/*
* Returns the replication apply delay in ms
*/
int
GetReplicationApplyDelay(void)
{
/* use volatile pointer to prevent code rearrangement */
volatile WalRcvData *walrcv = WalRcv;
XLogRecPtr receivePtr;
XLogRecPtr replayPtr;
long secs;
int usecs;
SpinLockAcquire(&walrcv->mutex);
receivePtr = walrcv->receivedUpto;
SpinLockRelease(&walrcv->mutex);
replayPtr = GetXLogReplayRecPtr(NULL);
if (XLByteLE(receivePtr, replayPtr))
return 0;
TimestampDifference(GetCurrentChunkReplayStartTime(),
GetCurrentTimestamp(),
&secs, &usecs);
return (((int) secs * 1000) + (usecs / 1000));
}
/*
* Returns the replication apply delay in ms or -1
* if the apply delay info is not available
*/
int
GetReplicationApplyDelay(void)
{
WalRcvData *walrcv = WalRcv;
XLogRecPtr receivePtr;
XLogRecPtr replayPtr;
long secs;
int usecs;
TimestampTz chunkReplayStartTime;
SpinLockAcquire(&walrcv->mutex);
receivePtr = walrcv->receivedUpto;
SpinLockRelease(&walrcv->mutex);
replayPtr = GetXLogReplayRecPtr(NULL);
if (receivePtr == replayPtr)
return 0;
chunkReplayStartTime = GetCurrentChunkReplayStartTime();
if (chunkReplayStartTime == 0)
return -1;
TimestampDifference(chunkReplayStartTime,
GetCurrentTimestamp(),
&secs, &usecs);
return (((int) secs * 1000) + (usecs / 1000));
}
/*
* pgespresso_stop_backup: finish taking an on-line backup dump
*
* Only parameter is the labelfile returned from pg_start_concurrent_backup
*
* Return is the XLOG filename containing end of backup location, combining
* both the TLI and the end location. NOTE: the user is responsible for
* ensuring that the last file is correctly archived.
*/
Datum
pgespresso_stop_backup(PG_FUNCTION_ARGS)
{
XLogRecPtr stoppoint;
text *labelfile = PG_GETARG_TEXT_P(0);
char *backupidstr;
char xlogfilename[MAXFNAMELEN];
backupidstr = text_to_cstring(labelfile);
if (!superuser() && !has_rolreplication(GetUserId()))
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser or replication role to run a backup"))));
#if PG_VERSION_NUM >= 90300
{
XLogSegNo xlogsegno;
TimeLineID endtli;
stoppoint = do_pg_stop_backup(backupidstr,
false, /* don't wait for archive */
&endtli);
XLByteToPrevSeg(stoppoint, xlogsegno);
XLogFileName(xlogfilename, endtli, xlogsegno);
}
#else
{
uint32 xlogid;
uint32 xlogseg;
stoppoint = do_pg_stop_backup(backupidstr,
false); /* don't wait for archive */
/*
* In 9.2 the do_pg_stop_backup doesn't return the timeline ID and
* ThisTimeLineID is always 0 in a normal backend during recovery.
* We get latest redo apply position timeline and we update it globally
*/
if (RecoveryInProgress()) {
TimeLineID replayTLI;
GetXLogReplayRecPtr(&replayTLI);
ThisTimeLineID = replayTLI;
elog(DEBUG1, "updated ThisTimeLineID = %u", ThisTimeLineID);
}
XLByteToPrevSeg(stoppoint, xlogid, xlogseg);
XLogFileName(xlogfilename, ThisTimeLineID, xlogid, xlogseg);
}
#endif
PG_RETURN_TEXT_P(cstring_to_text(xlogfilename));
}
/*
* Report the last WAL replay location (same format as pg_start_backup etc)
*
* This is useful for determining how much of WAL is visible to read-only
* connections during recovery.
*/
Datum
pg_last_xlog_replay_location(PG_FUNCTION_ARGS)
{
XLogRecPtr recptr;
recptr = GetXLogReplayRecPtr(NULL);
if (recptr == 0)
PG_RETURN_NULL();
PG_RETURN_LSN(recptr);
}
/*
* Report the last WAL replay location (same format as pg_start_backup etc)
*
* This is useful for determining how much of WAL is visible to read-only
* connections during recovery.
