You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@kudu.apache.org by al...@apache.org on 2018/09/10 20:37:40 UTC
[2/2] kudu git commit: [catalog_manager] updated warning message
[catalog_manager] updated warning message
Updated the warning message logged upon a failure to allocate
an extra replica for a tablet: don't call the new replica a replacement
because AsyncAddReplicaTask is used not only in re-replication scenarios,
but in replica movement scenarios as well.
Also, do not mention unsetting --raft_prepare_replacement_before_eviction
since the 3-2-3 replica management scheme is deprecated at this point
and is no better in the case of a whole tablet server failure.
This is a follow-up to 1fcce42200d22597e7e69baa7232b4de93d5e2a3.
There are no functional changes in this patch.
Change-Id: Ifb6905dc1870acd34553187594008ba34781ce6d
Reviewed-on: http://gerrit.cloudera.org:8080/11402
Tested-by: Kudu Jenkins
Reviewed-by: Adar Dembo <ad...@cloudera.com>
Project: http://git-wip-us.apache.org/repos/asf/kudu/repo
Commit: http://git-wip-us.apache.org/repos/asf/kudu/commit/953a09b8
Tree: http://git-wip-us.apache.org/repos/asf/kudu/tree/953a09b8
Diff: http://git-wip-us.apache.org/repos/asf/kudu/diff/953a09b8
Branch: refs/heads/master
Commit: 953a09b826b4a0ccd379480f7aac441186f8bacb
Parents: e357051
Author: Alexey Serbin <as...@cloudera.com>
Authored: Fri Sep 7 16:35:33 2018 -0700
Committer: Alexey Serbin <as...@cloudera.com>
Committed: Mon Sep 10 20:35:04 2018 +0000
----------------------------------------------------------------------
src/kudu/master/catalog_manager.cc | 27 +++++++++++----------------
1 file changed, 11 insertions(+), 16 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/kudu/blob/953a09b8/src/kudu/master/catalog_manager.cc
----------------------------------------------------------------------
diff --git a/src/kudu/master/catalog_manager.cc b/src/kudu/master/catalog_manager.cc
index 0dd8003..27e9722 100644
--- a/src/kudu/master/catalog_manager.cc
+++ b/src/kudu/master/catalog_manager.cc
@@ -3475,14 +3475,14 @@ bool AsyncAddReplicaTask::SendRequest(int attempt) {
auto replacement_replica = SelectReplica(ts_descs, excluded, rng_);
if (PREDICT_FALSE(!replacement_replica)) {
- auto msg = Substitute("no candidate replacement replica found for tablet $0",
+ auto msg = Substitute("no extra replica candidate found for tablet $0",
tablet_->ToString());
- // Check whether it's a situation when a replacement replica cannot be found
+ // Check whether it's a situation when an extra replica cannot be found
// due to an inconsistency in cluster configuration. If the tablet has the
- // replication factor of N, and the cluster is configured to use N->(N+1)->N
- // replication scheme (see --raft_prepare_replacement_before_eviction flag),
- // at least N+1 tablet servers should be registered to find a place
- // for a replacement replica.
+ // replication factor of N, and the cluster is using the N->(N+1)->N
+ // replica management scheme (see --raft_prepare_replacement_before_eviction
+ // flag), at least N+1 tablet servers should be registered to find a place
+ // for an extra replica.
TSDescriptorVector all_descriptors;
master_->ts_manager()->GetAllDescriptors(&all_descriptors);
const auto num_tservers_registered = all_descriptors.size();
@@ -3492,21 +3492,16 @@ bool AsyncAddReplicaTask::SendRequest(int attempt) {
TableMetadataLock l(tablet_->table().get(), LockMode::READ);
replication_factor = tablet_->table()->metadata().state().pb.num_replicas();
}
- DCHECK_GE(replication_factor, 0);
+ DCHECK_GE(replication_factor, 1);
const auto num_tservers_needed =
FLAGS_raft_prepare_replacement_before_eviction ? replication_factor + 1
: replication_factor;
if (num_tservers_registered < num_tservers_needed) {
msg += Substitute(
- "; the total number of registered tablet servers ($0) does not allow "
- "for replacement of the failed replica: at least $1 tablet servers "
- "are required", num_tservers_registered, num_tservers_needed);
- if (FLAGS_raft_prepare_replacement_before_eviction &&
- num_tservers_registered == replication_factor) {
- msg +=
- "; consider either adding an additional tablet server or running "
- "the cluster with --raft_prepare_replacement_before_eviction=false";
- }
+ ": the total number of registered tablet servers ($0) does not allow "
+ "for adding an extra replica; consider bringing up more "
+ "to have at least $1 tablet servers up and running",
+ num_tservers_registered, num_tservers_needed);
}
KLOG_EVERY_N_SECS(WARNING, 60) << LogPrefix() << msg;
return false;