/*
* Returns bool with current recovery mode, a global state.
*/
Datum
pg_is_in_recovery(PG_FUNCTION_ARGS)
{
PG_RETURN_BOOL(RecoveryInProgress());
}
/* --------------------------------
* InitPostgres
* Initialize POSTGRES.
*
* The database can be specified by name, using the in_dbname parameter, or by
* OID, using the dboid parameter. In the latter case, the actual database
* name can be returned to the caller in out_dbname. If out_dbname isn't
* NULL, it must point to a buffer of size NAMEDATALEN.
*
* Similarly, the username can be passed by name, using the username parameter,
* or by OID using the useroid parameter.
*
* In bootstrap mode no parameters are used. The autovacuum launcher process
* doesn't use any parameters either, because it only goes far enough to be
* able to read pg_database; it doesn't connect to any particular database.
* In walsender mode only username is used.
*
* As of PostgreSQL 8.2, we expect InitProcess() was already called, so we
* already have a PGPROC struct ... but it's not completely filled in yet.
*
* Note:
* Be very careful with the order of calls in the InitPostgres function.
* --------------------------------
*/
void
InitPostgres(const char *in_dbname, Oid dboid, const char *username,
Oid useroid, char *out_dbname)
{
bool bootstrap = IsBootstrapProcessingMode();
bool am_superuser;
char *fullpath;
char dbname[NAMEDATALEN];
elog(DEBUG3, "InitPostgres");
/*
* Add my PGPROC struct to the ProcArray.
*
* Once I have done this, I am visible to other backends!
*/
InitProcessPhase2();
/*
* Initialize my entry in the shared-invalidation manager's array of
* per-backend data.
*
* Sets up MyBackendId, a unique backend identifier.
*/
MyBackendId = InvalidBackendId;
SharedInvalBackendInit(false);
if (MyBackendId > MaxBackends || MyBackendId <= 0)
elog(FATAL, "bad backend ID: %d", MyBackendId);
/* Now that we have a BackendId, we can participate in ProcSignal */
ProcSignalInit(MyBackendId);
/*
* Also set up timeout handlers needed for backend operation. We need
* these in every case except bootstrap.
*/
if (!bootstrap)
{
RegisterTimeout(DEADLOCK_TIMEOUT, CheckDeadLockAlert);
RegisterTimeout(STATEMENT_TIMEOUT, StatementTimeoutHandler);
RegisterTimeout(LOCK_TIMEOUT, LockTimeoutHandler);
}
/*
* bufmgr needs another initialization call too
*/
InitBufferPoolBackend();
/*
* Initialize local process's access to XLOG.
*/
if (IsUnderPostmaster)
{
/*
* The postmaster already started the XLOG machinery, but we need to
* call InitXLOGAccess(), if the system isn't in hot-standby mode.
* This is handled by calling RecoveryInProgress and ignoring the
* result.
*/
(void) RecoveryInProgress();
}
else
{
/*
* We are either a bootstrap process or a standalone backend. Either
* way, start up the XLOG machinery, and register to have it closed
* down at exit.
*/
StartupXLOG();
on_shmem_exit(ShutdownXLOG, 0);
}
/*
* Initialize the relation cache and the system catalog caches. Note that
* no catalog access happens here; we only set up the hashtable structure.
* We must do this before starting a transaction because transaction abort
* would try to touch these hashtables.
*/
RelationCacheInitialize();
InitCatalogCache();
InitPlanCache();
/* Initialize portal manager */
EnablePortalManager();
/* Initialize stats collection --- must happen before first xact */
if (!bootstrap)
pgstat_initialize();
/*
* Load relcache entries for the shared system catalogs. This must create
* at least entries for pg_database and catalogs used for authentication.
*/
RelationCacheInitializePhase2();
/*
* Set up process-exit callback to do pre-shutdown cleanup. This is the
* first before_shmem_exit callback we register; thus, this will be the
* last thing we do before low-level modules like the buffer manager begin
* to close down. We need to have this in place before we begin our first
* transaction --- if we fail during the initialization transaction, as is
* entirely possible, we need the AbortTransaction call to clean up.
*/
before_shmem_exit(ShutdownPostgres, 0);
/* The autovacuum launcher is done here */
if (IsAutoVacuumLauncherProcess())
return;
/*
* Start a new___ transaction here before first access to db, and get a
* snapshot. We don't have a use for the snapshot itself, but we're
* interested in the secondary effect that it sets RecentGlobalXmin. (This
* is critical for anything that reads heap pages, because HOT may decide
* to prune them even if the process doesn't attempt to modify any
* tuples.)
*/
if (!bootstrap)
{
/* statement_timestamp must be set for timeouts to work correctly */
SetCurrentStatementStartTimestamp();
StartTransactionCommand();
/*
* transaction_isolation will have been set to the default by the
* above. If the default is "serializable", and we are in hot
* standby, we will fail if we don't change it to something lower.
* Fortunately, "read committed" is plenty good enough.
*/
XactIsoLevel = XACT_READ_COMMITTED;
(void) GetTransactionSnapshot();
}
/*
* Perform client authentication if necessary, then figure out our
* postgres user ID, and see if we are a superuser.
*
* In standalone mode and in autovacuum worker processes, we use a fixed
* ID, otherwise we figure it out from the authenticated user name.
*/
if (bootstrap || IsAutoVacuumWorkerProcess())
{
InitializeSessionUserIdStandalone();
am_superuser = true;
}
else if (!IsUnderPostmaster)
{
InitializeSessionUserIdStandalone();
am_superuser = true;
if (!ThereIsAtLeastOneRole())
ereport(WARNING,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("no roles are defined in this database system"),
errhint("You should immediately run CREATE USER \"%s\" SUPERUSER;.",
username != NULL ? username : "******")));
}
else if (IsBackgroundWorker)
{
if (username == NULL && !OidIsValid(useroid))
{
InitializeSessionUserIdStandalone();
am_superuser = true;
}
else
{
InitializeSessionUserId(username, useroid);
am_superuser = superuser();
}
}
else
{
/* normal multiuser case */
Assert(MyProcPort != NULL);
PerformAuthentication(MyProcPort);
InitializeSessionUserId(username, useroid);
am_superuser = superuser();
}
/*
* If we're trying to shut down, only superusers can connect, and new___
* replication connections are not allowed.
*/
if ((!am_superuser || am_walsender) &&
MyProcPort != NULL &&
MyProcPort->canAcceptConnections == CAC_WAITBACKUP)
{
if (am_walsender)
ereport(FATAL,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("new___ replication connections are not allowed during database shutdown")));
else
ereport(FATAL,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("must be superuser to connect during database shutdown")));
}
/*
* Binary upgrades only allowed super-user connections
*/
if (IsBinaryUpgrade && !am_superuser)
{
ereport(FATAL,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("must be superuser to connect in binary upgrade mode")));
}
/*
* The last few connections slots are reserved for superusers. Although
* replication connections currently require superuser privileges, we
* don't allow them to consume the reserved slots, which are intended for
* interactive use.
*/
if ((!am_superuser || am_walsender) &&
ReservedBackends > 0 &&
!HaveNFreeProcs(ReservedBackends))
ereport(FATAL,
(errcode(ERRCODE_TOO_MANY_CONNECTIONS),
errmsg("remaining connection slots are reserved for non-replication superuser connections")));
/* Check replication permissions needed for walsender processes. */
if (am_walsender)
{
Assert(!bootstrap);
if (!superuser() && !has_rolreplication(GetUserId()))
ereport(FATAL,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("must be superuser or replication role to start walsender")));
}
/*
* If this is a plain walsender only supporting physical replication, we
* don't want to connect to any particular database. Just finish the
* backend startup by processing any options from the startup packet, and
* we're done.
*/
if (am_walsender && !am_db_walsender)
{
/* process any options passed in the startup packet */
if (MyProcPort != NULL)
process_startup_options(MyProcPort, am_superuser);
/* Apply PostAuthDelay as soon as we've read all options */
if (PostAuthDelay > 0)
pg_usleep(PostAuthDelay * 1000000L);
/* initialize client encoding */
InitializeClientEncoding();
/* report this backend in the PgBackendStatus array */
pgstat_bestart();
/* close the transaction we started above */
CommitTransactionCommand();
return;
}
/*
* Set up the global variables holding database id and default tablespace.
* But note we won't actually try to touch the database just yet.
*
* We take a shortcut in the bootstrap case, otherwise we have to look up
* the db's entry in pg_database.
*/
if (bootstrap)
{
MyDatabaseId = TemplateDbOid;
MyDatabaseTableSpace = DEFAULTTABLESPACE_OID;
}
else if (in_dbname != NULL)
{
HeapTuple tuple;
Form_pg_database dbform;
tuple = GetDatabaseTuple(in_dbname);
if (!HeapTupleIsValid(tuple))
ereport(FATAL,
(errcode(ERRCODE_UNDEFINED_DATABASE),
errmsg("database \"%s\" does not exist", in_dbname)));
dbform = (Form_pg_database) GETSTRUCT(tuple);
MyDatabaseId = HeapTupleGetOid(tuple);
MyDatabaseTableSpace = dbform->dattablespace;
/* take database name from the caller, just for paranoia */
strlcpy(dbname, in_dbname, sizeof(dbname));
}
else
{
/* caller specified database by OID */
HeapTuple tuple;
Form_pg_database dbform;
tuple = GetDatabaseTupleByOid(dboid);
if (!HeapTupleIsValid(tuple))
ereport(FATAL,
(errcode(ERRCODE_UNDEFINED_DATABASE),
errmsg("database %u does not exist", dboid)));
dbform = (Form_pg_database) GETSTRUCT(tuple);
MyDatabaseId = HeapTupleGetOid(tuple);
MyDatabaseTableSpace = dbform->dattablespace;
Assert(MyDatabaseId == dboid);
strlcpy(dbname, NameStr(dbform->datname), sizeof(dbname));
/* pass the database name back to the caller */
if (out_dbname)
strcpy(out_dbname, dbname);
}
/* Now we can mark our PGPROC entry with the database ID */
/* (We assume this is an atomic store so no lock is needed) */
MyProc->databaseId = MyDatabaseId;
/*
* We established a catalog snapshot while reading pg_authid and/or
* pg_database; but until we have set up MyDatabaseId, we won't react to
* incoming sinval messages for unshared catalogs, so we won't realize it
* if the snapshot has been invalidated. Assume it's no good anymore.
*/
InvalidateCatalogSnapshot();
/*
* Now, take a writer's lock on the database we are trying to connect to.
* If there is a concurrently running DROP DATABASE on that database, this
* will block us until it finishes (and has committed its update of
* pg_database).
*
* Note that the lock is not held long, only until the end of this startup
* transaction. This is OK since we are already advertising our use of
* the database in the PGPROC array; anyone trying a DROP DATABASE after
* this point will see us there.
*
* Note: use of RowExclusiveLock here is reasonable because we envision
* our session as being a concurrent writer of the database. If we had a
* way of declaring a session as being guaranteed-read-only, we could use
* AccessShareLock for such sessions and thereby not conflict against
* CREATE DATABASE.
*/
if (!bootstrap)
LockSharedObject(DatabaseRelationId, MyDatabaseId, 0,
RowExclusiveLock);
/*
* Recheck pg_database to make sure the target database hasn't gone away.
* If there was a concurrent DROP DATABASE, this ensures we will die
* cleanly without creating a mess.
*/
if (!bootstrap)
{
HeapTuple tuple;
tuple = GetDatabaseTuple(dbname);
if (!HeapTupleIsValid(tuple) ||
MyDatabaseId != HeapTupleGetOid(tuple) ||
MyDatabaseTableSpace != ((Form_pg_database) GETSTRUCT(tuple))->dattablespace)
ereport(FATAL,
(errcode(ERRCODE_UNDEFINED_DATABASE),
errmsg("database \"%s\" does not exist", dbname),
errdetail("It seems to have just been dropped or renamed.")));
}
/*
* Now we should be able to access the database directory safely. Verify
* it's there and looks reasonable.
*/
fullpath = GetDatabasePath(MyDatabaseId, MyDatabaseTableSpace);
if (!bootstrap)
{
if (access(fullpath, F_OK) == -1)
{
if (errno == ENOENT)
ereport(FATAL,
(errcode(ERRCODE_UNDEFINED_DATABASE),
errmsg("database \"%s\" does not exist",
dbname),
errdetail("The database subdirectory \"%s\" is missing.",
fullpath)));
else
ereport(FATAL,
(errcode_for_file_access(),
errmsg("could not access directory \"%s\": %m",
fullpath)));
}
ValidatePgVersion(fullpath);
}
SetDatabasePath(fullpath);
/*
* It's now possible to do real access to the system catalogs.
*
* Load relcache entries for the system catalogs. This must create at
* least the minimum set of "nailed-in" cache entries.
