From 919b99d8ae45fe6646d4e3447922aca7f01e838c Mon Sep 17 00:00:00 2001 From: wangw Date: Thu, 21 Apr 2022 09:20:52 +0800 Subject: [PATCH v2] 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. 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 | 90 ++++++++++++++++++++- src/backend/replication/pgoutput/pgoutput.c | 6 ++ src/backend/replication/walsender.c | 39 ++++++++- src/include/replication/logical.h | 5 ++ 4 files changed, 134 insertions(+), 6 deletions(-) diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index d536a5f3ba..514e04a088 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -649,15 +649,38 @@ 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 not published. */ void OutputPluginUpdateProgress(struct LogicalDecodingContext *ctx) { + static int changes_count = 0; + if (!ctx->update_progress) return; - ctx->update_progress(ctx, ctx->write_location, ctx->write_xid); + /* + * 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); + changes_count = 0; + } } /* @@ -725,6 +748,9 @@ startup_cb_wrapper(LogicalDecodingContext *ctx, OutputPluginOptions *opt, bool i /* set output state */ ctx->accept_writes = false; + /* set lsn state */ + ctx->end_xact = false; + /* do the actual work: call callback */ ctx->callbacks.startup_cb(ctx, opt, is_init); @@ -752,6 +778,9 @@ shutdown_cb_wrapper(LogicalDecodingContext *ctx) /* set output state */ ctx->accept_writes = false; + /* set lsn state */ + ctx->end_xact = false; + /* do the actual work: call callback */ ctx->callbacks.shutdown_cb(ctx); @@ -787,6 +816,9 @@ begin_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn) ctx->write_xid = txn->xid; ctx->write_location = txn->first_lsn; + /* set lsn state */ + ctx->end_xact = false; + /* do the actual work: call callback */ ctx->callbacks.begin_cb(ctx, txn); @@ -818,6 +850,9 @@ commit_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; /* points to the end of the record */ + /* set lsn state */ + ctx->end_xact = true; + /* do the actual work: call callback */ ctx->callbacks.commit_cb(ctx, txn, commit_lsn); @@ -858,6 +893,9 @@ begin_prepare_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn) ctx->write_xid = txn->xid; ctx->write_location = txn->first_lsn; + /* set lsn state */ + ctx->end_xact = false; + /* * If the plugin supports two-phase commits then begin prepare callback is * mandatory @@ -902,6 +940,9 @@ prepare_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; /* points to the end of the record */ + /* set lsn state */ + ctx->end_xact = true; + /* * If the plugin supports two-phase commits then prepare callback is * mandatory @@ -946,6 +987,9 @@ commit_prepared_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; /* points to the end of the record */ + /* set lsn state */ + ctx->end_xact = true; + /* * If the plugin support two-phase commits then commit prepared callback * is mandatory @@ -991,6 +1035,9 @@ rollback_prepared_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; /* points to the end of the record */ + /* set lsn state */ + ctx->end_xact = true; + /* * If the plugin support two-phase commits then rollback prepared callback * is mandatory @@ -1040,6 +1087,9 @@ change_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = change->lsn; + /* set lsn state */ + ctx->end_xact = false; + ctx->callbacks.change_cb(ctx, txn, relation, change); /* Pop the error context stack */ @@ -1080,6 +1130,9 @@ truncate_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = change->lsn; + /* set lsn state */ + ctx->end_xact = false; + ctx->callbacks.truncate_cb(ctx, txn, nrelations, relations, change); /* Pop the error context stack */ @@ -1108,6 +1161,9 @@ filter_prepare_cb_wrapper(LogicalDecodingContext *ctx, TransactionId xid, /* set output state */ ctx->accept_writes = false; + /* set lsn state */ + ctx->end_xact = false; + /* do the actual work: call callback */ ret = ctx->callbacks.filter_prepare_cb(ctx, xid, gid); @@ -1138,6 +1194,9 @@ filter_by_origin_cb_wrapper(LogicalDecodingContext *ctx, RepOriginId origin_id) /* set output state */ ctx->accept_writes = false; + /* set lsn state */ + ctx->end_xact = false; + /* do the actual work: call callback */ ret = ctx->callbacks.filter_by_origin_cb(ctx, origin_id); @@ -1175,6 +1234,9 @@ message_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn != NULL ? txn->xid : InvalidTransactionId; ctx->write_location = message_lsn; + /* set lsn state */ + ctx->end_xact = false; + /* do the actual work: call callback */ ctx->callbacks.message_cb(ctx, txn, message_lsn, transactional, prefix, message_size, message); @@ -1217,6 +1279,9 @@ stream_start_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = first_lsn; + /* set lsn state */ + ctx->end_xact = false; + /* in streaming mode, stream_start_cb is required */ if (ctx->callbacks.stream_start_cb == NULL) ereport(ERROR, @@ -1264,6 +1329,9 @@ stream_stop_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = last_lsn; + /* set lsn state */ + ctx->end_xact = false; + /* in streaming mode, stream_stop_cb is required */ if (ctx->callbacks.stream_stop_cb == NULL) ereport(ERROR, @@ -1304,6 +1372,9 @@ stream_abort_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn->xid; ctx->write_location = abort_lsn; + /* set lsn state */ + ctx->end_xact = true; + /* in streaming mode, stream_abort_cb is required */ if (ctx->callbacks.stream_abort_cb == NULL) ereport(ERROR, @@ -1348,6 +1419,9 @@ stream_prepare_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; + /* set lsn state */ + ctx->end_xact = true; + /* in streaming mode with two-phase commits, stream_prepare_cb is required */ if (ctx->callbacks.stream_prepare_cb == NULL) ereport(ERROR, @@ -1388,6 +1462,9 @@ stream_commit_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn->xid; ctx->write_location = txn->end_lsn; + /* set lsn state */ + ctx->end_xact = true; + /* in streaming mode, stream_commit_cb is required */ if (ctx->callbacks.stream_commit_cb == NULL) ereport(ERROR, @@ -1435,6 +1512,9 @@ stream_change_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = change->lsn; + /* set lsn state */ + ctx->end_xact = false; + /* in streaming mode, stream_change_cb is required */ if (ctx->callbacks.stream_change_cb == NULL) ereport(ERROR, @@ -1480,6 +1560,9 @@ stream_message_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, ctx->write_xid = txn != NULL ? txn->xid : InvalidTransactionId; ctx->write_location = message_lsn; + /* set lsn state */ + ctx->end_xact = false; + /* do the actual work: call callback */ ctx->callbacks.stream_message_cb(ctx, txn, message_lsn, transactional, prefix, message_size, message); @@ -1527,6 +1610,9 @@ stream_truncate_cb_wrapper(ReorderBuffer *cache, ReorderBufferTXN *txn, */ ctx->write_location = change->lsn; + /* set lsn state */ + 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 2ea540ce4d..31b585a6fa 100644 --- a/src/backend/replication/pgoutput/pgoutput.c +++ b/src/backend/replication/pgoutput/pgoutput.c @@ -535,6 +535,8 @@ pgoutput_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, TransactionId xid = InvalidTransactionId; Relation ancestor = NULL; + OutputPluginUpdateProgress(ctx); + if (!is_publishable_relation(relation)) return; @@ -677,6 +679,8 @@ pgoutput_truncate(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Oid *relids; TransactionId xid = InvalidTransactionId; + OutputPluginUpdateProgress(ctx); + /* Remember the xid for the change in streaming mode. See pgoutput_change. */ if (in_streaming) xid = change->txn->xid; @@ -735,6 +739,8 @@ pgoutput_message(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, PGOutputData *data = (PGOutputData *) ctx->output_plugin_private; TransactionId xid = InvalidTransactionId; + OutputPluginUpdateProgress(ctx); + if (!data->messages) return; diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index 3b245c619f..12d5347b30 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -240,6 +240,7 @@ static void ProcessStandbyMessage(void); static void ProcessStandbyReplyMessage(void); static void ProcessStandbyHSFeedbackMessage(void); static void ProcessRepliesIfAny(void); +static void ProcessPendingWrites(void); static void WalSndKeepalive(bool requestReply); static void WalSndKeepaliveIfNecessary(void); static void WalSndCheckTimeOut(void); @@ -1288,6 +1289,16 @@ WalSndWriteData(LogicalDecodingContext *ctx, XLogRecPtr lsn, TransactionId xid, } /* If we have pending write here, go to slow path */ + ProcessPendingWrites(); +} + +/* + * Wait until there is no pending write. Also process replies from the other + * side and check timeouts during that. + */ +static void +ProcessPendingWrites(void) +{ for (;;) { long sleeptime; @@ -1336,24 +1347,44 @@ WalSndWriteData(LogicalDecodingContext *ctx, XLogRecPtr lsn, TransactionId xid, * LogicalDecodingContext 'update_progress' callback. * * Write the current position to the lag tracker (see XLogSendPhysical). + * + * In logical replication, if too many changes are processed then try to send a + * keepalive message. It might avoid a timeout in the subscriber. */ static void WalSndUpdateProgress(LogicalDecodingContext *ctx, XLogRecPtr lsn, TransactionId xid) { static TimestampTz sendTime = 0; TimestampTz now = GetCurrentTimestamp(); + 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, + if (end_xact && TimestampDifferenceExceeds(sendTime, now, WALSND_LOGICAL_LAG_TRACK_INTERVAL_MS)) - return; + { + LagTrackerWrite(lsn, now); + sendTime = now; + } - LagTrackerWrite(lsn, now); - sendTime = now; + /* + * 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 (!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 af551d6f4e..8f8ff92ec5 100644 --- a/src/include/replication/logical.h +++ b/src/include/replication/logical.h @@ -49,6 +49,11 @@ typedef struct LogicalDecodingContext */ bool fast_forward; + /* + * Is the end of transaction LSN? + */ + bool end_xact; + OutputPluginCallbacks callbacks; OutputPluginOptions options; -- 2.23.0.windows.1