return zero for anything and the collector simply starts from scratch
* with empty counters.
*
/*
* Verify it's of the expected format.
*/
- if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id)
- || format_id != PGSTAT_FILE_FORMAT_ID)
+ if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id) ||
+ format_id != PGSTAT_FILE_FORMAT_ID)
{
ereport(pgStatRunningInCollector ? LOG : WARNING,
(errmsg("corrupted statistics file \"%s\"", statfile)));
{
ereport(pgStatRunningInCollector ? LOG : WARNING,
(errmsg("corrupted statistics file \"%s\"", statfile)));
+ memset(&globalStats, 0, sizeof(globalStats));
+ goto done;
+ }
+
+ /*
+ * In the collector, disregard the timestamp we read from the permanent
+ * stats file; we should be willing to write a temp stats file immediately
+ * upon the first request from any backend. This only matters if the old
+ * file's timestamp is less than PGSTAT_STAT_INTERVAL ago, but that's not
+ * an unusual scenario.
+ */
+ if (pgStatRunningInCollector)
+ globalStats.stats_timestamp = 0;
+
+ /*
+ * Read archiver stats struct
+ */
+ if (fread(&archiverStats, 1, sizeof(archiverStats), fpin) != sizeof(archiverStats))
+ {
+ ereport(pgStatRunningInCollector ? LOG : WARNING,
+ (errmsg("corrupted statistics file \"%s\"", statfile)));
+ memset(&archiverStats, 0, sizeof(archiverStats));
goto done;
}
{
/*
* 'D' A PgStat_StatDBEntry struct describing a database
- * follows. Subsequently, zero to many 'T' and 'F' entries
- * will follow until a 'd' is encountered.
+ * follows.
*/
case 'D':
if (fread(&dbbuf, 1, offsetof(PgStat_StatDBEntry, tables),
* Add to the DB hash
*/
dbentry = (PgStat_StatDBEntry *) hash_search(dbhash,
- (void *) &dbbuf.databaseid,
+ (void *) &dbbuf.databaseid,
HASH_ENTER,
&found);
if (found)
dbentry->functions = NULL;
/*
- * Don't collect tables if not the requested DB (or the
- * shared-table info)
+ * In the collector, disregard the timestamp we read from the
+ * permanent stats file; we should be willing to write a temp
+ * stats file immediately upon the first request from any
+ * backend.
+ */
+ if (pgStatRunningInCollector)
+ dbentry->stats_timestamp = 0;
+
+ /*
+ * Don't create tables/functions hashtables for uninteresting
+ * databases.
*/
if (onlydb != InvalidOid)
{
memset(&hash_ctl, 0, sizeof(hash_ctl));
hash_ctl.keysize = sizeof(Oid);
hash_ctl.entrysize = sizeof(PgStat_StatTabEntry);
- hash_ctl.hash = oid_hash;
hash_ctl.hcxt = pgStatLocalContext;
dbentry->tables = hash_create("Per-database table",
PGSTAT_TAB_HASH_SIZE,
&hash_ctl,
- HASH_ELEM | HASH_FUNCTION | HASH_CONTEXT);
+ HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
+
+ hash_ctl.keysize = sizeof(Oid);
+ hash_ctl.entrysize = sizeof(PgStat_StatFuncEntry);
+ hash_ctl.hcxt = pgStatLocalContext;
+ dbentry->functions = hash_create("Per-database function",
+ PGSTAT_FUNCTION_HASH_SIZE,
+ &hash_ctl,
+ HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
+
+ /*
+ * If requested, read the data from the database-specific
+ * file. Otherwise we just leave the hashtables empty.
+ */
+ if (deep)
+ pgstat_read_db_statsfile(dbentry->databaseid,
+ dbentry->tables,
+ dbentry->functions,
+ permanent);
+
+ break;
+
+ case 'E':
+ goto done;
+
+ default:
+ ereport(pgStatRunningInCollector ? LOG : WARNING,
+ (errmsg("corrupted statistics file \"%s\"",
+ statfile)));
+ goto done;
+ }
+ }
+
+done:
+ FreeFile(fpin);
+
+ /* If requested to read the permanent file, also get rid of it. */
+ if (permanent)
+ {
+ elog(DEBUG2, "removing permanent stats file \"%s\"", statfile);
+ unlink(statfile);
+ }
+
+ return dbhash;
+}
+
+
+/* ----------
+ * pgstat_read_db_statsfile() -
+ *
+ * Reads in the existing statistics collector file for the given database,
+ * filling the passed-in tables and functions hash tables.