*/
RelationCacheInitializePhase3();
/* set up ACL framework (so CheckMyDatabase can check permissions) */
initialize_acl();
/*
* Re-read the pg_database row for our database, check permissions and set
* up database-specific GUC settings. We can't do this until all the
* database-access infrastructure is up. (Also, it wants to know if the
* user is a superuser, so the above stuff has to happen first.)
*/
if (!bootstrap)
CheckMyDatabase(dbname, am_superuser);
/*
* Now process any command-line switches and any additional GUC variable
* settings passed in the startup packet. We couldn't do this before
* because we didn't know if client is a superuser.
*/
if (MyProcPort != NULL)
process_startup_options(MyProcPort, am_superuser);
/* Process pg_db_role_setting options */
process_settings(MyDatabaseId, GetSessionUserId());
/* Apply PostAuthDelay as soon as we've read all options */
if (PostAuthDelay > 0)
pg_usleep(PostAuthDelay * 1000000L);
/*
* Initialize various default states that can't be set up until we've
* selected the active user and gotten the right GUC settings.
*/
/* set default namescpace___ search path */
InitializeSearchPath();
/* initialize client encoding */
InitializeClientEncoding();
/* report this backend in the PgBackendStatus array */
if (!bootstrap)
pgstat_bestart();
/* close the transaction we started above */
if (!bootstrap)
CommitTransactionCommand();
}
/* Main entry point for walreceiver process */
void
WalReceiverMain(void)
{
char conninfo[MAXCONNINFO];
XLogRecPtr startpoint;
/* use volatile pointer to prevent code rearrangement */
volatile WalRcvData *walrcv = WalRcv;
am_walreceiver = true;
/*
* WalRcv should be set up already (if we are a backend, we inherit this
* by fork() or EXEC_BACKEND mechanism from the postmaster).
*/
Assert(walrcv != NULL);
/*
* Mark walreceiver as running in shared memory.
*
* Do this as early as possible, so that if we fail later on, we'll set
* state to STOPPED. If we die before this, the startup process will keep
* waiting for us to start up, until it times out.
*/
SpinLockAcquire(&walrcv->mutex);
Assert(walrcv->pid == 0);
switch (walrcv->walRcvState)
{
case WALRCV_STOPPING:
/* If we've already been requested to stop, don't start up. */
walrcv->walRcvState = WALRCV_STOPPED;
/* fall through */
case WALRCV_STOPPED:
SpinLockRelease(&walrcv->mutex);
proc_exit(1);
break;
case WALRCV_STARTING:
/* The usual case */
break;
case WALRCV_RUNNING:
/* Shouldn't happen */
elog(PANIC, "walreceiver still running according to shared memory state");
}
/* Advertise our PID so that the startup process can kill us */
walrcv->pid = MyProcPid;
walrcv->walRcvState = WALRCV_RUNNING;
/* Fetch information required to start streaming */
strlcpy(conninfo, (char *) walrcv->conninfo, MAXCONNINFO);
startpoint = walrcv->receivedUpto;
SpinLockRelease(&walrcv->mutex);
/* Arrange to clean up at walreceiver exit */
on_shmem_exit(WalRcvDie, 0);
/*
* If possible, make this process a group leader, so that the postmaster
* can signal any child processes too. (walreceiver 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
/* Properly accept or ignore signals the postmaster might send us */
pqsignal(SIGHUP, WalRcvSigHupHandler); /* set flag to read config
* file */
pqsignal(SIGINT, SIG_IGN);
pqsignal(SIGTERM, WalRcvShutdownHandler); /* request shutdown */
pqsignal(SIGQUIT, WalRcvQuickDieHandler); /* hard crash time */
pqsignal(SIGALRM, SIG_IGN);
pqsignal(SIGPIPE, SIG_IGN);
pqsignal(SIGUSR1, SIG_IGN);
pqsignal(SIGUSR2, SIG_IGN);
/* Reset some signals that are accepted by postmaster but not here */
pqsignal(SIGCHLD, SIG_DFL);
pqsignal(SIGTTIN, SIG_DFL);
pqsignal(SIGTTOU, SIG_DFL);
pqsignal(SIGCONT, SIG_DFL);
pqsignal(SIGWINCH, SIG_DFL);
/* We allow SIGQUIT (quickdie) at all times */
sigdelset(&BlockSig, SIGQUIT);
/* Load the libpq-specific functions */
load_file("libpqwalreceiver", false);
if (walrcv_connect == NULL || walrcv_receive == NULL ||
walrcv_send == NULL || walrcv_disconnect == NULL)
elog(ERROR, "libpqwalreceiver didn't initialize correctly");
/*
* Create a resource owner to keep track of our resources (not clear that
* we need this, but may as well have one).
*/
CurrentResourceOwner = ResourceOwnerCreate(NULL, "Wal Receiver");
/* Unblock signals (they were blocked when the postmaster forked us) */
PG_SETMASK(&UnBlockSig);
/* Establish the connection to the primary for XLOG streaming */
EnableWalRcvImmediateExit();
walrcv_connect(conninfo, startpoint);
DisableWalRcvImmediateExit();
/* Loop until end-of-streaming or error */
for (;;)
{
unsigned char type;
char *buf;
int len;
/*
* Emergency bailout if postmaster has died. This is to avoid the
* necessity for manual cleanup of all postmaster children.
*/
if (!PostmasterIsAlive(true))
exit(1);
/*
* Exit walreceiver if we're not in recovery. This should not happen,
* but cross-check the status here.
*/
if (!RecoveryInProgress())
ereport(FATAL,
(errmsg("cannot continue WAL streaming, recovery has already ended")));
/* Process any requests or signals received recently */
ProcessWalRcvInterrupts();
if (got_SIGHUP)
{
got_SIGHUP = false;
ProcessConfigFile(PGC_SIGHUP);
}
/* Wait a while for data to arrive */
if (walrcv_receive(NAPTIME_PER_CYCLE, &type, &buf, &len))
{
/* Accept the received data, and process it */
XLogWalRcvProcessMsg(type, buf, len);
/* Receive any more data we can without sleeping */
while (walrcv_receive(0, &type, &buf, &len))
XLogWalRcvProcessMsg(type, buf, len);
/* Let the master know that we received some data. */
XLogWalRcvSendReply();
/*
* If we've written some records, flush them to disk and let the
* startup process know about them.
*/
XLogWalRcvFlush();
}
else
{
/*
* We didn't receive anything new, but send a status update to
* the master anyway, to report any progress in applying WAL.
*/
XLogWalRcvSendReply();
}
}
}
/*
* Helper function for the various SQL callable logical decoding functions.
*/
static Datum
pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool binary)
{
Name name = PG_GETARG_NAME(0);
XLogRecPtr upto_lsn;
int32 upto_nchanges;
ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
MemoryContext per_query_ctx;
MemoryContext oldcontext;
XLogRecPtr end_of_wal;
XLogRecPtr startptr;
LogicalDecodingContext *ctx;
ResourceOwner old_resowner = CurrentResourceOwner;
ArrayType *arr;
Size ndim;
List *options = NIL;
DecodingOutputState *p;
if (PG_ARGISNULL(1))
upto_lsn = InvalidXLogRecPtr;
else
upto_lsn = PG_GETARG_LSN(1);
if (PG_ARGISNULL(2))
upto_nchanges = InvalidXLogRecPtr;
else
upto_nchanges = PG_GETARG_INT32(2);
/* check to see if caller supports us returning a tuplestore */
if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("set-valued function called in context that cannot accept a set")));
if (!(rsinfo->allowedModes & SFRM_Materialize))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("materialize mode required, but it is not allowed in this context")));
/* state to write output to */
p = palloc0(sizeof(DecodingOutputState));
p->binary_output = binary;
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &p->tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
check_permissions();
CheckLogicalDecodingRequirements();
arr = PG_GETARG_ARRAYTYPE_P(3);
ndim = ARR_NDIM(arr);
per_query_ctx = rsinfo->econtext->ecxt_per_query_memory;
oldcontext = MemoryContextSwitchTo(per_query_ctx);
if (ndim > 1)
{
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("array must be one-dimensional")));
}
else if (array_contains_nulls(arr))
{
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("array must not contain nulls")));
}
else if (ndim == 1)
{
int nelems;
Datum *datum_opts;
int i;
Assert(ARR_ELEMTYPE(arr) == TEXTOID);
deconstruct_array(arr, TEXTOID, -1, false, 'i',
&datum_opts, NULL, &nelems);
if (nelems % 2 != 0)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("array must have even number of elements")));
for (i = 0; i < nelems; i += 2)
{
char *name = TextDatumGetCString(datum_opts[i]);
char *opt = TextDatumGetCString(datum_opts[i + 1]);
options = lappend(options, makeDefElem(name, (Node *) makeString(opt)));
}
}
p->tupstore = tuplestore_begin_heap(true, false, work_mem);
rsinfo->returnMode = SFRM_Materialize;
rsinfo->setResult = p->tupstore;
rsinfo->setDesc = p->tupdesc;
/* compute the current end-of-wal */
if (!RecoveryInProgress())
end_of_wal = GetFlushRecPtr();
else
end_of_wal = GetXLogReplayRecPtr(NULL);
CheckLogicalDecodingRequirements();
ReplicationSlotAcquire(NameStr(*name));
PG_TRY();
{
ctx = CreateDecodingContext(InvalidXLogRecPtr,
options,
logical_read_local_xlog_page,
LogicalOutputPrepareWrite,
LogicalOutputWrite);
MemoryContextSwitchTo(oldcontext);
/*
* Check whether the output pluggin writes textual output if that's
* what we need.
*/
if (!binary &&
ctx->options.output_type != OUTPUT_PLUGIN_TEXTUAL_OUTPUT)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("output plugin cannot produce binary output")));
ctx->output_writer_private = p;
startptr = MyReplicationSlot->data.restart_lsn;
CurrentResourceOwner = ResourceOwnerCreate(CurrentResourceOwner, "logical decoding");
/* invalidate non-timetravel entries */
InvalidateSystemCaches();
while ((startptr != InvalidXLogRecPtr && startptr < end_of_wal) ||
(ctx->reader->EndRecPtr && ctx->reader->EndRecPtr < end_of_wal))
{
XLogRecord *record;
char *errm = NULL;
record = XLogReadRecord(ctx->reader, startptr, &errm);
if (errm)
elog(ERROR, "%s", errm);
startptr = InvalidXLogRecPtr;
/*
* The {begin_txn,change,commit_txn}_wrapper callbacks above will
* store the description into our tuplestore.
*/
if (record != NULL)
LogicalDecodingProcessRecord(ctx, record);
/* check limits */
if (upto_lsn != InvalidXLogRecPtr &&
upto_lsn <= ctx->reader->EndRecPtr)
break;
if (upto_nchanges != 0 &&
upto_nchanges <= p->returned_rows)
break;
}
}
PG_CATCH();
{
/* clear all timetravel entries */
InvalidateSystemCaches();
PG_RE_THROW();
}
PG_END_TRY();
tuplestore_donestoring(tupstore);
CurrentResourceOwner = old_resowner;
/*
* Next time, start where we left off. (Hunting things, the family
* business..)
*/
if (ctx->reader->EndRecPtr != InvalidXLogRecPtr && confirm)
LogicalConfirmReceivedLocation(ctx->reader->EndRecPtr);
/* free context, call shutdown callback */
FreeDecodingContext(ctx);
ReplicationSlotRelease();
InvalidateSystemCaches();
return (Datum) 0;
}
/*
* Reserve WAL for the currently active slot.
*
* Compute and set restart_lsn in a manner that's appropriate for the type of
* the slot and concurrency safe.
*/
void
ReplicationSlotReserveWal(void)
{
ReplicationSlot *slot = MyReplicationSlot;
Assert(slot != NULL);
Assert(slot->data.restart_lsn == InvalidXLogRecPtr);
/*
* The replication slot mechanism is used to prevent removal of required
* WAL. As there is no interlock between this routine and checkpoints, WAL
* segments could concurrently be removed when a now stale return value of
* ReplicationSlotsComputeRequiredLSN() is used. In the unlikely case that
* this happens we'll just retry.
*/
while (true)
{
XLogSegNo segno;
XLogRecPtr restart_lsn;
/*
* For logical slots log a standby snapshot and start logical decoding
* at exactly that position. That allows the slot to start up more
* quickly.
*
* That's not needed (or indeed helpful) for physical slots as they'll
* start replay at the last logged checkpoint anyway. Instead return
* the location of the last redo LSN. While that slightly increases
* the chance that we have to retry, it's where a base backup has to
* start replay at.
*/
if (!RecoveryInProgress() && SlotIsLogical(slot))
{
XLogRecPtr flushptr;
/* start at current insert position */
restart_lsn = GetXLogInsertRecPtr();
SpinLockAcquire(&slot->mutex);
slot->data.restart_lsn = restart_lsn;
SpinLockRelease(&slot->mutex);
/* make sure we have enough information to start */
flushptr = LogStandbySnapshot();
/* and make sure it's fsynced to disk */
XLogFlush(flushptr);
}
else
{
restart_lsn = GetRedoRecPtr();
SpinLockAcquire(&slot->mutex);
slot->data.restart_lsn = restart_lsn;
SpinLockRelease(&slot->mutex);
}
/* prevent WAL removal as fast as possible */
ReplicationSlotsComputeRequiredLSN();
/*
* If all required WAL is still there, great, otherwise retry. The
* slot should prevent further removal of WAL, unless there's a
* concurrent ReplicationSlotsComputeRequiredLSN() after we've written
* the new restart_lsn above, so normally we should never need to loop
* more than twice.
