From d1aa9658ee1d467d5ec79d0e933c2b66b47aad93 Mon Sep 17 00:00:00 2001 From: "houzj.fnst" Date: Wed, 20 Apr 2022 16:45:07 +0800 Subject: [PATCH v31 1/5] Perform streaming logical transactions by parallel workers Currently, for large transactions, the publisher sends the data in multiple streams (changes divided into chunks depending upon logical_decoding_work_mem), and then on the subscriber-side, the apply worker writes the changes into temporary files and once it receives the commit, it reads from the file and applies the entire transaction. To improve the performance of such transactions, we can instead allow them to be applied via parallel workers. In this approach, we assign a new parallel apply worker (if available) as soon as the xact's first stream is received and the leader apply worker will send changes to this new worker via shared memory. The parallel apply worker will directly apply the change instead of writing it to temporary files. We keep this worker assigned till the transaction commit is received and also wait for the worker to finish at commit. This preserves commit ordering and avoids writing to and reading from file in most cases. We still need to spill if there is no worker available. This patch also extends the SUBSCRIPTION 'streaming' parameter so that the user can control whether to apply the streaming transaction in a parallel apply worker or spill the change to disk. The user can set the streaming parameter to 'on/off', 'parallel'. The parameter value 'parallel' means the streaming will be applied via a parallel apply worker, if available. The parameter value 'on' means the streaming transaction will be spilled to disk. The default value is 'off' (same as current behaviour). In addition, the patch extends the logical replication STREAM_ABORT message so that abort_time and abort_lsn can also be sent which can be used to update the replication origin in parallel apply worker when the streaming transaction is aborted. Because this message extension is needed to support parallel streaming, meaning that parallel streaming is not supported for publications on servers < PG16. --- doc/src/sgml/catalogs.sgml | 11 +- doc/src/sgml/config.sgml | 28 +- doc/src/sgml/logical-replication.sgml | 21 +- doc/src/sgml/monitoring.sgml | 15 +- doc/src/sgml/protocol.sgml | 29 +- doc/src/sgml/ref/create_subscription.sgml | 24 +- src/backend/access/transam/xact.c | 13 + src/backend/commands/define.c | 58 + src/backend/commands/subscriptioncmds.c | 10 +- src/backend/libpq/pqmq.c | 18 +- src/backend/postmaster/bgworker.c | 3 + .../libpqwalreceiver/libpqwalreceiver.c | 7 +- src/backend/replication/logical/Makefile | 1 + .../replication/logical/applyparallelworker.c | 1097 +++++++++++++++++ src/backend/replication/logical/decode.c | 10 +- src/backend/replication/logical/launcher.c | 167 ++- src/backend/replication/logical/proto.c | 37 +- .../replication/logical/reorderbuffer.c | 10 +- src/backend/replication/logical/tablesync.c | 6 +- src/backend/replication/logical/worker.c | 872 ++++++++++--- src/backend/replication/pgoutput/pgoutput.c | 20 +- src/backend/storage/ipc/procsignal.c | 4 + src/backend/tcop/postgres.c | 3 + src/backend/utils/activity/wait_event.c | 3 + src/backend/utils/misc/guc_tables.c | 12 + src/backend/utils/misc/postgresql.conf.sample | 1 + src/bin/pg_dump/pg_dump.c | 6 +- src/include/catalog/pg_subscription.h | 21 +- src/include/commands/defrem.h | 1 + src/include/replication/logicallauncher.h | 1 + src/include/replication/logicalproto.h | 28 +- src/include/replication/logicalworker.h | 6 + src/include/replication/pgoutput.h | 2 +- src/include/replication/reorderbuffer.h | 7 +- src/include/replication/walreceiver.h | 2 +- src/include/replication/worker_internal.h | 129 +- src/include/storage/procsignal.h | 1 + src/include/utils/wait_event.h | 1 + src/test/regress/expected/subscription.out | 12 +- src/test/regress/sql/subscription.sql | 6 +- src/tools/pgindent/typedefs.list | 5 + 41 files changed, 2442 insertions(+), 266 deletions(-) create mode 100644 src/backend/replication/logical/applyparallelworker.c diff --git a/doc/src/sgml/catalogs.sgml b/doc/src/sgml/catalogs.sgml index 00f833d210..c5769da26b 100644 --- a/doc/src/sgml/catalogs.sgml +++ b/doc/src/sgml/catalogs.sgml @@ -7892,11 +7892,16 @@ SCRAM-SHA-256$<iteration count>:&l - substream bool + substream char - If true, the subscription will allow streaming of in-progress - transactions + Controls how to handle the streaming of in-progress transactions: + f = disallow streaming of in-progress transactions, + t = spill the changes of in-progress transactions to + disk and apply at once after the transaction is committed on the + publisher, + p = apply changes directly using a parallel apply + worker if available (same as 't' if no worker is available) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 700914684d..cb2be8a2e1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4940,7 +4940,8 @@ ANY num_sync ( num_sync ( + max_parallel_apply_workers_per_subscription (integer) + + max_parallel_apply_workers_per_subscription configuration parameter + + + + + Maximum number of parallel apply workers per subscription. This + parameter controls the amount of parallelism for streaming of + in-progress transactions with subscription parameter + streaming = parallel. + + + The parallel apply workers are taken from the pool defined by + max_logical_replication_workers. + + + The default value is 2. This parameter can only be set in the + postgresql.conf file or on the server command + line. + + + + diff --git a/doc/src/sgml/logical-replication.sgml b/doc/src/sgml/logical-replication.sgml index 48fd8e33dc..7e5962d5e0 100644 --- a/doc/src/sgml/logical-replication.sgml +++ b/doc/src/sgml/logical-replication.sgml @@ -1335,6 +1335,16 @@ CONTEXT: processing remote data for replication origin "pg_16395" during "INSER might not violate any constraint. This can easily make the subscriber inconsistent. + + + When the streaming mode is parallel, the finish LSN of + failed transactions may not be logged. In that case, it may be necessary to + change the streaming mode to on or off and + cause the same conflicts again so the finish LSN of the failed transaction will + be written to the server log. For the usage of finish LSN, please refer to ALTER SUBSCRIPTION ... + SKIP. + @@ -1516,7 +1526,8 @@ CONTEXT: processing remote data for replication origin "pg_16395" during "INSER subscription. A disabled subscription or a crashed subscription will have zero rows in this view. If the initial data synchronization of any table is in progress, there will be additional workers for the tables - being synchronized. + being synchronized. Moreover, if the streaming transaction is applied in + parallel, there will be additional workers. @@ -1611,8 +1622,12 @@ CONTEXT: processing remote data for replication origin "pg_16395" during "INSER to the subscriber, plus some reserve for table synchronization. max_logical_replication_workers must be set to at least the number of subscriptions, again plus some reserve for the table - synchronization. Additionally the max_worker_processes - may need to be adjusted to accommodate for replication workers, at least + synchronization. In addition, if the subscription parameter + streaming is set to parallel, please + increase max_logical_replication_workers according to + the desired number of parallel apply workers. Additionally the + max_worker_processes may need to be adjusted to + accommodate for replication workers, at least (max_logical_replication_workers + 1). Note that some extensions and parallel queries also take worker slots from max_worker_processes. diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 1d9509a2f6..8765a4add1 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -3184,7 +3184,7 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i OID of the relation that the worker is synchronizing; null for the - main apply worker + main apply worker and the apply parallel worker @@ -3194,7 +3194,7 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i Last write-ahead log location received, the initial value of - this field being 0 + this field being 0; null for the apply parallel worker @@ -3203,7 +3203,8 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i last_msg_send_time timestamp with time zone - Send time of last message received from origin WAL sender + Send time of last message received from origin WAL sender; null for the + apply parallel worker @@ -3212,7 +3213,8 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i last_msg_receipt_time timestamp with time zone - Receipt time of last message received from origin WAL sender + Receipt time of last message received from origin WAL sender; null for + the apply parallel worker @@ -3221,7 +3223,8 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i latest_end_lsn pg_lsn - Last write-ahead log location reported to origin WAL sender + Last write-ahead log location reported to origin WAL sender; null for + the apply parallel worker @@ -3231,7 +3234,7 @@ SELECT pid, wait_event_type, wait_event FROM pg_stat_activity WHERE wait_event i Time of last write-ahead log location reported to origin WAL - sender + sender; null for the apply parallel worker diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml index f63c912e97..2b973c13eb 100644 --- a/doc/src/sgml/protocol.sgml +++ b/doc/src/sgml/protocol.sgml @@ -3100,7 +3100,7 @@ psql "dbname=postgres replication=database" -c "IDENTIFY_SYSTEM;" Protocol version. Currently versions 1, 2, - and 3 are supported. + 3, and 4 are supported. Version 2 is supported only for server version 14 @@ -3110,6 +3110,11 @@ psql "dbname=postgres replication=database" -c "IDENTIFY_SYSTEM;" Version 3 is supported only for server version 15 and above, and it allows streaming of two-phase commits. + + Version 4 is supported only for server version 16 + and above, and it allows applying streams of large in-progress + transactions in parallel. + @@ -6880,6 +6885,28 @@ psql "dbname=postgres replication=database" -c "IDENTIFY_SYSTEM;" + + + Int64 (XLogRecPtr) + + + The LSN of the abort. This field is available since protocol version + 4. + + + + + + Int64 (TimestampTz) + + + Abort timestamp of the transaction. The value is in number + of microseconds since PostgreSQL epoch (2000-01-01). This field is + available since protocol version 4. + + + + diff --git a/doc/src/sgml/ref/create_subscription.sgml b/doc/src/sgml/ref/create_subscription.sgml index 4e001f8111..175cce8506 100644 --- a/doc/src/sgml/ref/create_subscription.sgml +++ b/doc/src/sgml/ref/create_subscription.sgml @@ -222,13 +222,29 @@ CREATE SUBSCRIPTION subscription_name - streaming (boolean) + streaming (enum) Specifies whether to enable streaming of in-progress transactions - for this subscription. By default, all transactions - are fully decoded on the publisher and only then sent to the - subscriber as a whole. + for this subscription. The default value is off, + meaning all transactions are fully decoded on the publisher and only + then sent to the subscriber as a whole. + + + + If set to on, the incoming changes are written to + temporary files and then applied only after the transaction is + committed on the publisher and received by the subscriber. + + + + If set to parallel, incoming changes are directly + applied via one of the parallel apply workers, if available. If no + parallel worker is free to handle streaming transactions then the + changes are written to temporary files and applied after the + transaction is committed. Note that if an error happens when + applying changes in a parallel worker, the finish LSN of the + remote transaction might not be reported in the server log. diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c index 2bb975943c..d195f39cf7 100644 --- a/src/backend/access/transam/xact.c +++ b/src/backend/access/transam/xact.c @@ -1711,6 +1711,7 @@ RecordTransactionAbort(bool isSubXact) int nchildren; TransactionId *children; TimestampTz xact_time; + bool replorigin; /* * If we haven't been assigned an XID, nobody will care whether we aborted @@ -1741,6 +1742,13 @@ RecordTransactionAbort(bool isSubXact) elog(PANIC, "cannot abort transaction %u, it was already committed", xid); + /* + * Are we using the replication origins feature? Or, in other words, are + * we replaying remote actions? + */ + replorigin = (replorigin_session_origin != InvalidRepOriginId && + replorigin_session_origin != DoNotReplicateId); + /* Fetch the data we need for the abort record */ nrels = smgrGetPendingDeletes(false, &rels); nchildren = xactGetCommittedChildren(&children); @@ -1765,6 +1773,11 @@ RecordTransactionAbort(bool isSubXact) MyXactFlags, InvalidTransactionId, NULL); + if (replorigin) + /* Move LSNs forward for this replication origin */ + replorigin_session_advance(replorigin_session_origin_lsn, + XactLastRecEnd); + /* * Report the latest async abort LSN, so that the WAL writer knows to * flush this abort. There's nothing to be gained by delaying this, since diff --git a/src/backend/commands/define.c b/src/backend/commands/define.c index 86b89071ee..11312d1920 100644 --- a/src/backend/commands/define.c +++ b/src/backend/commands/define.c @@ -36,6 +36,7 @@ #include #include "catalog/namespace.h" +#include "catalog/pg_subscription.h" #include "commands/defrem.h" #include "nodes/makefuncs.h" #include "parser/parse_type.h" @@ -345,6 +346,63 @@ defGetStringList(DefElem *def) return (List *) def->arg; } +/* + * Extract the streaming mode value from a DefElem. This is like + * defGetBoolean() but also accepts the special value of "parallel". + */ +char +defGetStreamingMode(DefElem *def) +{ + /* + * If no parameter value given, assume "true" is meant. + */ + if (def->arg == NULL) + return SUBSTREAM_ON; + + /* + * Allow 0, 1, "false", "true", "off", "on" or "parallel". + */ + switch (nodeTag(def->arg)) + { + case T_Integer: + switch (intVal(def->arg)) + { + case 0: + return SUBSTREAM_OFF; + case 1: + return SUBSTREAM_ON; + default: + /* otherwise, error out below */ + break; + } + break; + default: + { + char *sval = defGetString(def); + + /* + * The set of strings accepted here should match up with the + * grammar's opt_boolean_or_string production. + */ + if (pg_strcasecmp(sval, "false") == 0 || + pg_strcasecmp(sval, "off") == 0) + return SUBSTREAM_OFF; + if (pg_strcasecmp(sval, "true") == 0 || + pg_strcasecmp(sval, "on") == 0) + return SUBSTREAM_ON; + if (pg_strcasecmp(sval, "parallel") == 0) + return SUBSTREAM_PARALLEL; + } + break; + } + + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("%s requires a Boolean value or \"parallel\"", + def->defname))); + return SUBSTREAM_OFF; /* keep compiler quiet */ +} + /* * Raise an error about a conflicting DefElem. */ diff --git a/src/backend/commands/subscriptioncmds.c b/src/backend/commands/subscriptioncmds.c index d042abe341..9e7903f32e 100644 --- a/src/backend/commands/subscriptioncmds.c +++ b/src/backend/commands/subscriptioncmds.c @@ -84,7 +84,7 @@ typedef struct SubOpts bool copy_data; bool refresh; bool binary; - bool streaming; + char streaming; bool twophase; bool disableonerr; char *origin; @@ -138,7 +138,7 @@ parse_subscription_options(ParseState *pstate, List *stmt_options, if (IsSet(supported_opts, SUBOPT_BINARY)) opts->binary = false; if (IsSet(supported_opts, SUBOPT_STREAMING)) - opts->streaming = false; + opts->streaming = SUBSTREAM_OFF; if (IsSet(supported_opts, SUBOPT_TWOPHASE_COMMIT)) opts->twophase = false; if (IsSet(supported_opts, SUBOPT_DISABLE_ON_ERR)) @@ -241,7 +241,7 @@ parse_subscription_options(ParseState *pstate, List *stmt_options, errorConflictingDefElem(defel, pstate); opts->specified_opts |= SUBOPT_STREAMING; - opts->streaming = defGetBoolean(defel); + opts->streaming = defGetStreamingMode(defel); } else if (strcmp(defel->defname, "two_phase") == 0) { @@ -631,7 +631,7 @@ CreateSubscription(ParseState *pstate, CreateSubscriptionStmt *stmt, values[Anum_pg_subscription_subowner - 1] = ObjectIdGetDatum(owner); values[Anum_pg_subscription_subenabled - 1] = BoolGetDatum(opts.enabled); values[Anum_pg_subscription_subbinary - 1] = BoolGetDatum(opts.binary); - values[Anum_pg_subscription_substream - 1] = BoolGetDatum(opts.streaming); + values[Anum_pg_subscription_substream - 