+ *
+ * As in pgstat_read_statsfiles, if the permanent file is requested, it is
+ * removed after reading.
+ *
+ * Note: this code has the ability to skip storing per-table or per-function
+ * data, if NULL is passed for the corresponding hashtable. That's not used
+ * at the moment though.
+ * ----------
+ */
+static void
+pgstat_read_db_statsfile(Oid databaseid, HTAB *tabhash, HTAB *funchash,
+ bool permanent)
+{
+ PgStat_StatTabEntry *tabentry;
+ PgStat_StatTabEntry tabbuf;
+ PgStat_StatFuncEntry funcbuf;
+ PgStat_StatFuncEntry *funcentry;
+ FILE *fpin;
+ int32 format_id;
+ bool found;
+ char statfile[MAXPGPATH];
- hash_ctl.keysize = sizeof(Oid);
- hash_ctl.entrysize = sizeof(PgStat_StatFuncEntry);
- hash_ctl.hash = oid_hash;
- hash_ctl.hcxt = pgStatLocalContext;
- dbentry->functions = hash_create("Per-database function",
- PGSTAT_FUNCTION_HASH_SIZE,
- &hash_ctl,
- HASH_ELEM | HASH_FUNCTION | HASH_CONTEXT);
+ get_dbstat_filename(permanent, false, databaseid, statfile, MAXPGPATH);
- /*
- * Arrange that following records add entries to this
- * database's hash tables.
- */
- tabhash = dbentry->tables;
- funchash = dbentry->functions;
- break;
+ /*
+ * Try to open the stats file. If it doesn't exist, the backends simply
+ * return zero for anything and the collector simply starts from scratch
+ * with empty counters.
+ *
+ * ENOENT is a possibility if the stats collector is not running or has
+ * not yet written the stats file the first time. Any other failure
+ * condition is suspicious.
+ */
+ if ((fpin = AllocateFile(statfile, PG_BINARY_R)) == NULL)
+ {
+ if (errno != ENOENT)
+ ereport(pgStatRunningInCollector ? LOG : WARNING,
+ (errcode_for_file_access(),
+ errmsg("could not open statistics file \"%s\": %m",
+ statfile)));
+ return;
+ }
- /*
- * 'd' End of this database.
- */
- case 'd':
- tabhash = NULL;
- funchash = NULL;
- break;
+ /*
+ * Verify it's of the expected format.
+ */
+ if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id) ||
+ format_id != PGSTAT_FILE_FORMAT_ID)
+ {
+ ereport(pgStatRunningInCollector ? LOG : WARNING,
+ (errmsg("corrupted statistics file \"%s\"", statfile)));
+ goto done;
+ }
+ /*
+ * We found an existing collector stats file. Read it and put all the
+ * hashtable entries into place.
+ */
+ for (;;)
+ {
+ switch (fgetc(fpin))
+ {
/*
* 'T' A PgStat_StatTabEntry follows.
*/
}
/*
- * Skip if table belongs to a not requested database.
+ * Skip if table data not wanted.
*/
if (tabhash == NULL)
break;
tabentry = (PgStat_StatTabEntry *) hash_search(tabhash,
- (void *) &tabbuf.tableid,
- HASH_ENTER, &found);
+ (void *) &tabbuf.tableid,
+ HASH_ENTER, &found);
if (found)
{
}
/*
- * Skip if function belongs to a not requested database.
+ * Skip if function data not wanted.