*/
XLByteToSeg(slot->data.restart_lsn, segno, wal_segment_size);
if (XLogGetLastRemovedSegno() < segno)
break;
}
}
/*
* START_REPLICATION
*/
static void
StartReplication(StartReplicationCmd *cmd)
{
StringInfoData buf;
/*
* Let postmaster know that we're streaming. Once we've declared us as a
* WAL sender process, postmaster will let us outlive the bgwriter and
* kill us last in the shutdown sequence, so we get a chance to stream all
* remaining WAL at shutdown, including the shutdown checkpoint. Note that
* there's no going back, and we mustn't write any WAL records after this.
*/
MarkPostmasterChildWalSender();
SendPostmasterSignal(PMSIGNAL_ADVANCE_STATE_MACHINE);
/*
* When promoting a cascading standby, postmaster sends SIGUSR2 to
* any cascading walsenders to kill them. But there is a corner-case where
* such walsender fails to receive SIGUSR2 and survives a standby promotion
* unexpectedly. This happens when postmaster sends SIGUSR2 before
* the walsender marks itself as a WAL sender, because postmaster sends
* SIGUSR2 to only the processes marked as a WAL sender.
*
* To avoid this corner-case, if recovery is NOT in progress even though
* the walsender is cascading one, we do the same thing as SIGUSR2 signal
* handler does, i.e., set walsender_ready_to_stop to true. Which causes
* the walsender to end later.
*
* When terminating cascading walsenders, usually postmaster writes
* the log message announcing the terminations. But there is a race condition
* here. If there is no walsender except this process before reaching here,
* postmaster thinks that there is no walsender and suppresses that
* log message. To handle this case, we always emit that log message here.
* This might cause duplicate log messages, but which is less likely to happen,
* so it's not worth writing some code to suppress them.
*/
if (am_cascading_walsender && !RecoveryInProgress())
{
ereport(LOG,
(errmsg("terminating walsender process to force cascaded standby "
"to update timeline and reconnect")));
walsender_ready_to_stop = true;
}
/*
* We assume here that we're logging enough information in the WAL for
* log-shipping, since this is checked in PostmasterMain().
*
* NOTE: wal_level can only change at shutdown, so in most cases it is
* difficult for there to be WAL data that we can still see that was written
* at wal_level='minimal'.
*/
/*
* When we first start replication the standby will be behind the primary.
* For some applications, for example, synchronous replication, it is
* important to have a clear state for this initial catchup mode, so we
* can trigger actions when we change streaming state later. We may stay
* in this state for a long time, which is exactly why we want to be able
* to monitor whether or not we are still here.
*/
WalSndSetState(WALSNDSTATE_CATCHUP);
/* Send a CopyBothResponse message, and start streaming */
pq_beginmessage(&buf, 'W');
pq_sendbyte(&buf, 0);
pq_sendint(&buf, 0, 2);
pq_endmessage(&buf);
pq_flush();
/*
* Initialize position to the received one, then the xlog records begin to
* be shipped from that position
*/
sentPtr = cmd->startpoint;
}
/*
* Actually do a base backup for the specified tablespaces.
*
* This is split out mainly to avoid complaints about "variable might be
* clobbered by longjmp" from stupider versions of gcc.
*/
static void
perform_base_backup(basebackup_options *opt, DIR *tblspcdir)
{
XLogRecPtr startptr;
TimeLineID starttli;
XLogRecPtr endptr;
TimeLineID endtli;
StringInfo labelfile;
StringInfo tblspc_map_file = NULL;
int datadirpathlen;
List *tablespaces = NIL;
datadirpathlen = strlen(DataDir);
backup_started_in_recovery = RecoveryInProgress();
labelfile = makeStringInfo();
tblspc_map_file = makeStringInfo();
startptr = do_pg_start_backup(opt->label, opt->fastcheckpoint, &starttli,
labelfile, tblspcdir, &tablespaces,
tblspc_map_file,
opt->progress, opt->sendtblspcmapfile);
/*
* Once do_pg_start_backup has been called, ensure that any failure causes
* us to abort the backup so we don't "leak" a backup counter. For this
* reason, *all* functionality between do_pg_start_backup() and
* do_pg_stop_backup() should be inside the error cleanup block!
*/
PG_ENSURE_ERROR_CLEANUP(base_backup_cleanup, (Datum) 0);
{
ListCell *lc;
tablespaceinfo *ti;
SendXlogRecPtrResult(startptr, starttli);
/*
* Calculate the relative path of temporary statistics directory in
* order to skip the files which are located in that directory later.
*/
if (is_absolute_path(pgstat_stat_directory) &&
strncmp(pgstat_stat_directory, DataDir, datadirpathlen) == 0)
statrelpath = psprintf("./%s", pgstat_stat_directory + datadirpathlen + 1);
else if (strncmp(pgstat_stat_directory, "./", 2) != 0)
statrelpath = psprintf("./%s", pgstat_stat_directory);
else
statrelpath = pgstat_stat_directory;
/* Add a node for the base directory at the end */
ti = palloc0(sizeof(tablespaceinfo));
ti->size = opt->progress ? sendDir(".", 1, true, tablespaces, true) : -1;
tablespaces = lappend(tablespaces, ti);
/* Send tablespace header */
SendBackupHeader(tablespaces);
/* Setup and activate network throttling, if client requested it */
if (opt->maxrate > 0)
{
throttling_sample =
(int64) opt->maxrate * (int64) 1024 / THROTTLING_FREQUENCY;
/*
* The minimum amount of time for throttling_sample bytes to be
* transferred.
*/
elapsed_min_unit = USECS_PER_SEC / THROTTLING_FREQUENCY;
/* Enable throttling. */
throttling_counter = 0;
/* The 'real data' starts now (header was ignored). */
throttled_last = GetCurrentIntegerTimestamp();
}
else
{
/* Disable throttling. */
throttling_counter = -1;
}
/* Send off our tablespaces one by one */
foreach(lc, tablespaces)
{
tablespaceinfo *ti = (tablespaceinfo *) lfirst(lc);
StringInfoData buf;
/* Send CopyOutResponse message */
pq_beginmessage(&buf, 'H');
pq_sendbyte(&buf, 0); /* overall format */
pq_sendint(&buf, 0, 2); /* natts */
pq_endmessage(&buf);
if (ti->path == NULL)
{
struct stat statbuf;
/* In the main tar, include the backup_label first... */
sendFileWithContent(BACKUP_LABEL_FILE, labelfile->data);
/*
* Send tablespace_map file if required and then the bulk of
* the files.
*/
if (tblspc_map_file && opt->sendtblspcmapfile)
{
sendFileWithContent(TABLESPACE_MAP, tblspc_map_file->data);
sendDir(".", 1, false, tablespaces, false);
}
else
sendDir(".", 1, false, tablespaces, true);
/* ... and pg_control after everything else. */
if (lstat(XLOG_CONTROL_FILE, &statbuf) != 0)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not stat control file \"%s\": %m",
XLOG_CONTROL_FILE)));
sendFile(XLOG_CONTROL_FILE, XLOG_CONTROL_FILE, &statbuf, false);
}
else
sendTablespace(ti->path, false);
/*
* If we're including WAL, and this is the main data directory we
* don't terminate the tar stream here. Instead, we will append
* the xlog files below and terminate it then. This is safe since
* the main data directory is always sent *last*.
*/
if (opt->includewal && ti->path == NULL)
{
Assert(lnext(lc) == NULL);
}
else
pq_putemptymessage('c'); /* CopyDone */
}
}
/*
* get_relation_info -
* Retrieves catalog information for a given relation.
*
* Given the Oid of the relation, return the following info into fields
* of the RelOptInfo struct:
*
* min_attr lowest valid AttrNumber
* max_attr highest valid AttrNumber
* indexlist list of IndexOptInfos for relation's indexes
* pages number of pages
* tuples number of tuples
*
* Also, initialize the attr_needed[] and attr_widths[] arrays. In most
* cases these are left as zeroes, but sometimes we need to compute attr
* widths here, and we may as well cache the results for costsize.c.
*
* If inhparent is true, all we need to do is set up the attr arrays:
* the RelOptInfo actually represents the appendrel formed by an inheritance
* tree, and so the parent rel's physical size and index information isn't
* important for it.
*/
void
get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
RelOptInfo *rel)
{
Index varno = rel->relid;
Relation relation;
bool hasindex;
List *indexinfos = NIL;
/*
* We need not lock the relation since it was already locked, either by
* the rewriter or when expand_inherited_rtentry() added it to the query's
* rangetable.
*/
relation = heap_open(relationObjectId, NoLock);
/* Temporary and unlogged relations are inaccessible during recovery. */
if (!RelationNeedsWAL(relation) && RecoveryInProgress())
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary or unlogged relations during recovery")));
rel->min_attr = FirstLowInvalidHeapAttributeNumber + 1;
rel->max_attr = RelationGetNumberOfAttributes(relation);
rel->reltablespace = RelationGetForm(relation)->reltablespace;
Assert(rel->max_attr >= rel->min_attr);
rel->attr_needed = (Relids *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(Relids));
rel->attr_widths = (int32 *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(int32));
/*
* Estimate relation size --- unless it's an inheritance parent, in which
* case the size will be computed later in set_append_rel_pathlist, and we
* must leave it zero for now to avoid bollixing the total_table_pages
* calculation.
*/
if (!inhparent)
estimate_rel_size(relation, rel->attr_widths - rel->min_attr,
&rel->pages, &rel->tuples, &rel->allvisfrac);
/*
* Make list of indexes. Ignore indexes on system catalogs if told to.
* Don't bother with indexes for an inheritance parent, either.
*/
if (inhparent ||
(IgnoreSystemIndexes && IsSystemClass(relation->rd_rel)))
hasindex = false;
else
hasindex = relation->rd_rel->relhasindex;
if (hasindex)
{
List *indexoidlist;
ListCell *l;
LOCKMODE lmode;
indexoidlist = RelationGetIndexList(relation);
/*
* For each index, we get the same type of lock that the executor will
* need, and do not release it. This saves a couple of trips to the
* shared lock manager while not creating any real loss of
* concurrency, because no schema changes could be happening on the
* index while we hold lock on the parent rel, and neither lock type
* blocks any other kind of index operation.
*/
if (rel->relid == root->parse->resultRelation)
lmode = RowExclusiveLock;
else
lmode = AccessShareLock;
foreach(l, indexoidlist)
{
Oid indexoid = lfirst_oid(l);
Relation indexRelation;
Form_pg_index index;
IndexOptInfo *info;
int ncolumns;
int i;
/*
* Extract info from the relation descriptor for the index.
*/
indexRelation = index_open(indexoid, lmode);
index = indexRelation->rd_index;
/*
* Ignore invalid indexes, since they can't safely be used for
* queries. Note that this is OK because the data structure we
* are constructing is only used by the planner --- the executor
* still needs to insert into "invalid" indexes!
*/
if (!index->indisvalid)
{
index_close(indexRelation, NoLock);
continue;
}
/*
* If the index is valid, but cannot yet be used, ignore it; but
* mark the plan we are generating as transient. See
* src/backend/access/heap/README.HOT for discussion.
*/
if (index->indcheckxmin &&
!TransactionIdPrecedes(HeapTupleHeaderGetXmin(indexRelation->rd_indextuple->t_data),
TransactionXmin))
{
root->glob->transientPlan = true;
index_close(indexRelation, NoLock);
continue;
}
info = makeNode(IndexOptInfo);
info->indexoid = index->indexrelid;
info->reltablespace =
RelationGetForm(indexRelation)->reltablespace;
info->rel = rel;
info->ncolumns = ncolumns = index->indnatts;
info->indexkeys = (int *) palloc(sizeof(int) * ncolumns);
info->indexcollations = (Oid *) palloc(sizeof(Oid) * ncolumns);
info->opfamily = (Oid *) palloc(sizeof(Oid) * ncolumns);
info->opcintype = (Oid *) palloc(sizeof(Oid) * ncolumns);
for (i = 0; i < ncolumns; i++)
{
info->indexkeys[i] = index->indkey.values[i];
info->indexcollations[i] = indexRelation->rd_indcollation[i];
info->opfamily[i] = indexRelation->rd_opfamily[i];
info->opcintype[i] = indexRelation->rd_opcintype[i];
}
info->relam = indexRelation->rd_rel->relam;
info->amcostestimate = indexRelation->rd_am->amcostestimate;
info->canreturn = index_can_return(indexRelation);
info->amcanorderbyop = indexRelation->rd_am->amcanorderbyop;
info->amoptionalkey = indexRelation->rd_am->amoptionalkey;
info->amsearcharray = indexRelation->rd_am->amsearcharray;
info->amsearchnulls = indexRelation->rd_am->amsearchnulls;
info->amhasgettuple = OidIsValid(indexRelation->rd_am->amgettuple);
info->amhasgetbitmap = OidIsValid(indexRelation->rd_am->amgetbitmap);
/*
* Fetch the ordering information for the index, if any.
