milvus-io
/
milvus
mirror of https://github.com/milvus-io/milvus.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

enhance: avoid the coexistence of the old coordinator and the new node/proxy (#35760) 

issue: #35719
pr: #35720 
In standalone mode, block the start process until the new coordinator is
active to avoid the coexistence of the old coordinator and the new
node/proxy
1. In the start/restart process, the new coordinator will become active
immediately and will not be blocked
2. In the rolling upgrade process, the new coordinator will not be
active until the old coordinator is down, and it will be blocked

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
pull/35817/head
wei liu 2024-08-29 12:33:01 +08:00 committed by GitHub
parent 8928c9d570
commit 50ec3dd4db
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 29 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
cmd/roles/roles.go
View File

@ -415,6 +415,35 @@ func (mr *MilvusRoles) Run() {
componentMap[typeutil.QueryCoordRole] = queryCoord
}
waitCoordBecomeHealthy := func() {
for {
select {
case <-ctx.Done():
log.Info("wait all coord become healthy loop quit")
return
default:
rcState := rootCoord.Health(ctx)
dcState := dataCoord.Health(ctx)
icState := indexCoord.Health(ctx)
qcState := queryCoord.Health(ctx)
if rcState == commonpb.StateCode_Healthy && dcState == commonpb.StateCode_Healthy && icState == commonpb.StateCode_Healthy && qcState == commonpb.StateCode_Healthy {
log.Info("all coord become healthy")
return
}
log.Info("wait all coord become healthy", zap.String("rootCoord", rcState.String()), zap.String("dataCoord", dcState.String()), zap.String("indexCoord", icState.String()), zap.String("queryCoord", qcState.String()))
time.Sleep(time.Second)
}
}
}
// In standalone mode, block the start process until the new coordinator is active to avoid the coexistence of the old coordinator and the new node/proxy
// 1. In the start/restart process, the new coordinator will become active immediately and will not be blocked
// 2. In the rolling upgrade process, the new coordinator will not be active until the old coordinator is down, and it will be blocked
if mr.Local {
waitCoordBecomeHealthy()
}
if mr.EnableQueryNode {
queryNode = mr.runQueryNode(ctx, local, &wg)
componentMap[typeutil.QueryNodeRole] = queryNode