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>
This commit is contained in:
Giteabot 2024-02-07 17:21:28 +08:00 committed by GitHub
parent 7ed79b748f
commit f0d34cd3b9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 5 deletions

View File

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