*/
if (info->relam == BTREE_AM_OID)
{
/*
* If it's a btree index, we can use its opfamily OIDs
* directly as the sort ordering opfamily OIDs.
*/
Assert(indexRelation->rd_am->amcanorder);
info->sortopfamily = info->opfamily;
info->reverse_sort = (bool *) palloc(sizeof(bool) * ncolumns);
info->nulls_first = (bool *) palloc(sizeof(bool) * ncolumns);
for (i = 0; i < ncolumns; i++)
{
int16 opt = indexRelation->rd_indoption[i];
info->reverse_sort[i] = (opt & INDOPTION_DESC) != 0;
info->nulls_first[i] = (opt & INDOPTION_NULLS_FIRST) != 0;
}
}
else if (indexRelation->rd_am->amcanorder)
{
/*
* Otherwise, identify the corresponding btree opfamilies by
* trying to map this index's "<" operators into btree. Since
* "<" uniquely defines the behavior of a sort order, this is
* a sufficient test.
*
* XXX This method is rather slow and also requires the
* undesirable assumption that the other index AM numbers its
* strategies the same as btree. It'd be better to have a way
* to explicitly declare the corresponding btree opfamily for
* each opfamily of the other index type. But given the lack
* of current or foreseeable amcanorder index types, it's not
* worth expending more effort on now.
*/
info->sortopfamily = (Oid *) palloc(sizeof(Oid) * ncolumns);
info->reverse_sort = (bool *) palloc(sizeof(bool) * ncolumns);
info->nulls_first = (bool *) palloc(sizeof(bool) * ncolumns);
for (i = 0; i < ncolumns; i++)
{
int16 opt = indexRelation->rd_indoption[i];
Oid ltopr;
Oid btopfamily;
Oid btopcintype;
int16 btstrategy;
info->reverse_sort[i] = (opt & INDOPTION_DESC) != 0;
info->nulls_first[i] = (opt & INDOPTION_NULLS_FIRST) != 0;
ltopr = get_opfamily_member(info->opfamily[i],
info->opcintype[i],
info->opcintype[i],
BTLessStrategyNumber);
if (OidIsValid(ltopr) &&
get_ordering_op_properties(ltopr,
&btopfamily,
&btopcintype,
&btstrategy) &&
btopcintype == info->opcintype[i] &&
btstrategy == BTLessStrategyNumber)
{
/* Successful mapping */
info->sortopfamily[i] = btopfamily;
}
else
{
/* Fail ... quietly treat index as unordered */
info->sortopfamily = NULL;
info->reverse_sort = NULL;
info->nulls_first = NULL;
break;
}
}
}
else
{
info->sortopfamily = NULL;
info->reverse_sort = NULL;
info->nulls_first = NULL;
}
/*
* Fetch the index expressions and predicate, if any. We must
* modify the copies we obtain from the relcache to have the
* correct varno for the parent relation, so that they match up
* correctly against qual clauses.
*/
info->indexprs = RelationGetIndexExpressions(indexRelation);
info->indpred = RelationGetIndexPredicate(indexRelation);
if (info->indexprs && varno != 1)
ChangeVarNodes((Node *) info->indexprs, 1, varno, 0);
if (info->indpred && varno != 1)
ChangeVarNodes((Node *) info->indpred, 1, varno, 0);
/* Build targetlist using the completed indexprs data */
info->indextlist = build_index_tlist(root, info, relation);
info->predOK = false; /* set later in indxpath.c */
info->unique = index->indisunique;
info->immediate = index->indimmediate;
info->hypothetical = false;
/*
* Estimate the index size. If it's not a partial index, we lock
* the number-of-tuples estimate to equal the parent table; if it
* is partial then we have to use the same methods as we would for
* a table, except we can be sure that the index is not larger
* than the table.
*/
if (info->indpred == NIL)
{
info->pages = RelationGetNumberOfBlocks(indexRelation);
info->tuples = rel->tuples;
}
else
{
double allvisfrac; /* dummy */
estimate_rel_size(indexRelation, NULL,
&info->pages, &info->tuples, &allvisfrac);
if (info->tuples > rel->tuples)
info->tuples = rel->tuples;
}
index_close(indexRelation, NoLock);
indexinfos = lcons(info, indexinfos);
}
list_free(indexoidlist);
}
/*
* Main entry point for bgwriter process
*
* This is invoked from AuxiliaryProcessMain, which has already created the
* basic execution environment, but not enabled signals yet.
*/
void
BackgroundWriterMain(void)
{
sigjmp_buf local_sigjmp_buf;
MemoryContext bgwriter_context;
bool prev_hibernate;
WritebackContext wb_context;
/*
* Properly accept or ignore signals the postmaster might send us.
*
* bgwriter doesn't participate in ProcSignal signalling, but a SIGUSR1
* handler is still needed for latch wakeups.
*/
pqsignal(SIGHUP, BgSigHupHandler); /* set flag to read config file */
pqsignal(SIGINT, SIG_IGN);
pqsignal(SIGTERM, ReqShutdownHandler); /* shutdown */
pqsignal(SIGQUIT, bg_quickdie); /* hard crash time */
pqsignal(SIGALRM, SIG_IGN);
pqsignal(SIGPIPE, SIG_IGN);
pqsignal(SIGUSR1, bgwriter_sigusr1_handler);
pqsignal(SIGUSR2, SIG_IGN);
/*
* Reset some signals that are accepted by postmaster but not here
*/
pqsignal(SIGCHLD, SIG_DFL);
pqsignal(SIGTTIN, SIG_DFL);
pqsignal(SIGTTOU, SIG_DFL);
pqsignal(SIGCONT, SIG_DFL);
pqsignal(SIGWINCH, SIG_DFL);
/* We allow SIGQUIT (quickdie) at all times */
sigdelset(&BlockSig, SIGQUIT);
/*
* Create a resource owner to keep track of our resources (currently only
* buffer pins).
*/
CurrentResourceOwner = ResourceOwnerCreate(NULL, "Background Writer");
/*
* We just started, assume there has been either a shutdown or
* end-of-recovery snapshot.
*/
last_snapshot_ts = GetCurrentTimestamp();
/*
* Create a memory context that we will do all our work in. We do this so
* that we can reset the context during error recovery and thereby avoid
* possible memory leaks. Formerly this code just ran in
* TopMemoryContext, but resetting that would be a really bad idea.
*/
bgwriter_context = AllocSetContextCreate(TopMemoryContext,
"Background Writer",
ALLOCSET_DEFAULT_SIZES);
MemoryContextSwitchTo(bgwriter_context);
WritebackContextInit(&wb_context, &bgwriter_flush_after);
/*
* If an exception is encountered, processing resumes here.
*
* See notes in postgres.c about the design of this coding.
*/
if (sigsetjmp(local_sigjmp_buf, 1) != 0)
{
/* Since not using PG_TRY, must reset error stack by hand */
error_context_stack = NULL;
/* Prevent interrupts while cleaning up */
HOLD_INTERRUPTS();
/* Report the error to the server log */
EmitErrorReport();
/*
* These operations are really just a minimal subset of
* AbortTransaction(). We don't have very many resources to worry
* about in bgwriter, but we do have LWLocks, buffers, and temp files.
*/
LWLockReleaseAll();
AbortBufferIO();
UnlockBuffers();
/* buffer pins are released here: */
ResourceOwnerRelease(CurrentResourceOwner,
RESOURCE_RELEASE_BEFORE_LOCKS,
false, true);
/* we needn't bother with the other ResourceOwnerRelease phases */
AtEOXact_Buffers(false);
AtEOXact_SMgr();
AtEOXact_Files();
AtEOXact_HashTables(false);
/*
* Now return to normal top-level context and clear ErrorContext for
* next time.
*/
MemoryContextSwitchTo(bgwriter_context);
FlushErrorState();
/* Flush any leaked data in the top-level context */
MemoryContextResetAndDeleteChildren(bgwriter_context);
/* re-initilialize to avoid repeated errors causing problems */
WritebackContextInit(&wb_context, &bgwriter_flush_after);
/* Now we can allow interrupts again */
RESUME_INTERRUPTS();
/*
* Sleep at least 1 second after any error. A write error is likely
* to be repeated, and we don't want to be filling the error logs as
* fast as we can.
*/
pg_usleep(1000000L);
/*
* Close all open files after any error. This is helpful on Windows,
* where holding deleted files open causes various strange errors.
* It's not clear we need it elsewhere, but shouldn't hurt.
*/
smgrcloseall();
/* Report wait end here, when there is no further possibility of wait */
pgstat_report_wait_end();
}
/* We can now handle ereport(ERROR) */
PG_exception_stack = &local_sigjmp_buf;
/*
* Unblock signals (they were blocked when the postmaster forked us)
*/
PG_SETMASK(&UnBlockSig);
/*
* Reset hibernation state after any error.
*/
prev_hibernate = false;
/*
* Loop forever
*/
for (;;)
{
bool can_hibernate;
int rc;
/* Clear any already-pending wakeups */
ResetLatch(MyLatch);
if (got_SIGHUP)
{
got_SIGHUP = false;
ProcessConfigFile(PGC_SIGHUP);
}
if (shutdown_requested)
{
/*
* From here on, elog(ERROR) should end with exit(1), not send
* control back to the sigsetjmp block above
*/
ExitOnAnyError = true;
/* Normal exit from the bgwriter is here */
proc_exit(0); /* done */
}
/*
* Do one cycle of dirty-buffer writing.
*/
can_hibernate = BgBufferSync(&wb_context);
/*
* Send off activity statistics to the stats collector
*/
pgstat_send_bgwriter();
if (FirstCallSinceLastCheckpoint())
{
/*
* After any checkpoint, close all smgr files. This is so we
* won't hang onto smgr references to deleted files indefinitely.
*/
smgrcloseall();
}
/*
* Log a new xl_running_xacts every now and then so replication can
* get into a consistent state faster (think of suboverflowed
* snapshots) and clean up resources (locks, KnownXids*) more
* frequently. The costs of this are relatively low, so doing it 4
* times (LOG_SNAPSHOT_INTERVAL_MS) a minute seems fine.
*
* We assume the interval for writing xl_running_xacts is
* significantly bigger than BgWriterDelay, so we don't complicate the
* overall timeout handling but just assume we're going to get called
* often enough even if hibernation mode is active. It's not that
* important that log_snap_interval_ms is met strictly. To make sure
* we're not waking the disk up unnecessarily on an idle system we
* check whether there has been any WAL inserted since the last time
* we've logged a running xacts.
*
* We do this logging in the bgwriter as its the only process that is
* run regularly and returns to its mainloop all the time. E.g.
* Checkpointer, when active, is barely ever in its mainloop and thus
* makes it hard to log regularly.
*/
if (XLogStandbyInfoActive() && !RecoveryInProgress())
{
TimestampTz timeout = 0;
TimestampTz now = GetCurrentTimestamp();
timeout = TimestampTzPlusMilliseconds(last_snapshot_ts,
LOG_SNAPSHOT_INTERVAL_MS);
/*
* only log if enough time has passed and some xlog record has
* been inserted.
*/
if (now >= timeout &&
last_snapshot_lsn != GetXLogInsertRecPtr())
{
last_snapshot_lsn = LogStandbySnapshot();
last_snapshot_ts = now;
}
}
/*
* Sleep until we are signaled or BgWriterDelay has elapsed.
*
* Note: the feedback control loop in BgBufferSync() expects that we
* will call it every BgWriterDelay msec. While it's not critical for
* correctness that that be exact, the feedback loop might misbehave
* if we stray too far from that. Hence, avoid loading this process
* down with latch events that are likely to happen frequently during
* normal operation.
*/
rc = WaitLatch(MyLatch,
WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
BgWriterDelay /* ms */ );
/*
* If no latch event and BgBufferSync says nothing's happening, extend
* the sleep in "hibernation" mode, where we sleep for much longer
* than bgwriter_delay says. Fewer wakeups save electricity. When a
* backend starts using buffers again, it will wake us up by setting
* our latch. Because the extra sleep will persist only as long as no
* buffer allocations happen, this should not distort the behavior of
* BgBufferSync's control loop too badly; essentially, it will think
* that the system-wide idle interval didn't exist.
*
* There is a race condition here, in that a backend might allocate a
* buffer between the time BgBufferSync saw the alloc count as zero
* and the time we call StrategyNotifyBgWriter. While it's not
* critical that we not hibernate anyway, we try to reduce the odds of
* that by only hibernating when BgBufferSync says nothing's happening
* for two consecutive cycles. Also, we mitigate any possible
* consequences of a missed wakeup by not hibernating forever.