*/
if (funchash == NULL)
break;
funcentry = (PgStat_StatFuncEntry *) hash_search(funchash,
- (void *) &funcbuf.functionid,
- HASH_ENTER, &found);
+ (void *) &funcbuf.functionid,
+ HASH_ENTER, &found);
if (found)
{
FreeFile(fpin);
if (permanent)
- unlink(PGSTAT_STAT_PERMANENT_FILENAME);
-
- return dbhash;
+ {
+ elog(DEBUG2, "removing permanent stats file \"%s\"", statfile);
+ unlink(statfile);
+ }
}
/* ----------
- * pgstat_read_statsfile_timestamp() -
+ * pgstat_read_db_statsfile_timestamp() -
+ *
+ * Attempt to determine the timestamp of the last db statfile write.
+ * Returns TRUE if successful; the timestamp is stored in *ts.
+ *
+ * This needs to be careful about handling databases for which no stats file
+ * exists, such as databases without a stat entry or those not yet written:
*
- * Attempt to fetch the timestamp of an existing stats file.
- * Returns TRUE if successful (timestamp is stored at *ts).
+ * - if there's a database entry in the global file, return the corresponding
+ * stats_timestamp value.
+ *
+ * - if there's no db stat entry (e.g. for a new or inactive database),
+ * there's no stats_timestamp value, but also nothing to write so we return
+ * the timestamp of the global statfile.
* ----------
*/
static bool
-pgstat_read_statsfile_timestamp(bool permanent, TimestampTz *ts)
+pgstat_read_db_statsfile_timestamp(Oid databaseid, bool permanent,
+ TimestampTz *ts)
{
+ PgStat_StatDBEntry dbentry;
PgStat_GlobalStats myGlobalStats;
+ PgStat_ArchiverStats myArchiverStats;
FILE *fpin;
int32 format_id;
const char *statfile = permanent ? PGSTAT_STAT_PERMANENT_FILENAME : pgstat_stat_filename;
/*
- * Try to open the status file. As above, anything but ENOENT is worthy
- * of complaining about.
+ * Try to open the stats file. As above, anything but ENOENT is worthy of
+ * complaining about.
*/
if ((fpin = AllocateFile(statfile, PG_BINARY_R)) == NULL)
{
/*
* Verify it's of the expected format.
*/
- if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id)
- || format_id != PGSTAT_FILE_FORMAT_ID)
+ if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id) ||
+ format_id != PGSTAT_FILE_FORMAT_ID)
{
ereport(pgStatRunningInCollector ? LOG : WARNING,
(errmsg("corrupted statistics file \"%s\"", statfile)));
/*
* Read global stats struct
*/
- if (fread(&myGlobalStats, 1, sizeof(myGlobalStats), fpin) != sizeof(myGlobalStats))
+ if (fread(&myGlobalStats, 1, sizeof(myGlobalStats),
+ fpin) != sizeof(myGlobalStats))
+ {
+ ereport(pgStatRunningInCollector ? LOG : WARNING,
+ (errmsg("corrupted statistics file \"%s\"", statfile)));
+ FreeFile(fpin);
+ return false;
+ }
+
+ /*
+ * Read archiver stats struct
+ */
+ if (fread(&myArchiverStats, 1, sizeof(myArchiverStats),
+ fpin) != sizeof(myArchiverStats))
{
ereport(pgStatRunningInCollector ? LOG : WARNING,
(errmsg("corrupted statistics file \"%s\"", statfile)));
return false;
}
+ /* By default, we're going to return the timestamp of the global file. */
*ts = myGlobalStats.stats_timestamp;
+ /*
+ * We found an existing collector stats file. Read it and look for a
+ * record for the requested database. If found, use its timestamp.
+ */
+ for (;;)
+ {
+ switch (fgetc(fpin))
+ {
+ /*
+ * 'D' A PgStat_StatDBEntry struct describing a database
+ * follows.
+ */
+ case 'D':
+ if (fread(&dbentry, 1, offsetof(PgStat_StatDBEntry, tables),
+ fpin) != offsetof(PgStat_StatDBEntry, tables))
+ {
+ ereport(pgStatRunningInCollector ? LOG : WARNING,
+ (errmsg("corrupted statistics file \"%s\"",
+ statfile)));
+ goto done;
+ }
+
+ /*
+ * If this is the DB we're looking for, save its timestamp and
+ * we're done.