1] = CharGetDatum(opts.streaming); values[Anum_pg_subscription_subtwophasestate - 1] = CharGetDatum(opts.twophase ? LOGICALREP_TWOPHASE_STATE_PENDING : @@ -1101,7 +1101,7 @@ AlterSubscription(ParseState *pstate, AlterSubscriptionStmt *stmt, if (IsSet(opts.specified_opts, SUBOPT_STREAMING)) { values[Anum_pg_subscription_substream - 1] = - BoolGetDatum(opts.streaming); + CharGetDatum(opts.streaming); replaces[Anum_pg_subscription_substream - 1] = true; } diff --git a/src/backend/libpq/pqmq.c b/src/backend/libpq/pqmq.c index 4d0415e379..6d5394e3b1 100644 --- a/src/backend/libpq/pqmq.c +++ b/src/backend/libpq/pqmq.c @@ -13,11 +13,13 @@ #include "postgres.h" +#include "access/parallel.h" #include "libpq/libpq.h" #include "libpq/pqformat.h" #include "libpq/pqmq.h" #include "miscadmin.h" #include "pgstat.h" +#include "replication/logicalworker.h" #include "tcop/tcopprot.h" #include "utils/builtins.h" @@ -162,9 +164,19 @@ mq_putmessage(char msgtype, const char *s, size_t len) result = shm_mq_sendv(pq_mq_handle, iov, 2, true, true); if (pq_mq_parallel_leader_pid != 0) - SendProcSignal(pq_mq_parallel_leader_pid, - PROCSIG_PARALLEL_MESSAGE, - pq_mq_parallel_leader_backend_id); + { + if (IsParallelWorker()) + SendProcSignal(pq_mq_parallel_leader_pid, + PROCSIG_PARALLEL_MESSAGE, + pq_mq_parallel_leader_backend_id); + else + { + Assert(IsLogicalParallelApplyWorker()); + SendProcSignal(pq_mq_parallel_leader_pid, + PROCSIG_PARALLEL_APPLY_MESSAGE, + pq_mq_parallel_leader_backend_id); + } + } if (result != SHM_MQ_WOULD_BLOCK) break; diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index 8dd7d64630..9f6199cbcc 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -128,6 +128,9 @@ static const struct }, { "ApplyWorkerMain", ApplyWorkerMain + }, + { + "ParallelApplyWorkerMain", ParallelApplyWorkerMain } }; diff --git a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c index 7f697b0f29..f17da260cb 100644 --- a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c +++ b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c @@ -20,6 +20,7 @@ #include #include "access/xlog.h" +#include "catalog/pg_subscription.h" #include "catalog/pg_type.h" #include "common/connect.h" #include "funcapi.h" @@ -443,9 +444,9 @@ libpqrcv_startstreaming(WalReceiverConn *conn, appendStringInfo(&cmd, "proto_version '%u'", options->proto.logical.proto_version); - if (options->proto.logical.streaming && - PQserverVersion(conn->streamConn) >= 140000) - appendStringInfoString(&cmd, ", streaming 'on'"); + if (options->proto.logical.streaming) + appendStringInfo(&cmd, ", streaming '%s'", + options->proto.logical.streaming); if (options->proto.logical.twophase && PQserverVersion(conn->streamConn) >= 150000) diff --git a/src/backend/replication/logical/Makefile b/src/backend/replication/logical/Makefile index c4e2fdeb71..2dc25e37bb 100644 --- a/src/backend/replication/logical/Makefile +++ b/src/backend/replication/logical/Makefile @@ -15,6 +15,7 @@ include $(top_builddir)/src/Makefile.global override CPPFLAGS := -I$(srcdir) $(CPPFLAGS) OBJS = \ + applyparallelworker.o \ decode.o \ launcher.o \ logical.o \ diff --git a/src/backend/replication/logical/applyparallelworker.c b/src/backend/replication/logical/applyparallelworker.c new file mode 100644 index 0000000000..6646cb60d9 --- /dev/null +++ b/src/backend/replication/logical/applyparallelworker.c @@ -0,0 +1,1097 @@ +/*------------------------------------------------------------------------- + * applyparallelworker.c + * Support routines for applying xact by parallel apply worker + * + * Copyright (c) 2016-2022, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/backend/replication/logical/applyparallelworker.c + * + * This file contains routines that are intended to support setting up, using, + * and tearing down a ParallelApplyWorkerInfo. + * + * Refer to the comments in file header of logical/worker.c to see more + * information about parallel apply worker. + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "libpq/pqformat.h" +#include "libpq/pqmq.h" +#include "mb/pg_wchar.h" +#include "pgstat.h" +#include "postmaster/interrupt.h" +#include "replication/logicallauncher.h" +#include "replication/logicalworker.h" +#include "replication/origin.h" +#include "replication/walreceiver.h" +#include "replication/worker_internal.h" +#include "storage/ipc.h" +#include "storage/procarray.h" +#include "tcop/tcopprot.h" +#include "utils/inval.h" +#include "utils/memutils.h" +#include "utils/resowner.h" +#include "utils/syscache.h" + +#define PG_LOGICAL_APPLY_SHM_MAGIC 0x787ca067 + +/* + * DSM keys for parallel apply worker. Unlike other parallel execution code, + * since we don't need to worry about DSM keys conflicting with plan_node_id we + * can use small integers. + */ +#define PARALLEL_APPLY_KEY_SHARED 1 +#define PARALLEL_APPLY_KEY_MQ 2 +#define PARALLEL_APPLY_KEY_ERROR_QUEUE 3 + +/* Queue size of DSM, 16 MB for now. */ +#define DSM_QUEUE_SIZE (16 * 1024 * 1024) + +/* + * Error queue size of DSM. It is desirable to make it large enough that a + * typical ErrorResponse can be sent without blocking. That way, a worker that + * errors out can write the whole message into the queue and terminate without + * waiting for the user backend. + */ +#define DSM_ERROR_QUEUE_SIZE (16 * 1024) + +/* + * There are three fields in each message received by the parallel apply + * worker: start_lsn, end_lsn and send_time. Because we have updated these + * statistics in the leader apply worker, we can ignore these fields in the + * parallel apply worker (see function LogicalRepApplyLoop). + */ +#define SIZE_STATS_MESSAGE (2 * sizeof(XLogRecPtr) + sizeof(TimestampTz)) + +/* + * Hash table entry to map xid to the parallel apply worker state. + */ +typedef struct ParallelApplyWorkerEntry +{ + TransactionId xid; /* Hash key -- must be first */ + ParallelApplyWorkerInfo *winfo; +} ParallelApplyWorkerEntry; + +/* Parallel apply workers hash table (initialized on first use). */ +static HTAB *ParallelApplyWorkersHash = NULL; + +/* + * A list to maintain the active parallel apply workers. The information for + * the new worker is added to the list after successfully launching it. The + * list entry is removed at the end of the transaction if there are already + * enough workers in the worker pool. For more information about the worker + * pool, see comments atop worker.c. We also remove the entry from the list if + * the worker is exited due to some error. + */ +static List *ParallelApplyWorkersList = NIL; + +/* + * Information shared between leader apply worker and parallel apply worker. + */ +ParallelApplyWorkerShared *MyParallelShared = NULL; + +/* + * Is there a message pending in parallel apply worker which we need to + * receive? + */ +volatile bool ParallelApplyMessagePending = false; + +/* + * Cache the parallel apply worker information required for applying the + * current streaming transaction. It is used to save the cost of searching the + * hash table when applying the changes between STREAM_START and STREAM_STOP. + */ +ParallelApplyWorkerInfo *stream_apply_worker = NULL; + +/* A list to maintain subtransactions, if any. */ +List *subxactlist = NIL; + +static bool parallel_apply_can_start(TransactionId xid); +static bool parallel_apply_setup_dsm(ParallelApplyWorkerInfo *winfo); +static ParallelApplyWorkerInfo *parallel_apply_setup_worker(void); +static bool parallel_apply_get_in_xact(ParallelApplyWorkerShared *wshared); +static void parallel_apply_free_worker_info(ParallelApplyWorkerInfo *winfo); + +/* + * Returns true, if it is allowed to start a parallel apply worker, false, + * otherwise. + */ +static bool +parallel_apply_can_start(TransactionId xid) +{ + if (!TransactionIdIsValid(xid)) + return false; + + /* + * Don't start a new parallel worker if not in parallel streaming mode. + */ + if (MySubscription->stream != SUBSTREAM_PARALLEL) + return false; + + /* Only leader apply workers can start parallel apply workers. */ + if (am_parallel_apply_worker()) + return false; + + /* + * Don't start a new parallel worker if user has set skiplsn as it's + * possible that user want to skip the streaming transaction. For + * streaming transaction, we need to spill the transaction to disk so that + * we can get the last LSN of the transaction to judge whether to skip + * before starting to apply the change. + */ + if (!XLogRecPtrIsInvalid(MySubscription->skiplsn)) + return false; + + /* + * For streaming transactions that are being applied using a parallel + * apply worker, we cannot decide whether to apply the change for a + * relation that is not in the READY state (see + * should_apply_changes_for_rel) as we won't know remote_final_lsn by that + * time. So, we don't start the new parallel apply worker in this case. + */ + if (!AllTablesyncsReady()) + return false; + + /* + * Parallel apply is not supported when subscribing to a publisher which + * cannot provide the abort_time and abort_lsn. + */ + if (walrcv_server_version(LogRepWorkerWalRcvConn) < 160000) + return false; + + return true; +} + +/* + * Start a parallel apply worker that will be used for the specified xid. + * + * If a parallel apply worker is found but not in use then re-use it, otherwise + * start a fresh one. Cache the worker information in ParallelApplyWorkersHash + * keyed by the specified xid. + */ +void +parallel_apply_start_worker(TransactionId xid) +{ + bool found; + ListCell *lc; + ParallelApplyWorkerInfo *winfo = NULL; + ParallelApplyWorkerEntry *entry = NULL; + + if (!parallel_apply_can_start(xid)) + return; + + /* First time through, initialize apply workers hashtable. */ + if (ParallelApplyWorkersHash == NULL) + { + HASHCTL ctl; + + MemSet(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(TransactionId); + ctl.entrysize = sizeof(ParallelApplyWorkerEntry); + ctl.hcxt = ApplyContext; + + ParallelApplyWorkersHash = hash_create("logical apply workers hash", + 16, &ctl, + HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + } + + /* Try to get a free parallel apply worker. */ + foreach(lc, ParallelApplyWorkersList) + { + ParallelApplyWorkerInfo *tmp_winfo; + + tmp_winfo = (ParallelApplyWorkerInfo *) lfirst(lc); + + if (tmp_winfo->error_mq_handle == NULL) + { + /* + * Release the worker information and try next one if the parallel + * apply worker exited cleanly. + */ + ParallelApplyWorkersList = foreach_delete_current(ParallelApplyWorkersList, lc); + shm_mq_detach(tmp_winfo->mq_handle); + dsm_detach(tmp_winfo->dsm_seg); + pfree(tmp_winfo); + } + else if (!tmp_winfo->in_use) + { + /* Found a worker that has not been assigned a transaction. */ + winfo = tmp_winfo; + break; + } + } + + /* Try to start a new parallel apply worker. */ + if (winfo == NULL) + winfo = parallel_apply_setup_worker(); + + /* Failed to start a new parallel apply worker. */ + if (winfo == NULL) + return; + + /* Create entry for requested transaction. */ + entry = hash_search(ParallelApplyWorkersHash, &xid, HASH_ENTER, &found); + if (found) + elog(ERROR, "hash table corrupted"); + + /* + * Set the in_parallel_apply_xact flag in the leader instead of the + * parallel apply worker to avoid the race condition where the leader has + * already started waiting for the parallel apply worker to finish + * processing the transaction while the child process has not yet + * processed the first STREAM_START and has not set the + * in_parallel_apply_xact to true. + */ + parallel_apply_set_in_xact(winfo->shared, true); + + winfo->in_use = true; + entry->winfo = winfo; + entry->xid = xid; +} + +/* + * Find the assigned worker for the given transaction, if any. + */ +ParallelApplyWorkerInfo * +parallel_apply_find_worker(TransactionId xid) +{ + bool found; + ParallelApplyWorkerEntry *entry = NULL; + + if (!TransactionIdIsValid(xid)) + return NULL; + + if (ParallelApplyWorkersHash == NULL) + return NULL; + + /* Return the cached parallel apply worker if valid. */ + if (stream_apply_worker != NULL) + return stream_apply_worker; + + /* + * Find entry for requested transaction. + */ + entry = hash_search(ParallelApplyWorkersHash, &xid, HASH_FIND, &found); + if (found) + { + /* + * We can't proceed if the parallel streaming worker has already + * exited. + */ + if (entry->winfo->error_mq_handle == NULL) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("lost connection to parallel apply worker"))); + + Assert(parallel_apply_get_in_xact(entry->winfo->shared)); + Assert(entry->winfo->in_use); + + return entry->winfo; + } + + return NULL; +} + +/* + * Remove the parallel apply worker entry from the hash table. And stop the + * worker if there are enough workers in the pool. + */ +void +parallel_apply_free_worker(ParallelApplyWorkerInfo *winfo, TransactionId xid) +{ + int napplyworkers; + + Assert(!am_parallel_apply_worker()); + Assert(!parallel_apply_get_in_xact(winfo->shared)); + + if (!hash_search(ParallelApplyWorkersHash, &xid, HASH_REMOVE, NULL)) + elog(ERROR, "hash table corrupted"); + + LWLockAcquire(LogicalRepWorkerLock, LW_SHARED); + napplyworkers = logicalrep_parallel_apply_worker_count(MyLogicalRepWorker->subid); + LWLockRelease(LogicalRepWorkerLock); + + winfo->in_use = false; + + /* Are there enough workers in the pool? */ + if (napplyworkers > (max_parallel_apply_workers_per_subscription / 2)) + { + logicalrep_worker_stop_by_slot(winfo->shared->logicalrep_worker_slot_no, + winfo->shared->logicalrep_worker_generation); + + ParallelApplyWorkersList = list_delete_ptr(ParallelApplyWorkersList, winfo); + + parallel_apply_free_worker_info(winfo); + } +} + +/* Free the parallel apply worker information. */ +static void +parallel_apply_free_worker_info(ParallelApplyWorkerInfo *winfo) +{ + Assert(winfo); + + if (winfo->mq_handle != NULL) + shm_mq_detach(winfo->mq_handle); + + if (winfo->error_mq_handle != NULL) + shm_mq_detach(winfo->error_mq_handle); + + if (winfo->dsm_seg != NULL) + dsm_detach(winfo->dsm_seg); + + pfree(winfo); +} + +/* Parallel apply worker main loop. */ +static void +LogicalParallelApplyLoop(shm_mq_handle *mqh, volatile ParallelApplyWorkerShared *shared) +{ + shm_mq_result shmq_res; + PGPROC *registrant; + ErrorContextCallback errcallback; + + registrant = BackendPidGetProc(MyBgworkerEntry->bgw_notify_pid); + SetLatch(®istrant->procLatch); + + /* + * Init the ApplyMessageContext which we clean up after each replication + * protocol message. + */ + ApplyMessageContext = AllocSetContextCreate(ApplyContext, + "ApplyMessageContext", + ALLOCSET_DEFAULT_SIZES); + + /* + * Push apply error context callback. Fields will be filled while applying + * a change. + */ + errcallback.callback = apply_error_callback; + errcallback.previous = error_context_stack; + error_context_stack = &errcallback; + + for (;;) + { + void *data; + Size len; + int c; + StringInfoData s; + MemoryContext oldctx; + + CHECK_FOR_INTERRUPTS(); + + /* Ensure we are reading the data into our memory context. */ + oldctx = MemoryContextSwitchTo(ApplyMessageContext); + + shmq_res = shm_mq_receive(mqh, &len, &data, false); + + if (shmq_res != SHM_MQ_SUCCESS) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("lost connection to the leader apply worker"))); + + if (len == 0) + break; + + s.cursor = 0; + s.maxlen = -1; + s.data = (char *) data; + s.len = len; + + /* + * The first byte of message for additional communication between + * leader apply worker and parallel apply workers can only be 'w'. + */ + c = pq_getmsgbyte(&s); + if (c != 'w') + elog(ERROR, "unexpected message \"%c\"", c); + + /* + * Ignore statistics fields that have been updated by the leader apply + * worker. + */ + s.cursor += SIZE_STATS_MESSAGE; + + apply_dispatch(&s); + + MemoryContextSwitchTo(oldctx); + MemoryContextReset(ApplyMessageContext); + + if (ConfigReloadPending) + { + ConfigReloadPending = false; + ProcessConfigFile(PGC_SIGHUP); + } + } + + /* Pop the error context stack. */ + error_context_stack = errcallback.previous; + + /* Signal main process that we are done. */ + SetLatch(®istrant->procLatch); +} + +/* + * Make sure the leader apply worker tries to read from our error queue one more + * time. This guards against the case where we exit uncleanly without sending + * an ErrorResponse, for example because some code calls proc_exit directly. + */ +static void +parallel_apply_shutdown(int code, Datum arg) +{ + SendProcSignal(MyLogicalRepWorker->apply_leader_pid, + PROCSIG_PARALLEL_APPLY_MESSAGE, + InvalidBackendId); + + dsm_detach((dsm_segment *) DatumGetPointer(arg)); +} + +/* + * Parallel apply worker entry point. + */ +void +ParallelApplyWorkerMain(Datum main_arg) +{ + ParallelApplyWorkerShared *shared; + dsm_handle handle; + dsm_segment *seg; + shm_toc *toc; + shm_mq *mq; + shm_mq_handle *mqh; + shm_mq_handle *error_mqh; + int worker_slot = DatumGetInt32(main_arg); + char originname[NAMEDATALEN]; + + /* Setup signal handling. */ + pqsignal(SIGHUP, SignalHandlerForConfigReload); + pqsignal(SIGTERM, die); + BackgroundWorkerUnblockSignals(); + + /* + * Attach to the dynamic shared memory segment for the parallel apply, and + * find its table of contents. + * + * Like parallel query, we don't need resource owner by this time. See + * ParallelWorkerMain. + */ + memcpy(&handle, MyBgworkerEntry->bgw_extra, sizeof(dsm_handle)); + seg = dsm_attach(handle); + if (seg == NULL) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("unable to map dynamic shared memory segment"))); + + toc = shm_toc_attach(PG_LOGICAL_APPLY_SHM_MAGIC, dsm_segment_address(seg)); + if (toc == NULL) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("bad magic number in dynamic shared memory segment"))); + + before_shmem_exit(parallel_apply_shutdown, PointerGetDatum(seg)); + + /* Look up the shared information. */ + shared = shm_toc_lookup(toc, PARALLEL_APPLY_KEY_SHARED, false); + MyParallelShared = shared; + + /* + * Attach to the message queue. + */ + mq = shm_toc_lookup(toc, PARALLEL_APPLY_KEY_MQ, false); + shm_mq_set_receiver(mq, MyProc); + mqh = shm_mq_attach(mq, seg, NULL); + + /* + * Primary initialization is complete. Now, we can attach to our slot. + * This is to ensure that the leader apply worker does not write data to + * the uninitialized memory queue. + */ + logicalrep_worker_attach(worker_slot); + MyParallelShared->logicalrep_worker_generation = MyLogicalRepWorker->generation; + MyParallelShared->logicalrep_worker_slot_no = worker_slot; + + /* + * Attach to the error queue. + */ + mq = shm_toc_lookup(toc, PARALLEL_APPLY_KEY_ERROR_QUEUE, false); + shm_mq_set_sender(mq, MyProc); + error_mqh = shm_mq_attach(mq, seg, NULL); + + pq_redirect_to_shm_mq(seg, error_mqh); + pq_set_parallel_leader(MyLogicalRepWorker->apply_leader_pid, + InvalidBackendId); + + MyLogicalRepWorker->last_send_time = MyLogicalRepWorker->last_recv_time = + MyLogicalRepWorker->reply_time = 0; + + InitializeApplyWorker(); + + /* + * Setup callback for syscache so that we know when something changes in + * the subscription relation state. + */ + CacheRegisterSyscacheCallback(SUBSCRIPTIONRELMAP, + invalidate_syncing_table_states, + (Datum) 0); + + /* + * Allocate the origin name in long-lived context for error context + * message. + */ + snprintf(originname, sizeof(originname), "pg_%u", MySubscription->oid); + apply_error_callback_arg.origin_name = MemoryContextStrdup(ApplyContext, + originname); + + LogicalParallelApplyLoop(mqh, shared); + + proc_exit(0); +} + +/* + * Handle receipt of an interrupt indicating a parallel apply worker message. + * + * Note: this is called within a signal handler! All we can do is set a flag + * that will cause the next CHECK_FOR_INTERRUPTS() to invoke + * HandleParallelApplyMessages(). + */ +void +HandleParallelApplyMessageInterrupt(void) +{ + InterruptPending = true; + ParallelApplyMessagePending = true; + SetLatch(MyLatch); +} + +/* + * Handle a single protocol message received from a single parallel apply + * worker. + */ +static void +HandleParallelApplyMessage(ParallelApplyWorkerInfo *winfo, StringInfo msg) +{ + char msgtype; + + msgtype = pq_getmsgbyte(msg); + + switch (msgtype) + { + case 'E': /* ErrorResponse */ + { + ErrorData edata; + ErrorContextCallback *save_error_context_stack; + + /* Parse ErrorResponse. */ + pq_parse_errornotice(msg, &edata); + + /* Death of a worker isn't enough justification for suicide. */ + edata.elevel = Min(edata.elevel, ERROR); + + /* + * If desired, add a context line to show that this is a + * message propagated from a parallel apply worker. Otherwise, + * it can sometimes be confusing to understand what actually + * happened. + */ + if (edata.context) + edata.context = psprintf("%s\n%s", edata.context, + _("parallel apply worker")); + else + edata.context = pstrdup(_("parallel apply worker")); + + /* + * Context beyond that should use the error context callbacks + * that were in effect in LogicalRepApplyLoop(). + */ + save_error_context_stack = error_context_stack; + error_context_stack = apply_error_context_stack; + + ThrowErrorData(&edata); + + /* Should not reach here after rethrowing an error. */ + error_context_stack = save_error_context_stack; + + break; + } + + case 'X': /* Terminate, indicating clean exit */ + { + shm_mq_detach(winfo->error_mq_handle); + winfo->error_mq_handle = NULL; + break; + } + + /* + * Don't need to do anything about NoticeResponse and + * NotifyResponse as the logical replication worker doesn't need + * to send messages to the client. + */ + case 'N': + case 'A': + break; + default: + { + elog(ERROR, "unrecognized message type received from parallel apply worker: %c (message length %d bytes)", + msgtype, msg->len); + } + } +} + +/* + * Handle any queued protocol messages received from parallel apply workers. + */ +void +HandleParallelApplyMessages(void) +{ + ListCell *lc; + MemoryContext oldcontext; + + static MemoryContext hpm_context = NULL; + + /* + * This is invoked from ProcessInterrupts(), and since some of the + * functions it calls contain CHECK_FOR_INTERRUPTS(), there is a potential + * for recursive calls if more signals are received while this runs. It's + * unclear that recursive entry would be safe, and it doesn't seem useful + * even if it is safe, so let's block interrupts until done. + */ + HOLD_INTERRUPTS(); + + /* + * Moreover, CurrentMemoryContext might be pointing almost anywhere. We + * don't want to risk leaking data into long-lived contexts, so let's do + * our work here in a private context that we can reset on each use. + */ + if (hpm_context == NULL) /* first time through? */ + hpm_context = AllocSetContextCreate(TopMemoryContext, + "HandleParallelApplyMessages", + ALLOCSET_DEFAULT_SIZES); + else + MemoryContextReset(hpm_context); + + oldcontext = MemoryContextSwitchTo(hpm_context); + + ParallelApplyMessagePending = false; + + foreach(lc, ParallelApplyWorkersList) + { + shm_mq_result res; + Size nbytes; + void *data; + ParallelApplyWorkerInfo *winfo = (ParallelApplyWorkerInfo *) lfirst(lc); + + if (winfo->error_mq_handle == NULL) + continue; + + res = shm_mq_receive(winfo->error_mq_handle, &nbytes, + &data, true); + + if (res == SHM_MQ_WOULD_BLOCK) + break; + else if (res == SHM_MQ_SUCCESS) + { + StringInfoData msg; + + initStringInfo(&msg); + appendBinaryStringInfo(&msg, data, nbytes); + HandleParallelApplyMessage(winfo, &msg); + pfree(msg.data); + } + else + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("lost connection to the leader apply worker"))); + } + + MemoryContextSwitchTo(oldcontext); + + /* Might as well clear the context on our way out */ + MemoryContextReset(hpm_context); + + RESUME_INTERRUPTS(); +} + +/* + * Set up a dynamic shared memory segment. + * + * We set up a control region that contains a ParallelApplyWorkerShared, plus + * one region to each of message queue and error queue. + * + * Returns true on success, false on failure. + */ +static bool +parallel_apply_setup_dsm(ParallelApplyWorkerInfo *winfo) +{ + shm_toc_estimator e; + Size segsize; + dsm_segment *seg; + shm_toc *toc; + ParallelApplyWorkerShared *shared; + shm_mq *mq; + Size queue_size = DSM_QUEUE_SIZE; + Size error_queue_size = DSM_ERROR_QUEUE_SIZE; + + /* + * Estimate how much shared memory we need. + * + * Because the TOC machinery may choose to insert padding of oddly-sized + * requests, we must estimate each chunk separately. + * + * We need one key to register the location of the header, and we need two + * other keys to track of the locations of the message queue and the error + * message queue. + */ + shm_toc_initialize_estimator(&e); + shm_toc_estimate_chunk(&e, sizeof(ParallelApplyWorkerShared)); + shm_toc_estimate_chunk(&e, queue_size); + shm_toc_estimate_chunk(&e, error_queue_size); + + shm_toc_estimate_keys(&e, 3); + segsize = shm_toc_estimate(&e); + + /* Create the shared memory segment and establish a table of contents. */ + seg = dsm_create(shm_toc_estimate(&e), 0); + if (seg == NULL) + return false; + + toc = shm_toc_create(PG_LOGICAL_APPLY_SHM_MAGIC, dsm_segment_address(seg), + segsize); + + /* Set up the header region. */ + shared = shm_toc_allocate(toc, sizeof(ParallelApplyWorkerShared)); + SpinLockInit(&shared->mutex); + + shared->in_parallel_apply_xact = false; + + shm_toc_insert(toc, PARALLEL_APPLY_KEY_SHARED, shared); + + /* Set up message queue for the worker. */ + mq = shm_mq_create(shm_toc_allocate(toc, queue_size), queue_size); + shm_toc_insert(toc, PARALLEL_APPLY_KEY_MQ, mq); + shm_mq_set_sender(mq, MyProc); + + /* Attach the queue. */ + winfo->mq_handle = shm_mq_attach(mq, seg, NULL); + + /* Set up error queue for the worker. */ + mq = shm_mq_create(shm_toc_allocate(toc, error_queue_size), + error_queue_size); + shm_toc_insert(toc, PARALLEL_APPLY_KEY_ERROR_QUEUE, mq); + shm_mq_set_receiver(mq, MyProc); + + /* Attach the queue. */ + winfo->error_mq_handle = shm_mq_attach(mq, seg, NULL); + + /* Return results to caller. */ + winfo->dsm_seg = seg; + winfo->shared = shared; + + return true; +} + +/* + * Start parallel apply worker process and allocate shared memory for it. + */ +static ParallelApplyWorkerInfo * +parallel_apply_setup_worker(void) +{ + MemoryContext oldcontext; + bool launched; + ParallelApplyWorkerInfo *winfo; + + oldcontext = MemoryContextSwitchTo(ApplyContext); + + winfo = (ParallelApplyWorkerInfo *) palloc0(sizeof(ParallelApplyWorkerInfo)); + + /* Setup shared memory. */ + if (!parallel_apply_setup_dsm(winfo)) + { + MemoryContextSwitchTo(oldcontext); + pfree(winfo); + + return NULL; + } + + launched = logicalrep_worker_launch(MyLogicalRepWorker->dbid, + MySubscription->oid, + MySubscription->name, + MyLogicalRepWorker->userid, + InvalidOid, + dsm_segment_handle(winfo->dsm_seg)); + + if (launched) + { + ParallelApplyWorkersList = lappend(ParallelApplyWorkersList, winfo); + } + else + { + parallel_apply_free_worker_info(winfo); + + winfo = NULL; + } + + MemoryContextSwitchTo(oldcontext); + + return winfo; +} + +/* + * Send the data to the specified parallel apply worker via shared-memory queue. + */ +void +parallel_apply_send_data(ParallelApplyWorkerInfo *winfo, Size nbytes, + const void *data) +{ + shm_mq_result result; + + result = shm_mq_send(winfo->mq_handle, nbytes, data, false, true); + + if (result != SHM_MQ_SUCCESS) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("could not send data to shared-memory queue"))); +} + +/* + * Wait until the parallel apply worker processed the transaction finish command. + */ +void +parallel_apply_wait_for_xact_finish(ParallelApplyWorkerInfo *winfo) +{ + for (;;) + { + if (!parallel_apply_get_in_xact(winfo->shared)) + break; + + /* If any workers have died, we have failed. */ + if (winfo->error_mq_handle == NULL) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("lost connection to parallel apply worker"))); + + /* Wait to be signalled. */ + (void) WaitLatch(MyLatch, + WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH, + 1000L, + WAIT_EVENT_LOGICAL_PARALLEL_APPLY_STATE_CHANGE); + + /* Reset the latch so we don't spin. */ + ResetLatch(MyLatch); + + /* An interrupt may have occurred while we were waiting. */ + CHECK_FOR_INTERRUPTS(); + } +} + +/* + * Set the in_parallel_apply_xact flag for the given parallel apply worker. + */ +void +parallel_apply_set_in_xact(ParallelApplyWorkerShared *wshared, + bool in_xact) +{ + SpinLockAcquire(&wshared->mutex); + wshared->in_parallel_apply_xact = in_xact; + SpinLockRelease(&wshared->mutex); +} + +/* + * Get the in_parallel_apply_xact flag for the given parallel apply worker. + */ +static bool +parallel_apply_get_in_xact(ParallelApplyWorkerShared *wshared) +{ + bool in_xact; + + SpinLockAcquire(&wshared->mutex); + in_xact = wshared->in_parallel_apply_xact; + SpinLockRelease(&wshared->mutex); + + return in_xact; +} + +/* + * Define a savepoint for a subxact in parallel apply worker if needed. + * + * The parallel apply worker can figure out if a new subtransaction was + * started by checking if the new change arrived with different xid. In that + * case define a named savepoint, so that we are able to rollback to it + * separately later. + */ +void +parallel_apply_subxact_info_add(TransactionId current_xid, TransactionId top_xid) +{ + if (current_xid != top_xid && + !list_member_xid(subxactlist, current_xid)) + { + MemoryContext oldctx; + char spname[MAXPGPATH]; + + parallel_apply_savepoint_name(MySubscription->oid, current_xid, + spname, sizeof(spname)); + + elog(DEBUG1, "defining savepoint %s in parallel apply worker", spname); + + /* We must be in transaction block to define the SAVEPOINT. */ + if (!IsTransactionBlock()) + { + BeginTransactionBlock(); + CommitTransactionCommand(); + } + + DefineSavepoint(spname); + + /* + * CommitTransactionCommand is needed to start a subtransaction after + * issuing a SAVEPOINT inside a transaction block (see + * StartSubTransaction()). + */ + CommitTransactionCommand(); + + oldctx = MemoryContextSwitchTo(ApplyContext); + subxactlist = lappend_xid(subxactlist, current_xid); + MemoryContextSwitchTo(oldctx); + } +} + +/* + * Handle STREAM ABORT message when the transaction was applied in a parallel + * apply worker. + */ +void +parallel_apply_stream_abort(LogicalRepStreamAbortData *abort_data) +{ + TransactionId xid = abort_data->xid; + TransactionId subxid = abort_data->subxid; + + /* + * Update origin state so we can restart streaming from correct position + * in case of crash. + */ + replorigin_session_origin_lsn = abort_data->abort_lsn; + replorigin_session_origin_timestamp = abort_data->abort_time; + + /* + * If the two XIDs are the same, it's in fact abort of toplevel xact, so + * just free the subxactlist. + */ + if (subxid == xid) + { + parallel_apply_replorigin_setup(); + + AbortCurrentTransaction(); + + if (IsTransactionBlock()) + { + EndTransactionBlock(false); + CommitTransactionCommand(); + } + + parallel_apply_replorigin_reset(); + + in_remote_transaction = false; + pgstat_report_activity(STATE_IDLE, NULL); + + list_free(subxactlist); + subxactlist = NIL; + } + else + { + /* + * OK, so it's a subxact. Rollback to the savepoint. + * + * We also need to read the subxactlist, determine the offset tracked + * for the subxact, and truncate the list. + */ + int i; + bool found = false; + char spname[MAXPGPATH]; + + parallel_apply_savepoint_name(MySubscription->oid, subxid, spname, + sizeof(spname)); + + elog(DEBUG1, "rolling back to savepoint %s in parallel apply worker", spname); + + for (i = list_length(subxactlist) - 1; i >= 0; i--) + { + TransactionId xid_tmp = lfirst_xid(list_nth_cell(subxactlist, i)); + + if (xid_tmp == subxid) + { + found = true; + break; + } + } + + if (found) + { + RollbackToSavepoint(spname); + CommitTransactionCommand(); + subxactlist = list_truncate(subxactlist, i + 1); + } + + pgstat_report_activity(STATE_IDLEINTRANSACTION, NULL); + } + + parallel_apply_set_in_xact(MyParallelShared, false); +} + +/* + * Form the savepoint name for the streaming transaction. + * + * Return the name in the supplied buffer. + */ +void +parallel_apply_savepoint_name(Oid suboid, TransactionId xid, + char *spname, int szsp) +{ + snprintf(spname, szsp, "pg_sp_%u_%u", suboid, xid); +} + +/* Setup replication origin tracking. */ +void +parallel_apply_replorigin_setup(void) +{ + RepOriginId originid; + char originname[NAMEDATALEN]; + bool started_tx = false; + + /* This function might be called inside or outside of transaction. */ + if (!IsTransactionState()) + { + StartTransactionCommand(); + started_tx = true; + } + + snprintf(originname, sizeof(originname), "pg_%u", MySubscription->oid); + originid = replorigin_by_name(originname, false); + replorigin_session_setup(originid); + replorigin_session_origin = originid; + + if (started_tx) + CommitTransactionCommand(); +} + +/* Reset replication