*/
if (rc == WL_TIMEOUT && can_hibernate && prev_hibernate)
{
/* Ask for notification at next buffer allocation */
StrategyNotifyBgWriter(MyProc->pgprocno);
/* Sleep ... */
rc = WaitLatch(MyLatch,
WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
BgWriterDelay * HIBERNATE_FACTOR);
/* Reset the notification request in case we timed out */
StrategyNotifyBgWriter(-1);
}
/*
* Emergency bailout if postmaster has died. This is to avoid the
* necessity for manual cleanup of all postmaster children.
*/
if (rc & WL_POSTMASTER_DEATH)
exit(1);
prev_hibernate = can_hibernate;
}
}
/*
* Actually do a base backup for the specified tablespaces.
*
* This is split out mainly to avoid complaints about "variable might be
* clobbered by longjmp" from stupider versions of gcc.
*/
static void
perform_base_backup(basebackup_options *opt, DIR *tblspcdir)
{
XLogRecPtr startptr;
TimeLineID starttli;
XLogRecPtr endptr;
TimeLineID endtli;
char *labelfile;
int datadirpathlen;
datadirpathlen = strlen(DataDir);
backup_started_in_recovery = RecoveryInProgress();
startptr = do_pg_start_backup(opt->label, opt->fastcheckpoint, &starttli,
&labelfile);
/*
* Once do_pg_start_backup has been called, ensure that any failure causes
* us to abort the backup so we don't "leak" a backup counter. For this reason,
* *all* functionality between do_pg_start_backup() and do_pg_stop_backup()
* should be inside the error cleanup block!
*/
PG_ENSURE_ERROR_CLEANUP(base_backup_cleanup, (Datum) 0);
{
List *tablespaces = NIL;
ListCell *lc;
struct dirent *de;
tablespaceinfo *ti;
SendXlogRecPtrResult(startptr, starttli);
/*
* Calculate the relative path of temporary statistics directory in order
* to skip the files which are located in that directory later.
*/
if (is_absolute_path(pgstat_stat_directory) &&
strncmp(pgstat_stat_directory, DataDir, datadirpathlen) == 0)
statrelpath = psprintf("./%s", pgstat_stat_directory + datadirpathlen + 1);
else if (strncmp(pgstat_stat_directory, "./", 2) != 0)
statrelpath = psprintf("./%s", pgstat_stat_directory);
else
statrelpath = pgstat_stat_directory;
/* Collect information about all tablespaces */
while ((de = ReadDir(tblspcdir, "pg_tblspc")) != NULL)
{
char fullpath[MAXPGPATH];
char linkpath[MAXPGPATH];
char *relpath = NULL;
int rllen;
/* Skip special stuff */
if (strcmp(de->d_name, ".") == 0 || strcmp(de->d_name, "..") == 0)
continue;
snprintf(fullpath, sizeof(fullpath), "pg_tblspc/%s", de->d_name);
#if defined(HAVE_READLINK) || defined(WIN32)
rllen = readlink(fullpath, linkpath, sizeof(linkpath));
if (rllen < 0)
{
ereport(WARNING,
(errmsg("could not read symbolic link \"%s\": %m",
fullpath)));
continue;
}
else if (rllen >= sizeof(linkpath))
{
ereport(WARNING,
(errmsg("symbolic link \"%s\" target is too long",
fullpath)));
continue;
}
linkpath[rllen] = '\0';
/*
* Relpath holds the relative path of the tablespace directory
* when it's located within PGDATA, or NULL if it's located
* elsewhere.
*/
if (rllen > datadirpathlen &&
strncmp(linkpath, DataDir, datadirpathlen) == 0 &&
IS_DIR_SEP(linkpath[datadirpathlen]))
relpath = linkpath + datadirpathlen + 1;
ti = palloc(sizeof(tablespaceinfo));
ti->oid = pstrdup(de->d_name);
ti->path = pstrdup(linkpath);
ti->rpath = relpath ? pstrdup(relpath) : NULL;
ti->size = opt->progress ? sendTablespace(fullpath, true) : -1;
tablespaces = lappend(tablespaces, ti);
#else
/*
* If the platform does not have symbolic links, it should not be
* possible to have tablespaces - clearly somebody else created
* them. Warn about it and ignore.
*/
ereport(WARNING,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("tablespaces are not supported on this platform")));
#endif
}
/* Add a node for the base directory at the end */
ti = palloc0(sizeof(tablespaceinfo));
ti->size = opt->progress ? sendDir(".", 1, true, tablespaces) : -1;
tablespaces = lappend(tablespaces, ti);
/* Send tablespace header */
SendBackupHeader(tablespaces);
/* Setup and activate network throttling, if client requested it */
if (opt->maxrate > 0)
{
throttling_sample =
(int64) opt->maxrate * (int64) 1024 / THROTTLING_FREQUENCY;
/*
* The minimum amount of time for throttling_sample bytes to be
* transfered.
*/
elapsed_min_unit = USECS_PER_SEC / THROTTLING_FREQUENCY;
/* Enable throttling. */
throttling_counter = 0;
/* The 'real data' starts now (header was ignored). */
throttled_last = GetCurrentIntegerTimestamp();
}
else
{
/* Disable throttling. */
throttling_counter = -1;
}
/* Send off our tablespaces one by one */
foreach(lc, tablespaces)
{
tablespaceinfo *ti = (tablespaceinfo *) lfirst(lc);
StringInfoData buf;
/* Send CopyOutResponse message */
pq_beginmessage(&buf, 'H');
pq_sendbyte(&buf, 0); /* overall format */
pq_sendint(&buf, 0, 2); /* natts */
pq_endmessage(&buf);
if (ti->path == NULL)
{
struct stat statbuf;
/* In the main tar, include the backup_label first... */
sendFileWithContent(BACKUP_LABEL_FILE, labelfile);
/* ... then the bulk of the files ... */
sendDir(".", 1, false, tablespaces);
/* ... and pg_control after everything else. */
if (lstat(XLOG_CONTROL_FILE, &statbuf) != 0)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not stat control file \"%s\": %m",
XLOG_CONTROL_FILE)));
sendFile(XLOG_CONTROL_FILE, XLOG_CONTROL_FILE, &statbuf, false);
}
else
sendTablespace(ti->path, false);
/*
* If we're including WAL, and this is the main data directory we
* don't terminate the tar stream here. Instead, we will append
* the xlog files below and terminate it then. This is safe since
* the main data directory is always sent *last*.
*/
if (opt->includewal && ti->path == NULL)
{
Assert(lnext(lc) == NULL);
}
else
pq_putemptymessage('c'); /* CopyDone */
}
}
/*
* Compute an xlog file name and decimal byte offset given a WAL location,
* such as is returned by pg_stop_backup() or pg_xlog_switch().
*
* Note that a location exactly at a segment boundary is taken to be in
* the previous segment. This is usually the right thing, since the
* expected usage is to determine which xlog file(s) are ready to archive.
*/
Datum
pg_xlogfile_name_offset(PG_FUNCTION_ARGS)
{
text *location = PG_GETARG_TEXT_P(0);
char *locationstr;
unsigned int uxlogid;
unsigned int uxrecoff;
uint32 xlogid;
uint32 xlogseg;
uint32 xrecoff;
XLogRecPtr locationpoint;
char xlogfilename[MAXFNAMELEN];
Datum values[2];
bool isnull[2];
TupleDesc resultTupleDesc;
HeapTuple resultHeapTuple;
Datum result;
if (RecoveryInProgress())
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("recovery is in progress"),
errhint("pg_xlogfile_name_offset() cannot be executed during recovery.")));
/*
* Read input and parse
*/
locationstr = text_to_cstring(location);
validate_xlog_location(locationstr);
if (sscanf(locationstr, "%X/%X", &uxlogid, &uxrecoff) != 2)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("could not parse transaction log location \"%s\"",
locationstr)));
locationpoint.xlogid = uxlogid;
locationpoint.xrecoff = uxrecoff;
/*
* Construct a tuple descriptor for the result row. This must match this
* function's pg_proc entry!
*/
resultTupleDesc = CreateTemplateTupleDesc(2, false);
TupleDescInitEntry(resultTupleDesc, (AttrNumber) 1, "file_name",
TEXTOID, -1, 0);
TupleDescInitEntry(resultTupleDesc, (AttrNumber) 2, "file_offset",
INT4OID, -1, 0);
resultTupleDesc = BlessTupleDesc(resultTupleDesc);
/*
* xlogfilename
*/
XLByteToPrevSeg(locationpoint, xlogid, xlogseg);
XLogFileName(xlogfilename, ThisTimeLineID, xlogid, xlogseg);
values[0] = CStringGetTextDatum(xlogfilename);
isnull[0] = false;
/*
* offset
*/
xrecoff = locationpoint.xrecoff - xlogseg * XLogSegSize;
values[1] = UInt32GetDatum(xrecoff);
isnull[1] = false;
/*
* Tuple jam: Having first prepared your Datums, then squash together
*/
resultHeapTuple = heap_form_tuple(resultTupleDesc, values, isnull);
result = HeapTupleGetDatum(resultHeapTuple);
PG_RETURN_DATUM(result);
}
/*
* Optionally prune and repair fragmentation in the specified page.
*
* This is an opportunistic function. It will perform housekeeping
* only if the page heuristically looks like a candidate for pruning and we
* can acquire buffer cleanup lock without blocking.
*
* Note: this is called quite often. It's important that it fall out quickly
* if there's not any use in pruning.
*
* Caller must have pin on the buffer, and must *not* have a lock on it.
*
* OldestXmin is the cutoff XID used to distinguish whether tuples are DEAD
* or RECENTLY_DEAD (see HeapTupleSatisfiesVacuum).
*/
void
heap_page_prune_opt(Relation relation, Buffer buffer)
{
Page page = BufferGetPage(buffer);
Size minfree;
TransactionId OldestXmin;
/*
* We can't write WAL in recovery mode, so there's no point trying to
* clean the page. The master will likely issue a cleaning WAL record soon
* anyway, so this is no particular loss.
*/
if (RecoveryInProgress())
return;
/*
* Use the appropriate xmin horizon for this relation. If it's a proper
* catalog relation or a user defined, additional, catalog relation, we
* need to use the horizon that includes slots, otherwise the data-only
* horizon can be used. Note that the toast relation of user defined
* relations are *not* considered catalog relations.
*
* It is OK to apply the old snapshot limit before acquiring the cleanup
* lock because the worst that can happen is that we are not quite as
* aggressive about the cleanup (by however many transaction IDs are
* consumed between this point and acquiring the lock). This allows us to
* save significant overhead in the case where the page is found not to be
* prunable.
*/
if (IsCatalogRelation(relation) ||
RelationIsAccessibleInLogicalDecoding(relation))
OldestXmin = RecentGlobalXmin;
else
OldestXmin =
TransactionIdLimitedForOldSnapshots(RecentGlobalDataXmin,
relation);
Assert(TransactionIdIsValid(OldestXmin));
/*
* Let's see if we really need pruning.
*
* Forget it if page is not hinted to contain something prunable that's
* older than OldestXmin.
*/
if (!PageIsPrunable(page, OldestXmin))
return;
/*
* We prune when a previous UPDATE failed to find enough space on the page
* for a new tuple version, or when free space falls below the relation's
* fill-factor target (but not less than 10%).
*
* Checking free space here is questionable since we aren't holding any
* lock on the buffer; in the worst case we could get a bogus answer. It's
* unlikely to be *seriously* wrong, though, since reading either pd_lower
* or pd_upper is probably atomic. Avoiding taking a lock seems more
* important than sometimes getting a wrong answer in what is after all
* just a heuristic estimate.
*/
minfree = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
minfree = Max(minfree, BLCKSZ / 10);
if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
{
/* OK, try to get exclusive buffer lock */
if (!ConditionalLockBufferForCleanup(buffer))
return;
/*
* Now that we have buffer lock, get accurate information about the
* page's free space, and recheck the heuristic about whether to
* prune. (We needn't recheck PageIsPrunable, since no one else could
* have pruned while we hold pin.)
*/
if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
{
TransactionId ignore = InvalidTransactionId; /* return value not
* needed */
/* OK to prune */
(void) heap_page_prune(relation, buffer, OldestXmin, true, &ignore);
}
/* And release buffer lock */
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
}
}
/*
* SQL-callable interface to mark a range as no longer summarized
*/
Datum
brin_desummarize_range(PG_FUNCTION_ARGS)
{
Oid indexoid = PG_GETARG_OID(0);
int64 heapBlk64 = PG_GETARG_INT64(1);
BlockNumber heapBlk;
Oid heapoid;
Relation heapRel;
Relation indexRel;
bool done;
if (RecoveryInProgress())
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("recovery is in progress"),
errhint("BRIN control functions cannot be executed during recovery.")));
if (heapBlk64 > MaxBlockNumber || heapBlk64 < 0)
{
char *blk = psprintf(INT64_FORMAT, heapBlk64);
ereport(ERROR,
(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
errmsg("block number out of range: %s", blk)));
}
heapBlk = (BlockNumber) heapBlk64;
/*
* We must lock table before index to avoid deadlocks. However, if the
* passed indexoid isn't an index then IndexGetRelation() will fail.
