/*
* 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;
/*
* 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 */
slot->data.restart_lsn = GetXLogInsertRecPtr();
/* make sure we have enough information to start */
flushptr = LogStandbySnapshot();
/* and make sure it's fsynced to disk */
XLogFlush(flushptr);
}
else
{
slot->data.restart_lsn = GetRedoRecPtr();
}
/* 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;
}
}
/*
* Write a backup block if needed when we are setting a hint. Note that
* this may be called for a variety of page types, not just heaps.
*
* Callable while holding just share lock on the buffer content.
*
* We can't use the plain backup block mechanism since that relies on the
* Buffer being exclusively locked. Since some modifications (setting LSN, hint
* bits) are allowed in a sharelocked buffer that can lead to wal checksum
* failures. So instead we copy the page and insert the copied data as normal
* record data.
*
* We only need to do something if page has not yet been full page written in
* this checkpoint round. The LSN of the inserted wal record is returned if we
* had to write, InvalidXLogRecPtr otherwise.
*
* It is possible that multiple concurrent backends could attempt to write WAL
* records. In that case, multiple copies of the same block would be recorded
* in separate WAL records by different backends, though that is still OK from
* a correctness perspective.
*/
XLogRecPtr
XLogSaveBufferForHint(Buffer buffer, bool buffer_std)
{
XLogRecPtr recptr = InvalidXLogRecPtr;
XLogRecPtr lsn;
XLogRecPtr RedoRecPtr;
/*
* Ensure no checkpoint can change our view of RedoRecPtr.
*/
Assert(MyPgXact->delayChkpt);
/*
* Update RedoRecPtr so that we can make the right decision
*/
RedoRecPtr = GetRedoRecPtr();
/*
* We assume page LSN is first data on *every* page that can be passed to
* XLogInsert, whether it has the standard page layout or not. Since we're
* only holding a share-lock on the page, we must take the buffer header
* lock when we look at the LSN.
*/
lsn = BufferGetLSNAtomic(buffer);
if (lsn <= RedoRecPtr)
{
int flags;
char copied_buffer[BLCKSZ];
char *origdata = (char *) BufferGetBlock(buffer);
RelFileNode rnode;
ForkNumber forkno;
BlockNumber blkno;
/*
* Copy buffer so we don't have to worry about concurrent hint bit or
* lsn updates. We assume pd_lower/upper cannot be changed without an
* exclusive lock, so the contents bkp are not racy.
*/
if (buffer_std)
{
/* Assume we can omit data between pd_lower and pd_upper */
Page page = BufferGetPage(buffer);
uint16 lower = ((PageHeader) page)->pd_lower;
uint16 upper = ((PageHeader) page)->pd_upper;
memcpy(copied_buffer, origdata, lower);
memcpy(copied_buffer + upper, origdata + upper, BLCKSZ - upper);
}
else
memcpy(copied_buffer, origdata, BLCKSZ);
XLogBeginInsert();
flags = REGBUF_FORCE_IMAGE;
if (buffer_std)
flags |= REGBUF_STANDARD;
BufferGetTag(buffer, &rnode, &forkno, &blkno);
XLogRegisterBlock(0, &rnode, forkno, blkno, copied_buffer, flags);
recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI_FOR_HINT);
}
return recptr;
}
static int64
nextval_internal(Oid relid)
{
SeqTable elm;
Relation seqrel;
Buffer buf;
Page page;
HeapTupleData seqtuple;
Form_pg_sequence seq;
int64 incby,
maxv,
minv,
cache,
log,
fetch,
last;
int64 result,
next,
rescnt = 0;
bool logit = false;
/* open and AccessShareLock sequence */
init_sequence(relid, &elm, &seqrel);
if (pg_class_aclcheck(elm->relid, GetUserId(),
ACL_USAGE | ACL_UPDATE) != ACLCHECK_OK)
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("permission denied for sequence %s",
RelationGetRelationName(seqrel))));
/* read-only transactions may only modify temp sequences */
if (!seqrel->rd_islocaltemp)
PreventCommandIfReadOnly("nextval()");
/*
* Forbid this during parallel operation because, to make it work,
* the cooperating backends would need to share the backend-local cached
* sequence information. Currently, we don't support that.
*/
PreventCommandIfParallelMode("nextval()");
if (elm->last != elm->cached) /* some numbers were cached */
{
Assert(elm->last_valid);
Assert(elm->increment != 0);
elm->last += elm->increment;
relation_close(seqrel, NoLock);
last_used_seq = elm;
return elm->last;
}
/* lock page' buffer and read tuple */
seq = read_seq_tuple(elm, seqrel, &buf, &seqtuple);
page = BufferGetPage(buf);
last = next = result = seq->last_value;
incby = seq->increment_by;
maxv = seq->max_value;
minv = seq->min_value;
fetch = cache = seq->cache_value;
log = seq->log_cnt;
if (!seq->is_called)
{
rescnt++; /* return last_value if not is_called */
fetch--;
}
/*
* Decide whether we should emit a WAL log record. If so, force up the
* fetch count to grab SEQ_LOG_VALS more values than we actually need to
* cache. (These will then be usable without logging.)