+ */
+ if (dbentry.databaseid == databaseid)
+ {
+ *ts = dbentry.stats_timestamp;
+ goto done;
+ }
+
+ break;
+
+ case 'E':
+ goto done;
+
+ default:
+ ereport(pgStatRunningInCollector ? LOG : WARNING,
+ (errmsg("corrupted statistics file \"%s\"",
+ statfile)));
+ goto done;
+ }
+ }
+
+done:
FreeFile(fpin);
return true;
}
static void
backend_read_statsfile(void)
{
- TimestampTz cur_ts;
- TimestampTz min_ts;
+ TimestampTz min_ts = 0;
+ TimestampTz ref_ts = 0;
+ Oid inquiry_db;
int count;
/* already read it? */
Assert(!pgStatRunningInCollector);
/*
- * We set the minimum acceptable timestamp to PGSTAT_STAT_INTERVAL msec
- * before now. This indirectly ensures that the collector needn't write
- * the file more often than PGSTAT_STAT_INTERVAL. In an autovacuum
- * worker, however, we want a lower delay to avoid using stale data, so we
- * use PGSTAT_RETRY_DELAY (since the number of worker is low, this
- * shouldn't be a problem).
- *
- * Note that we don't recompute min_ts after sleeping; so we might end up
- * accepting a file a bit older than PGSTAT_STAT_INTERVAL. In practice
- * that shouldn't happen, though, as long as the sleep time is less than
- * PGSTAT_STAT_INTERVAL; and we don't want to lie to the collector about
- * what our cutoff time really is.
+ * In a normal backend, we check staleness of the data for our own DB, and
+ * so we send MyDatabaseId in inquiry messages. In the autovac launcher,
+ * check staleness of the shared-catalog data, and send InvalidOid in
+ * inquiry messages so as not to force writing unnecessary data.
*/
- cur_ts = GetCurrentTimestamp();
- if (IsAutoVacuumWorkerProcess())
- min_ts = TimestampTzPlusMilliseconds(cur_ts, -PGSTAT_RETRY_DELAY);
+ if (IsAutoVacuumLauncherProcess())
+ inquiry_db = InvalidOid;
else
- min_ts = TimestampTzPlusMilliseconds(cur_ts, -PGSTAT_STAT_INTERVAL);
+ inquiry_db = MyDatabaseId;
/*
* Loop until fresh enough stats file is available or we ran out of time.
*/
for (count = 0; count < PGSTAT_POLL_LOOP_COUNT; count++)
{
+ bool ok;
TimestampTz file_ts = 0;
+ TimestampTz cur_ts;
CHECK_FOR_INTERRUPTS();
- if (pgstat_read_statsfile_timestamp(false, &file_ts) &&
- file_ts >= min_ts)
+ ok = pgstat_read_db_statsfile_timestamp(inquiry_db, false, &file_ts);
+
+ cur_ts = GetCurrentTimestamp();
+ /* Calculate min acceptable timestamp, if we didn't already */
+ if (count == 0 || cur_ts < ref_ts)
+ {
+ /*
+ * We set the minimum acceptable timestamp to PGSTAT_STAT_INTERVAL
+ * msec before now. This indirectly ensures that the collector
+ * needn't write the file more often than PGSTAT_STAT_INTERVAL. In
+ * an autovacuum worker, however, we want a lower delay to avoid
+ * using stale data, so we use PGSTAT_RETRY_DELAY (since the
+ * number of workers is low, this shouldn't be a problem).
+ *
+ * We don't recompute min_ts after sleeping, except in the
+ * unlikely case that cur_ts went backwards. So we might end up
+ * accepting a file a bit older than PGSTAT_STAT_INTERVAL. In
+ * practice that shouldn't happen, though, as long as the sleep
+ * time is less than PGSTAT_STAT_INTERVAL; and we don't want to
+ * tell the collector that our cutoff time is less than what we'd
+ * actually accept.