* Rather than emitting a not-very-helpful error message, postpone
* complaining, expecting that the is-it-an-index test below will fail.
*/
heapoid = IndexGetRelation(indexoid, true);
if (OidIsValid(heapoid))
heapRel = table_open(heapoid, ShareUpdateExclusiveLock);
else
heapRel = NULL;
indexRel = index_open(indexoid, ShareUpdateExclusiveLock);
/* Must be a BRIN index */
if (indexRel->rd_rel->relkind != RELKIND_INDEX ||
indexRel->rd_rel->relam != BRIN_AM_OID)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is not a BRIN index",
RelationGetRelationName(indexRel))));
/* User must own the index (comparable to privileges needed for VACUUM) */
if (!pg_class_ownercheck(indexoid, GetUserId()))
aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_INDEX,
RelationGetRelationName(indexRel));
/*
* Since we did the IndexGetRelation call above without any lock, it's
* barely possible that a race against an index drop/recreation could have
* netted us the wrong table. Recheck.
*/
if (heapRel == NULL || heapoid != IndexGetRelation(indexoid, false))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_TABLE),
errmsg("could not open parent table of index %s",
RelationGetRelationName(indexRel))));
/* the revmap does the hard work */
do
{
done = brinRevmapDesummarizeRange(indexRel, heapBlk);
}
while (!done);
relation_close(indexRel, ShareUpdateExclusiveLock);
relation_close(heapRel, ShareUpdateExclusiveLock);
PG_RETURN_VOID();
}
/*
* Helper function for the various SQL callable logical decoding functions.
*/
static Datum
pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool binary)
{
Name name;
XLogRecPtr upto_lsn;
int32 upto_nchanges;
ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
MemoryContext per_query_ctx;
MemoryContext oldcontext;
XLogRecPtr end_of_wal;
XLogRecPtr startptr;
LogicalDecodingContext *ctx;
ResourceOwner old_resowner = CurrentResourceOwner;
ArrayType *arr;
Size ndim;
List *options = NIL;
DecodingOutputState *p;
check_permissions();
CheckLogicalDecodingRequirements();
if (PG_ARGISNULL(0))
ereport(ERROR,
(errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED),
errmsg("slot name must not be null")));
name = PG_GETARG_NAME(0);
if (PG_ARGISNULL(1))
upto_lsn = InvalidXLogRecPtr;
else
upto_lsn = PG_GETARG_LSN(1);
if (PG_ARGISNULL(2))
upto_nchanges = InvalidXLogRecPtr;
else
upto_nchanges = PG_GETARG_INT32(2);
if (PG_ARGISNULL(3))
ereport(ERROR,
(errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED),
errmsg("options array must not be null")));
arr = PG_GETARG_ARRAYTYPE_P(3);
/* check to see if caller supports us returning a tuplestore */
if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("set-valued function called in context that cannot accept a set")));
if (!(rsinfo->allowedModes & SFRM_Materialize))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("materialize mode required, but it is not allowed in this context")));
/* state to write output to */
p = palloc0(sizeof(DecodingOutputState));
p->binary_output = binary;
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &p->tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
per_query_ctx = rsinfo->econtext->ecxt_per_query_memory;
oldcontext = MemoryContextSwitchTo(per_query_ctx);
/* Deconstruct options array */
ndim = ARR_NDIM(arr);
if (ndim > 1)
{
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("array must be one-dimensional")));
}
else if (array_contains_nulls(arr))
{
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("array must not contain nulls")));
}
else if (ndim == 1)
{
int nelems;
Datum *datum_opts;
int i;
Assert(ARR_ELEMTYPE(arr) == TEXTOID);
deconstruct_array(arr, TEXTOID, -1, false, 'i',
&datum_opts, NULL, &nelems);
if (nelems % 2 != 0)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("array must have even number of elements")));
for (i = 0; i < nelems; i += 2)
{
char *name = TextDatumGetCString(datum_opts[i]);
char *opt = TextDatumGetCString(datum_opts[i + 1]);
options = lappend(options, makeDefElem(name, (Node *) makeString(opt), -1));
}
}
p->tupstore = tuplestore_begin_heap(true, false, work_mem);
rsinfo->returnMode = SFRM_Materialize;
rsinfo->setResult = p->tupstore;
rsinfo->setDesc = p->tupdesc;
/* compute the current end-of-wal */
if (!RecoveryInProgress())
end_of_wal = GetFlushRecPtr();
else
end_of_wal = GetXLogReplayRecPtr(NULL);
ReplicationSlotAcquire(NameStr(*name));
PG_TRY();
{
/* restart at slot's confirmed_flush */
ctx = CreateDecodingContext(InvalidXLogRecPtr,
options,
logical_read_local_xlog_page,
LogicalOutputPrepareWrite,
LogicalOutputWrite);
MemoryContextSwitchTo(oldcontext);
/*
* Check whether the output plugin writes textual output if that's
* what we need.
*/
if (!binary &&
ctx->options.output_type !=OUTPUT_PLUGIN_TEXTUAL_OUTPUT)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("logical decoding output plugin \"%s\" produces binary output, but function \"%s\" expects textual data",
NameStr(MyReplicationSlot->data.plugin),
format_procedure(fcinfo->flinfo->fn_oid))));
ctx->output_writer_private = p;
/*
* Decoding of WAL must start at restart_lsn so that the entirety of
* xacts that committed after the slot's confirmed_flush can be
* accumulated into reorder buffers.
*/
startptr = MyReplicationSlot->data.restart_lsn;
CurrentResourceOwner = ResourceOwnerCreate(CurrentResourceOwner, "logical decoding");
/* invalidate non-timetravel entries */
InvalidateSystemCaches();
while ((startptr != InvalidXLogRecPtr && startptr < end_of_wal) ||
(ctx->reader->EndRecPtr != InvalidXLogRecPtr && ctx->reader->EndRecPtr < end_of_wal))
{
XLogRecord *record;
char *errm = NULL;
record = XLogReadRecord(ctx->reader, startptr, &errm);
if (errm)
elog(ERROR, "%s", errm);
/*
* Now that we've set up the xlog reader state, subsequent calls
* pass InvalidXLogRecPtr to say "continue from last record"
*/
startptr = InvalidXLogRecPtr;
/*
* The {begin_txn,change,commit_txn}_wrapper callbacks above will
* store the description into our tuplestore.
*/
if (record != NULL)
LogicalDecodingProcessRecord(ctx, ctx->reader);
/* check limits */
if (upto_lsn != InvalidXLogRecPtr &&
upto_lsn <= ctx->reader->EndRecPtr)
break;
if (upto_nchanges != 0 &&
upto_nchanges <= p->returned_rows)
break;
CHECK_FOR_INTERRUPTS();
}
tuplestore_donestoring(tupstore);
CurrentResourceOwner = old_resowner;
/*
* Next time, start where we left off. (Hunting things, the family
* business..)
*/
if (ctx->reader->EndRecPtr != InvalidXLogRecPtr && confirm)
{
LogicalConfirmReceivedLocation(ctx->reader->EndRecPtr);
/*
* If only the confirmed_flush_lsn has changed the slot won't get
* marked as dirty by the above. Callers on the walsender interface
* are expected to keep track of their own progress and don't need
* it written out. But SQL-interface users cannot specify their own
* start positions and it's harder for them to keep track of their
* progress, so we should make more of an effort to save it for them.
*
* Dirty the slot so it's written out at the next checkpoint. We'll
* still lose its position on crash, as documented, but it's better
* than always losing the position even on clean restart.
*/
ReplicationSlotMarkDirty();
}
/* free context, call shutdown callback */
FreeDecodingContext(ctx);
ReplicationSlotRelease();
InvalidateSystemCaches();
}
PG_CATCH();
{
/* clear all timetravel entries */
InvalidateSystemCaches();
PG_RE_THROW();
}
PG_END_TRY();
return (Datum) 0;
}
/*
* IsCheckpointOnSchedule -- are we on schedule to finish this checkpoint
* in time?
*
* Compares the current progress against the time/segments elapsed since last
* checkpoint, and returns true if the progress we've made this far is greater
* than the elapsed time/segments.
*/
static bool
IsCheckpointOnSchedule(double progress)
{
XLogRecPtr recptr;
struct timeval now;
double elapsed_xlogs,
elapsed_time;
Assert(ckpt_active);
/* Scale progress according to checkpoint_completion_target. */
progress *= CheckPointCompletionTarget;
/*
* Check against the cached value first. Only do the more expensive
* calculations once we reach the target previously calculated. Since
* neither time or WAL insert pointer moves backwards, a freshly
* calculated value can only be greater than or equal to the cached value.
*/
if (progress < ckpt_cached_elapsed)
return false;
/*
* Check progress against WAL segments written and checkpoint_segments.
*
* We compare the current WAL insert location against the location
* computed before calling CreateCheckPoint. The code in XLogInsert that
* actually triggers a checkpoint when checkpoint_segments is exceeded
* compares against RedoRecptr, so this is not completely accurate.
* However, it's good enough for our purposes, we're only calculating an
* estimate anyway.
*/
if (!RecoveryInProgress())
{
recptr = GetInsertRecPtr();
elapsed_xlogs =
(((double) (int32) (recptr.xlogid - ckpt_start_recptr.xlogid)) * XLogSegsPerFile +
((double) recptr.xrecoff - (double) ckpt_start_recptr.xrecoff) / XLogSegSize) /
CheckPointSegments;
if (progress < elapsed_xlogs)
{
ckpt_cached_elapsed = elapsed_xlogs;
return false;
}
}
/*
* Check progress against time elapsed and checkpoint_timeout.
*/
gettimeofday(&now, NULL);
elapsed_time = ((double) ((pg_time_t) now.tv_sec - ckpt_start_time) +
now.tv_usec / 1000000.0) / CheckPointTimeout;
if (progress < elapsed_time)
{
ckpt_cached_elapsed = elapsed_time;
return false;
}
/* It looks like we're on schedule. */
return true;
}
/*
* Main entry point for checkpointer process
*
* This is invoked from AuxiliaryProcessMain, which has already created the
* basic execution environment, but not enabled signals yet.
*/
void
CheckpointerMain(void)
{
sigjmp_buf local_sigjmp_buf;
MemoryContext checkpointer_context;
CheckpointerShmem->checkpointer_pid = MyProcPid;
/*
* If possible, make this process a group leader, so that the postmaster
* can signal any child processes too. (checkpointer 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
/*
* Properly accept or ignore signals the postmaster might send us
*
* Note: we deliberately ignore SIGTERM, because during a standard Unix
* system shutdown cycle, init will SIGTERM all processes at once. We
* want to wait for the backends to exit, whereupon the postmaster will
* tell us it's okay to shut down (via SIGUSR2).
*/
pqsignal(SIGHUP, ChkptSigHupHandler); /* set flag to read config
* file */
pqsignal(SIGINT, ReqCheckpointHandler); /* request checkpoint */
pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
pqsignal(SIGQUIT, chkpt_quickdie); /* hard crash time */
pqsignal(SIGALRM, SIG_IGN);
pqsignal(SIGPIPE, SIG_IGN);
pqsignal(SIGUSR1, chkpt_sigusr1_handler);
pqsignal(SIGUSR2, ReqShutdownHandler); /* request shutdown */
/*
* Reset some signals that are accepted by postmaster but not here
*/
pqsignal(SIGCHLD, SIG_DFL);
pqsignal(SIGTTIN, SIG_DFL);
pqsignal(SIGTTOU, SIG_DFL);
pqsignal(SIGCONT, SIG_DFL);
pqsignal(SIGWINCH, SIG_DFL);
/* We allow SIGQUIT (quickdie) at all times */
sigdelset(&BlockSig, SIGQUIT);
/*
* Initialize so that first time-driven event happens at the correct time.
*/
last_checkpoint_time = last_xlog_switch_time = (pg_time_t) time(NULL);
/*
* Create a resource owner to keep track of our resources (currently only
* buffer pins).
*/
CurrentResourceOwner = ResourceOwnerCreate(NULL, "Checkpointer");
/*
* Create a memory context that we will do all our work in. We do this so
* that we can reset the context during error recovery and thereby avoid
* possible memory leaks. Formerly this code just ran in
* TopMemoryContext, but resetting that would be a really bad idea.
*/
checkpointer_context = AllocSetContextCreate(TopMemoryContext,
"Checkpointer",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
MemoryContextSwitchTo(checkpointer_context);
/*
* If an exception is encountered, processing resumes here.
*
* See notes in postgres.c about the design of this coding.
