mirror of
https://github.com/postgres/postgres.git
synced 2025-08-28 18:48:04 +03:00
Adjust max_slot_wal_keep_size behavior per review
In pg_replication_slot, change output from normal/reserved/lost to reserved/extended/unreserved/ lost, which better expresses the possible states particularly near the time where segments are no longer safe but checkpoint has not run yet. Under the new definition, reserved means the slot is consuming WAL that's still under the normal WAL size constraints; extended means it's consuming WAL that's being protected by wal_keep_segments or the slot itself, whose size is below max_slot_wal_keep_size; unreserved means the WAL is no longer safe, but checkpoint has not yet removed those files. Such as slot is in imminent danger, but can still continue for a little while and may catch up to the reserved WAL space. Also, there were some bugs in the calculations used to report the status; fixed those. Backpatch to 13. Reported-by: Fujii Masao <masao.fujii@oss.nttdata.com> Author: Kyotaro Horiguchi <horikyota.ntt@gmail.com> Reviewed-by: Fujii Masao <masao.fujii@oss.nttdata.com> Reviewed-by: Álvaro Herrera <alvherre@alvh.no-ip.org> Discussion: https://postgr.es/m/20200616.120236.1809496990963386593.horikyota.ntt@gmail.com
This commit is contained in:
@@ -359,24 +359,47 @@ pg_get_replication_slots(PG_FUNCTION_ARGS)
|
||||
nulls[i++] = true;
|
||||
break;
|
||||
|
||||
case WALAVAIL_NORMAL:
|
||||
values[i++] = CStringGetTextDatum("normal");
|
||||
break;
|
||||
|
||||
case WALAVAIL_RESERVED:
|
||||
values[i++] = CStringGetTextDatum("reserved");
|
||||
break;
|
||||
|
||||
case WALAVAIL_REMOVED:
|
||||
values[i++] = CStringGetTextDatum("lost");
|
||||
case WALAVAIL_EXTENDED:
|
||||
values[i++] = CStringGetTextDatum("extended");
|
||||
break;
|
||||
|
||||
default:
|
||||
elog(ERROR, "invalid walstate: %d", (int) walstate);
|
||||
case WALAVAIL_UNRESERVED:
|
||||
values[i++] = CStringGetTextDatum("unreserved");
|
||||
break;
|
||||
|
||||
case WALAVAIL_REMOVED:
|
||||
|
||||
/*
|
||||
* If we read the restart_lsn long enough ago, maybe that file
|
||||
* has been removed by now. However, the walsender could have
|
||||
* moved forward enough that it jumped to another file after
|
||||
* we looked. If checkpointer signalled the process to
|
||||
* termination, then it's definitely lost; but if a process is
|
||||
* still alive, then "unreserved" seems more appropriate.
|
||||
*/
|
||||
if (!XLogRecPtrIsInvalid(slot_contents.data.restart_lsn))
|
||||
{
|
||||
int pid;
|
||||
|
||||
SpinLockAcquire(&slot->mutex);
|
||||
pid = slot->active_pid;
|
||||
SpinLockRelease(&slot->mutex);
|
||||
if (pid != 0)
|
||||
{
|
||||
values[i++] = CStringGetTextDatum("unreserved");
|
||||
break;
|
||||
}
|
||||
}
|
||||
values[i++] = CStringGetTextDatum("lost");
|
||||
break;
|
||||
}
|
||||
|
||||
if (max_slot_wal_keep_size_mb >= 0 &&
|
||||
(walstate == WALAVAIL_NORMAL || walstate == WALAVAIL_RESERVED) &&
|
||||
(walstate == WALAVAIL_RESERVED || walstate == WALAVAIL_EXTENDED) &&
|
||||
((last_removed_seg = XLogGetLastRemovedSegno()) != 0))
|
||||
{
|
||||
XLogRecPtr min_safe_lsn;
|
||||
|
Reference in New Issue
Block a user