/* * Set the state of a slot. * * This doesn't maintain the non-persistent state at all, * but since the slot isn't in use that's OK. * * There's intentionally no check to prevent slots going backwards * because they can actually go backwards if the master crashes when * it hasn't yet flushed slot state to disk then we copy the older * slot state after recovery. * * There's no checking done for xmin or catalog xmin either, since * we can't really do anything useful that accounts for xid wrap-around. * * Note that this is test harness code. You shouldn't expose slot internals * to SQL like this for any real world usage. See the README. */ Datum test_slot_timelines_advance_logical_slot(PG_FUNCTION_ARGS) { char *slotname = text_to_cstring(PG_GETARG_TEXT_P(0)); TransactionId new_xmin = (TransactionId) PG_GETARG_INT64(1); TransactionId new_catalog_xmin = (TransactionId) PG_GETARG_INT64(2); XLogRecPtr restart_lsn = PG_GETARG_LSN(3); XLogRecPtr confirmed_lsn = PG_GETARG_LSN(4); CheckSlotRequirements(); ReplicationSlotAcquire(slotname); if (MyReplicationSlot->data.database != MyDatabaseId) elog(ERROR, "Trying to update a slot on a different database"); MyReplicationSlot->data.xmin = new_xmin; MyReplicationSlot->data.catalog_xmin = new_catalog_xmin; MyReplicationSlot->data.restart_lsn = restart_lsn; MyReplicationSlot->data.confirmed_flush = confirmed_lsn; clear_slot_transient_state(); ReplicationSlotMarkDirty(); ReplicationSlotSave(); ReplicationSlotRelease(); ReplicationSlotsComputeRequiredXmin(false); ReplicationSlotsComputeRequiredLSN(); PG_RETURN_VOID(); }
/* * Load all replication slots from disk into memory at server startup. This * needs to be run before we start crash recovery. */ void StartupReplicationSlots(XLogRecPtr checkPointRedo) { DIR *replication_dir; struct dirent *replication_de; ereport(DEBUG1, (errmsg("starting up replication slots"))); /* restore all slots by iterating over all on-disk entries */ replication_dir = AllocateDir("pg_replslot"); while ((replication_de = ReadDir(replication_dir, "pg_replslot")) != NULL) { struct stat statbuf; char path[MAXPGPATH]; if (strcmp(replication_de->d_name, ".") == 0 || strcmp(replication_de->d_name, "..") == 0) continue; snprintf(path, MAXPGPATH, "pg_replslot/%s", replication_de->d_name); /* we're only creating directories here, skip if it's not our's */ if (lstat(path, &statbuf) == 0 && !S_ISDIR(statbuf.st_mode)) continue; /* we crashed while a slot was being setup or deleted, clean up */ if (string_endswith(replication_de->d_name, ".tmp")) { if (!rmtree(path, true)) { ereport(WARNING, (errcode_for_file_access(), errmsg("could not remove directory \"%s\"", path))); continue; } fsync_fname("pg_replslot", true); continue; } /* looks like a slot in a normal state, restore */ RestoreSlotFromDisk(replication_de->d_name); } FreeDir(replication_dir); /* currently no slots exist, we're done. */ if (max_replication_slots <= 0) return; /* Now that we have recovered all the data, compute replication xmin */ ReplicationSlotsComputeRequiredXmin(); ReplicationSlotsComputeRequiredLSN(); }
/* * Release the replication slot that this backend considers to own. * * This or another backend can re-acquire the slot later. * Resources this slot requires will be preserved. */ void ReplicationSlotRelease(void) { ReplicationSlot *slot = MyReplicationSlot; Assert(slot != NULL && slot->active_pid != 0); if (slot->data.persistency == RS_EPHEMERAL) { /* * Delete the slot. There is no !PANIC case where this is allowed to * fail, all that may happen is an incomplete cleanup of the on-disk * data. */ ReplicationSlotDropAcquired(); } /* * If slot needed to temporarily restrain both data and catalog xmin to * create the catalog snapshot, remove that temporary constraint. * Snapshots