origin tracking. */ +void +parallel_apply_replorigin_reset(void) +{ + bool started_tx = false; + + /* This function might be called inside or outside of transaction. */ + if (!IsTransactionState()) + { + StartTransactionCommand(); + started_tx = true; + } + + replorigin_session_reset(); + + replorigin_session_origin = InvalidRepOriginId; + replorigin_session_origin_lsn = InvalidXLogRecPtr; + replorigin_session_origin_timestamp = 0; + + if (started_tx) + CommitTransactionCommand(); +} diff --git a/src/backend/replication/logical/decode.c b/src/backend/replication/logical/decode.c index 4d0bf1930d..27057ec377 100644 --- a/src/backend/replication/logical/decode.c +++ b/src/backend/replication/logical/decode.c @@ -652,9 +652,10 @@ DecodeCommit(LogicalDecodingContext *ctx, XLogRecordBuffer *buf, { for (i = 0; i < parsed->nsubxacts; i++) { - ReorderBufferForget(ctx->reorder, parsed->subxacts[i], buf->origptr); + ReorderBufferForget(ctx->reorder, parsed->subxacts[i], buf->origptr, + commit_time); } - ReorderBufferForget(ctx->reorder, xid, buf->origptr); + ReorderBufferForget(ctx->reorder, xid, buf->origptr, commit_time); return; } @@ -822,10 +823,11 @@ DecodeAbort(LogicalDecodingContext *ctx, XLogRecordBuffer *buf, for (i = 0; i < parsed->nsubxacts; i++) { ReorderBufferAbort(ctx->reorder, parsed->subxacts[i], - buf->record->EndRecPtr); + buf->record->EndRecPtr, abort_time); } - ReorderBufferAbort(ctx->reorder, xid, buf->record->EndRecPtr); + ReorderBufferAbort(ctx->reorder, xid, buf->record->EndRecPtr, + abort_time); } /* update the decoding stats */ diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 3bbd522724..7657729eef 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -54,6 +54,7 @@ int max_logical_replication_workers = 4; int max_sync_workers_per_subscription = 2; +int max_parallel_apply_workers_per_subscription = 2; LogicalRepWorker *MyLogicalRepWorker = NULL; @@ -73,6 +74,7 @@ static void logicalrep_launcher_onexit(int code, Datum arg); static void logicalrep_worker_onexit(int code, Datum arg); static void logicalrep_worker_detach(void); static void logicalrep_worker_cleanup(LogicalRepWorker *worker); +static void logicalrep_worker_stop_internal(LogicalRepWorker *worker); static bool on_commit_launcher_wakeup = false; @@ -151,8 +153,10 @@ get_subscription_list(void) * * This is only needed for cleaning up the shared memory in case the worker * fails to attach. + * + * Return whether the attach was successful. */ -static void +static bool WaitForReplicationWorkerAttach(LogicalRepWorker *worker, uint16 generation, BackgroundWorkerHandle *handle) @@ -168,11 +172,11 @@ WaitForReplicationWorkerAttach(LogicalRepWorker *worker, LWLockAcquire(LogicalRepWorkerLock, LW_SHARED); - /* Worker either died or has started; no need to do anything. */ + /* Worker either died or has started. Return false if died. */ if (!worker->in_use || worker->proc) { LWLockRelease(LogicalRepWorkerLock); - return; + return worker->in_use; } LWLockRelease(LogicalRepWorkerLock); @@ -187,7 +191,7 @@ WaitForReplicationWorkerAttach(LogicalRepWorker *worker, if (generation == worker->generation) logicalrep_worker_cleanup(worker); LWLockRelease(LogicalRepWorkerLock); - return; + return false; } /* @@ -209,6 +213,8 @@ WaitForReplicationWorkerAttach(LogicalRepWorker *worker, /* * Walks the workers array and searches for one that matches given * subscription id and relid. + * + * We are only interested in the leader apply worker or table sync worker. */ LogicalRepWorker * logicalrep_worker_find(Oid subid, Oid relid, bool only_running) @@ -223,6 +229,10 @@ logicalrep_worker_find(Oid subid, Oid relid, bool only_running) { LogicalRepWorker *w = &LogicalRepCtx->workers[i]; + /* Skip parallel apply workers. */ + if (isParallelApplyWorker(w)) + continue; + if (w->in_use && w->subid == subid && w->relid == relid && (!only_running || w->proc)) { @@ -259,11 +269,13 @@ logicalrep_workers_find(Oid subid, bool only_running) } /* - * Start new apply background worker, if possible. + * Start new background worker, if possible. + * + * Returns true on success, false on failure. */ -void +bool logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, Oid userid, - Oid relid) + Oid relid, dsm_handle subworker_dsm) { BackgroundWorker bgw; BackgroundWorkerHandle *bgw_handle; @@ -272,7 +284,12 @@ logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, Oid userid, int slot = 0; LogicalRepWorker *worker = NULL; int nsyncworkers; + int nparallelapplyworkers; TimestampTz now; + bool is_subworker = (subworker_dsm != DSM_HANDLE_INVALID); + + /* Sanity check: we don't support table sync in subworker. */ + Assert(!(is_subworker && OidIsValid(relid))); ereport(DEBUG1, (errmsg_internal("starting logical replication worker for subscription \"%s\"", @@ -350,7 +367,19 @@ retry: if (OidIsValid(relid) && nsyncworkers >= max_sync_workers_per_subscription) { LWLockRelease(LogicalRepWorkerLock); - return; + return false; + } + + nparallelapplyworkers = logicalrep_parallel_apply_worker_count(subid); + + /* + * Return silently if the number of parallel apply workers reached the + * limit per subscription. + */ + if (is_subworker && nparallelapplyworkers >= max_parallel_apply_workers_per_subscription) + { + LWLockRelease(LogicalRepWorkerLock); + return false; } /* @@ -364,7 +393,7 @@ retry: (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of logical replication worker slots"), errhint("You might need to increase max_logical_replication_workers."))); - return; + return false; } /* Prepare the worker slot. */ @@ -379,6 +408,7 @@ retry: worker->relstate = SUBREL_STATE_UNKNOWN; worker->relstate_lsn = InvalidXLogRecPtr; worker->stream_fileset = NULL; + worker->apply_leader_pid = is_subworker ? MyProcPid : InvalidPid; worker->last_lsn = InvalidXLogRecPtr; TIMESTAMP_NOBEGIN(worker->last_send_time); TIMESTAMP_NOBEGIN(worker->last_recv_time); @@ -396,10 +426,18 @@ retry: BGWORKER_BACKEND_DATABASE_CONNECTION; bgw.bgw_start_time = BgWorkerStart_RecoveryFinished; snprintf(bgw.bgw_library_name, BGW_MAXLEN, "postgres"); - snprintf(bgw.bgw_function_name, BGW_MAXLEN, "ApplyWorkerMain"); + + if (is_subworker) + snprintf(bgw.bgw_function_name, BGW_MAXLEN, "ParallelApplyWorkerMain"); + else + snprintf(bgw.bgw_function_name, BGW_MAXLEN, "ApplyWorkerMain"); + if (OidIsValid(relid)) snprintf(bgw.bgw_name, BGW_MAXLEN, "logical replication worker for subscription %u sync %u", subid, relid); + else if (is_subworker) + snprintf(bgw.bgw_name, BGW_MAXLEN, + "logical replication parallel apply worker for subscription %u", subid); else snprintf(bgw.bgw_name, BGW_MAXLEN, "logical replication worker for subscription %u", subid); @@ -409,6 +447,9 @@ retry: bgw.bgw_notify_pid = MyProcPid; bgw.bgw_main_arg = Int32GetDatum(slot); + if (is_subworker) + memcpy(bgw.bgw_extra, &subworker_dsm, sizeof(dsm_handle)); + if (!RegisterDynamicBackgroundWorker(&bgw, &bgw_handle)) { /* Failed to start worker, so clean up the worker slot. */ @@ -421,11 +462,11 @@ retry: (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase max_worker_processes."))); - return; + return false; } /* Now wait until it attaches. */ - WaitForReplicationWorkerAttach(worker, generation, bgw_handle); + return WaitForReplicationWorkerAttach(worker, generation, bgw_handle); } /* @@ -436,19 +477,53 @@ void logicalrep_worker_stop(Oid subid, Oid relid) { LogicalRepWorker *worker; - uint16 generation; LWLockAcquire(LogicalRepWorkerLock, LW_SHARED); worker = logicalrep_worker_find(subid, relid, false); - /* No worker, nothing to do. */ - if (!worker) + if (worker) { - LWLockRelease(LogicalRepWorkerLock); - return; + Assert(!isParallelApplyWorker(worker)); + logicalrep_worker_stop_internal(worker); } + LWLockRelease(LogicalRepWorkerLock); +} + +/* + * Stop the logical replication worker corresponding to the input slot number, + * and wait until it detaches from the slot. + */ +void +logicalrep_worker_stop_by_slot(int slot_no, uint16 generation) +{ + LogicalRepWorker *worker; + + LWLockAcquire(LogicalRepWorkerLock, LW_SHARED); + + worker = &LogicalRepCtx->workers[slot_no]; + + /* + * Only stop the worker if the generation matches and the worker is alive. + */ + if (worker->generation == generation && worker->proc) + logicalrep_worker_stop_internal(worker); + + LWLockRelease(LogicalRepWorkerLock); +} + +/* + * Workhorse for logicalrep_worker_stop(), logicalrep_worker_detach() and + * logicalrep_worker_stop_by_slot(). Stop the worker and wait for it to die. + */ +static void +logicalrep_worker_stop_internal(LogicalRepWorker *worker) +{ + uint16 generation; + + Assert(LWLockHeldByMe(LogicalRepWorkerLock)); + /* * Remember which generation was our worker so we can check if what we see * is still the same one. @@ -485,10 +560,7 @@ logicalrep_worker_stop(Oid subid, Oid relid) * different, meaning that a different worker has taken the slot. */ if (!worker->in_use || worker->generation != generation) - { - LWLockRelease(LogicalRepWorkerLock); return; - } /* Worker has assigned proc, so it has started. */ if (worker->proc) @@ -522,8 +594,6 @@ logicalrep_worker_stop(Oid subid, Oid relid) LWLockAcquire(LogicalRepWorkerLock, LW_SHARED); } - - LWLockRelease(LogicalRepWorkerLock); } /* @@ -594,11 +664,32 @@ logicalrep_worker_attach(int slot) } /* - * Detach the worker (cleans up the worker info). + * Stop the parallel apply workers if any, and detach the leader apply worker + * (cleans up the worker info). */ static void logicalrep_worker_detach(void) { + /* Stop the parallel apply workers. */ + if (!am_parallel_apply_worker() && !am_tablesync_worker()) + { + List *workers; + ListCell *lc; + + LWLockAcquire(LogicalRepWorkerLock, LW_SHARED); + + workers = logicalrep_workers_find(MyLogicalRepWorker->subid, true); + foreach(lc, workers) + { + LogicalRepWorker *w = (LogicalRepWorker *) lfirst(lc); + + if (isParallelApplyWorker(w)) + logicalrep_worker_stop_internal(w); + } + + LWLockRelease(LogicalRepWorkerLock); + } + /* Block concurrent access. */ LWLockAcquire(LogicalRepWorkerLock, LW_EXCLUSIVE); @@ -621,6 +712,7 @@ logicalrep_worker_cleanup(LogicalRepWorker *worker) worker->userid = InvalidOid; worker->subid = InvalidOid; worker->relid = InvalidOid; + worker->apply_leader_pid = InvalidPid; } /* @@ -679,6 +771,33 @@ logicalrep_sync_worker_count(Oid subid) return res; } +/* + * Count the number of registered (but not necessarily running) parallel apply + * workers for a subscription. + */ +int +logicalrep_parallel_apply_worker_count(Oid subid) +{ + int i; + int res = 0; + + Assert(LWLockHeldByMe(LogicalRepWorkerLock)); + + /* + * Scan all attached parallel apply workers, only counting those which + * have the given subscription id. + */ + for (i = 0; i < max_logical_replication_workers; i++) + { + LogicalRepWorker *w = &LogicalRepCtx->workers[i]; + + if (w->subid == subid && isParallelApplyWorker(w)) + res++; + } + + return res; +} + /* * ApplyLauncherShmemSize * Compute space needed for replication launcher shared memory @@ -868,7 +987,7 @@ ApplyLauncherMain(Datum main_arg) wait_time = wal_retrieve_retry_interval; logicalrep_worker_launch(sub->dbid, sub->oid, sub->name, - sub->owner, InvalidOid); + sub->owner, InvalidOid, DSM_HANDLE_INVALID); } } diff --git a/src/backend/replication/logical/proto.c b/src/backend/replication/logical/proto.c index ff8513e2d2..2da9ab7b29 100644 --- a/src/backend/replication/logical/proto.c +++ b/src/backend/replication/logical/proto.c @@ -1163,10 +1163,14 @@ logicalrep_read_stream_commit(StringInfo in, LogicalRepCommitData *commit_data) /* * Write STREAM ABORT to the output stream. Note that xid and subxid will be * same for the top-level transaction abort. + * + * If abort_info is true, send the abort_lsn and abort_time fields, otherwise + * don't. */ void logicalrep_write_stream_abort(StringInfo out, TransactionId xid, - TransactionId subxid) + TransactionId subxid, XLogRecPtr abort_lsn, + TimestampTz abort_time, bool abort_info) { pq_sendbyte(out, LOGICAL_REP_MSG_STREAM_ABORT); @@ -1175,19 +1179,40 @@ logicalrep_write_stream_abort(StringInfo out, TransactionId xid, /* transaction ID */ pq_sendint32(out, xid); pq_sendint32(out, subxid); + + if (abort_info) + { + pq_sendint64(out, abort_lsn); + pq_sendint64(out, abort_time); + } } /* * Read STREAM ABORT from the output stream. + * + * If read_abort_lsn is true, try to read the abort_lsn and abort_time fields, + * otherwise don't. */ void -logicalrep_read_stream_abort(StringInfo in, TransactionId *xid, - TransactionId *subxid) +logicalrep_read_stream_abort(StringInfo in, + LogicalRepStreamAbortData *abort_data, + bool read_abort_lsn) { - Assert(xid && subxid); + Assert(abort_data); + + abort_data->xid = pq_getmsgint(in, 4); + abort_data->subxid = pq_getmsgint(in, 4); - *xid = pq_getmsgint(in, 4); - *subxid = pq_getmsgint(in, 4); + if (read_abort_lsn) + { + abort_data->abort_lsn = pq_getmsgint64(in); + abort_data->abort_time = pq_getmsgint64(in); + } + else + { + abort_data->abort_lsn = InvalidXLogRecPtr; + abort_data->abort_time = 0; + } } /* diff --git a/src/backend/replication/logical/reorderbuffer.c b/src/backend/replication/logical/reorderbuffer.c index 03d9c9c86a..94bfc6762e 100644 --- a/src/backend/replication/logical/reorderbuffer.c +++ b/src/backend/replication/logical/reorderbuffer.c @@ -2839,7 +2839,8 @@ ReorderBufferFinishPrepared(ReorderBuffer *rb, TransactionId xid, * disk. */ void -ReorderBufferAbort(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn) +ReorderBufferAbort(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn, + TimestampTz abort_time) { ReorderBufferTXN *txn; @@ -2850,6 +2851,8 @@ ReorderBufferAbort(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn) if (txn == NULL) return; + txn->xact_time.abort_time = abort_time; + /* For streamed transactions notify the remote node about the abort. */ if (rbtxn_is_streamed(txn)) { @@ -2924,7 +2927,8 @@ ReorderBufferAbortOld(ReorderBuffer *rb, TransactionId oldestRunningXid) * to this xid might re-create the transaction incompletely. */ void -ReorderBufferForget(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn) +ReorderBufferForget(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn, + TimestampTz abort_time) { ReorderBufferTXN *txn; @@ -2935,6 +2939,8 @@ ReorderBufferForget(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn) if (txn == NULL) return; + txn->xact_time.abort_time = abort_time; + /* For streamed transactions notify the remote node about the abort. */ if (rbtxn_is_streamed(txn)) rb->stream_abort(rb, txn, lsn); diff --git a/src/backend/replication/logical/tablesync.c b/src/backend/replication/logical/tablesync.c index 831d42016c..47ae9a80dd 100644 --- a/src/backend/replication/logical/tablesync.c +++ b/src/backend/replication/logical/tablesync.c @@ -609,7 +609,8 @@ process_syncing_tables_for_apply(XLogRecPtr current_lsn) MySubscription->oid, MySubscription->name, MyLogicalRepWorker->userid, - rstate->relid); + rstate->relid, + DSM_HANDLE_INVALID); hentry->last_start_time = now; } } @@ -630,6 +631,9 @@ process_syncing_tables_for_apply(XLogRecPtr current_lsn) void process_syncing_tables(XLogRecPtr current_lsn) { + if (am_parallel_apply_worker()) + return; + if (am_tablesync_worker()) process_syncing_tables_for_sync(current_lsn); else diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index 56f753d987..900d061a12 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -22,8 +22,54 @@ * STREAMED TRANSACTIONS * --------------------- * Streamed transactions (large transactions exceeding a memory limit on the - * upstream) are not applied immediately, but instead, the data is written - * to temporary files and then applied at once when the final commit arrives. + * upstream) are applied using one of two approaches: + * + * 1) Parallel apply workers + * + * If streaming = parallel, we assign a new parallel apply worker (if + * available) as soon as the xact's first stream is received. The leader apply + * worker will send changes to this new worker via shared memory. We keep this + * worker assigned till the transaction commit is received and also wait for + * the worker to finish at commit. This preserves commit ordering and avoids + * file I/O in most cases. We still need to spill to a file if there is no + * worker available. It is important to maintain commit order to avoid failures + * due to (a) transaction dependencies, say if we insert a row in the first + * transaction and update it in the second transaction then allowing to apply + * both in parallel can lead to failure in the update. (b) deadlocks, allowing + * transactions that update the same set of rows/tables in opposite order to be + * applied in parallel can lead to deadlocks. + * + * We maintain a worker pool to avoid restarting workers for each streaming + * transaction. We maintain each worker's information in the + * ParallelApplyWorkersList. After successfully launching a new worker, its + * information is added to the ParallelApplyWorkersList. Once the worker + * finishes applying the transaction, we mark it available for use. Now, + * before starting a new worker to apply the streaming transaction, we check + * the list and use any worker, if available. Note that we maintain a maximum + * of half the max_parallel_apply_workers_per_subscription workers in the pool + * and after that, we simply exit the worker after applying the transaction. + * This worker pool threshold is a bit arbitrary and we can provide a guc for + * this in the future if required. + * + * The leader apply worker will create separate dynamic shared memory segment + * when each parallel apply worker starts. The reason for this design is that + * we cannot count how many workers will be started. It may be possible to + * allocate enough shared memory in one segment based on the maximum number of + * parallel apply workers (max_parallel_apply_workers_per_subscription), but this + * may waste some memory if no process is actually started. + * + * The dynamic shared memory segment will contain (a) a shm_mq that can be + * used to send changes in the transaction from leader apply worker to parallel + * apply worker (b) another shm_mq that can be used to send errors (and other + * messages reported via elog/ereport) from the parallel apply worker to leader + * apply worker (c) necessary information to be shared among parallel apply + * workers and leader apply worker (i.e. in_parallel_apply_xact flag and the + * corresponding LogicalRepWorker slot information). + * + * In case, no worker is available to handle the streamed transaction, we + * follow approach 2. + * + * 2) Write to temporary files and apply when the final commit arrives * * Unlike the regular (non-streamed) case, handling streamed transactions has * to handle aborts of both the toplevel transaction and subtransactions. This @@ -219,20 +265,35 @@ typedef struct ApplyExecutionData PartitionTupleRouting *proute; /* partition routing info */ } ApplyExecutionData; -/* Struct for saving and restoring apply errcontext information */ -typedef struct ApplyErrorCallbackArg +/* + * What action to take for the transaction. + * + * TRANS_LEADER_APPLY means that we are in the leader apply worker and changes + * of the transaction are applied directly in the worker. + * + * TRANS_LEADER_SERIALIZE means that we are in leader apply worker and changes + * are written to temporary files and then applied when the final commit + * arrives. + * + * TRANS_LEADER_SEND_TO_PARALLEL means that we are in the leader apply worker + * and need to send the changes to the parallel apply worker. + * + * TRANS_PARALLEL_APPLY means that we are in the parallel apply worker and + * changes of the transaction are applied directly in the worker. + */ +typedef enum { - LogicalRepMsgType command; /* 0 if invalid */ - LogicalRepRelMapEntry *rel; + /* The action for non-streaming transactions. */ + TRANS_LEADER_APPLY, - /* Remote node information */ - int remote_attnum; /* -1 if invalid */ - TransactionId remote_xid; - XLogRecPtr finish_lsn; - char *origin_name; -} ApplyErrorCallbackArg; + /* Actions for streaming transactions. */ + TRANS_LEADER_SERIALIZE, + TRANS_LEADER_SEND_TO_PARALLEL, + TRANS_PARALLEL_APPLY +} TransApplyAction; -static ApplyErrorCallbackArg apply_error_callback_arg = +/* errcontext tracker */ +ApplyErrorCallbackArg apply_error_callback_arg = { .command = 0, .rel = NULL, @@ -242,7 +303,9 @@ static ApplyErrorCallbackArg apply_error_callback_arg = .origin_name = NULL, }; -static MemoryContext ApplyMessageContext = NULL; +ErrorContextCallback *apply_error_context_stack = NULL; + +MemoryContext ApplyMessageContext = NULL; MemoryContext ApplyContext = NULL; /* per stream context for streaming transactions */ @@ -251,7 +314,7 @@ static MemoryContext LogicalStreamingContext = NULL; WalReceiverConn *LogRepWorkerWalRcvConn = NULL; Subscription *MySubscription = NULL; -static bool MySubscriptionValid = false; +bool MySubscriptionValid = false; bool in_remote_transaction = false; static XLogRecPtr remote_final_lsn = InvalidXLogRecPtr; @@ -261,17 +324,25 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; +/* + * The number of changes sent to parallel apply workers during one streaming + * block. + */ +static uint32 nchanges = 0; + /* * We enable skipping all data modification changes (INSERT, UPDATE, etc.) for * the subscription if the remote transaction's finish LSN matches the subskiplsn. * Once we start skipping changes, we don't stop it until we skip all changes of * the transaction even if pg_subscription is updated and MySubscription->skiplsn - * gets changed or reset during that. Also, in streaming transaction cases, we - * don't skip receiving and spooling the changes since we decide whether or not + * gets changed or reset during that. Also, in streaming transaction cases (streaming = on), + * we don't skip receiving and spooling the changes since we decide whether or not * to skip applying the changes when starting to apply changes. The subskiplsn is * cleared after successfully skipping the transaction or applying non-empty * transaction. The latter prevents the mistakenly specified subskiplsn from - * being left. + * being left. Note that we cannot skip the streaming transactions when using + * parallel apply workers because we cannot get the finish LSN before + * applying the changes. */ static XLogRecPtr skip_xact_finish_lsn = InvalidXLogRecPtr; #define is_skipping_changes() (unlikely(!XLogRecPtrIsInvalid(skip_xact_finish_lsn))) @@ -325,9 +396,6 @@ static void maybe_reread_subscription(void); static void DisableSubscriptionAndExit(void); -/* prototype needed because of stream_commit */ -static void apply_dispatch(StringInfo s); - static void apply_handle_commit_internal(LogicalRepCommitData *commit_data); static void apply_handle_insert_internal(ApplyExecutionData *edata, ResultRelInfo *relinfo, @@ -360,10 +428,12 @@ static void stop_skipping_changes(void); static void clear_subscription_skip_lsn(XLogRecPtr finish_lsn); /* Functions for apply error callback */ -static void apply_error_callback(void *arg); static inline void set_apply_error_context_xact(TransactionId xid, XLogRecPtr lsn); static inline void reset_apply_error_context_info(void); +static TransApplyAction get_transaction_apply_action(TransactionId xid, + ParallelApplyWorkerInfo **winfo); + /* * Should this worker apply changes for given relation. * @@ -376,12 +446,34 @@ static inline void reset_apply_error_context_info(void); * record + 1 (ie start of next record) and next record can be COMMIT of * transaction we are now processing (which is what we set remote_final_lsn * to in apply_handle_begin). + * + * Note that for streaming transactions that are being applied in the parallel + * apply worker, we disallow applying changes on a table that is not in + * the READY state, because we cannot decide whether to apply the change as we + * won't know remote_final_lsn by that time. + * + * We already checked this in parallel_apply_can_start() before assigning the + * streaming transaction to the parallel worker, but it also needs to be + * checked here because if the user executes ALTER SUBSCRIPTION ... REFRESH + * PUBLICATION in parallel, the new table can be added to pg_subscription_rel + * while applying this transaction. */ static bool should_apply_changes_for_rel(LogicalRepRelMapEntry *rel) { if (am_tablesync_worker()) return MyLogicalRepWorker->relid == rel->localreloid; + else if (am_parallel_apply_worker()) + { + if (rel->state != SUBREL_STATE_READY) + ereport(ERROR, + (errmsg("logical replication apply workers for subscription \"%s\" will restart", + MySubscription->name), + errdetail("Cannot handle streamed replication transaction using parallel " + "apply workers until all tables are synchronized."))); + + return true; + } else return (rel->state == SUBREL_STATE_READY || (rel->state == SUBREL_STATE_SYNCDONE && @@ -427,43 +519,87 @@ end_replication_step(void) } /* - * Handle streamed transactions. + * Handle streamed transactions for both the leader apply worker and the parallel + * apply workers. + * + * In streaming case (receiving a block of streamed transaction), for + * SUBSTREAM_ON mode, simply redirect it to a file for the proper toplevel + * transaction, and for SUBSTREAM_PARALLEL mode, send the changes to parallel + * apply workers (LOGICAL_REP_MSG_RELATION or LOGICAL_REP_MSG_TYPE changes + * will be applied by both leader apply worker and parallel apply workers). * - * If in streaming mode (receiving a block of streamed transaction), we - * simply redirect it to a file for the proper toplevel transaction. + * For non-streamed transactions, returns false; + * For streamed transactions, returns true if in leader apply worker, false + * otherwise. * - * Returns true for streamed transactions, false otherwise (regular mode). + * Exception: If the message being processed is LOGICAL_REP_MSG_RELATION + * or LOGICAL_REP_MSG_TYPE, return false even if the message needs to be sent + * to a parallel apply worker. */ static bool handle_streamed_transaction(LogicalRepMsgType action, StringInfo s) { - TransactionId xid; + TransactionId current_xid = InvalidTransactionId; + ParallelApplyWorkerInfo *winfo = NULL; + TransApplyAction apply_action; + + apply_action = get_transaction_apply_action(stream_xid, &winfo); /* not in streaming mode */ - if (!in_streamed_transaction) + if (apply_action == TRANS_LEADER_APPLY) return false; - Assert(stream_fd != NULL); Assert(TransactionIdIsValid(stream_xid)); /* * We should have received XID of the subxact as the first part of the * message, so extract it. */ - xid = pq_getmsgint(s, 4); + current_xid = pq_getmsgint(s, 4); - if (!TransactionIdIsValid(xid)) + if (!TransactionIdIsValid(current_xid)) ereport(ERROR, (errcode(ERRCODE_PROTOCOL_VIOLATION), errmsg_internal("invalid transaction ID in streamed replication transaction"))); - /* Add the new subxact to the array (unless already there). */ - subxact_info_add(xid); + switch (apply_action) + { + case TRANS_LEADER_SERIALIZE: + Assert(stream_fd != NULL); + + /* Add the new subxact to the array (unless already there). */ + subxact_info_add(current_xid); - /* write the change to the current file */ - stream_write_change(action, s); + /* write the change to the current file */ + stream_write_change(action, s); + return true; - return true; + case TRANS_LEADER_SEND_TO_PARALLEL: + Assert(winfo); + + parallel_apply_send_data(winfo, s->len, s->data); + nchanges += 1; + + /* + * XXX The publisher side doesn't always send relation/type update + * messages after the streaming transaction, so also update the + * relation/type in leader apply worker here. See function + * cleanup_rel_sync_cache. + */ + if (action == LOGICAL_REP_MSG_RELATION || + action == LOGICAL_REP_MSG_TYPE) + return false; + return true; + + case TRANS_PARALLEL_APPLY: + /* Define a savepoint for a subxact if needed. */ + parallel_apply_subxact_info_add(current_xid, stream_xid); + return false; + + default: + Assert(false); + return false; /* silence compiler warning */ + } } /* @@ -899,8 +1035,11 @@ apply_handle_prepare_internal(LogicalRepPreparedTxnData *prepare_data) * BeginTransactionBlock is necessary to balance the EndTransactionBlock * called within the PrepareTransactionBlock below. */ - BeginTransactionBlock(); - CommitTransactionCommand(); /* Completes the preceding Begin command. */ + if (!IsTransactionBlock()) + { + BeginTransactionBlock(); + CommitTransactionCommand(); /* Completes the preceding Begin command. */ + } /* * Update origin state so we can restart streaming from correct position @@ -969,6 +1108,12 @@ apply_handle_prepare(StringInfo s) /* * Handle a COMMIT PREPARED of a previously PREPARED transaction. + * + * Note that we don't need to wait here if the transaction was prepared in a + * parallel apply worker. Because we have already waited for the prepare to + * finish in apply_handle_stream_prepare() which will ensure all the operations + * in that transaction have happened in the subscriber and no concurrent + * transaction can create deadlock or transaction dependency issues. */ static void apply_handle_commit_prepared(StringInfo s) @@ -1012,6 +1157,12 @@ apply_handle_commit_prepared(StringInfo s) /* * Handle a ROLLBACK PREPARED of a previously PREPARED TRANSACTION. + * + * Note that we don't need to wait here if the transaction was prepared in a + * parallel apply worker. Because we have already waited for the prepare to + * finish in apply_handle_stream_prepare() which will ensure all the operations + * in that transaction have happened in the subscriber and no concurrent + * transaction can create deadlock or transaction dependency issues. */ static void apply_handle_rollback_prepared(StringInfo s) @@ -1065,17 +1216,15 @@ apply_handle_rollback_prepared(StringInfo s) /* * Handle STREAM PREPARE. - * - * Logic is in two parts: - * 1. Replay all the spooled operations - * 2. Mark the transaction as prepared */ static void apply_handle_stream_prepare(StringInfo s) { LogicalRepPreparedTxnData prepare_data; + ParallelApplyWorkerInfo *winfo = NULL; + TransApplyAction apply_action; - if (in_streamed_transaction) + if (in_streamed_transaction || stream_apply_worker) ereport(ERROR, (errcode(ERRCODE_PROTOCOL_VIOLATION), errmsg_internal("STREAM PREPARE message without STREAM STOP"))); @@ -1089,24 +1238,76 @@ apply_handle_stream_prepare(StringInfo s) logicalrep_read_stream_prepare(s, &prepare_data); set_apply_error_context_xact(prepare_data.xid, prepare_data.prepare_lsn); - elog(DEBUG1, "received prepare for streamed transaction %u", prepare_data.xid); + apply_action = get_transaction_apply_action(prepare_data.xid, &winfo); - /* Replay all the spooled operations. */ - apply_spooled_messages(prepare_data.xid, prepare_data.prepare_lsn); + switch (apply_action) + { + case TRANS_LEADER_SERIALIZE: - /* Mark the transaction as prepared. */ - apply_handle_prepare_internal(&prepare_data); + /* + * The transaction has been serialized to file, so replay all the + * spooled operations. + */ + apply_spooled_messages(prepare_data.xid, prepare_data.prepare_lsn); - CommitTransactionCommand(); + /* Mark the transaction as prepared. */ + apply_handle_prepare_internal(&prepare_data); - pgstat_report_stat(false); + CommitTransactionCommand(); - store_flush_position(prepare_data.end_lsn); + store_flush_position(prepare_data.end_lsn); - in_remote_transaction = false; + /* Unlink the files with serialized changes and subxact info. */ + stream_cleanup_files(MyLogicalRepWorker->subid, prepare_data.xid); + break; + + case TRANS_LEADER_SEND_TO_PARALLEL: + Assert(winfo); + + parallel_apply_replorigin_reset(); - /* unlink the files with serialized changes and subxact info. */ - stream_cleanup_files(MyLogicalRepWorker->subid, prepare_data.xid); + /* Send STREAM PREPARE message to the parallel apply worker. */ + parallel_apply_send_data(winfo, s->len, s->data); + + /* + * After sending the data to the parallel apply worker, wait for + * that worker to finish. This is necessary to maintain commit + * order which avoids failures due to transaction dependencies and + * deadlocks. + */ + parallel_apply_wait_for_xact_finish(winfo); + parallel_apply_replorigin_setup(); + parallel_apply_free_worker(winfo, prepare_data.xid); + + store_flush_position(prepare_data.end_lsn); + break; + + case TRANS_PARALLEL_APPLY: + parallel_apply_replorigin_setup(); + + /* Mark the transaction as prepared. */ + apply_handle_prepare_internal(&prepare_data); + + CommitTransactionCommand(); + + parallel_apply_replorigin_reset(); + + list_free(subxactlist); + subxactlist = NIL; + + parallel_apply_set_in_xact(MyParallelShared, false); + + elog(DEBUG1, "finished