public inbox for [email protected]help / color / mirror / Atom feed
[PATCH 1/3] bootstrap: convert Typ to a List* 2+ messages / 2 participants [nested] [flat]
* [PATCH 1/3] bootstrap: convert Typ to a List* @ 2020-11-20 02:48 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Justin Pryzby @ 2020-11-20 02:48 UTC (permalink / raw) --- src/backend/bootstrap/bootstrap.c | 69 ++++++++++++++----------------- 1 file changed, 31 insertions(+), 38 deletions(-) diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 6f615e6622..18eb62ca47 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -159,7 +159,7 @@ struct typmap FormData_pg_type am_typ; }; -static struct typmap **Typ = NULL; +static List *Typ = NIL; /* List of struct typmap* */ static struct typmap *Ap = NULL; static Datum values[MAXATTR]; /* current row's attribute values */ @@ -597,7 +597,7 @@ boot_openrel(char *relname) * pg_type must be filled before any OPEN command is executed, hence we * can now populate the Typ array if we haven't yet. */ - if (Typ == NULL) + if (Typ == NIL) populate_typ_array(); if (boot_reldesc != NULL) @@ -688,7 +688,7 @@ DefineAttr(char *name, char *type, int attnum, int nullness) typeoid = gettype(type); - if (Typ != NULL) + if (Typ != NIL) { attrtypes[attnum]->atttypid = Ap->am_oid; attrtypes[attnum]->attlen = Ap->am_typ.typlen; @@ -877,36 +877,25 @@ populate_typ_array(void) Relation rel; TableScanDesc scan; HeapTuple tup; - int nalloc; - int i; - - Assert(Typ == NULL); - nalloc = 512; - Typ = (struct typmap **) - MemoryContextAlloc(TopMemoryContext, nalloc * sizeof(struct typmap *)); + Assert(Typ == NIL); rel = table_open(TypeRelationId, NoLock); scan = table_beginscan_catalog(rel, 0, NULL); - i = 0; while ((tup = heap_getnext(scan, ForwardScanDirection)) != NULL) { Form_pg_type typForm = (Form_pg_type) GETSTRUCT(tup); + struct typmap *newtyp; + MemoryContext old; - /* make sure there will be room for a trailing NULL pointer */ - if (i >= nalloc - 1) - { - nalloc *= 2; - Typ = (struct typmap **) - repalloc(Typ, nalloc * sizeof(struct typmap *)); - } - Typ[i] = (struct typmap *) - MemoryContextAlloc(TopMemoryContext, sizeof(struct typmap)); - Typ[i]->am_oid = typForm->oid; - memcpy(&(Typ[i]->am_typ), typForm, sizeof(Typ[i]->am_typ)); - i++; + old = MemoryContextSwitchTo(TopMemoryContext); + newtyp = (struct typmap *) palloc(sizeof(struct typmap)); + Typ = lappend(Typ, newtyp); + MemoryContextSwitchTo(old); + + newtyp->am_oid = typForm->oid; + memcpy(&newtyp->am_typ, typForm, sizeof(newtyp->am_typ)); } - Typ[i] = NULL; /* Fill trailing NULL pointer */ table_endscan(scan); table_close(rel, NoLock); } @@ -925,16 +914,17 @@ populate_typ_array(void) static Oid gettype(char *type) { - if (Typ != NULL) + if (Typ != NIL) { - struct typmap **app; + ListCell *lc; - for (app = Typ; *app != NULL; app++) + foreach (lc, Typ) { - if (strncmp(NameStr((*app)->am_typ.typname), type, NAMEDATALEN) == 0) + struct typmap *app = lfirst(lc); + if (strncmp(NameStr(app->am_typ.typname), type, NAMEDATALEN) == 0) { - Ap = *app; - return (*app)->am_oid; + Ap = app; + return app->am_oid; } } } @@ -980,14 +970,17 @@ boot_get_type_io_data(Oid typid, if (Typ != NULL) { /* We have the boot-time contents of pg_type, so use it */ - struct typmap **app; - struct typmap *ap; - - app = Typ; - while (*app && (*app)->am_oid != typid) - ++app; - ap = *app; - if (ap == NULL) + struct typmap *ap = NULL; + ListCell *lc; + + foreach (lc, Typ) + { + ap = lfirst(lc); + if (ap->am_oid == typid) + break; + } + + if (!ap || ap->am_oid != typid) elog(ERROR, "type OID %u not found in Typ list", typid); *typlen = ap->am_typ.typlen; -- 2.26.2 --------------EED78D4A67CFF327F6B880D2 Content-Type: text/x-patch; charset=UTF-8; name="0002-Allow-composite-types-in-bootstrap-20210122b.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="0002-Allow-composite-types-in-bootstrap-20210122b.patch" ^ permalink raw reply [nested|flat] 2+ messages in thread
* Re: Synchronizing slots from primary to standby @ 2024-02-01 03:51 Amit Kapila <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Amit Kapila @ 2024-02-01 03:51 UTC (permalink / raw) To: Masahiko Sawada <[email protected]>; +Cc: shveta malik <[email protected]>; Zhijie Hou (Fujitsu) <[email protected]>; Peter Smith <[email protected]>; Bertrand Drouvot <[email protected]>; Ajin Cherian <[email protected]>; Dilip Kumar <[email protected]>; Nisha Moond <[email protected]>; Hayato Kuroda (Fujitsu) <[email protected]>; Bharath Rupireddy <[email protected]>; Peter Eisentraut <[email protected]>; Bruce Momjian <[email protected]>; Ashutosh Sharma <[email protected]>; Andres Freund <[email protected]>; pgsql-hackers; Alvaro Herrera <[email protected]> On Wed, Jan 31, 2024 at 9:20 PM Masahiko Sawada <[email