Skip to content

Improve the failover efficiency #362

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
git-hulk merged 1 commit into from
Oct 12, 2025
Merged

Improve the failover efficiency #362

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 14 additions & 10 deletions controller/cluster.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,27 +138,30 @@ func (c *ClusterChecker) increaseFailureCount(shardIndex int, node store.Node) i
}

log := logger.Get().With(
zap.String("cluster_name", c.clusterName),
zap.String("id", node.ID()),
zap.Bool("is_master", node.IsMaster()),
zap.String("addr", node.Addr()))
if count%c.options.maxFailureCount == 0 {
if count%c.options.maxFailureCount == 0 || count > c.options.maxFailureCount {
cluster, err := c.clusterStore.GetCluster(c.ctx, c.namespace, c.clusterName)
if err != nil {
log.Error("Failed to get the clusterName info", zap.Error(err))
log.Error("Failed to get the cluster info", zap.Error(err))
return count
}
newMasterID, err := cluster.PromoteNewMaster(c.ctx, shardIndex, node.ID(), "")
if err == nil {
// the node is normal if it can be elected as the new master,
// because it requires the node is healthy.
c.resetFailureCount(newMasterID)
err = c.clusterStore.UpdateCluster(c.ctx, c.namespace, cluster)
}
if err != nil {
log.Error("Failed to promote the new master", zap.Error(err))
} else {
log.With(zap.String("new_master_id", newMasterID)).Info("Promote the new master")
return count
}
err = c.clusterStore.UpdateCluster(c.ctx, c.namespace, cluster)
if err != nil {
log.Error("Failed to update the cluster", zap.Error(err))
return count
}
// the node is normal if it can be elected as the new master,
// because it requires the node is healthy.
c.resetFailureCount(newMasterID)
log.With(zap.String("new_master_id", newMasterID)).Info("Promote the new master")
}
return count
}
Expand Down Expand Up @@ -216,6 +219,7 @@ func (c *ClusterChecker) parallelProbeNodes(ctx context.Context, cluster *store.
go func(shardIdx int, n store.Node) {
defer wg.Done()
log := logger.Get().With(
zap.String("cluster_name", c.clusterName),
zap.String("id", n.ID()),
zap.Bool("is_master", n.IsMaster()),
zap.String("addr", n.Addr()),
Expand Down
2 changes: 1 addition & 1 deletion store/cluster_node.go
100644 → 100755
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ const (
dialTimeout = 3200 * time.Millisecond
readTimeout = 3 * time.Second
writeTimeout = 3 * time.Second
minIdleConns = 3
minIdleConns = 10
)

var (
Expand Down
Loading