*/
Datum
pg_last_xlog_replay_location(PG_FUNCTION_ARGS)
{
XLogRecPtr recptr;
char location[MAXFNAMELEN];
recptr = GetXLogReplayRecPtr(NULL);
if (recptr.xlogid == 0 && recptr.xrecoff == 0)
PG_RETURN_NULL();
snprintf(location, sizeof(location), "%X/%X",
recptr.xlogid, recptr.xrecoff);
PG_RETURN_TEXT_P(cstring_to_text(location));
}
/*
* read_page callback for logical decoding contexts.
*
* Public because it would likely be very helpful for someone writing another
* output method outside walsender, e.g. in a bgworker.
*
* TODO: The walsender has it's own version of this, but it relies on the
* walsender's latch being set whenever WAL is flushed. No such infrastructure
* exists for normal backends, so we have to do a check/sleep/repeat style of
* loop for now.
*/
int
logical_read_local_xlog_page(XLogReaderState *state, XLogRecPtr targetPagePtr,
int reqLen, XLogRecPtr targetRecPtr, char *cur_page, TimeLineID *pageTLI)
{
XLogRecPtr flushptr,
loc;
int count;
loc = targetPagePtr + reqLen;
while (1)
{
/*
* TODO: we're going to have to do something more intelligent about
* timelines on standbys. Use readTimeLineHistory() and
* tliOfPointInHistory() to get the proper LSN? For now we'll catch
* that case earlier, but the code and TODO is left in here for when
* that changes.
*/
if (!RecoveryInProgress())
{
*pageTLI = ThisTimeLineID;
flushptr = GetFlushRecPtr();
}
else
flushptr = GetXLogReplayRecPtr(pageTLI);
if (loc <= flushptr)
break;
CHECK_FOR_INTERRUPTS();
pg_usleep(1000L);
}
/* more than one block available */
if (targetPagePtr + XLOG_BLCKSZ <= flushptr)
count = XLOG_BLCKSZ;
/* not enough data there */
else if (targetPagePtr + reqLen > flushptr)
return -1;
/* part of the page available */
else
count = flushptr - targetPagePtr;
XLogRead(cur_page, *pageTLI, targetPagePtr, XLOG_BLCKSZ);
return count;
}
/*
* Send reply message to primary, indicating our current XLOG positions and
* the current time.
*/
static void
XLogWalRcvSendReply(void)
{
char buf[sizeof(StandbyReplyMessage) + 1];
TimestampTz now;
/*
* If the user doesn't want status to be reported to the master, be sure
* to exit before doing anything at all.
*/
if (wal_receiver_status_interval <= 0)
return;
/* Get current timestamp. */
now = GetCurrentTimestamp();
/*
* We can compare the write and flush positions to the last message we
* sent without taking any lock, but the apply position requires a spin
* lock, so we don't check that unless something else has changed or 10
* seconds have passed. This means that the apply log position will
* appear, from the master's point of view, to lag slightly, but since
* this is only for reporting purposes and only on idle systems, that's
* probably OK.
*/
if (XLByteEQ(reply_message.write, LogstreamResult.Write)
&& XLByteEQ(reply_message.flush, LogstreamResult.Flush)
&& !TimestampDifferenceExceeds(reply_message.sendTime, now,
wal_receiver_status_interval * 1000))
return;
/* Construct a new message. */
reply_message.write = LogstreamResult.Write;
reply_message.flush = LogstreamResult.Flush;
reply_message.apply = GetXLogReplayRecPtr();
reply_message.sendTime = now;
elog(DEBUG2, "sending write %X/%X flush %X/%X apply %X/%X",
reply_message.write.xlogid, reply_message.write.xrecoff,
reply_message.flush.xlogid, reply_message.flush.xrecoff,
reply_message.apply.xlogid, reply_message.apply.xrecoff);
/* Prepend with the message type and send it. */
buf[0] = 'r';
memcpy(&buf[1], &reply_message, sizeof(StandbyReplyMessage));
walrcv_send(buf, sizeof(StandbyReplyMessage) + 1);
}
/*
* pgespresso_start_backup: set up for taking an on-line backup dump
*
* Essentially what this does is to return a backup label file that the
* user is responsible for placing in the $PGDATA of the backup AFTER
* the backup has been taken. The label file must not be written to the
* data directory of the server from which the backup is taken because
* this type of backup presumes and allows that more than one backup
* may be in progress at any one time. The label file
* contains the user-supplied label string (typically this would be used
* to tell where the backup dump will be stored) and the starting time and
* starting WAL location for the dump.