+ */
+ ref_ts = cur_ts;
+ if (IsAutoVacuumWorkerProcess())
+ min_ts = TimestampTzPlusMilliseconds(ref_ts,
+ -PGSTAT_RETRY_DELAY);
+ else
+ min_ts = TimestampTzPlusMilliseconds(ref_ts,
+ -PGSTAT_STAT_INTERVAL);
+ }
+
+ /*
+ * If the file timestamp is actually newer than cur_ts, we must have
+ * had a clock glitch (system time went backwards) or there is clock
+ * skew between our processor and the stats collector's processor.
+ * Accept the file, but send an inquiry message anyway to make
+ * pgstat_recv_inquiry do a sanity check on the collector's time.
+ */
+ if (ok && file_ts > cur_ts)
+ {
+ /*
+ * A small amount of clock skew between processors isn't terribly
+ * surprising, but a large difference is worth logging. We
+ * arbitrarily define "large" as 1000 msec.
+ */
+ if (file_ts >= TimestampTzPlusMilliseconds(cur_ts, 1000))
+ {
+ char *filetime;
+ char *mytime;
+
+ /* Copy because timestamptz_to_str returns a static buffer */
+ filetime = pstrdup(timestamptz_to_str(file_ts));
+ mytime = pstrdup(timestamptz_to_str(cur_ts));
+ elog(LOG, "stats collector's time %s is later than backend local time %s",
+ filetime, mytime);
+ pfree(filetime);
+ pfree(mytime);
+ }
+
+ pgstat_send_inquiry(cur_ts, min_ts, inquiry_db);
+ break;
+ }
+
+ /* Normal acceptance case: file is not older than cutoff time */
+ if (ok && file_ts >= min_ts)
break;
/* Not there or too old, so kick the collector and wait a bit */
if ((count % PGSTAT_INQ_LOOP_COUNT) == 0)
- pgstat_send_inquiry(min_ts);
+ pgstat_send_inquiry(cur_ts, min_ts, inquiry_db);
pg_usleep(PGSTAT_RETRY_DELAY * 1000L);
}
if (count >= PGSTAT_POLL_LOOP_COUNT)
- elog(WARNING, "pgstat wait timeout");
+ ereport(LOG,
+ (errmsg("using stale statistics instead of current ones "
+ "because stats collector is not responding")));
- /* Autovacuum launcher wants stats about all databases */
+ /*
+ * Autovacuum launcher wants stats about all databases, but a shallow read
+ * is sufficient. Regular backends want a deep read for just the tables
+ * they can see (MyDatabaseId + shared catalogs).
+ */
if (IsAutoVacuumLauncherProcess())
- pgStatDBHash = pgstat_read_statsfile(InvalidOid, false);
+ pgStatDBHash = pgstat_read_statsfiles(InvalidOid, false, false);
else
- pgStatDBHash = pgstat_read_statsfile(MyDatabaseId, false);
+ pgStatDBHash = pgstat_read_statsfiles(MyDatabaseId, false, true);
}
if (!pgStatLocalContext)
pgStatLocalContext = AllocSetContextCreate(TopMemoryContext,
"Statistics snapshot",
- ALLOCSET_SMALL_MINSIZE,
- ALLOCSET_SMALL_INITSIZE,
- ALLOCSET_SMALL_MAXSIZE);
+ ALLOCSET_SMALL_SIZES);
}
/* ----------
* pgstat_clear_snapshot() -
*
- * Discard any data collected in the current transaction. Any subsequent
+ * Discard any data collected in the current transaction. Any subsequent
* request will cause new snapshots to be read.
*
* This is also invoked during transaction commit or abort to discard
static void
pgstat_recv_inquiry(PgStat_MsgInquiry *msg, int len)
{
- if (msg->inquiry_time > last_statrequest)
- last_statrequest = msg->inquiry_time;
+ PgStat_StatDBEntry *dbentry;
+
+ elog(DEBUG2, "received inquiry for database %u", msg->databaseid);
+
+ /*
+ * If there's already a write request for this DB, there's nothing to do.
+ *
+ * Note that if a request is found, we return early and skip the below
+ * check for clock skew. This is okay, since the only way for a DB
+ * request to be present in the list is that we have been here since the
+ * last write round. It seems sufficient to check for clock skew once per
+ * write round.