processing the transaction finish command"); + break; + + default: + Assert(false); + break; + } + + pgstat_report_stat(false); + + in_remote_transaction = false; /* Process any tables that are being synchronized in parallel. */ process_syncing_tables(prepare_data.end_lsn); @@ -1135,7 +1336,7 @@ apply_handle_origin(StringInfo s) * ORIGIN message can only come inside streaming transaction or inside * remote transaction and before any actual writes. */ - if (!in_streamed_transaction && + if (!in_streamed_transaction && stream_apply_worker == NULL && (!in_remote_transaction || (IsTransactionState() && !am_tablesync_worker()))) ereport(ERROR, @@ -1150,24 +1351,14 @@ static void apply_handle_stream_start(StringInfo s) { bool first_segment; + ParallelApplyWorkerInfo *winfo = NULL; + TransApplyAction apply_action; - if (in_streamed_transaction) + if (in_streamed_transaction || stream_apply_worker) ereport(ERROR, (errcode(ERRCODE_PROTOCOL_VIOLATION), errmsg_internal("duplicate STREAM START message"))); - /* - * Start a transaction on stream start, this transaction will be committed - * on the stream stop unless it is a tablesync worker in which case it - * will be committed after processing all the messages. We need the - * transaction for handling the buffile, used for serializing the - * streaming data and subxact info. - */ - begin_replication_step(); - - /* notify handle methods we're processing a remote transaction */ - in_streamed_transaction = true; - /* extract XID of the top-level transaction */ stream_xid = logicalrep_read_stream_start(s, &first_segment); @@ -1179,35 +1370,90 @@ apply_handle_stream_start(StringInfo s) set_apply_error_context_xact(stream_xid, InvalidXLogRecPtr); /* - * Initialize the worker's stream_fileset if we haven't yet. This will be - * used for the entire duration of the worker so create it in a permanent - * context. We create this on the very first streaming message from any - * transaction and then use it for this and other streaming transactions. - * Now, we could create a fileset at the start of the worker as well but - * then we won't be sure that it will ever be used. + * For the first stream start, check if there is any free parallel apply + * worker we can use to process this transaction. */ - if (MyLogicalRepWorker->stream_fileset == NULL) + if (first_segment) + parallel_apply_start_worker(stream_xid); + + apply_action = get_transaction_apply_action(stream_xid, &winfo); + + switch (apply_action) { - MemoryContext oldctx; + case TRANS_LEADER_SERIALIZE: - oldctx = MemoryContextSwitchTo(ApplyContext); + /* + * Notify handle methods we're processing a remote in-progress + * transaction. + */ + in_streamed_transaction = true; - MyLogicalRepWorker->stream_fileset = palloc(sizeof(FileSet)); - FileSetInit(MyLogicalRepWorker->stream_fileset); + /* + * Start a transaction on stream start, this transaction will be + * committed on the stream stop unless it is a tablesync worker in + * which case it will be committed after processing all the + * messages. We need the transaction for handling the buffile, + * used for serializing the streaming data and subxact info. + */ + begin_replication_step(); - MemoryContextSwitchTo(oldctx); - } + /* + * Initialize the worker's stream_fileset if we haven't yet. This + * will be used for the entire duration of the worker so create it + * in a permanent context. We create this on the very first + * streaming message from any transaction and then use it for this + * and other streaming transactions. Now, we could create a + * fileset at the start of the worker as well but then we won't be + * sure that it will ever be used. + */ + if (MyLogicalRepWorker->stream_fileset == NULL) + { + MemoryContext oldctx; - /* open the spool file for this transaction */ - stream_open_file(MyLogicalRepWorker->subid, stream_xid, first_segment); + oldctx = MemoryContextSwitchTo(ApplyContext); - /* if this is not the first segment, open existing subxact file */ - if (!first_segment) - subxact_info_read(MyLogicalRepWorker->subid, stream_xid); + MyLogicalRepWorker->stream_fileset = palloc(sizeof(FileSet)); + FileSetInit(MyLogicalRepWorker->stream_fileset); - pgstat_report_activity(STATE_RUNNING, NULL); + MemoryContextSwitchTo(oldctx); + } - end_replication_step(); + /* Open the spool file for this transaction. */ + stream_open_file(MyLogicalRepWorker->subid, stream_xid, first_segment); + + /* If this is not the first segment, open existing subxact file. */ + if (!first_segment) + subxact_info_read(MyLogicalRepWorker->subid, stream_xid); + + end_replication_step(); + break; + + case TRANS_LEADER_SEND_TO_PARALLEL: + Assert(winfo); + + parallel_apply_send_data(winfo, s->len, s->data); + + nchanges = 0; + + /* Cache the parallel apply worker for this transaction. */ + stream_apply_worker = winfo; + break; + + case TRANS_PARALLEL_APPLY: + + /* + * Make sure the handle apply_dispatch methods are aware we're in + * a remote transaction. + */ + in_remote_transaction = true; + break; + + default: + Assert(false); + break; + } + + pgstat_report_activity(STATE_RUNNING, NULL); } /* @@ -1216,58 +1462,78 @@ apply_handle_stream_start(StringInfo s) static void apply_handle_stream_stop(StringInfo s) { - if (!in_streamed_transaction) + ParallelApplyWorkerInfo *winfo = NULL; + TransApplyAction apply_action; + + if (!am_parallel_apply_worker() && + (!in_streamed_transaction && !stream_apply_worker)) ereport(ERROR, (errcode(ERRCODE_PROTOCOL_VIOLATION), errmsg_internal("STREAM STOP message without STREAM START"))); - /* - * Close the file with serialized changes, and serialize information about - * subxacts for the toplevel transaction. - */ - subxact_info_write(MyLogicalRepWorker->subid, stream_xid); - stream_close_file(); + apply_action = get_transaction_apply_action(stream_xid, &winfo); - /* We must be in a valid transaction state */ - Assert(IsTransactionState()); + switch (apply_action) + { + case TRANS_LEADER_SERIALIZE: - /* Commit the per-stream transaction */ - CommitTransactionCommand(); + /* + * Close the file with serialized changes, and serialize + * information about subxacts for the toplevel transaction. + */ + subxact_info_write(MyLogicalRepWorker->subid, stream_xid); + stream_close_file(); + + /* We must be in a valid transaction state */ + Assert(IsTransactionState()); - in_streamed_transaction = false; + /* Commit the per-stream transaction */ + CommitTransactionCommand(); - /* Reset per-stream context */ - MemoryContextReset(LogicalStreamingContext); + /* Reset per-stream context */ + MemoryContextReset(LogicalStreamingContext); + + pgstat_report_activity(STATE_IDLE, NULL); + + in_streamed_transaction = false; + break; + + case TRANS_LEADER_SEND_TO_PARALLEL: + Assert(winfo); + + parallel_apply_send_data(winfo, s->len, s->data); + + elog(DEBUG1, "applied %u changes in the streaming chunk", nchanges); + + stream_apply_worker = NULL; + + pgstat_report_activity(STATE_IDLE, NULL); + break; + + case TRANS_PARALLEL_APPLY: + pgstat_report_activity(STATE_IDLEINTRANSACTION, NULL); + break; + + default: + Assert(false); + break; + } - pgstat_report_activity(STATE_IDLE, NULL); reset_apply_error_context_info(); } /* - * Handle STREAM abort message. + * Handle STREAM ABORT message when the transaction was spilled to disk. */ static void -apply_handle_stream_abort(StringInfo s) +serialize_stream_abort(TransactionId xid, TransactionId subxid) { - TransactionId xid; - TransactionId subxid; - - if (in_streamed_transaction) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("STREAM ABORT message without STREAM STOP"))); - - logicalrep_read_stream_abort(s, &xid, &subxid); - /* * If the two XIDs are the same, it's in fact abort of toplevel xact, so * just delete the files with serialized info. */ if (xid == subxid) - { - set_apply_error_context_xact(xid, InvalidXLogRecPtr); stream_cleanup_files(MyLogicalRepWorker->subid, xid); - } else { /* @@ -1291,8 +1557,6 @@ apply_handle_stream_abort(StringInfo s) bool found = false; char path[MAXPGPATH]; - set_apply_error_context_xact(subxid, InvalidXLogRecPtr); - subidx = -1; begin_replication_step(); subxact_info_read(MyLogicalRepWorker->subid, xid); @@ -1317,7 +1581,6 @@ apply_handle_stream_abort(StringInfo s) cleanup_subxact_info(); end_replication_step(); CommitTransactionCommand(); - reset_apply_error_context_info(); return; } @@ -1340,6 +1603,100 @@ apply_handle_stream_abort(StringInfo s) end_replication_step(); CommitTransactionCommand(); } +} + +/* + * Handle STREAM ABORT message. + */ +static void +apply_handle_stream_abort(StringInfo s) +{ + TransactionId xid; + TransactionId subxid; + LogicalRepStreamAbortData abort_data; + bool read_abort_lsn = false; + ParallelApplyWorkerInfo *winfo = NULL; + TransApplyAction apply_action; + + if (in_streamed_transaction || stream_apply_worker) + ereport(ERROR, + (errcode(ERRCODE_PROTOCOL_VIOLATION), + errmsg_internal("STREAM ABORT message without STREAM STOP"))); + + /* + * Check whether the publisher sends abort_lsn and abort_time. + * + * Note that the parallel apply worker is only started when the publisher + * sends abort_lsn and abort_time. + */ + if (am_parallel_apply_worker() || + (MySubscription->stream == SUBSTREAM_PARALLEL && + walrcv_server_version(LogRepWorkerWalRcvConn) >= 160000)) + read_abort_lsn = true; + + logicalrep_read_stream_abort(s, &abort_data, read_abort_lsn); + + xid = abort_data.xid; + subxid = abort_data.subxid; + + set_apply_error_context_xact(subxid, abort_data.abort_lsn); + + apply_action = get_transaction_apply_action(xid, &winfo); + + switch (apply_action) + { + case TRANS_LEADER_SERIALIZE: + + /* + * We are in leader apply worker and the transaction has been + * serialized to file. + */ + serialize_stream_abort(xid, subxid); + break; + + case TRANS_LEADER_SEND_TO_PARALLEL: + Assert(winfo); + + if (subxid == xid) + parallel_apply_replorigin_reset(); + + /* Send STREAM ABORT message to the parallel apply worker. */ + parallel_apply_send_data(winfo, s->len, s->data); + + /* + * After sending the data to the parallel apply worker, wait for + * that worker to finish. This is necessary to maintain commit + * order which avoids failures due to transaction dependencies and + * deadlocks. + */ + parallel_apply_wait_for_xact_finish(winfo); + + if (subxid == xid) + { + parallel_apply_replorigin_setup(); + parallel_apply_free_worker(winfo, xid); + } + else + { + /* + * Set in_parallel_apply_xact to true again as we only aborted + * the subtransaction and the top transaction is still in + * progress. + */ + parallel_apply_set_in_xact(winfo->shared, true); + } + break; + + case TRANS_PARALLEL_APPLY: + parallel_apply_stream_abort(&abort_data); + + elog(DEBUG1, "finished processing the transaction finish command"); + break; + + default: + Assert(false); + break; + } reset_apply_error_context_info(); } @@ -1471,8 +1828,10 @@ apply_handle_stream_commit(StringInfo s) { TransactionId xid; LogicalRepCommitData commit_data; + ParallelApplyWorkerInfo *winfo = NULL; + TransApplyAction apply_action; - if (in_streamed_transaction) + if (in_streamed_transaction || stream_apply_worker) ereport(ERROR, (errcode(ERRCODE_PROTOCOL_VIOLATION), errmsg_internal("STREAM COMMIT message without STREAM STOP"))); @@ -1480,14 +1839,73 @@ apply_handle_stream_commit(StringInfo s) xid = logicalrep_read_stream_commit(s, &commit_data); set_apply_error_context_xact(xid, commit_data.commit_lsn); - elog(DEBUG1, "received commit for streamed transaction %u", xid); + apply_action = get_transaction_apply_action(xid, &winfo); - apply_spooled_messages(xid, commit_data.commit_lsn); + switch (apply_action) + { + case TRANS_LEADER_SERIALIZE: - apply_handle_commit_internal(&commit_data); + /* + * The transaction has been serialized to file, so replay all the + * spooled operations. + */ + apply_spooled_messages(xid, commit_data.commit_lsn); + + apply_handle_commit_internal(&commit_data); + + /* Unlink the files with serialized changes and subxact info. */ + stream_cleanup_files(MyLogicalRepWorker->subid, xid); + break; + + case TRANS_LEADER_SEND_TO_PARALLEL: + Assert(winfo); - /* unlink the files with serialized changes and subxact info */ - stream_cleanup_files(MyLogicalRepWorker->subid, xid); + parallel_apply_replorigin_reset(); + + /* Send STREAM COMMIT message to the parallel apply worker. */ + parallel_apply_send_data(winfo, s->len, s->data); + + /* + * After sending the data to the parallel apply worker, wait for + * that worker to finish. This is necessary to maintain commit + * order which avoids failures due to transaction dependencies and + * deadlocks. + */ + parallel_apply_wait_for_xact_finish(winfo); + parallel_apply_replorigin_setup(); + + pgstat_report_stat(false); + store_flush_position(commit_data.end_lsn); + stop_skipping_changes(); + + parallel_apply_free_worker(winfo, xid); + + /* + * The transaction is either non-empty or skipped, so we clear the + * subskiplsn. + */ + clear_subscription_skip_lsn(commit_data.commit_lsn); + break; + + case TRANS_PARALLEL_APPLY: + parallel_apply_replorigin_setup(); + + apply_handle_commit_internal(&commit_data); + + parallel_apply_replorigin_reset(); + + list_free(subxactlist); + subxactlist = NIL; + + parallel_apply_set_in_xact(MyParallelShared, false); + + elog(DEBUG1, "finished processing the transaction finish command"); + break; + + default: + Assert(false); + break; + } /* Process any tables that are being synchronized in parallel. */ process_syncing_tables(commit_data.end_lsn); @@ -1531,6 +1949,13 @@ apply_handle_commit_internal(LogicalRepCommitData *commit_data) replorigin_session_origin_timestamp = commit_data->committime; CommitTransactionCommand(); + + if (IsTransactionBlock()) + { + EndTransactionBlock(false); + CommitTransactionCommand(); + } + pgstat_report_stat(false); store_flush_position(commit_data->end_lsn); @@ -2468,7 +2893,7 @@ apply_handle_truncate(StringInfo s) /* * Logical replication protocol message dispatcher. */ -static void +void apply_dispatch(StringInfo s) { LogicalRepMsgType action = pq_getmsgbyte(s); @@ -2637,6 +3062,10 @@ store_flush_position(XLogRecPtr remote_lsn) { FlushPosition *flushpos; + /* Skip if not the leader apply worker */ + if (am_parallel_apply_worker()) + return; + /* Need to do this in permanent context */ MemoryContextSwitchTo(ApplyContext); @@ -2651,7 +3080,7 @@ store_flush_position(XLogRecPtr remote_lsn) /* Update statistics of the worker. */ -static void +void UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) { MyLogicalRepWorker->last_lsn = last_lsn; @@ -2701,6 +3130,7 @@ LogicalRepApplyLoop(XLogRecPtr last_received) errcallback.callback = apply_error_callback; errcallback.previous = error_context_stack; error_context_stack = &errcallback; + apply_error_context_stack = error_context_stack; /* This outer loop iterates once per wait. */ for (;;) @@ -2803,7 +3233,8 @@ LogicalRepApplyLoop(XLogRecPtr last_received) /* confirm all writes so far */ send_feedback(last_received, false, false); - if (!in_remote_transaction && !in_streamed_transaction) + if (!in_remote_transaction && !in_streamed_transaction + && !stream_apply_worker) { /* * If we didn't get any transactions for a while there might be @@ -2915,6 +3346,7 @@ LogicalRepApplyLoop(XLogRecPtr last_received) /* Pop the error context stack */ error_context_stack = errcallback.previous; + apply_error_context_stack = error_context_stack; /* All done */ walrcv_endstreaming(LogRepWorkerWalRcvConn, &tli); @@ -3115,7 +3547,7 @@ maybe_reread_subscription(void) /* * Callback from subscription syscache invalidation. */ -static void +void subscription_change_cb(Datum arg, int cacheid, uint32 hashvalue) { MySubscriptionValid = false; @@ -3570,37 +4002,14 @@ start_apply(XLogRecPtr origin_startpos) PG_END_TRY(); } -/* Logical Replication Apply worker entry point */ +/* + * Initialize the database connection, in-memory subscription and necessary + * config options. + */ void -ApplyWorkerMain(Datum main_arg) +InitializeApplyWorker(void) { - int worker_slot = DatumGetInt32(main_arg); MemoryContext oldctx; - char originname[NAMEDATALEN]; - XLogRecPtr origin_startpos = InvalidXLogRecPtr; - char *myslotname = NULL; - WalRcvStreamOptions options; - int server_version; - - /* Attach to slot */ - logicalrep_worker_attach(worker_slot); - - /* Setup signal handling */ - pqsignal(SIGHUP, SignalHandlerForConfigReload); - pqsignal(SIGTERM, die); - BackgroundWorkerUnblockSignals(); - - /* - * We don't currently need any ResourceOwner in a walreceiver process, but - * if we did, we could call CreateAuxProcessResourceOwner here. - */ - - /* Initialise stats to a sanish value */ - MyLogicalRepWorker->last_send_time = MyLogicalRepWorker->last_recv_time = - MyLogicalRepWorker->reply_time = GetCurrentTimestamp(); - - /* Load the libpq-specific functions */ - load_file("libpqwalreceiver", false); /* Run as replica session replication role. */ SetConfigOption("session_replication_role", "replica", @@ -3660,12 +4069,50 @@ ApplyWorkerMain(Datum main_arg) ereport(LOG, (errmsg("logical replication table synchronization worker for subscription \"%s\", table \"%s\" has started", MySubscription->name, get_rel_name(MyLogicalRepWorker->relid)))); + else if (am_parallel_apply_worker()) + ereport(LOG, + (errmsg("logical replication parallel apply worker for subscription \"%s\" has started", + MySubscription->name))); else ereport(LOG, (errmsg("logical replication apply worker for subscription \"%s\" has started", MySubscription->name))); CommitTransactionCommand(); +} + +/* Logical Replication Apply worker entry point */ +void +ApplyWorkerMain(Datum main_arg) +{ + int worker_slot = DatumGetInt32(main_arg); + char originname[NAMEDATALEN]; + XLogRecPtr origin_startpos = InvalidXLogRecPtr; + char *myslotname = NULL; + WalRcvStreamOptions options; + int server_version; + + /* Attach to slot */ + logicalrep_worker_attach(worker_slot); + + /* Setup signal handling */ + pqsignal(SIGHUP, SignalHandlerForConfigReload); + pqsignal(SIGTERM, die); + BackgroundWorkerUnblockSignals(); + + /* + * We don't currently need any ResourceOwner in a walreceiver process, but + * if we did, we could call CreateAuxProcessResourceOwner here. + */ + + /* Initialise stats to a sanish value */ + MyLogicalRepWorker->last_send_time = MyLogicalRepWorker->last_recv_time = + MyLogicalRepWorker->reply_time = GetCurrentTimestamp(); + + /* Load the libpq-specific functions */ + load_file("libpqwalreceiver", false); + + InitializeApplyWorker(); /* Connect to the origin and start the replication. */ elog(DEBUG1, "connecting to publisher using connection string \"%s\"", @@ -3752,13 +4199,23 @@ ApplyWorkerMain(Datum main_arg) server_version = walrcv_server_version(LogRepWorkerWalRcvConn); options.proto.logical.proto_version = + server_version >= 160000 ? LOGICALREP_PROTO_STREAM_PARALLEL_VERSION_NUM : server_version >= 150000 ? LOGICALREP_PROTO_TWOPHASE_VERSION_NUM : server_version >= 140000 ? LOGICALREP_PROTO_STREAM_VERSION_NUM : LOGICALREP_PROTO_VERSION_NUM; options.proto.logical.publication_names = MySubscription->publications; options.proto.logical.binary = MySubscription->binary; - options.proto.logical.streaming = MySubscription->stream; + + if (server_version >= 160000 && + MySubscription->stream == SUBSTREAM_PARALLEL) + options.proto.logical.streaming = pstrdup("parallel"); + else if (server_version >= 140000 && + MySubscription->stream != SUBSTREAM_OFF) + options.proto.logical.streaming = pstrdup("on"); + else + options.proto.logical.streaming = NULL; + options.proto.logical.twophase = false; options.proto.logical.origin = pstrdup(MySubscription->origin); @@ -3855,6 +4312,15 @@ IsLogicalWorker(void) return MyLogicalRepWorker != NULL; } +/* + * Is current process a logical replication parallel apply worker? + */ +bool +IsLogicalParallelApplyWorker(void) +{ + return am_parallel_apply_worker(); +} + /* * Start skipping changes of the transaction if the given LSN matches the * LSN specified by subscription's skiplsn. @@ -3917,7 +4383,8 @@ clear_subscription_skip_lsn(XLogRecPtr finish_lsn) XLogRecPtr myskiplsn = MySubscription->skiplsn; bool started_tx = false; - if (likely(XLogRecPtrIsInvalid(myskiplsn))) + if (likely(XLogRecPtrIsInvalid(myskiplsn)) || + am_parallel_apply_worker()) return; if (!IsTransactionState()) @@ -3989,7 +4456,7 @@ clear_subscription_skip_lsn(XLogRecPtr finish_lsn) } /* Error callback to give more context info about the change being applied */ -static void +void apply_error_callback(void *arg) { ApplyErrorCallbackArg *errarg = &apply_error_callback_arg; @@ -4017,23 +4484,47 @@ apply_error_callback(void *arg) errarg->remote_xid, LSN_FORMAT_ARGS(errarg->finish_lsn)); } - else if (errarg->remote_attnum < 0) - errcontext("processing remote data for replication origin \"%s\" during \"%s\" for replication target relation \"%s.%s\" in transaction %u finished at %X/%X", - errarg->origin_name, - logicalrep_message_type(errarg->command), - errarg->rel->remoterel.nspname, - errarg->rel->remoterel.relname, - errarg->remote_xid, - LSN_FORMAT_ARGS(errarg->finish_lsn)); else - errcontext("processing remote data for replication origin \"%s\" during \"%s\" for replication target relation \"%s.%s\" column \"%s\" in transaction %u finished at %X/%X", - errarg->origin_name, - logicalrep_message_type(errarg->command), - errarg->rel->remoterel.nspname, - errarg->rel->remoterel.relname, - errarg->rel->remoterel.attnames[errarg->remote_attnum], - errarg->remote_xid, - LSN_FORMAT_ARGS(errarg->finish_lsn)); + { + if (errarg->remote_attnum < 0) + { + if (XLogRecPtrIsInvalid(errarg->finish_lsn)) + errcontext("processing remote data for replication origin \"%s\" during \"%s\" for replication target relation \"%s.%s\" in transaction %u", + errarg->origin_name, + logicalrep_message_type(errarg->command), + errarg->rel->remoterel.nspname, + errarg->rel->remoterel.relname, + errarg->remote_xid); + else + errcontext("processing remote data for replication origin \"%s\" during \"%s\" for replication target relation \"%s.%s\" in transaction %u finished at %X/%X", + errarg->origin_name, + logicalrep_message_type(errarg->command), + errarg->rel->remoterel.nspname, + errarg->rel->remoterel.relname, + errarg->remote_xid, + LSN_FORMAT_ARGS(errarg->finish_lsn)); + } + else + { + if (XLogRecPtrIsInvalid(errarg->finish_lsn)) + errcontext("processing remote data for replication origin \"%s\" during \"%s\" for replication target relation \"%s.%s\" column \"%s\" in transaction %u", + errarg->origin_name, + logicalrep_message_type(errarg->command), + errarg->rel->remoterel.nspname, + errarg->rel->remoterel.relname, + errarg->rel->remoterel.attnames[errarg->remote_attnum], + errarg->remote_xid); + else + errcontext("processing remote data for replication origin \"%s\" during \"%s\" for replication target relation \"%s.%s\" column \"%s\" in transaction %u finished at %X/%X", + errarg->origin_name, + logicalrep_message_type(errarg->command), + errarg->rel->remoterel.nspname, + errarg->rel->remoterel.relname, + errarg->rel->remoterel.attnames[errarg->remote_attnum], + errarg->remote_xid, + LSN_FORMAT_ARGS(errarg->finish_lsn)); + } + } } /* Set transaction information of apply error callback */ @@ -4053,3 +4544,28 @@ reset_apply_error_context_info(void) apply_error_callback_arg.remote_attnum = -1; set_apply_error_context_xact(InvalidTransactionId, InvalidXLogRecPtr); } + +/* + * Return the action to take for the given transaction. *winfo is assigned to + * the destination parallel worker info (if the action is + * TRANS_LEADER_SEND_TO_PARALLEL), otherwise *winfo is assigned NULL. + */ +static TransApplyAction +get_transaction_apply_action(TransactionId xid, ParallelApplyWorkerInfo **winfo) +{ + *winfo = NULL; + + if (am_parallel_apply_worker()) + return TRANS_PARALLEL_APPLY; + else if (in_remote_transaction) + return TRANS_LEADER_APPLY; + + /* + * Check if we are processing this transaction using a parallel apply + * worker and if so, send the changes to that worker. + */ + else if ((*winfo = parallel_apply_find_worker(xid))) + return TRANS_LEADER_SEND_TO_PARALLEL; + else + return TRANS_LEADER_SERIALIZE; +} diff --git a/src/backend/replication/pgoutput/pgoutput.c b/src/backend/replication/pgoutput/pgoutput.c index 03b13ae679..b3769820bc 100644 --- a/src/backend/replication/pgoutput/pgoutput.c +++ b/src/backend/replication/pgoutput/pgoutput.c @@ -369,7 +369,7 @@ parse_output_parameters(List *options, PGOutputData *data) errmsg("conflicting or redundant options"))); streaming_given = true; - data->streaming = defGetBoolean(defel); + data->streaming = defGetStreamingMode(defel); } else if (strcmp(defel->defname, "two_phase") == 0) { @@ -461,13 +461,20 @@ pgoutput_startup(LogicalDecodingContext *ctx, OutputPluginOptions *opt, * we only allow it with sufficient version of the protocol, and when * the output plugin supports it. */ - if (!data->streaming) + if (data->streaming == SUBSTREAM_OFF) ctx->streaming = false; - else if (data->protocol_version < LOGICALREP_PROTO_STREAM_VERSION_NUM) + else if (data->streaming == SUBSTREAM_ON && + data->protocol_version < LOGICALREP_PROTO_STREAM_VERSION_NUM) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("requested proto_version=%d does not support streaming, need %d or higher", data->protocol_version, LOGICALREP_PROTO_STREAM_VERSION_NUM))); + else if (data->streaming == SUBSTREAM_PARALLEL && + data->protocol_version < LOGICALREP_PROTO_STREAM_PARALLEL_VERSION_NUM) + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("requested proto_version=%d does not support streaming=parallel mode, need %d or higher", + data->protocol_version, LOGICALREP_PROTO_STREAM_PARALLEL_VERSION_NUM))); else if (!ctx->streaming) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), @@ -513,7 +520,7 @@ pgoutput_startup(LogicalDecodingContext *ctx, OutputPluginOptions *opt, * Disable the streaming and prepared transactions during the slot * initialization mode. */ - ctx->streaming = false; + ctx->streaming = SUBSTREAM_OFF; ctx->twophase = false; } } @@ -1843,6 +1850,8 @@ pgoutput_stream_abort(struct LogicalDecodingContext *ctx, XLogRecPtr abort_lsn) { ReorderBufferTXN *toptxn; + PGOutputData *data = (PGOutputData *) ctx->output_plugin_private; + bool abort_info = (data->streaming == SUBSTREAM_PARALLEL); /* * The abort should happen outside streaming block, even for streamed @@ -1856,7 +1865,8 @@ pgoutput_stream_abort(struct LogicalDecodingContext *ctx, Assert(rbtxn_is_streamed(toptxn)); OutputPluginPrepareWrite(ctx, true); - logicalrep_write_stream_abort(ctx->out, toptxn->xid, txn->xid); + logicalrep_write_stream_abort(ctx->out, toptxn->xid, txn->xid, abort_lsn, txn->xact_time.abort_time, abort_info); + OutputPluginWrite(ctx, true); cleanup_rel_sync_cache(toptxn->xid, false); diff --git a/src/backend/storage/ipc/procsignal.c b/src/backend/storage/ipc/procsignal.c index 21a9fc0fdd..9cd54287b6 100644 --- a/src/backend/storage/ipc/procsignal.c +++ b/src/backend/storage/ipc/procsignal.c @@ -22,6 +22,7 @@ #include "commands/async.h" #include "miscadmin.h" #include "pgstat.h" +#include "replication/logicalworker.h" #include "replication/walsender.h" #include "storage/condition_variable.h" #include "storage/ipc.h" @@ -657,6 +658,9 @@ procsignal_sigusr1_handler(SIGNAL_ARGS) if (CheckProcSignal(PROCSIG_LOG_MEMORY_CONTEXT)) HandleLogMemoryContextInterrupt(); + if (CheckProcSignal(PROCSIG_PARALLEL_APPLY_MESSAGE)) + HandleParallelApplyMessageInterrupt(); + if (CheckProcSignal(PROCSIG_RECOVERY_CONFLICT_DATABASE)) RecoveryConflictInterrupt(PROCSIG_RECOVERY_CONFLICT_DATABASE); diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index 35eff28bd3..0ee50020d7 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -3377,6 +3377,9 @@ ProcessInterrupts(void) if (LogMemoryContextPending) ProcessLogMemoryContextInterrupt(); + + if (ParallelApplyMessagePending) + HandleParallelApplyMessages(); } /* diff --git a/src/backend/utils/activity/wait_event.c b/src/backend/utils/activity/wait_event.c index 92f24a6c9b..c96647c4ed 100644 --- a/src/backend/utils/activity/wait_event.c +++ b/src/backend/utils/activity/wait_event.c @@ -388,6 +388,9 @@ pgstat_get_wait_ipc(WaitEventIPC w) case WAIT_EVENT_HASH_GROW_BUCKETS_REINSERT: event_name = "HashGrowBucketsReinsert"; break; + case WAIT_EVENT_LOGICAL_PARALLEL_APPLY_STATE_CHANGE: + event_name = "LogicalParallelApplyStateChange"; + break; case WAIT_EVENT_LOGICAL_SYNC_DATA: event_name = "LogicalSyncData"; break; diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c index 550e95056c..84f6a11357 100644 --- a/src/backend/utils/misc/guc_tables.c +++ b/src/backend/utils/misc/guc_tables.c @@ -2973,6 +2973,18 @@ struct config_int ConfigureNamesInt[] = NULL, NULL, NULL }, + { + {"max_parallel_apply_workers_per_subscription", + PGC_SIGHUP, + REPLICATION_SUBSCRIBERS, + gettext_noop("Maximum number of parallel apply workers per subscription."), + NULL, + }, + &max_parallel_apply_workers_per_subscription, + 2, 0, MAX_BACKENDS, + NULL, NULL, NULL + }, + { {"log_rotation_age", PGC_SIGHUP, LOGGING_WHERE, gettext_noop("Sets the amount of time to wait before forcing " diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2ae76e5cfb..6603f0e977 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -360,6 +360,7 @@ #max_logical_replication_workers = 4 # taken from max_worker_processes # (change requires restart) #max_sync_workers_per_subscription = 2 # taken from max_logical_replication_workers +#max_parallel_apply_workers_per_subscription = 2 # taken from max_logical_replication_workers #------------------------------------------------------------------------------ diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 67b6d9079e..026cf46828 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -4480,7 +4480,7 @@ getSubscriptions(Archive *fout) if (fout->remoteVersion >= 140000) appendPQExpBufferStr(query, " s.substream,\n"); else - appendPQExpBufferStr(query, " false AS substream,\n"); + appendPQExpBufferStr(query, " 'f' AS substream,\n"); if (fout->remoteVersion >= 150000) appendPQExpBufferStr(query, @@ -4617,8 +4617,10 @@ dumpSubscription(Archive *fout, const SubscriptionInfo *subinfo) if (strcmp(subinfo->subbinary, "t") == 0) appendPQExpBufferStr(query, ", binary = true"); - if (strcmp(subinfo->substream, "f") != 0) + if (strcmp(subinfo->substream, "t") == 0) appendPQExpBufferStr(query, ", streaming = on"); + else if (strcmp(subinfo->substream, "p") == 0) + appendPQExpBufferStr(query, ", streaming = parallel"); if (strcmp(subinfo->subtwophasestate, two_phase_disabled) != 0) appendPQExpBufferStr(query, ", two_phase = on"); diff --git a/src/include/catalog/pg_subscription.h b/src/include/catalog/pg_subscription.h index 7b98714f30..016afbc204 100644 --- a/src/include/catalog/pg_subscription.h +++ b/src/include/catalog/pg_subscription.h @@ -80,7 +80,8 @@ CATALOG(pg_subscription,6100,SubscriptionRelationId) BKI_SHARED_RELATION BKI_ROW bool subbinary; /* True if the subscription wants the * publisher to send data in binary */ - bool substream; /* Stream in-progress transactions. */ + char substream; /* Stream in-progress transactions. See + * SUBSTREAM_xxx constants. */ char subtwophasestate; /* Stream two-phase transactions */ @@ -124,7 +125,8 @@ typedef struct Subscription bool enabled; /* Indicates if the subscription is enabled */ bool binary; /* Indicates if the subscription wants data in * binary format */ - bool stream; /* Allow streaming in-progress transactions. */ + char stream; /* Allow streaming in-progress transactions. + * See SUBSTREAM_xxx constants. */ char twophasestate; /* Allow streaming two-phase transactions */ bool disableonerr; /* Indicates if the subscription should be * automatically disabled if a worker error @@ -137,6 +139,21 @@ typedef struct Subscription * specified origin */ } Subscription; +/* Disallow streaming in-progress transactions. */ +#define SUBSTREAM_OFF 'f' + +/* + * Streaming in-progress transactions are written to a temporary file and + * applied only after the transaction is committed on upstream. + */ +#define SUBSTREAM_ON 't' + +/* + * Streaming in-progress transactions are applied immediately via a parallel + * apply worker. + */ +#define SUBSTREAM_PARALLEL 'p' + extern Subscription *GetSubscription(Oid subid, bool missing_ok); extern void FreeSubscription(Subscription *sub); extern void DisableSubscription(Oid subid); diff --git a/src/include/commands/defrem.h b/src/include/commands/defrem.h index 56d2bb6616..f6ba5ffc01 100644 --- a/src/include/commands/defrem.h +++ b/src/include/commands/defrem.h @@ -154,6 +154,7 @@ extern List *defGetQualifiedName(DefElem *def); extern TypeName *defGetTypeName(DefElem *def); extern int defGetTypeLength(DefElem *def); extern List *defGetStringList(DefElem *def); +extern char defGetStreamingMode(DefElem *def); extern void errorConflictingDefElem(DefElem *defel, ParseState *pstate) pg_attribute_noreturn(); #endif /* DEFREM_H */ diff --git a/src/include/replication/logicallauncher.h b/src/include/replication/logicallauncher.h index f1e2821e25..d513ef533a 100644 --- a/src/include/replication/logicallauncher.h +++ b/src/include/replication/logicallauncher.h @@ -14,6 +14,7 @@ extern PGDLLIMPORT int max_logical_replication_workers; extern PGDLLIMPORT int max_sync_workers_per_subscription; +extern PGDLLIMPORT int max_parallel_apply_workers_per_subscription; extern void ApplyLauncherRegister(void); extern void ApplyLauncherMain(Datum main_arg); diff --git a/src/include/replication/logicalproto.h b/src/include/replication/logicalproto.h index 7eaa4c97ed..035eddceca 100644 --- a/src/include/replication/logicalproto.h +++ b/src/include/replication/logicalproto.h @@ -32,12 +32,17 @@ * * LOGICALREP_PROTO_TWOPHASE_VERSION_NUM is the minimum protocol version with * support for two-phase commit decoding (at prepare time). Introduced in PG15. + * + * LOGICALREP_PROTO_STREAM_PARALLEL_VERSION_NUM is the minimum protocol version + * where we support applying large streaming transactions in parallel. + * Introduced in PG16. */ #define LOGICALREP_PROTO_MIN_VERSION_NUM 1 #define LOGICALREP_PROTO_VERSION_NUM 1 #define LOGICALREP_PROTO_STREAM_VERSION_NUM 2 #define LOGICALREP_PROTO_TWOPHASE_VERSION_NUM 3 -#define LOGICALREP_PROTO_MAX_VERSION_NUM LOGICALREP_PROTO_TWOPHASE_VERSION_NUM +#define LOGICALREP_PROTO_STREAM_PARALLEL_VERSION_NUM 4 +#define LOGICALREP_PROTO_MAX_VERSION_NUM LOGICALREP_PROTO_STREAM_PARALLEL_VERSION_NUM /* * Logical message types @@ -175,6 +180,17 @@ typedef struct LogicalRepRollbackPreparedTxnData char gid[GIDSIZE]; } LogicalRepRollbackPreparedTxnData; +/* + * Transaction protocol information for stream abort. + */ +typedef struct LogicalRepStreamAbortData +{ + TransactionId xid; + TransactionId subxid; + XLogRecPtr abort_lsn; + TimestampTz abort_time; +} LogicalRepStreamAbortData; + extern void logicalrep_write_begin(StringInfo out, ReorderBufferTXN *txn); extern void logicalrep_read_begin(StringInfo in, LogicalRepBeginData *begin_data); @@ -246,9 +262,13 @@ extern void logicalrep_write_stream_commit(StringInfo out, ReorderBufferTXN *txn extern TransactionId logicalrep_read_stream_commit(StringInfo in, LogicalRepCommitData *commit_data); extern void logicalrep_write_stream_abort(StringInfo out, TransactionId xid, - TransactionId subxid); -extern void logicalrep_read_stream_abort(StringInfo in, TransactionId *xid, - TransactionId *subxid); + TransactionId subxid, + XLogRecPtr abort_lsn, + TimestampTz abort_time, + bool abort_info); +extern void logicalrep_read_stream_abort(StringInfo in, + LogicalRepStreamAbortData *abort_data, + bool read_abort_lsn); extern char *logicalrep_message_type(LogicalRepMsgType action); #endif /* LOGICAL_PROTO_H */ diff --git a/src/include/replication/logicalworker.h b/src/include/replication/logicalworker.h index cd1b6e8afc..96d7e81b06 100644 --- a/src/include/replication/logicalworker.h +++ b/src/include/replication/logicalworker.h @@ -12,8 +12,14 @@ #ifndef LOGICALWORKER_H #define LOGICALWORKER_H +extern PGDLLIMPORT volatile bool ParallelApplyMessagePending; + extern void ApplyWorkerMain(Datum main_arg); +extern void ParallelApplyWorkerMain(Datum main_arg); extern bool IsLogicalWorker(void); +extern bool IsLogicalParallelApplyWorker(void); +extern void HandleParallelApplyMessageInterrupt(void); +extern void HandleParallelApplyMessages(void); #endif /* LOGICALWORKER_H */ diff --git a/src/include/replication/pgoutput.h b/src/include/replication/pgoutput.h index 02027550e2..3c30da8205 100644 --- a/src/include/replication/pgoutput.h +++ b/src/include/replication/pgoutput.h @@ -26,7 +26,7 @@ typedef struct PGOutputData List *publication_names; List *publications; bool binary; - bool streaming; + char streaming; bool messages; bool two_phase; char *origin; diff --git a/src/include/replication/reorderbuffer.h b/src/include/replication/reorderbuffer.h index 02b59a1931..1549116338 100644 --- a/src/include/replication/reorderbuffer.h +++ b/src/include/replication/reorderbuffer.h @@ -301,6 +301,7 @@ typedef struct ReorderBufferTXN { TimestampTz commit_time; TimestampTz prepare_time; + TimestampTz abort_time; } xact_time; /* @@ -664,9 +665,11 @@ extern void ReorderBufferAssignChild(ReorderBuffer *rb, TransactionId xid, extern void ReorderBufferCommitChild(ReorderBuffer *rb, TransactionId xid, TransactionId subxid, XLogRecPtr commit_lsn, XLogRecPtr end_lsn); -extern void ReorderBufferAbort(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn); +extern void ReorderBufferAbort(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn, + TimestampTz abort_time); extern void ReorderBufferAbortOld(ReorderBuffer *rb, TransactionId oldestRunningXid); -extern void ReorderBufferForget(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn); +extern void ReorderBufferForget(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn, + TimestampTz abort_time); extern void ReorderBufferInvalidate(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn); extern void ReorderBufferSetBaseSnapshot(ReorderBuffer *rb, TransactionId xid, diff --git a/src/include/replication/walreceiver.h b/src/include/replication/walreceiver.h index 9339f29303..7e930d5777 100644 --- a/src/include/replication/walreceiver.h +++ b/src/include/replication/walreceiver.h @@ -182,7 +182,7 @@ typedef struct uint32 proto_version; /* Logical protocol version */ List *publication_names; /* String list of publications */ bool binary; /* Ask publisher to use binary */ - bool streaming; /* Streaming of large transactions */ + char *streaming; /* Streaming of large transactions */ bool twophase; /* Streaming of two-phase transactions at * prepare time */ char *origin; /* Only publish data originating from the diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index 901845abc2..7214b17131 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -17,8 +17,12 @@ #include "access/xlogdefs.h" #include "catalog/pg_subscription.h" #include "datatype/timestamp.h" +#include "miscadmin.h" +#include "replication/logicalrelation.h" #include "storage/fileset.h" #include "storage/lock.h" +#include "storage/shm_mq.h" +#include "storage/shm_toc.h" #include "storage/spin.h" @@ -60,6 +64,12 @@ typedef struct LogicalRepWorker */ FileSet *stream_fileset; + /* + * PID of leader apply worker if this slot is used for a parallel apply + * worker, InvalidPid otherwise. + */ + pid_t apply_leader_pid; + /* Stats. */ XLogRecPtr last_lsn; TimestampTz last_send_time; @@ -68,9 +78,82 @@ typedef struct LogicalRepWorker TimestampTz reply_time; } LogicalRepWorker; +/* Struct for saving and restoring apply errcontext information */ +typedef struct ApplyErrorCallbackArg +{ + LogicalRepMsgType command; /* 0 if invalid */ + LogicalRepRelMapEntry *rel; + + /* Remote node information */ + int remote_attnum; /* -1 if invalid */ + TransactionId remote_xid; + XLogRecPtr finish_lsn; + char *origin_name; +} ApplyErrorCallbackArg; + +/* + * Struct for sharing information between leader apply worker and parallel + * apply workers. + */ +typedef struct ParallelApplyWorkerShared +{ + slock_t mutex; + + /* + * Flag used to ensure commit ordering. + * + * The parallel apply worker will set it to false after handling the + * transaction finish commands while the apply leader will wait for it to + * become false before proceeding in transaction finish commands (e.g. + * STREAM_COMMIT/STREAM_ABORT/STREAM_PREPARE). + */ + bool in_parallel_apply_xact; + + /* Information from the corresponding LogicalRepWorker slot. */ + uint16 logicalrep_worker_generation; + + int logicalrep_worker_slot_no; +} ParallelApplyWorkerShared; + +/* + * Information which is used to manage the parallel apply worker. + */ +typedef struct ParallelApplyWorkerInfo +{ + shm_mq_handle *mq_handle; + + /* + * The queue used to transfer messages from the parallel apply worker to + * the leader apply worker. NULL if the parallel apply worker exited + * cleanly. + */ + shm_mq_handle *error_mq_handle; + + dsm_segment *dsm_seg; + + /* + * Indicates whether the worker is available to be used for parallel apply + * transaction? + */ + bool in_use; + + ParallelApplyWorkerShared *shared; +} ParallelApplyWorkerInfo; + /* Main memory context for apply worker. Permanent during worker lifetime. */ extern PGDLLIMPORT MemoryContext ApplyContext; +extern PGDLLIMPORT MemoryContext ApplyMessageContext; + +extern PGDLLIMPORT ErrorContextCallback *apply_error_context_stack; +extern PGDLLIMPORT ApplyErrorCallbackArg apply_error_callback_arg; + +extern PGDLLIMPORT bool MySubscriptionValid; + +extern PGDLLIMPORT ParallelApplyWorkerShared *MyParallelShared; + +extern PGDLLIMPORT List *subxactlist; + /* libpqreceiver connection */ extern PGDLLIMPORT struct WalReceiverConn *LogRepWorkerWalRcvConn; @@ -79,18 +162,22 @@ extern PGDLLIMPORT Subscription *MySubscription; extern PGDLLIMPORT LogicalRepWorker *MyLogicalRepWorker; extern PGDLLIMPORT bool in_remote_transaction; +extern PGDLLIMPORT ParallelApplyWorkerInfo *stream_apply_worker; extern void logicalrep_worker_attach(int slot); extern LogicalRepWorker *logicalrep_worker_find(Oid subid, Oid relid, bool only_running); extern List *logicalrep_workers_find(Oid subid, bool only_running); -extern void logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, - Oid userid, Oid relid); +extern bool logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, + Oid userid, Oid relid, + dsm_handle subworker_dsm); extern void logicalrep_worker_stop(Oid subid, Oid relid); +extern void logicalrep_worker_stop_by_slot(int slot_no, uint16 generation); extern void logicalrep_worker_wakeup(Oid subid, Oid relid); extern void logicalrep_worker_wakeup_ptr(LogicalRepWorker *worker); extern int logicalrep_sync_worker_count(Oid subid); +extern int logicalrep_parallel_apply_worker_count(Oid subid); extern void ReplicationOriginNameForTablesync(Oid suboid, Oid relid, char *originname, int szorgname); @@ -103,10 +190,48 @@ extern void process_syncing_tables(XLogRecPtr current_lsn); extern void invalidate_syncing_table_states(Datum arg, int cacheid, uint32 hashvalue); +extern void UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, + bool reply); + +extern void apply_dispatch(StringInfo s); + +extern void InitializeApplyWorker(void); + +/* Function for apply error callback */ +extern void apply_error_callback(void *arg); + +extern void subscription_change_cb(Datum arg, int cacheid, uint32 hashvalue); + +/* Parallel apply worker setup and interactions */ +extern void parallel_apply_start_worker(TransactionId xid); +extern ParallelApplyWorkerInfo *parallel_apply_find_worker(TransactionId xid); +extern void parallel_apply_set_in_xact(ParallelApplyWorkerShared *wshared, + bool in_xact); +extern void parallel_apply_free_worker(ParallelApplyWorkerInfo *winfo, + TransactionId xid); +extern void parallel_apply_wait_for_xact_finish(ParallelApplyWorkerInfo *winfo); +extern void parallel_apply_send_data(ParallelApplyWorkerInfo *winfo, Size nbytes, + const void *data); + +extern void parallel_apply_subxact_info_add(TransactionId current_xid, TransactionId top_xid); +extern void parallel_apply_stream_abort(LogicalRepStreamAbortData *abort_data); +extern void parallel_apply_savepoint_name(Oid suboid, Oid relid, + char *spname, int szsp); +extern void parallel_apply_replorigin_setup(void); +extern void parallel_apply_replorigin_reset(void); + +#define isParallelApplyWorker(worker) (worker->apply_leader_pid != InvalidPid) + static inline bool am_tablesync_worker(void) { return OidIsValid(MyLogicalRepWorker->relid); } +static inline bool +am_parallel_apply_worker(void) +{ + return isParallelApplyWorker(MyLogicalRepWorker); +} + #endif /* WORKER_INTERNAL_H */ diff --git a/src/include/storage/procsignal.h b/src/include/storage/procsignal.h index ee636900f3..93a51f4254 100644 --- a/src/include/storage/procsignal.h +++ b/src/include/storage/procsignal.h @@ -35,6 +35,7 @@ typedef enum PROCSIG_WALSND_INIT_STOPPING, /* ask walsenders to prepare for shutdown */ PROCSIG_BARRIER, /* global barrier interrupt */ PROCSIG_LOG_MEMORY_CONTEXT, /* ask backend to log the memory contexts */ + PROCSIG_PARALLEL_APPLY_MESSAGE, /* Message from parallel apply workers */ /* Recovery conflict reasons */ PROCSIG_RECOVERY_CONFLICT_DATABASE, diff --git a/src/include/utils/wait_event.h b/src/include/utils/wait_event.h index 6f2d5612e0..b2cdd554e1 100644 --- a/src/include/utils/wait_event.h +++ b/src/include/utils/wait_event.h @@ -105,6 +105,7 @@ typedef enum WAIT_EVENT_HASH_GROW_BUCKETS_ALLOCATE, WAIT_EVENT_HASH_GROW_BUCKETS_ELECT, WAIT_EVENT_HASH_GROW_BUCKETS_REINSERT, + WAIT_EVENT_LOGICAL_PARALLEL_APPLY_STATE_CHANGE, WAIT_EVENT_LOGICAL_SYNC_DATA, WAIT_EVENT_LOGICAL_SYNC_STATE_CHANGE, WAIT_EVENT_MQ_INTERNAL, diff --git a/src/test/regress/expected/subscription.out b/src/test/regress/expected/subscription.out index ef0ebf96b9..99b9e867e4 100644 --- a/src/test/regress/expected/subscription.out +++ b/src/test/regress/expected/subscription.out @@ -217,9 +217,9 @@ ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE); (1 row) DROP SUBSCRIPTION regress_testsub; --- fail - streaming must be boolean +-- fail - streaming must be boolean or 'parallel' CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, streaming = foo); -ERROR: streaming requires a Boolean value +ERROR: streaming requires a Boolean value or "parallel" -- now it works CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, streaming = true); WARNING: tables were not subscribed, you will have to run ALTER SUBSCRIPTION ... REFRESH PUBLICATION to subscribe the tables @@ -230,6 +230,14 @@ WARNING: tables were not subscribed, you will have to run ALTER SUBSCRIPTION .. regress_testsub | regress_subscription_user | f | {testpub} | f | t | d | f | any | off | dbname=regress_doesnotexist | 0/0 (1 row) +ALTER SUBSCRIPTION regress_testsub SET (streaming = parallel); +\dRs+ + List of subscriptions + Name | Owner | Enabled | Publication | Binary | Streaming | Two-phase commit | Disable on error | Origin | Synchronous commit | Conninfo | Skip LSN +-----------------+---------------------------+---------+-------------+--------+-----------+------------------+------------------+--------+--------------------+-----------------------------+---------- + regress_testsub | regress_subscription_user | f | {testpub} | f | p | d | f | any | off | dbname=regress_doesnotexist | 0/0 +(1 row) + ALTER SUBSCRIPTION regress_testsub SET (streaming = false); ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE); \dRs+ diff --git a/src/test/regress/sql/subscription.sql b/src/test/regress/sql/subscription.sql index 4425fafc46..ed148e4bd4 100644 --- a/src/test/regress/sql/subscription.sql +++ b/src/test/regress/sql/subscription.sql @@ -156,7 +156,7 @@ ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE); DROP SUBSCRIPTION regress_testsub; --- fail - streaming must be boolean +-- fail - streaming must be boolean or 'parallel' CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUBLICATION testpub WITH (connect = false, streaming = foo); -- now it works @@ -164,6 +164,10 @@ CREATE SUBSCRIPTION regress_testsub CONNECTION 'dbname=regress_doesnotexist' PUB \dRs+ +ALTER SUBSCRIPTION regress_testsub SET (streaming = parallel); + +\dRs+ + ALTER SUBSCRIPTION regress_testsub SET (streaming = false); ALTER SUBSCRIPTION regress_testsub SET (slot_name = NONE); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 5b3b305963..d205aed082 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1471,6 +1471,7 @@ LogicalRepRelId LogicalRepRelMapEntry LogicalRepRelation LogicalRepRollbackPreparedTxnData +LogicalRepStreamAbortData LogicalRepTupleData LogicalRepTyp LogicalRepWorker @@ -1662,6 +1663,9 @@ OverrideStackEntry OverridingKind PACE_HEADER PACL +ParallelApplyWorkerEntry +ParallelApplyWorkerInfo +ParallelApplyWorkerShared PATH PBOOL PCtxtHandle @@ -2783,6 +2787,7 @@ TransactionStmtKind TransformInfo TransformJsonStringValuesState TransitionCaptureState +TransApplyAction TrgmArc TrgmArcInfo TrgmBound -- 2.23.0.windows.1