From 1b623c3f227e819efd2c72c67d551c84f6418272 Mon Sep 17 00:00:00 2001 From: Hayato Kuroda Date: Mon, 1 Dec 2025 16:28:38 +0900 Subject: [PATCH v10 2/9] Introduce a shared hash table to store parallelized transactions This hash table is used for ensuring that parallel workers wait until dependent transactions are committed. The shared hash table contains transaction IDs that the leader allocated to parallel workers. The hash entries are inserted with a remote XID when the leader bypasses remote transactions to parallel apply workers. Entries are deleted when parallel workers are committed to corresponding transactions. When the parallel worker tries to wait for other transactions, it checks the hash table for the remote XIDs. The process can go ahead only when entries are removed from the hash. Author: Hou Zhijie Author: Hayato Kuroda --- .../replication/logical/applyparallelworker.c | 100 +++++++++++++++++- .../utils/activity/wait_event_names.txt | 1 + src/include/replication/worker_internal.h | 4 + src/include/storage/lwlocklist.h | 1 + src/tools/pgindent/typedefs.list | 1 + 5 files changed, 106 insertions(+), 1 deletion(-) diff --git a/src/backend/replication/logical/applyparallelworker.c b/src/backend/replication/logical/applyparallelworker.c index af80329c8af..88d78053297 100644 --- a/src/backend/replication/logical/applyparallelworker.c +++ b/src/backend/replication/logical/applyparallelworker.c @@ -221,12 +221,35 @@ typedef struct ParallelApplyWorkerEntry ParallelApplyWorkerInfo *winfo; } ParallelApplyWorkerEntry; +/* an entry in the parallelized_txns shared hash table */ +typedef struct ParallelizedTxnEntry +{ + TransactionId xid; /* Hash key */ +} ParallelizedTxnEntry; + /* * A hash table used to cache the state of streaming transactions being applied * by the parallel apply workers. */ static HTAB *ParallelApplyTxnHash = NULL; +/* + * A hash table used to track the parallelized transactions that could be + * depended on by other transactions. + */ +static dsa_area *parallel_apply_dsa_area = NULL; +static dshash_table *parallelized_txns = NULL; + +/* parameters for the parallelized_txns shared hash table */ +static const dshash_parameters dsh_params = { + sizeof(TransactionId), + sizeof(ParallelizedTxnEntry), + dshash_memcmp, + dshash_memhash, + dshash_memcpy, + LWTRANCHE_PARALLEL_APPLY_DSA +}; + /* * A list (pool) of active parallel apply workers. The information for * the new worker is added to the list after successfully launching it. The @@ -260,6 +283,8 @@ static List *subxactlist = NIL; static void pa_free_worker_info(ParallelApplyWorkerInfo *winfo); static ParallelTransState pa_get_xact_state(ParallelApplyWorkerShared *wshared); static PartialFileSetState pa_get_fileset_state(void); +static void pa_attach_parallelized_txn_hash(dsa_handle *pa_dsa_handle, + dshash_table_handle *pa_dshash_handle); /* * Returns true if it is OK to start a parallel apply worker, false otherwise. @@ -337,6 +362,15 @@ pa_setup_dsm(ParallelApplyWorkerInfo *winfo) shm_mq *mq; Size queue_size = DSM_QUEUE_SIZE; Size error_queue_size = DSM_ERROR_QUEUE_SIZE; + dsa_handle parallel_apply_dsa_handle; + dshash_table_handle parallelized_txns_handle; + + pa_attach_parallelized_txn_hash(¶llel_apply_dsa_handle, + ¶llelized_txns_handle); + + if (parallel_apply_dsa_handle == DSA_HANDLE_INVALID || + parallelized_txns_handle == DSHASH_HANDLE_INVALID) + return false; /* * Estimate how much shared memory we need. @@ -372,6 +406,8 @@ pa_setup_dsm(ParallelApplyWorkerInfo *winfo) pg_atomic_init_u32(&(shared->pending_stream_count), 0); shared->last_commit_end = InvalidXLogRecPtr; shared->fileset_state = FS_EMPTY; + shared->parallel_apply_dsa_handle = parallel_apply_dsa_handle; + shared->parallelized_txns_handle = parallelized_txns_handle; shm_toc_insert(toc, PARALLEL_APPLY_KEY_SHARED, shared); @@ -867,6 +903,8 @@ ParallelApplyWorkerMain(Datum main_arg) shm_mq *mq; shm_mq_handle *mqh; shm_mq_handle *error_mqh; + dsa_handle pa_dsa_handle; + dshash_table_handle pa_dshash_handle; ReplOriginId originid; int worker_slot = DatumGetInt32(main_arg); char originname[NAMEDATALEN]; @@ -953,6 +991,8 @@ ParallelApplyWorkerMain(Datum main_arg) InitializingApplyWorker = false; + pa_attach_parallelized_txn_hash(&pa_dsa_handle, &pa_dshash_handle); + /* Setup replication origin tracking. */ StartTransactionCommand(); ReplicationOriginNameForLogicalRep(MySubscription->oid, InvalidOid, @@ -1648,6 +1688,51 @@ pa_xact_finish(ParallelApplyWorkerInfo *winfo, XLogRecPtr remote_lsn) pa_free_worker(winfo); } +/* + * Attach to the shared hash table for parallelized transactions. + */ +static void +pa_attach_parallelized_txn_hash(dsa_handle *pa_dsa_handle, + dshash_table_handle *pa_dshash_handle) +{ + MemoryContext oldctx; + + if (parallelized_txns) + { + Assert(parallel_apply_dsa_area); + *pa_dsa_handle = dsa_get_handle(parallel_apply_dsa_area); + *pa_dshash_handle = dshash_get_hash_table_handle(parallelized_txns); + return; + } + + /* Be sure any local memory allocated by DSA routines is persistent. */ + oldctx = MemoryContextSwitchTo(ApplyContext); + + if (am_leader_apply_worker()) + { + /* Initialize dynamic shared hash table for last-start times. */ + parallel_apply_dsa_area = dsa_create(LWTRANCHE_PARALLEL_APPLY_DSA); + dsa_pin(parallel_apply_dsa_area); + dsa_pin_mapping(parallel_apply_dsa_area); + parallelized_txns = dshash_create(parallel_apply_dsa_area, &dsh_params, NULL); + + /* Store handles in shared memory for other backends to use. */ + *pa_dsa_handle = dsa_get_handle(parallel_apply_dsa_area); + *pa_dshash_handle = dshash_get_hash_table_handle(parallelized_txns); + } + else if (am_parallel_apply_worker()) + { + /* Attach to existing dynamic shared hash table. */ + parallel_apply_dsa_area = dsa_attach(MyParallelShared->parallel_apply_dsa_handle); + dsa_pin_mapping(parallel_apply_dsa_area); + parallelized_txns = dshash_attach(parallel_apply_dsa_area, &dsh_params, + MyParallelShared->parallelized_txns_handle, + NULL); + } + + MemoryContextSwitchTo(oldctx); +} + /* * Wait for the given transaction to finish. */ @@ -1658,7 +1743,20 @@ pa_wait_for_depended_transaction(TransactionId xid) for (;;) { - /* XXX wait until given transaction is finished */ + ParallelizedTxnEntry *txn_entry; + + txn_entry = dshash_find(parallelized_txns, &xid, false); + + /* The entry is removed only if the transaction is committed */ + if (txn_entry == NULL) + break; + + dshash_release_lock(parallelized_txns, txn_entry); + + pa_lock_transaction(xid, AccessShareLock); + pa_unlock_transaction(xid, AccessShareLock); + + CHECK_FOR_INTERRUPTS(); } elog(DEBUG1, "finish waiting for depended xid %u", xid); diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt index 6be80d2daad..ebb571c5cff 100644 --- a/src/backend/utils/activity/wait_event_names.txt +++ b/src/backend/utils/activity/wait_event_names.txt @@ -412,6 +412,7 @@ XactSLRU "Waiting to access the transaction status SLRU cache." ParallelVacuumDSA "Waiting for parallel vacuum dynamic shared memory allocation." AioUringCompletion "Waiting for another process to complete IO via io_uring." ShmemIndex "Waiting to find or allocate space in shared memory." +ParallelApplyDSA "Waiting for parallel apply dynamic shared memory allocation." # No "ABI_compatibility" region here as WaitEventLWLock has its own C code. diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index ccdb7e104f2..1660f28dd81 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -15,6 +15,7 @@ #include "access/xlogdefs.h" #include "catalog/pg_subscription.h" #include "datatype/timestamp.h" +#include "lib/dshash.h" #include "miscadmin.h" #include "replication/logicalrelation.h" #include "replication/walreceiver.h" @@ -196,6 +197,9 @@ typedef struct ParallelApplyWorkerShared */ PartialFileSetState fileset_state; FileSet fileset; + + dsa_handle parallel_apply_dsa_handle; + dshash_table_handle parallelized_txns_handle; } ParallelApplyWorkerShared; /* diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h index 59ee097977d..df7393e2e7f 100644 --- a/src/include/storage/lwlocklist.h +++ b/src/include/storage/lwlocklist.h @@ -138,3 +138,4 @@ PG_LWLOCKTRANCHE(XACT_SLRU, XactSLRU) PG_LWLOCKTRANCHE(PARALLEL_VACUUM_DSA, ParallelVacuumDSA) PG_LWLOCKTRANCHE(AIO_URING_COMPLETION, AioUringCompletion) PG_LWLOCKTRANCHE(SHMEM_INDEX, ShmemIndex) +PG_LWLOCKTRANCHE(PARALLEL_APPLY_DSA, ParallelApplyDSA) diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index e3c1007abdf..7845daabaed 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2128,6 +2128,7 @@ ParallelHashJoinBatch ParallelHashJoinBatchAccessor ParallelHashJoinState ParallelIndexScanDesc +ParallelizedTxnEntry ParallelSlot ParallelSlotArray ParallelSlotResultHandler -- 2.47.3