can only be exported while the initial snapshot is still * acquired. */ if (!TransactionIdIsValid(slot->data.xmin) && TransactionIdIsValid(slot->effective_xmin)) { SpinLockAcquire(&slot->mutex); slot->effective_xmin = InvalidTransactionId; SpinLockRelease(&slot->mutex); ReplicationSlotsComputeRequiredXmin(false); } if (slot->data.persistency == RS_PERSISTENT) { /* * Mark persistent slot inactive. We're not freeing it, just * disconnecting, but wake up others that may be waiting for it. */ SpinLockAcquire(&slot->mutex); slot->active_pid = 0; SpinLockRelease(&slot->mutex); ConditionVariableBroadcast(&slot->active_cv); } MyReplicationSlot = NULL; /* might not have been set when we've been a plain slot */ LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); MyPgXact->vacuumFlags &= ~PROC_IN_LOGICAL_DECODING; LWLockRelease(ProcArrayLock); }
/* * Permanently drop the replication slot which will be released by the point * this function returns. */ static void ReplicationSlotDropPtr(ReplicationSlot *slot) { char path[MAXPGPATH]; char tmppath[MAXPGPATH]; /* * If some other backend ran this code concurrently with us, we might try * to delete a slot with a certain name while someone else was trying to * create a slot with the same name. */ LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* Generate pathnames. */ sprintf(path, "pg_replslot/%s", NameStr(slot->data.name)); sprintf(tmppath, "pg_replslot/%s.tmp", NameStr(slot->data.name)); /* * Rename the slot directory on disk, so that we'll no longer recognize * this as a valid slot. Note that if this fails, we've got to mark the * slot inactive before bailing out. If we're dropping an ephemeral or a * temporary slot, we better never fail hard as the caller won't expect * the slot to survive and this might get called during error handling. */ if (rename(path, tmppath) == 0) { /* * We need to fsync() the directory we just renamed and its parent to * make sure that our changes are on disk in a crash-safe fashion. If * fsync() fails, we can't be sure whether the changes are on disk or * not. For now, we handle that by panicking; * StartupReplicationSlots() will try to straighten it out after * restart. */ START_CRIT_SECTION(); fsync_fname(tmppath, true); fsync_fname("pg_replslot", true); END_CRIT_SECTION(); } else { bool fail_softly = slot->data.persistency != RS_PERSISTENT; SpinLockAcquire(&slot->mutex); slot->active_pid = 0; SpinLockRelease(&slot->mutex); /* wake up anyone waiting on this slot */ ConditionVariableBroadcast(&slot->active_cv); ereport(fail_softly ? WARNING : ERROR, (errcode_for_file_access(), errmsg("could not rename file \"%s\" to \"%s\": %m", path, tmppath))); } /* * The slot is definitely gone. Lock out concurrent scans of the array * long enough to kill it. It's OK to clear the active PID here without * grabbing the mutex because nobody else can be scanning the array here, * and nobody can be attached to this slot and thus access it without * scanning the array. * * Also wake up processes waiting for it. */ LWLockAcquire(ReplicationSlotControlLock, LW_EXCLUSIVE); slot->active_pid = 0; slot->in_use = false; LWLockRelease(ReplicationSlotControlLock); ConditionVariableBroadcast(&slot->active_cv); /* * Slot is dead and doesn't prevent resource removal anymore, recompute * limits. */ ReplicationSlotsComputeRequiredXmin(false); ReplicationSlotsComputeRequiredLSN(); /* * If removing the directory fails, the worst thing that will happen is * that the user won't be able to create a new slot with the same name * until the next server restart. We warn about it, but that's all. */ if (!rmtree(tmppath, true)) ereport(WARNING, (errcode_for_file_access(), errmsg("could not remove directory \"%s\"", tmppath))); /* * We release this at the very end, so that nobody starts trying to create * a slot while we're still cleaning up the detritus of the old one. */ LWLockRelease(ReplicationSlotAllocationLock); }
