Skip to content
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

puller: fix retry logic when check store version failed (#11903) #11929

Merged
merged 3 commits into from
Jan 19, 2025
Merged

puller: fix retry logic when check store version failed (#11903) #11929

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f306163
This is an automated cherry-pick of #11903
lidezhu Dec 24, 2024
44fd0bc
wip
lidezhu Dec 25, 2024
a179ba0
remove
lidezhu Jan 19, 2025
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
22 changes: 20 additions & 2 deletions cdc/kv/client.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,7 @@ var (
metricFeedDuplicateRequestCounter = eventFeedErrorCounter.WithLabelValues("DuplicateRequest")
metricFeedUnknownErrorCounter = eventFeedErrorCounter.WithLabelValues("Unknown")
metricFeedRPCCtxUnavailable = eventFeedErrorCounter.WithLabelValues("RPCCtxUnavailable")
metricGetStoreErr = eventFeedErrorCounter.WithLabelValues("GetStoreErr")
metricStoreSendRequestErr = eventFeedErrorCounter.WithLabelValues("SendRequestToStore")
metricConnectToStoreErr = eventFeedErrorCounter.WithLabelValues("ConnectToStore")
)
Expand Down Expand Up @@ -685,8 +686,17 @@ func (s *eventFeedSession) requestRegionToStore(
time.Sleep(delay)
}
bo := tikv.NewBackoffer(ctx, tikvRequestMaxBackoff)
s.client.regionCache.OnSendFail(bo, rpcCtx, regionScheduleReload, err)
errInfo := newRegionErrorInfo(sri, &connectToStoreErr{})
var regionErr error
var scheduleReload bool
if cerror.Is(err, cerror.ErrGetAllStoresFailed) {
regionErr = &getStoreErr{}
scheduleReload = true
} else {
regionErr = &connectToStoreErr{}
scheduleReload = regionScheduleReload
}
s.client.regionCache.OnSendFail(bo, rpcCtx, scheduleReload, err)
errInfo := newRegionErrorInfo(sri, regionErr)
s.onRegionFail(ctx, errInfo)
continue
}
Expand Down Expand Up @@ -961,6 +971,10 @@ func (s *eventFeedSession) handleError(ctx context.Context, errInfo regionErrorI
metricConnectToStoreErr.Inc()
case *sendRequestToStoreErr:
metricStoreSendRequestErr.Inc()
case *getStoreErr:
metricGetStoreErr.Inc()
s.scheduleDivideRegionAndRequest(ctx, errInfo.span)
return nil
default:
//[TODO] Move all OnSendFail logic here
// We expect some unknown error to trigger RegionCache recheck its store state and change leader to peer to
Expand Down Expand Up @@ -1514,3 +1528,7 @@ func (e *connectToStoreErr) Error() string { return "connect to store error" }
type sendRequestToStoreErr struct{}

func (e *sendRequestToStoreErr) Error() string { return "send request to store error" }

type getStoreErr struct{}

func (e *getStoreErr) Error() string { return "get store error" }
Loading