From 074d24df1e82b5c794a5da9fb6cda5b77b60b27b Mon Sep 17 00:00:00 2001 From: antirez Date: Wed, 15 May 2019 12:16:43 +0200 Subject: [PATCH] Narrow the effects of PR #6029 to the exact state. CLIENT PAUSE may be used, in other contexts, for a long time making all the slaves time out. Better for now to be more specific about what should disable senidng PINGs. An alternative to that would be to virtually refresh the slave interactions when clients are paused, however for now I went for this more conservative solution. --- src/replication.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/src/replication.c b/src/replication.c index bfe50c92..63a67a06 100644 --- a/src/replication.c +++ b/src/replication.c @@ -30,6 +30,7 @@ #include "server.h" +#include "cluster.h" #include #include @@ -2601,12 +2602,23 @@ void replicationCron(void) { /* First, send PING according to ping_slave_period. */ if ((replication_cron_loops % server.repl_ping_slave_period) == 0 && - listLength(server.slaves) && !clientsArePaused()) + listLength(server.slaves)) { - ping_argv[0] = createStringObject("PING",4); - replicationFeedSlaves(server.slaves, server.slaveseldb, - ping_argv, 1); - decrRefCount(ping_argv[0]); + /* Note that we don't send the PING if the clients are paused during + * a Redis Cluster manual failover: the PING we send will otherwise + * alter the replication offsets of master and slave, and will no longer + * match the one stored into 'mf_master_offset' state. */ + int manual_failover_in_progress = + server.cluster_enabled && + server.cluster->mf_end && + clientsArePaused(); + + if (!manual_failover_in_progress) { + ping_argv[0] = createStringObject("PING",4); + replicationFeedSlaves(server.slaves, server.slaveseldb, + ping_argv, 1); + decrRefCount(ping_argv[0]); + } } /* Second, send a newline to all the slaves in pre-synchronization