diff options
author | Lunny Xiao <xiaolunwen@gmail.com> | 2024-08-21 01:04:57 +0800 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-08-20 17:04:57 +0000 |
commit | c03baab678ba5b2e9d974aea147e660417f5d3f7 (patch) | |
tree | 2b890d549a150cc1c9f6101218789601f40b960f /modules/indexer | |
parent | 8b92eba21f5c5cca277b8101ada0ea7a1fb32ae0 (diff) | |
download | gitea-c03baab678ba5b2e9d974aea147e660417f5d3f7.tar.gz gitea-c03baab678ba5b2e9d974aea147e660417f5d3f7.zip |
Refactor the usage of batch catfile (#31754)
When opening a repository, it will call `ensureValidRepository` and also
`CatFileBatch`. But sometimes these will not be used until repository
closed. So it's a waste of CPU to invoke 3 times git command for every
open repository.
This PR removed all of these from `OpenRepository` but only kept
checking whether the folder exists. When a batch is necessary, the
necessary functions will be invoked.
Diffstat (limited to 'modules/indexer')
-rw-r--r-- | modules/indexer/code/bleve/bleve.go | 20 | ||||
-rw-r--r-- | modules/indexer/code/elasticsearch/elasticsearch.go | 20 |
2 files changed, 22 insertions, 18 deletions
diff --git a/modules/indexer/code/bleve/bleve.go b/modules/indexer/code/bleve/bleve.go index 8056b58ec2..542bdfb501 100644 --- a/modules/indexer/code/bleve/bleve.go +++ b/modules/indexer/code/bleve/bleve.go @@ -16,10 +16,10 @@ import ( "code.gitea.io/gitea/modules/analyze" "code.gitea.io/gitea/modules/charset" "code.gitea.io/gitea/modules/git" + "code.gitea.io/gitea/modules/gitrepo" "code.gitea.io/gitea/modules/indexer/code/internal" indexer_internal "code.gitea.io/gitea/modules/indexer/internal" inner_bleve "code.gitea.io/gitea/modules/indexer/internal/bleve" - "code.gitea.io/gitea/modules/log" "code.gitea.io/gitea/modules/setting" "code.gitea.io/gitea/modules/timeutil" "code.gitea.io/gitea/modules/typesniffer" @@ -189,21 +189,23 @@ func (b *Indexer) addDelete(filename string, repo *repo_model.Repository, batch func (b *Indexer) Index(ctx context.Context, repo *repo_model.Repository, sha string, changes *internal.RepoChanges) error { batch := inner_bleve.NewFlushingBatch(b.inner.Indexer, maxBatchSize) if len(changes.Updates) > 0 { - // Now because of some insanity with git cat-file not immediately failing if not run in a valid git directory we need to run git rev-parse first! - if err := git.EnsureValidGitRepository(ctx, repo.RepoPath()); err != nil { - log.Error("Unable to open git repo: %s for %-v: %v", repo.RepoPath(), repo, err) + r, err := gitrepo.OpenRepository(ctx, repo) + if err != nil { return err } - - batchWriter, batchReader, cancel := git.CatFileBatch(ctx, repo.RepoPath()) - defer cancel() + defer r.Close() + gitBatch, err := r.NewBatch(ctx) + if err != nil { + return err + } + defer gitBatch.Close() for _, update := range changes.Updates { - if err := b.addUpdate(ctx, batchWriter, batchReader, sha, update, repo, batch); err != nil { + if err := b.addUpdate(ctx, gitBatch.Writer, gitBatch.Reader, sha, update, repo, batch); err != nil { return err } } - cancel() + gitBatch.Close() } for _, filename := range changes.RemovedFilenames { if err := b.addDelete(filename, repo, batch); err != nil { diff --git a/modules/indexer/code/elasticsearch/elasticsearch.go b/modules/indexer/code/elasticsearch/elasticsearch.go index e4622fd66e..0bda180fac 100644 --- a/modules/indexer/code/elasticsearch/elasticsearch.go +++ b/modules/indexer/code/elasticsearch/elasticsearch.go @@ -15,11 +15,11 @@ import ( "code.gitea.io/gitea/modules/analyze" "code.gitea.io/gitea/modules/charset" "code.gitea.io/gitea/modules/git" + "code.gitea.io/gitea/modules/gitrepo" "code.gitea.io/gitea/modules/indexer/code/internal" indexer_internal "code.gitea.io/gitea/modules/indexer/internal" inner_elasticsearch "code.gitea.io/gitea/modules/indexer/internal/elasticsearch" "code.gitea.io/gitea/modules/json" - "code.gitea.io/gitea/modules/log" "code.gitea.io/gitea/modules/setting" "code.gitea.io/gitea/modules/timeutil" "code.gitea.io/gitea/modules/typesniffer" @@ -154,17 +154,19 @@ func (b *Indexer) addDelete(filename string, repo *repo_model.Repository) elasti func (b *Indexer) Index(ctx context.Context, repo *repo_model.Repository, sha string, changes *internal.RepoChanges) error { reqs := make([]elastic.BulkableRequest, 0) if len(changes.Updates) > 0 { - // Now because of some insanity with git cat-file not immediately failing if not run in a valid git directory we need to run git rev-parse first! - if err := git.EnsureValidGitRepository(ctx, repo.RepoPath()); err != nil { - log.Error("Unable to open git repo: %s for %-v: %v", repo.RepoPath(), repo, err) + r, err := gitrepo.OpenRepository(ctx, repo) + if err != nil { return err } - - batchWriter, batchReader, cancel := git.CatFileBatch(ctx, repo.RepoPath()) - defer cancel() + defer r.Close() + batch, err := r.NewBatch(ctx) + if err != nil { + return err + } + defer batch.Close() for _, update := range changes.Updates { - updateReqs, err := b.addUpdate(ctx, batchWriter, batchReader, sha, update, repo) + updateReqs, err := b.addUpdate(ctx, batch.Writer, batch.Reader, sha, update, repo) if err != nil { return err } @@ -172,7 +174,7 @@ func (b *Indexer) Index(ctx context.Context, repo *repo_model.Repository, sha st reqs = append(reqs, updateReqs...) } } - cancel() + batch.Close() } for _, filename := range changes.RemovedFilenames { |