+ */
+ if (list_member_oid(pending_write_requests, msg->databaseid))
+ return;
+
+ /*
+ * Check to see if we last wrote this database at a time >= the requested
+ * cutoff time. If so, this is a stale request that was generated before
+ * we updated the DB file, and we don't need to do so again.
+ *
+ * If the requestor's local clock time is older than stats_timestamp, we
+ * should suspect a clock glitch, ie system time going backwards; though
+ * the more likely explanation is just delayed message receipt. It is
+ * worth expending a GetCurrentTimestamp call to be sure, since a large
+ * retreat in the system clock reading could otherwise cause us to neglect
+ * to update the stats file for a long time.
+ */
+ dbentry = pgstat_get_db_entry(msg->databaseid, false);
+ if (dbentry == NULL)
+ {
+ /*
+ * We have no data for this DB. Enter a write request anyway so that
+ * the global stats will get updated. This is needed to prevent
+ * backend_read_statsfile from waiting for data that we cannot supply,
+ * in the case of a new DB that nobody has yet reported any stats for.
+ * See the behavior of pgstat_read_db_statsfile_timestamp.
+ */
+ }
+ else if (msg->clock_time < dbentry->stats_timestamp)
+ {
+ TimestampTz cur_ts = GetCurrentTimestamp();
+
+ if (cur_ts < dbentry->stats_timestamp)
+ {
+ /*
+ * Sure enough, time went backwards. Force a new stats file write
+ * to get back in sync; but first, log a complaint.
+ */
+ char *writetime;
+ char *mytime;
+
+ /* Copy because timestamptz_to_str returns a static buffer */
+ writetime = pstrdup(timestamptz_to_str(dbentry->stats_timestamp));
+ mytime = pstrdup(timestamptz_to_str(cur_ts));
+ elog(LOG,
+ "stats_timestamp %s is later than collector's time %s for database %u",
+ writetime, mytime, dbentry->databaseid);
+ pfree(writetime);
+ pfree(mytime);
+ }
+ else
+ {
+ /*
+ * Nope, it's just an old request. Assuming msg's clock_time is
+ * >= its cutoff_time, it must be stale, so we can ignore it.
+ */
+ return;
+ }
+ }
+ else if (msg->cutoff_time <= dbentry->stats_timestamp)
+ {
+ /* Stale request, ignore it */
+ return;
+ }
+
+ /*
+ * We need to write this DB, so create a request.
+ */
+ pending_write_requests = lappend_oid(pending_write_requests,
+ msg->databaseid);
}
PgStat_TableEntry *tabmsg = &(msg->m_entry[i]);
tabentry = (PgStat_StatTabEntry *) hash_search(dbentry->tables,
- (void *) &(tabmsg->t_id),
+ (void *) &(tabmsg->t_id),
HASH_ENTER, &found);
if (!found)
tabentry->tuples_updated += tabmsg->t_counts.t_tuples_updated;
tabentry->tuples_deleted += tabmsg->t_counts.t_tuples_deleted;
tabentry->tuples_hot_updated += tabmsg->t_counts.t_tuples_hot_updated;
+ /* If table was truncated, first reset the live/dead counters */
+ if (tabmsg->t_counts.t_truncated)
+ {
+ tabentry->n_live_tuples = 0;
+ tabentry->n_dead_tuples = 0;
+ }
tabentry->n_live_tuples += tabmsg->t_counts.t_delta_live_tuples;
tabentry->n_dead_tuples += tabmsg->t_counts.t_delta_dead_tuples;
tabentry->changes_since_analyze += tabmsg->t_counts.t_changed_tuples;
static void
pgstat_recv_dropdb(PgStat_MsgDropdb *msg, int len)
{
+ Oid dbid = msg->m_databaseid;
PgStat_StatDBEntry *dbentry;
/*
* Lookup the database in the hashtable.
*/
- dbentry = pgstat_get_db_entry(msg->m_databaseid, false);
+ dbentry = pgstat_get_db_entry(dbid, false);
/*
- * If found, remove it.
+ * If found, remove it (along with the db statfile).