*
* If this is the first nextval after a checkpoint, we must force a new___
* WAL record to be written anyway, else replay starting from the
* checkpoint would fail to advance the sequence past the logged values.
* In this case we may as well fetch extra values.
*/
if (log < fetch || !seq->is_called)
{
/* forced log to satisfy local demand for values */
fetch = log = fetch + SEQ_LOG_VALS;
logit = true;
}
else
{
XLogRecPtr redoptr = GetRedoRecPtr();
if (PageGetLSN(page) <= redoptr)
{
/* last update of seq was before checkpoint */
fetch = log = fetch + SEQ_LOG_VALS;
logit = true;
}
}
while (fetch) /* try to fetch cache [+ log ] numbers */
{
/*
* Check MAXVALUE for ascending sequences and MINVALUE for descending
* sequences
*/
if (incby > 0)
{
/* ascending sequence */
if ((maxv >= 0 && next > maxv - incby) ||
(maxv < 0 && next + incby > maxv))
{
if (rescnt > 0)
break; /* stop fetching */
if (!seq->is_cycled)
{
char buf[100];
snprintf(buf, sizeof(buf), INT64_FORMAT, maxv);
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("nextval: reached maximum value of sequence \"%s\" (%s)",
RelationGetRelationName(seqrel), buf)));
}
next = minv;
}
else
next += incby;
}
else
{
/* descending sequence */
if ((minv < 0 && next < minv - incby) ||
(minv >= 0 && next + incby < minv))
{
if (rescnt > 0)
break; /* stop fetching */
if (!seq->is_cycled)
{
char buf[100];
snprintf(buf, sizeof(buf), INT64_FORMAT, minv);
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("nextval: reached minimum value of sequence \"%s\" (%s)",
RelationGetRelationName(seqrel), buf)));
}
next = maxv;
}
else
next += incby;
}
fetch--;
if (rescnt < cache)
{
log--;
rescnt++;
last = next;
if (rescnt == 1) /* if it's first result - */
result = next; /* it's what to return */
}
}
log -= fetch; /* adjust for any unfetched numbers */
Assert(log >= 0);
/* save info in local cache */
elm->last = result; /* last returned number */
elm->cached = last; /* last fetched number */
elm->last_valid = true;
last_used_seq = elm;
/*
* If something needs to be WAL logged, acquire an xid, so this
* transaction's commit will trigger a WAL flush and wait for
* syncrep. It's sufficient to ensure the toplevel transaction has an xid,
* no need to assign xids subxacts, that'll already trigger an appropriate
* wait. (Have to do that here, so we're outside the critical section)
*/
if (logit && RelationNeedsWAL(seqrel))
GetTopTransactionId();
/* ready to change the on-disk (or really, in-buffer) tuple */
START_CRIT_SECTION();
/*
* We must mark the buffer dirty before doing XLogInsert(); see notes in
* SyncOneBuffer(). However, we don't apply the desired changes just yet.
* This looks like a violation of the buffer update protocol, but it is in
* fact safe because we hold exclusive lock on the buffer. Any other
* process, including a checkpoint, that tries to examine the buffer
* contents will block until we release the lock, and then will see the
* final state that we install below.
*/
MarkBufferDirty(buf);
/* XLOG stuff */
if (logit && RelationNeedsWAL(seqrel))
{
xl_seq_rec xlrec;
XLogRecPtr recptr;
/*
* We don't log the current state of the tuple, but rather the state
* as it would appear after "log" more fetches. This lets us skip
* that many future WAL records, at the cost that we lose those
* sequence values if we crash.
*/
XLogBeginInsert();
XLogRegisterBuffer(0, buf, REGBUF_WILL_INIT);
/* set values that will be saved in xlog */
seq->last_value = next;
seq->is_called = true;
seq->log_cnt = 0;
xlrec.node = seqrel->rd_node;
XLogRegisterData((char *) &xlrec, sizeof(xl_seq_rec));
XLogRegisterData((char *) seqtuple.t_data, seqtuple.t_len);
recptr = XLogInsert(RM_SEQ_ID, XLOG_SEQ_LOG);
PageSetLSN(page, recptr);
}
/* Now update sequence tuple to the intended final state */
seq->last_value = last; /* last fetched number */
seq->is_called = true;
seq->log_cnt = log; /* how much is logged */
END_CRIT_SECTION();
UnlockReleaseBuffer(buf);
relation_close(seqrel, NoLock);
return result;
}
