forgejo/modules/indexer/stats/indexer.go

89 lines
2.3 KiB
Go
Raw Normal View History

// Copyright 2020 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package stats
import (
"context"
"code.gitea.io/gitea/models/db"
repo_model "code.gitea.io/gitea/models/repo"
"code.gitea.io/gitea/modules/graceful"
"code.gitea.io/gitea/modules/log"
)
// Indexer defines an interface to index repository stats
Refactor indexer (#25174) Refactor `modules/indexer` to make it more maintainable. And it can be easier to support more features. I'm trying to solve some of issue searching, this is a precursor to making functional changes. Current supported engines and the index versions: | engines | issues | code | | - | - | - | | db | Just a wrapper for database queries, doesn't need version | - | | bleve | The version of index is **2** | The version of index is **6** | | elasticsearch | The old index has no version, will be treated as version **0** in this PR | The version of index is **1** | | meilisearch | The old index has no version, will be treated as version **0** in this PR | - | ## Changes ### Split Splited it into mutiple packages ```text indexer ├── internal │   ├── bleve │   ├── db │   ├── elasticsearch │   └── meilisearch ├── code │   ├── bleve │   ├── elasticsearch │   └── internal └── issues ├── bleve ├── db ├── elasticsearch ├── internal └── meilisearch ``` - `indexer/interanal`: Internal shared package for indexer. - `indexer/interanal/[engine]`: Internal shared package for each engine (bleve/db/elasticsearch/meilisearch). - `indexer/code`: Implementations for code indexer. - `indexer/code/internal`: Internal shared package for code indexer. - `indexer/code/[engine]`: Implementation via each engine for code indexer. - `indexer/issues`: Implementations for issues indexer. ### Deduplication - Combine `Init/Ping/Close` for code indexer and issues indexer. - ~Combine `issues.indexerHolder` and `code.wrappedIndexer` to `internal.IndexHolder`.~ Remove it, use dummy indexer instead when the indexer is not ready. - Duplicate two copies of creating ES clients. - Duplicate two copies of `indexerID()`. ### Enhancement - [x] Support index version for elasticsearch issues indexer, the old index without version will be treated as version 0. - [x] Fix spell of `elastic_search/ElasticSearch`, it should be `Elasticsearch`. - [x] Improve versioning of ES index. We don't need `Aliases`: - Gitea does't need aliases for "Zero Downtime" because it never delete old indexes. - The old code of issues indexer uses the orignal name to create issue index, so it's tricky to convert it to an alias. - [x] Support index version for meilisearch issues indexer, the old index without version will be treated as version 0. - [x] Do "ping" only when `Ping` has been called, don't ping periodically and cache the status. - [x] Support the context parameter whenever possible. - [x] Fix outdated example config. - [x] Give up the requeue logic of issues indexer: When indexing fails, call Ping to check if it was caused by the engine being unavailable, and only requeue the task if the engine is unavailable. - It is fragile and tricky, could cause data losing (It did happen when I was doing some tests for this PR). And it works for ES only. - Just always requeue the failed task, if it caused by bad data, it's a bug of Gitea which should be fixed. --------- Co-authored-by: Giteabot <teabot@gitea.io>
2023-06-23 12:37:56 +00:00
// TODO: this indexer is quite different from the others, maybe this package should be moved out from module/indexer
type Indexer interface {
Index(id int64) error
Close()
}
// indexer represents a indexer instance
var indexer Indexer
// Init initialize the repo indexer
func Init() error {
indexer = &DBIndexer{}
if err := initStatsQueue(); err != nil {
return err
}
go populateRepoIndexer(db.DefaultContext)
return nil
}
// populateRepoIndexer populate the repo indexer with pre-existing data. This
// should only be run when the indexer is created for the first time.
func populateRepoIndexer(ctx context.Context) {
log.Info("Populating the repo stats indexer with existing repositories")
isShutdown := graceful.GetManager().IsShutdown()
exist, err := db.IsTableNotEmpty("repository")
if err != nil {
log.Fatal("System error: %v", err)
} else if !exist {
return
}
var maxRepoID int64
if maxRepoID, err = db.GetMaxID("repository"); err != nil {
log.Fatal("System error: %v", err)
}
// start with the maximum existing repo ID and work backwards, so that we
// don't include repos that are created after gitea starts; such repos will
// already be added to the indexer, and we don't need to add them again.
for maxRepoID > 0 {
select {
case <-isShutdown:
log.Info("Repository Stats Indexer population shutdown before completion")
return
default:
}
ids, err := repo_model.GetUnindexedRepos(ctx, repo_model.RepoIndexerTypeStats, maxRepoID, 0, 50)
if err != nil {
log.Error("populateRepoIndexer: %v", err)
return
} else if len(ids) == 0 {
break
}
for _, id := range ids {
select {
case <-isShutdown:
log.Info("Repository Stats Indexer population shutdown before completion")
return
default:
}
if err := statsQueue.Push(id); err != nil {
log.Error("statsQueue.Push: %v", err)
}
maxRepoID = id - 1
}
}
log.Info("Done (re)populating the repo stats indexer with existing repositories")
}