*/
if (dbentry)
{
+ char statfile[MAXPGPATH];
+
+ get_dbstat_filename(false, false, dbid, statfile, MAXPGPATH);
+
+ elog(DEBUG2, "removing stats file \"%s\"", statfile);
+ unlink(statfile);
+
if (dbentry->tables != NULL)
hash_destroy(dbentry->tables);
if (dbentry->functions != NULL)
hash_destroy(dbentry->functions);
if (hash_search(pgStatDBHash,
- (void *) &(dbentry->databaseid),
+ (void *) &dbid,
HASH_REMOVE, NULL) == NULL)
ereport(ERROR,
- (errmsg("database hash table corrupted "
- "during cleanup --- abort")));
+ (errmsg("database hash table corrupted during cleanup --- abort")));
}
}
static void
pgstat_recv_resetcounter(PgStat_MsgResetcounter *msg, int len)
{
- HASHCTL hash_ctl;
PgStat_StatDBEntry *dbentry;
/*
dbentry->functions = NULL;
/*
- * Reset database-level stats too. This should match the initialization
- * code in pgstat_get_db_entry().
+ * Reset database-level stats, too. This creates empty hash tables for
+ * tables and functions.
*/
- dbentry->n_xact_commit = 0;
- dbentry->n_xact_rollback = 0;
- dbentry->n_blocks_fetched = 0;
- dbentry->n_blocks_hit = 0;
- dbentry->n_tuples_returned = 0;
- dbentry->n_tuples_fetched = 0;
- dbentry->n_tuples_inserted = 0;
- dbentry->n_tuples_updated = 0;
- dbentry->n_tuples_deleted = 0;
- dbentry->last_autovac_time = 0;
- dbentry->n_temp_bytes = 0;
- dbentry->n_temp_files = 0;
- dbentry->n_deadlocks = 0;
- dbentry->n_block_read_time = 0;
- dbentry->n_block_write_time = 0;
-
- dbentry->stat_reset_timestamp = GetCurrentTimestamp();
-
- memset(&hash_ctl, 0, sizeof(hash_ctl));
- hash_ctl.keysize = sizeof(Oid);
- hash_ctl.entrysize = sizeof(PgStat_StatTabEntry);
- hash_ctl.hash = oid_hash;
- dbentry->tables = hash_create("Per-database table",
- PGSTAT_TAB_HASH_SIZE,
- &hash_ctl,
- HASH_ELEM | HASH_FUNCTION);
-
- hash_ctl.keysize = sizeof(Oid);
- hash_ctl.entrysize = sizeof(PgStat_StatFuncEntry);
- hash_ctl.hash = oid_hash;
- dbentry->functions = hash_create("Per-database function",
- PGSTAT_FUNCTION_HASH_SIZE,
- &hash_ctl,
- HASH_ELEM | HASH_FUNCTION);
+ reset_dbentry_counters(dbentry);
}
/* ----------
memset(&globalStats, 0, sizeof(globalStats));
globalStats.stat_reset_timestamp = GetCurrentTimestamp();
}
+ else if (msg->m_resettarget == RESET_ARCHIVER)
+ {
+ /* Reset the archiver statistics for the cluster. */
+ memset(&archiverStats, 0, sizeof(archiverStats));
+ archiverStats.stat_reset_timestamp = GetCurrentTimestamp();
+ }
/*
* Presumably the sender of this message validated the target, don't
tabentry = pgstat_get_tab_entry(dbentry, msg->m_tableoid, true);
- tabentry->n_live_tuples = msg->m_tuples;
- /* Resetting dead_tuples to 0 is an approximation ... */
- tabentry->n_dead_tuples = 0;
+ tabentry->n_live_tuples = msg->m_live_tuples;
+ tabentry->n_dead_tuples = msg->m_dead_tuples;
if (msg->m_autovacuum)
{
tabentry->n_dead_tuples = msg->m_dead_tuples;
/*
- * We reset changes_since_analyze to zero, forgetting any changes that
- * occurred while the ANALYZE was in progress.
+ * If commanded, reset changes_since_analyze to zero. This forgets any
+ * changes that were committed while the ANALYZE was in progress, but we
+ * have no good way to estimate how many of those there were.