/* * Permanently drop replication slot identified by the passed in name. */ void ReplicationSlotDrop(const char *name) { ReplicationSlot *slot = NULL; int i; bool active; char path[MAXPGPATH]; char tmppath[MAXPGPATH]; ReplicationSlotValidateName(name, ERROR); /* * If some other backend ran this code currently with us, we might both * try to free the same slot at the same time. Or we might try to delete * a slot with a certain name while someone else was trying to create a * slot with the same name. */ LWLockAcquire(ReplicationSlotAllocationLock, LW_EXCLUSIVE); /* Search for the named slot and mark it active if we find it. */ LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); for (i = 0; i < max_replication_slots; i++) { ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i]; if (s->in_use && strcmp(name, NameStr(s->data.name)) == 0) { volatile ReplicationSlot *vslot = s; SpinLockAcquire(&s->mutex); active = vslot->active; vslot->active = true; SpinLockRelease(&s->mutex); slot = s; break; } } LWLockRelease(ReplicationSlotControlLock); /* If we did not find the slot or it was already active, error out. */ if (slot == NULL) ereport(ERROR, (errcode(ERRCODE_UNDEFINED_OBJECT), errmsg("replication slot \"%s\" does not exist", name))); if (active) ereport(ERROR, (errcode(ERRCODE_OBJECT_IN_USE), errmsg("replication slot \"%s\" is already active", name))); /* Generate pathnames. */ sprintf(path, "pg_replslot/%s", NameStr(slot->data.name)); sprintf(tmppath, "pg_replslot/%s.tmp", NameStr(slot->data.name)); /* * Rename the slot directory on disk, so that we'll no longer recognize * this as a valid slot. Note that if this fails, we've got to mark the * slot inactive again before bailing out. */ if (rename(path, tmppath) != 0) { volatile ReplicationSlot *vslot = slot; SpinLockAcquire(&slot->mutex); vslot->active = false; SpinLockRelease(&slot->mutex); ereport(ERROR, (errcode_for_file_access(), errmsg("could not rename \"%s\" to \"%s\": %m", path, tmppath))); } /* * We need to fsync() the directory we just renamed and its parent to make * sure that our changes are on disk in a crash-safe fashion. If fsync() * fails, we can't be sure whether the changes are on disk or not. For * now, we handle that by panicking; StartupReplicationSlots() will * try to straighten it out after restart. */ START_CRIT_SECTION(); fsync_fname(tmppath, true); fsync_fname("pg_replslot", true); END_CRIT_SECTION(); /* * The slot is definitely gone. Lock out concurrent scans of the array * long enough to kill it. It's OK to clear the active flag here without * grabbing the mutex because nobody else can be scanning the array here, * and nobody can be attached to this slot and thus access it without * scanning the array. */ LWLockAcquire(ReplicationSlotControlLock, LW_EXCLUSIVE); slot->active = false; slot->in_use = false; LWLockRelease(ReplicationSlotControlLock); /* * Slot is dead and doesn't prevent resource removal anymore, recompute * limits. */ ReplicationSlotsComputeRequiredXmin(); ReplicationSlotsComputeRequiredLSN(); /* * If removing the directory fails, the worst thing that will happen is * that the user won't be able to create a new slot with the same name * until the next server restart. We warn about it, but that's all. */ if (!rmtree(tmppath, true)) ereport(WARNING, (errcode_for_file_access(), errmsg("could not remove directory \"%s\"", tmppath))); /* * We release this at the very end, so that nobody starts trying to create * a slot while we're still cleaning up the detritus of the old one. */ LWLockRelease(ReplicationSlotAllocationLock); }