protected]> wrote: > > On Wed, Jan 31, 2024 at 7:42 PM Amit Kapila <[email protected]> wrote: > > > > > > Considering my previous where we don't want to restart for a required > > parameter change, isn't it better to avoid repeated restart (say when > > the user gave an invalid dbname)? BTW, I think this restart interval > > is added based on your previous complaint [1]. > > I think it's useful that the slotsync worker restarts immediately when > a required parameter is changed but waits to restart when it exits > with an error. IIUC the apply worker does so; if it restarts due to a > subscription parameter change, it resets the last-start time so that > the launcher will restart it without waiting. > Agreed, this idea sounds good to me. > > > > > > > > --- > > > When I dropped a database on the primary that has a failover slot, I > > > got the following logs on the standby: > > > > > > 2024-01-31 17:25:21.750 JST [1103933] FATAL: replication slot "s" is > > > active for PID 1103935 > > > 2024-01-31 17:25:21.750 JST [1103933] CONTEXT: WAL redo at 0/3020D20 > > > for Database/DROP: dir 1663/16384 > > > 2024-01-31 17:25:21.751 JST [1103930] LOG: startup process (PID > > > 1103933) exited with exit code 1 > > > > > > It seems that because the slotsync worker created the slot on the > > > standby, the slot's active_pid is still valid. > > > > > > > But we release the slot after sync. And we do take a shared lock on > > the database to make the startup process wait for slotsync. There is > > one gap which is that we don't reset active_pid for temp slots in > > ReplicationSlotRelease(), so for temp slots such an error can occur > > but OTOH, we immediately make the slot persistent after sync. As per > > my understanding, it is only possible to get this error if the initial > > sync doesn't happen and the slot remains temporary. Is that your case? > > How did reproduce this? > > I created a failover slot manually on the primary and dropped the > database where the failover slot is created. So this would not happen > in normal cases. > Right, it won't happen in normal cases (say for walsender). This can happen in some cases even without this patch as noted in comments just above active_pid check in ReplicationSlotsDropDBSlots(). Now, we need to think whether we should just update the comments above active_pid check to explain this case or try to engineer some solution for this not-so-common case. I guess if we want a solution we need to stop slotsync worker temporarily till the drop database WAL is applied or something like that. > BTW I've tested the following switch/fail-back scenario but it seems > not to work fine. Am I missing something? > > Setup: > node1 is the primary, node2 is the physical standby for node1, and > node3 is the subscriber connecting to node1. > > Steps: > 1. [node1]: create a table and a publication for the table. > 2. [node2]: set enable_syncslot = on and start (to receive WALs from node1). > 3. [node3]: create a subscription with failover = true for the publication. > 4. [node2]: promote to the new standby. > 5. [node3]: alter subscription to connect the new primary, node2. > 6. [node1]: stop, set enable_syncslot = on (and other required > parameters), then start as a new standby. > > Then I got the error "exiting from slot synchronization because same > name slot "test_sub" already exists on the standby". > > The logical replication slot that was created on the old primary > (node1) has been synchronized to the old standby (node2). Therefore on > node2, the slot's "synced" field is true. However, once node1 starts > as the new standby with slot synchronization, the slotsync worker > cannot synchronize the slot because the slot's "synced" field on the > primary is false. > Yeah, we avoided doing anything in this case because the user could have manually created another slot with the same name on standby. Unlike WAL slots can be modified on standby as we allow decoding on standby, so we can't allow to overwrite the existing slots. We won't be able to distinguish whether the existing slot was a slot that the user wants to sync with primary or a slot created on standby to perform decoding. I think in this case user first needs to drop the slot on new standby. We probably need to document it as well unless we decide to do something else. What do you think? -- With Regards, Amit Kapila. ^ permalink raw reply [nested|flat] 2+ messages in thread
end of thread, other threads:[~2024-02-01 03:51 UTC | newest] Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-11-20 02:48 [PATCH 1/3] bootstrap: convert Typ to a List* Justin Pryzby <[email protected]> 2024-02-01 03:51 Re: Synchronizing slots from primary to standby Amit Kapila <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox