fix: Elasticsearch: Request Entity Too Large #28117 (#29062) (#29075)

Backport #29062 by @inferno-umar

Fix for gitea putting everything into one request without batching and
sending it to Elasticsearch for indexing as issued in #28117

This issue occured in large repositories while Gitea tries to
index the code using ElasticSearch.

Co-authored-by: dark-angel <70754989+inferno-umar@users.noreply.github.com>
(cherry picked from commit f0d34cd3b97dd2c9f29fc401ec58ea0661b7ca7d)
This commit is contained in:
Giteabot 2024-02-07 17:21:28 +08:00 committed by Earl Warren
parent 941c47f08f
commit e6f59f6e14
No known key found for this signature in database
GPG key ID: 0579CB2928A78A00

View file

@ -180,11 +180,17 @@ func (b *Indexer) Index(ctx context.Context, repo *repo_model.Repository, sha st
} }
if len(reqs) > 0 { if len(reqs) > 0 {
_, err := b.inner.Client.Bulk(). esBatchSize := 50
Index(b.inner.VersionedIndexName()).
Add(reqs...). for i := 0; i < len(reqs); i += esBatchSize {
Do(ctx) _, err := b.inner.Client.Bulk().
return err Index(b.inner.VersionedIndexName()).
Add(reqs[i:min(i+esBatchSize, len(reqs))]...).
Do(ctx)
if err != nil {
return err
}
}
} }
return nil return nil
} }