*/
if (sigsetjmp(local_sigjmp_buf, 1) != 0)
{
/* Since not using PG_TRY, must reset error stack by hand */
error_context_stack = NULL;
/* Prevent interrupts while cleaning up */
HOLD_INTERRUPTS();
/* Report the error to the server log */
EmitErrorReport();
/*
* These operations are really just a minimal subset of
* AbortTransaction(). We don't have very many resources to worry
* about in checkpointer, but we do have LWLocks, buffers, and temp
* files.
*/
LWLockReleaseAll();
AbortBufferIO();
UnlockBuffers();
/* buffer pins are released here: */
ResourceOwnerRelease(CurrentResourceOwner,
RESOURCE_RELEASE_BEFORE_LOCKS,
false, true);
/* we needn't bother with the other ResourceOwnerRelease phases */
AtEOXact_Buffers(false);
AtEOXact_Files();
AtEOXact_HashTables(false);
/* Warn any waiting backends that the checkpoint failed. */
if (ckpt_active)
{
/* use volatile pointer to prevent code rearrangement */
volatile CheckpointerShmemStruct *cps = CheckpointerShmem;
SpinLockAcquire(&cps->ckpt_lck);
cps->ckpt_failed++;
cps->ckpt_done = cps->ckpt_started;
SpinLockRelease(&cps->ckpt_lck);
ckpt_active = false;
}
/*
* Now return to normal top-level context and clear ErrorContext for
* next time.
*/
MemoryContextSwitchTo(checkpointer_context);
FlushErrorState();
/* Flush any leaked data in the top-level context */
MemoryContextResetAndDeleteChildren(checkpointer_context);
/* Now we can allow interrupts again */
RESUME_INTERRUPTS();
/*
* Sleep at least 1 second after any error. A write error is likely
* to be repeated, and we don't want to be filling the error logs as
* fast as we can.
*/
pg_usleep(1000000L);
/*
* Close all open files after any error. This is helpful on Windows,
* where holding deleted files open causes various strange errors.
* It's not clear we need it elsewhere, but shouldn't hurt.
*/
smgrcloseall();
}
/* We can now handle ereport(ERROR) */
PG_exception_stack = &local_sigjmp_buf;
/*
* Unblock signals (they were blocked when the postmaster forked us)
*/
PG_SETMASK(&UnBlockSig);
/*
* Use the recovery target timeline ID during recovery
*/
if (RecoveryInProgress())
ThisTimeLineID = GetRecoveryTargetTLI();
/*
* Ensure all shared memory values are set correctly for the config. Doing
* this here ensures no race conditions from other concurrent updaters.
*/
UpdateSharedMemoryConfig();
/*
* Advertise our latch that backends can use to wake us up while we're
* sleeping.
*/
ProcGlobal->checkpointerLatch = &MyProc->procLatch;
/*
* Loop forever
*/
for (;;)
{
bool do_checkpoint = false;
int flags = 0;
pg_time_t now;
int elapsed_secs;
int cur_timeout;
int rc;
/* Clear any already-pending wakeups */
ResetLatch(&MyProc->procLatch);
/*
* Process any requests or signals received recently.
*/
AbsorbFsyncRequests();
if (got_SIGHUP)
{
got_SIGHUP = false;
ProcessConfigFile(PGC_SIGHUP);
/*
* Checkpointer is the last process to shut down, so we ask it to
* hold the keys for a range of other tasks required most of which
* have nothing to do with checkpointing at all.
*
* For various reasons, some config values can change dynamically
* so the primary copy of them is held in shared memory to make
* sure all backends see the same value. We make Checkpointer
* responsible for updating the shared memory copy if the
* parameter setting changes because of SIGHUP.
*/
UpdateSharedMemoryConfig();
}
if (checkpoint_requested)
{
checkpoint_requested = false;
do_checkpoint = true;
BgWriterStats.m_requested_checkpoints++;
}
if (shutdown_requested)
{
/*
* From here on, elog(ERROR) should end with exit(1), not send
* control back to the sigsetjmp block above
*/
ExitOnAnyError = true;
/* Close down the database */
ShutdownXLOG(0, 0);
/* Normal exit from the checkpointer is here */
proc_exit(0); /* done */
}
/*
* Force a checkpoint if too much time has elapsed since the last one.
* Note that we count a timed checkpoint in stats only when this
* occurs without an external request, but we set the CAUSE_TIME flag
* bit even if there is also an external request.
*/
now = (pg_time_t) time(NULL);
elapsed_secs = now - last_checkpoint_time;
if (elapsed_secs >= CheckPointTimeout)
{
if (!do_checkpoint)
BgWriterStats.m_timed_checkpoints++;
do_checkpoint = true;
flags |= CHECKPOINT_CAUSE_TIME;
}
/*
* Do a checkpoint if requested.
*/
if (do_checkpoint)
{
bool ckpt_performed = false;
bool do_restartpoint;
/* use volatile pointer to prevent code rearrangement */
volatile CheckpointerShmemStruct *cps = CheckpointerShmem;
/*
* Check if we should perform a checkpoint or a restartpoint. As a
* side-effect, RecoveryInProgress() initializes TimeLineID if
* it's not set yet.
*/
do_restartpoint = RecoveryInProgress();
/*
* Atomically fetch the request flags to figure out what kind of a
* checkpoint we should perform, and increase the started-counter
* to acknowledge that we've started a new checkpoint.
*/
SpinLockAcquire(&cps->ckpt_lck);
flags |= cps->ckpt_flags;
cps->ckpt_flags = 0;
cps->ckpt_started++;
SpinLockRelease(&cps->ckpt_lck);
/*
* The end-of-recovery checkpoint is a real checkpoint that's
* performed while we're still in recovery.
*/
if (flags & CHECKPOINT_END_OF_RECOVERY)
do_restartpoint = false;
/*
* We will warn if (a) too soon since last checkpoint (whatever
* caused it) and (b) somebody set the CHECKPOINT_CAUSE_XLOG flag
* since the last checkpoint start. Note in particular that this
* implementation will not generate warnings caused by
* CheckPointTimeout < CheckPointWarning.
*/
if (!do_restartpoint &&
(flags & CHECKPOINT_CAUSE_XLOG) &&
elapsed_secs < CheckPointWarning)
ereport(LOG,
(errmsg_plural("checkpoints are occurring too frequently (%d second apart)",
"checkpoints are occurring too frequently (%d seconds apart)",
elapsed_secs,
elapsed_secs),
errhint("Consider increasing the configuration parameter \"checkpoint_segments\".")));
/*
* Initialize checkpointer-private variables used during
* checkpoint
*/
ckpt_active = true;
if (!do_restartpoint)
ckpt_start_recptr = GetInsertRecPtr();
ckpt_start_time = now;
ckpt_cached_elapsed = 0;
/*
* Do the checkpoint.
*/
if (!do_restartpoint)
{
CreateCheckPoint(flags);
ckpt_performed = true;
}
else
ckpt_performed = CreateRestartPoint(flags);
/*
* After any checkpoint, close all smgr files. This is so we
* won't hang onto smgr references to deleted files indefinitely.
*/
smgrcloseall();
/*
* Indicate checkpoint completion to any waiting backends.
*/
SpinLockAcquire(&cps->ckpt_lck);
cps->ckpt_done = cps->ckpt_started;
SpinLockRelease(&cps->ckpt_lck);
if (ckpt_performed)
{
/*
* Note we record the checkpoint start time not end time as
* last_checkpoint_time. This is so that time-driven
* checkpoints happen at a predictable spacing.
*/
last_checkpoint_time = now;
}
else
{
/*
* We were not able to perform the restartpoint (checkpoints
* throw an ERROR in case of error). Most likely because we
* have not received any new checkpoint WAL records since the
* last restartpoint. Try again in 15 s.
*/
last_checkpoint_time = now - CheckPointTimeout + 15;
}
ckpt_active = false;
}
/* Check for archive_timeout and switch xlog files if necessary. */
CheckArchiveTimeout();
/*
* Send off activity statistics to the stats collector. (The reason
* why we re-use bgwriter-related code for this is that the bgwriter
* and checkpointer used to be just one process. It's probably not
* worth the trouble to split the stats support into two independent
* stats message types.)
*/
pgstat_send_bgwriter();
/*
* Sleep until we are signaled or it's time for another checkpoint or
* xlog file switch.
*/
now = (pg_time_t) time(NULL);
elapsed_secs = now - last_checkpoint_time;
if (elapsed_secs >= CheckPointTimeout)
continue; /* no sleep for us ... */
cur_timeout = CheckPointTimeout - elapsed_secs;
if (XLogArchiveTimeout > 0 && !RecoveryInProgress())
{
elapsed_secs = now - last_xlog_switch_time;
if (elapsed_secs >= XLogArchiveTimeout)
continue; /* no sleep for us ... */
cur_timeout = Min(cur_timeout, XLogArchiveTimeout - elapsed_secs);
}
rc = WaitLatch(&MyProc->procLatch,
WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
cur_timeout * 1000L /* convert to ms */ );
/*
* Emergency bailout if postmaster has died. This is to avoid the
* necessity for manual cleanup of all postmaster children.
*/
if (rc & WL_POSTMASTER_DEATH)
exit(1);
}
}
/*
* Optionally prune and repair fragmentation in the specified page.
*
* This is an opportunistic function. It will perform housekeeping
* only if the page heuristically looks like a candidate for pruning and we
* can acquire buffer cleanup lock without blocking.
*
* Note: this is called quite often. It's important that it fall out quickly
* if there's not any use in pruning.
*
* Caller must have pin on the buffer, and must *not* have a lock on it.
*
* OldestXmin is the cutoff XID used to distinguish whether tuples are DEAD
* or RECENTLY_DEAD (see HeapTupleSatisfiesVacuum).
*/
void
heap_page_prune_opt(Relation relation, Buffer buffer, TransactionId OldestXmin)
{
Page page = BufferGetPage(buffer);
Size minfree;
/*
* Let's see if we really need pruning.
*
* Forget it if page is not hinted to contain something prunable that's
* older than OldestXmin.
*/
if (!PageIsPrunable(page, OldestXmin))
return;
/*
* We can't write WAL in recovery mode, so there's no point trying to
* clean the page. The master will likely issue a cleaning WAL record soon
* anyway, so this is no particular loss.
*/
if (RecoveryInProgress())
return;
/*
* We prune when a previous UPDATE failed to find enough space on the page
* for a new tuple version, or when free space falls below the relation's
* fill-factor target (but not less than 10%).
*
* Checking free space here is questionable since we aren't holding any
* lock on the buffer; in the worst case we could get a bogus answer. It's
* unlikely to be *seriously* wrong, though, since reading either pd_lower
* or pd_upper is probably atomic. Avoiding taking a lock seems more
* important than sometimes getting a wrong answer in what is after all
* just a heuristic estimate.
*/
minfree = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
minfree = Max(minfree, BLCKSZ / 10);
if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
{
/* OK, try to get exclusive buffer lock */
if (!ConditionalLockBufferForCleanup(buffer))
return;
/*
* Now that we have buffer lock, get accurate information about the
* page's free space, and recheck the heuristic about whether to
* prune. (We needn't recheck PageIsPrunable, since no one else could
* have pruned while we hold pin.)
*/
if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
{
TransactionId ignore = InvalidTransactionId; /* return value not
* needed */
/* OK to prune */
(void) heap_page_prune(relation, buffer, OldestXmin, true, &ignore);
}
/* And release buffer lock */
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
}
}
/*
* ProcSleep -- put a process to sleep on the specified lock
*
* Caller must have set MyProc->heldLocks to reflect locks already held
* on the lockable object by this process (under all XIDs).
*
* The lock table's partition lock must be held at entry, and will be held
* at exit.
*
* Result: STATUS_OK if we acquired the lock, STATUS_ERROR if not (deadlock).
*
* ASSUME: that no one will fiddle with the queue until after
* we release the partition lock.
*
* NOTES: The process queue is now a priority queue for locking.
*
* P() on the semaphore should put us to sleep. The process
* semaphore is normally zero, so when we try to acquire it, we sleep.
*/
int
ProcSleep(LOCALLOCK *locallock, LockMethod lockMethodTable)
{
LOCKMODE lockmode = locallock->tag.mode;
LOCK *lock = locallock->lock;
PROCLOCK *proclock = locallock->proclock;
uint32 hashcode = locallock->hashcode;
LWLockId partitionLock = LockHashPartitionLock(hashcode);
PROC_QUEUE *waitQueue = &(lock->waitProcs);
LOCKMASK myHeldLocks = MyProc->heldLocks;
bool early_deadlock = false;
bool allow_autovacuum_cancel = true;
int myWaitStatus;
PGPROC *proc;
int i;
/*
* Determine where to add myself in the wait queue.
*
* Normally I should go at the end of the queue. However, if I already
* hold locks that conflict with the request of any previous waiter, put
* myself in the queue just in front of the first such waiter. This is not
* a necessary step, since deadlock detection would move me to before that
* waiter anyway; but it's relatively cheap to detect such a conflict
* immediately, and avoid delaying till deadlock timeout.
