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

mainlining forage changes #1635

Merged
merged 3 commits into from
Apr 22, 2024
Merged

mainlining forage changes #1635

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
803fcc5
experiment: stop workflow erroring on ES load failure
heavycrystal Apr 17, 2024
cb1a7de
experiment: fix logs
heavycrystal Apr 17, 2024
64c62a8
explicit logging id
heavycrystal Apr 22, 2024
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
16 changes: 11 additions & 5 deletions flow/connectors/connelasticsearch/elasticsearch.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@ func (esc *ElasticsearchConnector) SyncQRepRecords(ctx context.Context, config *
qRecordJsonMap[field.Name] = json.RawMessage(shared.
UnsafeFastStringToReadOnlyBytes(r.Val))
default:
qRecordJsonMap[field.Name] = qRecord[i].Value()
qRecordJsonMap[field.Name] = r.Value()
}
}
qRecordJsonBytes, err := json.Marshal(qRecordJsonMap)
Expand All @@ -159,16 +159,21 @@ func (esc *ElasticsearchConnector) SyncQRepRecords(ctx context.Context, config *
Body: bytes.NewReader(qRecordJsonBytes),

// OnFailure is called for each failed operation, log and let parent handle
OnFailure: func(ctx context.Context, _ esutil.BulkIndexerItem,
OnFailure: func(ctx context.Context, item esutil.BulkIndexerItem,
res esutil.BulkIndexerResponseItem, err error,
) {
bulkIndexMutex.Lock()
defer bulkIndexMutex.Unlock()
if err != nil {
bulkIndexErrors = append(bulkIndexErrors, err)
} else {
causeString := ""
if res.Error.Cause.Type != "" || res.Error.Cause.Reason != "" {
causeString = fmt.Sprintf("(caused by type:%s reason:%s)", res.Error.Cause.Type, res.Error.Cause.Reason)
}
bulkIndexErrors = append(bulkIndexErrors,
fmt.Errorf("%s %s %v", res.Error.Type, res.Error.Reason, res.Error.Cause))
fmt.Errorf("id:%s type:%s reason:%s %s", item.DocumentID, res.Error.Type,
res.Error.Reason, causeString))
}
},
})
Expand All @@ -191,8 +196,9 @@ func (esc *ElasticsearchConnector) SyncQRepRecords(ctx context.Context, config *
}
bulkIndexerHasShutdown = true
if len(bulkIndexErrors) > 0 {
esc.logger.Error("[es] failed to bulk index records", slog.Any("errors", bulkIndexErrors))
return 0, fmt.Errorf("[es] failed to bulk index records: %v", bulkIndexErrors)
for _, err := range bulkIndexErrors {
esc.logger.Error("[es] failed to index record", slog.Any("err", err))
}
}

err = esc.FinishQRepPartition(ctx, partition, config.FlowJobName, startTime)
Expand Down
5 changes: 1 addition & 4 deletions flow/connectors/postgres/qrep.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,10 +123,7 @@ func (c *PostgresConnector) getNumRowsPartitions(
}

// Calculate the number of partitions
numPartitions := totalRows.Int64 / numRowsPerPartition
if totalRows.Int64%numRowsPerPartition != 0 {
numPartitions++
}
numPartitions := shared.DivCeil(totalRows.Int64, numRowsPerPartition)
c.logger.Info(fmt.Sprintf("total rows: %d, num partitions: %d, num rows per partition: %d",
totalRows.Int64, numPartitions, numRowsPerPartition))

Expand Down
Loading