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

dedupe index on all the queries for a table instead of query batches #3338

Merged
merged 2 commits into from
Feb 16, 2021
Merged

dedupe index on all the queries for a table instead of query batches #3338

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
426b150
dedupe index on all the queries for a table instead query batches
sandeepsukhani Feb 14, 2021
ca8cbef
convert sync.Mutex to sync.RWMutex in deduper to allow concurrent che…
sandeepsukhani Feb 15, 2021
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
Next Next commit
dedupe index on all the queries for a table instead query batches
  • Loading branch information
@sandeepsukhani
sandeepsukhani committed Feb 15, 2021
commit 426b1506eaaecb222818bb0d06a55c7170bace0f
6 changes: 1 addition & 5 deletions pkg/storage/stores/shipper/downloads/table.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -282,8 +282,6 @@ func (t *Table) MultiQueries(ctx context.Context, queries []chunk.IndexQuery, ca

level.Debug(log).Log("table-name", t.name, "query-count", len(queries))

id := shipper_util.NewIndexDeduper(callback)

for name, db := range t.dbs {
err := db.View(func(tx *bbolt.Tx) error {
bucket := tx.Bucket(bucketName)
Expand All @@ -292,9 +290,7 @@ func (t *Table) MultiQueries(ctx context.Context, queries []chunk.IndexQuery, ca
}

for _, query := range queries {
if err := t.boltDBIndexClient.QueryWithCursor(ctx, bucket.Cursor(), query, func(query chunk.IndexQuery, batch chunk.ReadBatch) (shouldContinue bool) {
return id.Callback(query, batch)
}); err != nil {
if err := t.boltDBIndexClient.QueryWithCursor(ctx, bucket.Cursor(), query, callback); err != nil {
return err
}
}
Expand Down
6 changes: 1 addition & 5 deletions pkg/storage/stores/shipper/uploads/table.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -189,8 +189,6 @@ func (lt *Table) MultiQueries(ctx context.Context, queries []chunk.IndexQuery, c
lt.dbSnapshotsMtx.RLock()
defer lt.dbSnapshotsMtx.RUnlock()

id := shipper_util.NewIndexDeduper(callback)

for _, db := range lt.dbSnapshots {
err := db.boltdb.View(func(tx *bbolt.Tx) error {
bucket := tx.Bucket(bucketName)
Expand All @@ -199,9 +197,7 @@ func (lt *Table) MultiQueries(ctx context.Context, queries []chunk.IndexQuery, c
}

for _, query := range queries {
if err := lt.boltdbIndexClient.QueryWithCursor(ctx, bucket.Cursor(), query, func(query chunk.IndexQuery, batch chunk.ReadBatch) (shouldContinue bool) {
return id.Callback(query, batch)
}); err != nil {
if err := lt.boltdbIndexClient.QueryWithCursor(ctx, bucket.Cursor(), query, callback); err != nil {
return err
}
}
Expand Down
4 changes: 3 additions & 1 deletion pkg/storage/stores/shipper/util/queries.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,10 +33,12 @@ func QueriesByTable(queries []chunk.IndexQuery) map[string][]chunk.IndexQuery {
func DoParallelQueries(ctx context.Context, tableQuerier TableQuerier, queries []chunk.IndexQuery, callback chunk_util.Callback) error {
errs := make(chan error)

id := NewIndexDeduper(callback)

for i := 0; i < len(queries); i += maxQueriesPerGoroutine {
q := queries[i:util_math.Min(i+maxQueriesPerGoroutine, len(queries))]
go func(queries []chunk.IndexQuery) {
errs <- tableQuerier.MultiQueries(ctx, queries, callback)
errs <- tableQuerier.MultiQueries(ctx, queries, id.Callback)
}(q)
}

Expand Down