*/
- tabentry->changes_since_analyze = 0;
+ if (msg->m_resetcounter)
+ tabentry->changes_since_analyze = 0;
if (msg->m_autovacuum)
{
}
+/* ----------
+ * pgstat_recv_archiver() -
+ *
+ * Process a ARCHIVER message.
+ * ----------
+ */
+static void
+pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len)
+{
+ if (msg->m_failed)
+ {
+ /* Failed archival attempt */
+ ++archiverStats.failed_count;
+ memcpy(archiverStats.last_failed_wal, msg->m_xlog,
+ sizeof(archiverStats.last_failed_wal));
+ archiverStats.last_failed_timestamp = msg->m_timestamp;
+ }
+ else
+ {
+ /* Successful archival operation */
+ ++archiverStats.archived_count;
+ memcpy(archiverStats.last_archived_wal, msg->m_xlog,
+ sizeof(archiverStats.last_archived_wal));
+ archiverStats.last_archived_timestamp = msg->m_timestamp;
+ }
+}
+
/* ----------
* pgstat_recv_bgwriter() -
*
for (i = 0; i < msg->m_nentries; i++, funcmsg++)
{
funcentry = (PgStat_StatFuncEntry *) hash_search(dbentry->functions,
- (void *) &(funcmsg->f_id),
+ (void *) &(funcmsg->f_id),
HASH_ENTER, &found);
if (!found)
HASH_REMOVE, NULL);
}
}
+
+/* ----------
+ * pgstat_write_statsfile_needed() -
+ *
+ * Do we need to write out any stats files?
+ * ----------
+ */
+static bool
+pgstat_write_statsfile_needed(void)
+{
+ if (pending_write_requests != NIL)
+ return true;
+
+ /* Everything was written recently */
+ return false;
+}
+
+/* ----------
+ * pgstat_db_requested() -
+ *
+ * Checks whether stats for a particular DB need to be written to a file.
+ * ----------
+ */
+static bool
+pgstat_db_requested(Oid databaseid)
+{
+ /*
+ * If any requests are outstanding at all, we should write the stats for
+ * shared catalogs (the "database" with OID 0). This ensures that
+ * backends will see up-to-date stats for shared catalogs, even though
+ * they send inquiry messages mentioning only their own DB.
+ */
+ if (databaseid == InvalidOid && pending_write_requests != NIL)
+ return true;
+
+ /* Search to see if there's an open request to write this database. */
+ if (list_member_oid(pending_write_requests, databaseid))
+ return true;
+
+ return false;
+}
+
+/*
+ * Convert a potentially unsafely truncated activity string (see
+ * PgBackendStatus.st_activity_raw's documentation) into a correctly truncated
+ * one.
+ *
+ * The returned string is allocated in the caller's memory context and may be
+ * freed.
+ */
+char *
+pgstat_clip_activity(const char *raw_activity)
+{
+ char *activity;
+ int rawlen;
+ int cliplen;
+
+ /*
+ * Some callers, like pgstat_get_backend_current_activity(), do not
+ * guarantee that the buffer isn't concurrently modified. We try to take
+ * care that the buffer is always terminated by a NUL byte regardless, but
+ * let's still be paranoid about the string's length. In those cases the
+ * underlying buffer is guaranteed to be pgstat_track_activity_query_size
+ * large.
+ */
+ activity = pnstrdup(raw_activity, pgstat_track_activity_query_size - 1);
+
+ /* now double-guaranteed to be NUL terminated */
+ rawlen = strlen(activity);
+
+ /*
+ * All supported server-encodings make it possible to determine the length
+ * of a multi-byte character from its first byte (this is not the case for
+ * client encodings, see GB18030). As st_activity is always stored using
+ * server encoding, this allows us to perform multi-byte aware truncation,
+ * even if the string earlier was truncated in the middle of a multi-byte
+ * character.
+ */
+ cliplen = pg_mbcliplen(activity, rawlen,
+ pgstat_track_activity_query_size - 1);
+
+ activity[cliplen] = '\0';
+
+ return activity;
+}
projects / postgresql / blobdiff