*/
Datum
pgespresso_start_backup(PG_FUNCTION_ARGS)
{
text *backupid = PG_GETARG_TEXT_P(0);
bool fast = PG_GETARG_BOOL(1);
char *backupidstr;
char *labelfile;
backupidstr = text_to_cstring(backupid);
if (!superuser() && !has_rolreplication(GetUserId()))
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("must be superuser or replication role to run a backup")));
/*
* ThisTimeLineID is always 0 in a normal backend during recovery.
* We get latest redo apply position timeline and we update it globally
* to make do_pg_start_backup use the correct value when generating
* the backup label text
*/
if (RecoveryInProgress()) {
TimeLineID replayTLI;
GetXLogReplayRecPtr(&replayTLI);
ThisTimeLineID = replayTLI;
elog(DEBUG1, "updated ThisTimeLineID = %u", ThisTimeLineID);
}
/*
* Starting from 9.3 the do_pg_start_backup returns the timeline ID
* in *starttli_p additional argument
*/
#if PG_VERSION_NUM >= 90300
do_pg_start_backup(backupidstr, fast, NULL, &labelfile);
#else
do_pg_start_backup(backupidstr, fast, &labelfile);
#endif
PG_RETURN_TEXT_P(cstring_to_text(labelfile));
}
/*
* 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;
}
/*
* 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;
/*
* 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_SIZES);
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();
ConditionVariableCancelSleep();
pgstat_report_wait_end();
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);
/* Warn any waiting backends that the checkpoint failed. */
if (ckpt_active)
{
SpinLockAcquire(&CheckpointerShmem->ckpt_lck);
CheckpointerShmem->ckpt_failed++;
CheckpointerShmem->ckpt_done = CheckpointerShmem->ckpt_started;
SpinLockRelease(&CheckpointerShmem->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);
/*
* 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(MyLatch);
/*
* 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;
/*
* 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(&CheckpointerShmem->ckpt_lck);
flags |= CheckpointerShmem->ckpt_flags;
CheckpointerShmem->ckpt_flags = 0;
CheckpointerShmem->ckpt_started++;
SpinLockRelease(&CheckpointerShmem->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 \"max_wal_size\".")));
/*
* Initialize checkpointer-private variables used during
* checkpoint.
*/
ckpt_active = true;
if (do_restartpoint)
ckpt_start_recptr = GetXLogReplayRecPtr(NULL);
else
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(&CheckpointerShmem->ckpt_lck);
CheckpointerShmem->ckpt_done = CheckpointerShmem->ckpt_started;
SpinLockRelease(&CheckpointerShmem->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(MyLatch,
WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
cur_timeout * 1000L /* convert to ms */,
WAIT_EVENT_CHECKPOINTER_MAIN);
/*
* 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);
}
}
/*
* 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 and maintain ThisTimeLineID.
* RecoveryInProgress() will update ThisTimeLineID on promotion.
*/
if (!RecoveryInProgress())
end_of_wal = GetFlushRecPtr();
else
end_of_wal = GetXLogReplayRecPtr(&ThisTimeLineID);
ReplicationSlotAcquire(NameStr(*name), true);
PG_TRY();
{
/* restart at slot's confirmed_flush */
ctx = CreateDecodingContext(InvalidXLogRecPtr,
options,
false,
logical_read_local_xlog_page,
LogicalOutputPrepareWrite,
LogicalOutputWrite, NULL);
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();
/* Decode until we run out of records */
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;
}
/*
* 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;
}