*
* Special case: if I find I should go in front of some waiter, check to
* see if I conflict with already-held locks or the requests before that
* waiter. If not, then just grant myself the requested lock immediately.
* This is the same as the test for immediate grant in LockAcquire, except
* we are only considering the part of the wait queue before my insertion
* point.
*/
if (myHeldLocks != 0)
{
LOCKMASK aheadRequests = 0;
proc = (PGPROC *) waitQueue->links.next;
for (i = 0; i < waitQueue->size; i++)
{
/* Must he wait for me? */
if (lockMethodTable->conflictTab[proc->waitLockMode] & myHeldLocks)
{
/* Must I wait for him ? */
if (lockMethodTable->conflictTab[lockmode] & proc->heldLocks)
{
/*
* Yes, so we have a deadlock. Easiest way to clean up
* correctly is to call RemoveFromWaitQueue(), but we
* can't do that until we are *on* the wait queue. So, set
* a flag to check below, and break out of loop. Also,
* record deadlock info for later message.
*/
RememberSimpleDeadLock(MyProc, lockmode, lock, proc);
early_deadlock = true;
break;
}
/* I must go before this waiter. Check special case. */
if ((lockMethodTable->conflictTab[lockmode] & aheadRequests) == 0 &&
LockCheckConflicts(lockMethodTable,
lockmode,
lock,
proclock,
MyProc) == STATUS_OK)
{
/* Skip the wait and just grant myself the lock. */
GrantLock(lock, proclock, lockmode);
GrantAwaitedLock();
return STATUS_OK;
}
/* Break out of loop to put myself before him */
break;
}
/* Nope, so advance to next waiter */
aheadRequests |= LOCKBIT_ON(proc->waitLockMode);
proc = (PGPROC *) proc->links.next;
}
/*
* If we fall out of loop normally, proc points to waitQueue head, so
* we will insert at tail of queue as desired.
*/
}
else
{
/* I hold no locks, so I can't push in front of anyone. */
proc = (PGPROC *) &(waitQueue->links);
}
/*
* Insert self into queue, ahead of the given proc (or at tail of queue).
*/
SHMQueueInsertBefore(&(proc->links), &(MyProc->links));
waitQueue->size++;
lock->waitMask |= LOCKBIT_ON(lockmode);
/* Set up wait information in PGPROC object, too */
MyProc->waitLock = lock;
MyProc->waitProcLock = proclock;
MyProc->waitLockMode = lockmode;
MyProc->waitStatus = STATUS_WAITING;
/*
* If we detected deadlock, give up without waiting. This must agree with
* CheckDeadLock's recovery code, except that we shouldn't release the
* semaphore since we haven't tried to lock it yet.
*/
if (early_deadlock)
{
RemoveFromWaitQueue(MyProc, hashcode);
return STATUS_ERROR;
}
/* mark that we are waiting for a lock */
lockAwaited = locallock;
/*
* Release the lock table's partition lock.
*
* NOTE: this may also cause us to exit critical-section state, possibly
* allowing a cancel/die interrupt to be accepted. This is OK because we
* have recorded the fact that we are waiting for a lock, and so
* LockErrorCleanup will clean up if cancel/die happens.
*/
LWLockRelease(partitionLock);
/*
* Also, now that we will successfully clean up after an ereport, it's
* safe to check to see if there's a buffer pin deadlock against the
* Startup process. Of course, that's only necessary if we're doing Hot
* Standby and are not the Startup process ourselves.
*/
if (RecoveryInProgress() && !InRecovery)
CheckRecoveryConflictDeadlock();
/* Reset deadlock_state before enabling the timeout handler */
deadlock_state = DS_NOT_YET_CHECKED;
/*
* Set timer so we can wake up after awhile and check for a deadlock. If a
* deadlock is detected, the handler releases the process's semaphore and
* sets MyProc->waitStatus = STATUS_ERROR, allowing us to know that we
* must report failure rather than success.
*
* By delaying the check until we've waited for a bit, we can avoid
* running the rather expensive deadlock-check code in most cases.
*/
enable_timeout_after(DEADLOCK_TIMEOUT, DeadlockTimeout);
/*
* If someone wakes us between LWLockRelease and PGSemaphoreLock,
* PGSemaphoreLock will not block. The wakeup is "saved" by the semaphore
* implementation. While this is normally good, there are cases where a
* saved wakeup might be leftover from a previous operation (for example,
* we aborted ProcWaitForSignal just before someone did ProcSendSignal).
* So, loop to wait again if the waitStatus shows we haven't been granted
* nor denied the lock yet.
*
* We pass interruptOK = true, which eliminates a window in which
* cancel/die interrupts would be held off undesirably. This is a promise
* that we don't mind losing control to a cancel/die interrupt here. We
* don't, because we have no shared-state-change work to do after being
* granted the lock (the grantor did it all). We do have to worry about
* canceling the deadlock timeout and updating the locallock table, but if
* we lose control to an error, LockErrorCleanup will fix that up.
*/
do
{
PGSemaphoreLock(&MyProc->sem, true);
/*
* waitStatus could change from STATUS_WAITING to something else
* asynchronously. Read it just once per loop to prevent surprising
* behavior (such as missing log messages).
*/
myWaitStatus = MyProc->waitStatus;
/*
* If we are not deadlocked, but are waiting on an autovacuum-induced
* task, send a signal to interrupt it.
*/
if (deadlock_state == DS_BLOCKED_BY_AUTOVACUUM && allow_autovacuum_cancel)
{
PGPROC *autovac = GetBlockingAutoVacuumPgproc();
PGXACT *autovac_pgxact = &ProcGlobal->allPgXact[autovac->pgprocno];
LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
/*
* Only do it if the worker is not working to protect against Xid
* wraparound.
*/
if ((autovac != NULL) &&
(autovac_pgxact->vacuumFlags & PROC_IS_AUTOVACUUM) &&
!(autovac_pgxact->vacuumFlags & PROC_VACUUM_FOR_WRAPAROUND))
{
int pid = autovac->pid;
StringInfoData locktagbuf;
StringInfoData logbuf; /* errdetail for server log */
initStringInfo(&locktagbuf);
initStringInfo(&logbuf);
DescribeLockTag(&locktagbuf, &lock->tag);
appendStringInfo(&logbuf,
_("Process %d waits for %s on %s."),
MyProcPid,
GetLockmodeName(lock->tag.locktag_lockmethodid,
lockmode),
locktagbuf.data);
/* release lock as quickly as possible */
LWLockRelease(ProcArrayLock);
ereport(LOG,
(errmsg("sending cancel to blocking autovacuum PID %d",
pid),
errdetail_log("%s", logbuf.data)));
pfree(logbuf.data);
pfree(locktagbuf.data);
/* send the autovacuum worker Back to Old Kent Road */
if (kill(pid, SIGINT) < 0)
{
/* Just a warning to allow multiple callers */
ereport(WARNING,
(errmsg("could not send signal to process %d: %m",
pid)));
}
}
else
LWLockRelease(ProcArrayLock);
/* prevent signal from being resent more than once */
allow_autovacuum_cancel = false;
}
/*
* If awoken after the deadlock check interrupt has run, and
* log_lock_waits is on, then report about the wait.
*/
if (log_lock_waits && deadlock_state != DS_NOT_YET_CHECKED)
{
StringInfoData buf;
const char *modename;
long secs;
int usecs;
long msecs;
initStringInfo(&buf);
DescribeLockTag(&buf, &locallock->tag.lock);
modename = GetLockmodeName(locallock->tag.lock.locktag_lockmethodid,
lockmode);
TimestampDifference(get_timeout_start_time(DEADLOCK_TIMEOUT),
GetCurrentTimestamp(),
&secs, &usecs);
msecs = secs * 1000 + usecs / 1000;
usecs = usecs % 1000;
if (deadlock_state == DS_SOFT_DEADLOCK)
ereport(LOG,
(errmsg("process %d avoided deadlock for %s on %s by rearranging queue order after %ld.%03d ms",
MyProcPid, modename, buf.data, msecs, usecs)));
else if (deadlock_state == DS_HARD_DEADLOCK)
{
/*
* This message is a bit redundant with the error that will be
* reported subsequently, but in some cases the error report
* might not make it to the log (eg, if it's caught by an
* exception handler), and we want to ensure all long-wait
* events get logged.
*/
ereport(LOG,
(errmsg("process %d detected deadlock while waiting for %s on %s after %ld.%03d ms",
MyProcPid, modename, buf.data, msecs, usecs)));
}
if (myWaitStatus == STATUS_WAITING)
ereport(LOG,
(errmsg("process %d still waiting for %s on %s after %ld.%03d ms",
MyProcPid, modename, buf.data, msecs, usecs)));
else if (myWaitStatus == STATUS_OK)
ereport(LOG,
(errmsg("process %d acquired %s on %s after %ld.%03d ms",
MyProcPid, modename, buf.data, msecs, usecs)));
else
{
Assert(myWaitStatus == STATUS_ERROR);
/*
* Currently, the deadlock checker always kicks its own
* process, which means that we'll only see STATUS_ERROR when
* deadlock_state == DS_HARD_DEADLOCK, and there's no need to
* print redundant messages. But for completeness and
* future-proofing, print a message if it looks like someone
* else kicked us off the lock.
*/
if (deadlock_state != DS_HARD_DEADLOCK)
ereport(LOG,
(errmsg("process %d failed to acquire %s on %s after %ld.%03d ms",
MyProcPid, modename, buf.data, msecs, usecs)));
}
/*
* At this point we might still need to wait for the lock. Reset
* state so we don't print the above messages again.
*/
deadlock_state = DS_NO_DEADLOCK;
pfree(buf.data);
}
} while (myWaitStatus == STATUS_WAITING);
/*
* Disable the timer, if it's still running
*/
disable_timeout(DEADLOCK_TIMEOUT, false);
/*
* Re-acquire the lock table's partition lock. We have to do this to hold
* off cancel/die interrupts before we can mess with lockAwaited (else we
* might have a missed or duplicated locallock update).
*/
LWLockAcquire(partitionLock, LW_EXCLUSIVE);
/*
* We no longer want LockErrorCleanup to do anything.
*/
lockAwaited = NULL;
/*
* If we got the lock, be sure to remember it in the locallock table.
*/
if (MyProc->waitStatus == STATUS_OK)
GrantAwaitedLock();
/*
* We don't have to do anything else, because the awaker did all the
* necessary update of the lock table and MyProc.
*/
return MyProc->waitStatus;
}
/*
* IsCheckpointOnSchedule -- are we on schedule to finish this checkpoint
* (or restartpoint) in time?
*
* Compares the current progress against the time/segments elapsed since last
* checkpoint, and returns true if the progress we've made this far is greater
* than the elapsed time/segments.
*/
static bool
IsCheckpointOnSchedule(double progress)
{
XLogRecPtr recptr;
struct timeval now;
double elapsed_xlogs,
elapsed_time;
Assert(ckpt_active);
/* Scale progress according to checkpoint_completion_target. */
progress *= CheckPointCompletionTarget;
/*
* Check against the cached value first. Only do the more expensive
* calculations once we reach the target previously calculated. Since
* neither time or WAL insert pointer moves backwards, a freshly
* calculated value can only be greater than or equal to the cached value.
*/
if (progress < ckpt_cached_elapsed)
return false;
/*
* Check progress against WAL segments written and CheckPointSegments.
*
* We compare the current WAL insert location against the location
* computed before calling CreateCheckPoint. The code in XLogInsert that
* actually triggers a checkpoint when CheckPointSegments is exceeded
* compares against RedoRecptr, so this is not completely accurate.
* However, it's good enough for our purposes, we're only calculating an
* estimate anyway.
*
* During recovery, we compare last replayed WAL record's location with
* the location computed before calling CreateRestartPoint. That maintains
* the same pacing as we have during checkpoints in normal operation, but
* we might exceed max_wal_size by a fair amount. That's because there can
* be a large gap between a checkpoint's redo-pointer and the checkpoint
* record itself, and we only start the restartpoint after we've seen the
* checkpoint record. (The gap is typically up to CheckPointSegments *
* checkpoint_completion_target where checkpoint_completion_target is the
* value that was in effect when the WAL was generated).
*/
if (RecoveryInProgress())
recptr = GetXLogReplayRecPtr(NULL);
else
recptr = GetInsertRecPtr();
elapsed_xlogs = (((double) (recptr - ckpt_start_recptr)) / XLogSegSize) / CheckPointSegments;
if (progress < elapsed_xlogs)
{
ckpt_cached_elapsed = elapsed_xlogs;
return false;
}
/*
* Check progress against time elapsed and checkpoint_timeout.
*/
gettimeofday(&now, NULL);
elapsed_time = ((double) ((pg_time_t) now.tv_sec - ckpt_start_time) +
now.tv_usec / 1000000.0) / CheckPointTimeout;
if (progress < elapsed_time)
{
ckpt_cached_elapsed = elapsed_time;
return false;
}
/* It looks like we're on schedule. */
return true;
}
