From dddfb8efda84ea981315deb529bb0c351d69ee02 Mon Sep 17 00:00:00 2001 From: Amit Kapila Date: Thu, 28 Apr 2022 15:19:01 +0530 Subject: [PATCH v19] Fix the logical replication timeout during large transactions. The problem is that we don't send keep-alive messages for a long time while processing large transactions during logical replication where we don't send any data of such transactions. This can happen when the table modified in the transaction is not published or because all the changes got filtered. We do try to send the keep_alive if necessary at the end of the transaction (via WalSndWriteData()) but by that time the subscriber-side can timeout and exit. To fix this we try to send the keepalive message if required after processing certain threshold of changes. --- src/backend/replication/logical/logical.c | 57 +++++++++++++++++++-- src/backend/replication/pgoutput/pgoutput.c | 6 +++ src/backend/replication/walsender.c | 24 +++++++-- src/include/replication/logical.h | 2 + 4 files changed, 83 insertions(+), 6 deletions(-) diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 788769dd73..985838fc4c 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -669,17 +669,41 @@ OutputPluginWrite(struct LogicalDecodingContext *ctx, bool last_write) } /* - * Update progress tracking (if supported). + * Update progress tracking and try to send a keepalive message (if supported). + * + * For a large transaction, if we don't send any change to the downstream for a + * long time (exceeds the wal_receiver_timeout of standby) then it can timeout. + * This can happen when all or most of the changes are either not published or + * got filtered out. */ void OutputPluginUpdateProgress(struct LogicalDecodingContext *ctx, bool skipped_xact) { + static int changes_count = 0; + if (!ctx->update_progress) return; - ctx->update_progress(ctx, ctx->write_location, ctx->write_xid, - skipped_xact); + /* + * We don't want to try sending a keepalive message after processing each + * change as that can have overhead. Tests revealed that there is no + * noticeable overhead in doing it after continuously processing 100 or so + * changes. + */ +#define CHANGES_THRESHOLD 100 + + /* + * If we are at the end of transaction LSN, update progress tracking. + * Otherwise, after continuously processing CHANGES_THRESHOLD changes, we + * try to send a keepalive message if required. + */ + if (ctx->end_xact || ++changes_count >= CHANGES_THRESHOLD) + { + ctx->update_progress(ctx, ctx->write_location, ctx->write_xid, + skipped_xact); + changes_count = 0; + } } /* @@ -746,6 +770,7 @@ startup_cb_wrapper(LogicalDecodingContext *ctx, OutputPluginOptions *opt, bool i /* set output state */ ctx->accept_writes = false; + ctx->end_xact = false; /* do the actual work: call callback */ ctx->callbacks.startup_cb(ctx, opt, is_init); @@ -773,6 +798,7 @@ shutdown_cb_wrapper(LogicalDecodingContext *ctx) /* set output state */ ctx->accept_writes = false; + ctx->end_xact = false; /* do the actual work: call callback */ ctx->callbacks.shutdown_cb(ctx); @@ -808,6 +834,7 @@ begin_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn) ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = txn->first_lsn; + ctx->end_xact = false; /* do the actual work: call callback */ ctx->callbacks.begin_cb(ctx, txn); @@ -839,6 +866,7 @@ commit_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; /* points to the end of the record */ + ctx->end_xact = true; /* do the actual work: call callback */ ctx->callbacks.commit_cb(ctx, txn, commit_lsn); @@ -879,6 +907,7 @@ begin_prepare_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn) ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = txn->first_lsn; + ctx->end_xact = false; /* * If the plugin supports two-phase commits then begin prepare callback is @@ -923,6 +952,7 @@ prepare_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; /* points to the end of the record */ + ctx->end_xact = true; /* * If the plugin supports two-phase commits then prepare callback is @@ -967,6 +997,7 @@ commit_prepared_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; /* points to the end of the record */ + ctx->end_xact = true; /* * If the plugin support two-phase commits then commit prepared callback @@ -1012,6 +1043,7 @@ rollback_prepared_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; /* points to the end of the record */ + ctx->end_xact = true; /* * If the plugin support two-phase commits then rollback prepared callback @@ -1062,6 +1094,8 @@ change_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = change->lsn; + ctx->end_xact = false; + ctx->callbacks.change_cb(ctx, txn, relation, change); /* Pop the error context stack */ @@ -1102,6 +1136,8 @@ truncate_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = change->lsn; + ctx->end_xact = false; + ctx->callbacks.truncate_cb(ctx, txn, nrelations, relations, change); /* Pop the error context stack */ @@ -1129,6 +1165,7 @@ filter_prepare_cb_wrapper(LogicalDecodingContext *ctx, TransactionId xid, /* set output state */ ctx->accept_writes = false; + ctx->end_xact = false; /* do the actual work: call callback */ ret = ctx->callbacks.filter_prepare_cb(ctx, xid, gid); @@ -1159,6 +1196,7 @@ filter_by_origin_cb_wrapper(LogicalDecodingContext *ctx, RepOriginId origin_id) /* set output state */ ctx->accept_writes = false; + ctx->end_xact = false; /* do the actual work: call callback */ ret = ctx->callbacks.filter_by_origin_cb(ctx, origin_id); @@ -1196,6 +1234,7 @@ message_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn != NULL ? txn->xid : InvalidTransactionId; ctx->write_location = message_lsn; + ctx->end_xact = false; /* do the actual work: call callback */ ctx->callbacks.message_cb(ctx, txn, message_lsn, transactional, prefix, @@ -1239,6 +1278,8 @@ stream_start_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = first_lsn; + ctx->end_xact = false; + /* in streaming mode, stream_start_cb is required */ if (ctx->callbacks.stream_start_cb == NULL) ereport(ERROR, @@ -1286,6 +1327,8 @@ stream_stop_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = last_lsn; + ctx->end_xact = false; + /* in streaming mode, stream_stop_cb is required */ if (ctx->callbacks.stream_stop_cb == NULL) ereport(ERROR, @@ -1325,6 +1368,7 @@ stream_abort_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = abort_lsn; + ctx->end_xact = true; /* in streaming mode, stream_abort_cb is required */ if (ctx->callbacks.stream_abort_cb == NULL) @@ -1369,6 +1413,7 @@ stream_prepare_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; + ctx->end_xact = true; /* in streaming mode with two-phase commits, stream_prepare_cb is required */ if (ctx->callbacks.stream_prepare_cb == NULL) @@ -1409,6 +1454,7 @@ stream_commit_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; + ctx->end_xact = true; /* in streaming mode, stream_commit_cb is required */ if (ctx->callbacks.stream_commit_cb == NULL) @@ -1457,6 +1503,8 @@ stream_change_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = change->lsn; + ctx->end_xact = false; + /* in streaming mode, stream_change_cb is required */ if (ctx->callbacks.stream_change_cb == NULL) ereport(ERROR, @@ -1501,6 +1549,7 @@ stream_message_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->accept_writes = true; ctx->write_xid = txn != NULL ? txn->xid : InvalidTransactionId; ctx->write_location = message_lsn; + ctx->end_xact = false; /* do the actual work: call callback */ ctx->callbacks.stream_message_cb(ctx, txn, message_lsn, transactional, prefix, @@ -1549,6 +1598,8 @@ stream_truncate_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = change->lsn; + ctx->end_xact = false; + ctx->callbacks.stream_truncate_cb(ctx, txn, nrelations, relations, change); /* Pop the error context stack */ diff --git a/src/backend/replication/pgoutput/pgoutput.c b/src/backend/replication/pgoutput/pgoutput.c index b197bfd565..4e2531601f 100644 --- a/src/backend/replication/pgoutput/pgoutput.c +++ b/src/backend/replication/pgoutput/pgoutput.c @@ -1360,6 +1360,8 @@ pgoutput_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, TupleTableSlot *old_slot = NULL; TupleTableSlot *new_slot = NULL; + OutputPluginUpdateProgress(ctx, false); + if (!is_publishable_relation(relation)) return; @@ -1592,6 +1594,8 @@ pgoutput_truncate(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Oid *relids; TransactionId xid = InvalidTransactionId; + OutputPluginUpdateProgress(ctx, false); + /* Remember the xid for the change in streaming mode. See pgoutput_change. */ if (in_streaming) xid = change->txn->xid; @@ -1655,6 +1659,8 @@ pgoutput_message(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, PGOutputData *data = (PGOutputData *) ctx->output_plugin_private; TransactionId xid = InvalidTransactionId; + OutputPluginUpdateProgress(ctx, false); + if (!data->messages) return; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 63a818140b..79fffe849b 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -1482,14 +1482,20 @@ WalSndUpdateProgress(LogicalDecodingContext *ctx, XLogRecPtr lsn, TransactionId { static TimestampTz sendTime = 0; TimestampTz now = GetCurrentTimestamp(); + bool pending_writes = false; + bool end_xact = ctx->end_xact; /* * Track lag no more than once per WALSND_LOGICAL_LAG_TRACK_INTERVAL_MS to * avoid flooding the lag tracker when we commit frequently. + * + * We don't have a mechanism to get the ack for any LSN other than end xact + * LSN from the downstream. So, we track lag only for end of transaction + * LSN. */ #define WALSND_LOGICAL_LAG_TRACK_INTERVAL_MS 1000 - if (TimestampDifferenceExceeds(sendTime, now, - WALSND_LOGICAL_LAG_TRACK_INTERVAL_MS)) + if (end_xact && TimestampDifferenceExceeds(sendTime, now, + WALSND_LOGICAL_LAG_TRACK_INTERVAL_MS)) { LagTrackerWrite(lsn, now); sendTime = now; @@ -1515,8 +1521,20 @@ WalSndUpdateProgress(LogicalDecodingContext *ctx, XLogRecPtr lsn, TransactionId /* If we have pending write here, make sure it's actually flushed */ if (pq_is_send_pending()) - ProcessPendingWrites(); + pending_writes = true; } + + /* + * Process pending writes if any or try to send a keepalive if required. We + * don't need to try sending keep alive messages at the transaction end as + * that will be done at a later point in time. This is required only for + * large transactions where we don't send any changes to the downstream and + * the receiver can timeout due to that. + */ + if (pending_writes || (!end_xact && + now >= TimestampTzPlusMilliseconds(last_reply_timestamp, + wal_sender_timeout / 2))) + ProcessPendingWrites(); } /* diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h index a6ef16ad5b..edadacd589 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -107,6 +107,8 @@ typedef struct LogicalDecodingContext bool prepared_write; XLogRecPtr write_location; TransactionId write_xid; + /* Are we processing the end LSN of a transaction? */ + bool end_xact; } LogicalDecodingContext; -- 2.28.0.windows.1