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

Jump to bottom

lightning: auto resume from recoverable error #33510

Merged
merged 7 commits into from
Mar 29, 2022
Merged

lightning: auto resume from recoverable error #33510

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b2b1c3e
lightning: auto resume from recoverable error
buchuitoudegou Mar 28, 2022
5adb540
lightning: recover from more recoverable error
buchuitoudegou Mar 28, 2022
696fb10
add ut
buchuitoudegou Mar 29, 2022
cf4ee79
Merge branch 'master' into lightning-ignore-connerr
buchuitoudegou Mar 29, 2022
459b1e3
Merge branch 'master' into lightning-ignore-connerr
buchuitoudegou Mar 29, 2022
d216f58
simplify branch
buchuitoudegou Mar 29, 2022
7df870d
Merge branch 'master' into lightning-ignore-connerr
ti-chi-bot Mar 29, 2022
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
9 changes: 6 additions & 3 deletions br/pkg/lightning/restore/restore.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -972,11 +972,14 @@ func (rc *Controller) saveStatusCheckpoint(ctx context.Context, tableName string
switch {
sleepymole marked this conversation as resolved.
Show resolved Hide resolved
case err == nil:
break
case !common.IsContextCanceledError(err):
case utils.IsRetryableError(err), utils.MessageIsRetryableStorageError(err.Error()), common.IsContextCanceledError(err):
// recoverable error, should not be recorded in checkpoint
// which will prevent lightning from automatically recovering
return nil
default:
// unrecoverable error
merger.SetInvalid()
rc.errorSummaries.record(tableName, err, statusIfSucceed)
default:
return nil
}

if engineID == checkpoints.WholeTableEngineID {
Expand Down
13 changes: 12 additions & 1 deletion br/pkg/lightning/restore/table_restore_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ import (
"context"
"encoding/json"
"fmt"
"net"
"net/http"
"net/http/httptest"
"os"
Expand Down Expand Up @@ -989,8 +990,18 @@ func (s *tableRestoreSuite) TestSaveStatusCheckpoint() {
rc.checkpointsWg.Add(1)
go rc.listenCheckpointUpdates()

rc.errorSummaries = makeErrorSummaries(log.L())

err := rc.saveStatusCheckpoint(context.Background(), common.UniqueTable("test", "tbl"), indexEngineID, errors.New("connection refused"), checkpoints.CheckpointStatusImported)
require.NoError(s.T(), err)
require.Equal(s.T(), 0, len(rc.errorSummaries.summary))

err = rc.saveStatusCheckpoint(context.Background(), common.UniqueTable("test", "tbl"), indexEngineID, &net.DNSError{IsTimeout: true}, checkpoints.CheckpointStatusImported)
require.NoError(s.T(), err)
require.Equal(s.T(), 0, len(rc.errorSummaries.summary))

start := time.Now()
err := rc.saveStatusCheckpoint(context.Background(), common.UniqueTable("test", "tbl"), indexEngineID, nil, checkpoints.CheckpointStatusImported)
err = rc.saveStatusCheckpoint(context.Background(), common.UniqueTable("test", "tbl"), indexEngineID, nil, checkpoints.CheckpointStatusImported)
require.NoError(s.T(), err)
elapsed := time.Since(start)
require.GreaterOrEqual(s.T(), elapsed, time.Millisecond*100)
Expand Down