You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

indexer.go 2.3KB

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>
1 year ago
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788
  1. // Copyright 2020 The Gitea Authors. All rights reserved.
  2. // SPDX-License-Identifier: MIT
  3. package stats
  4. import (
  5. "context"
  6. "code.gitea.io/gitea/models/db"
  7. repo_model "code.gitea.io/gitea/models/repo"
  8. "code.gitea.io/gitea/modules/graceful"
  9. "code.gitea.io/gitea/modules/log"
  10. )
  11. // Indexer defines an interface to index repository stats
  12. // TODO: this indexer is quite different from the others, maybe this package should be moved out from module/indexer
  13. type Indexer interface {
  14. Index(id int64) error
  15. Close()
  16. }
  17. // indexer represents a indexer instance
  18. var indexer Indexer
  19. // Init initialize the repo indexer
  20. func Init() error {
  21. indexer = &DBIndexer{}
  22. if err := initStatsQueue(); err != nil {
  23. return err
  24. }
  25. go populateRepoIndexer(db.DefaultContext)
  26. return nil
  27. }
  28. // populateRepoIndexer populate the repo indexer with pre-existing data. This
  29. // should only be run when the indexer is created for the first time.
  30. func populateRepoIndexer(ctx context.Context) {
  31. log.Info("Populating the repo stats indexer with existing repositories")
  32. isShutdown := graceful.GetManager().IsShutdown()
  33. exist, err := db.IsTableNotEmpty("repository")
  34. if err != nil {
  35. log.Fatal("System error: %v", err)
  36. } else if !exist {
  37. return
  38. }
  39. var maxRepoID int64
  40. if maxRepoID, err = db.GetMaxID("repository"); err != nil {
  41. log.Fatal("System error: %v", err)
  42. }
  43. // start with the maximum existing repo ID and work backwards, so that we
  44. // don't include repos that are created after gitea starts; such repos will
  45. // already be added to the indexer, and we don't need to add them again.
  46. for maxRepoID > 0 {
  47. select {
  48. case <-isShutdown:
  49. log.Info("Repository Stats Indexer population shutdown before completion")
  50. return
  51. default:
  52. }
  53. ids, err := repo_model.GetUnindexedRepos(ctx, repo_model.RepoIndexerTypeStats, maxRepoID, 0, 50)
  54. if err != nil {
  55. log.Error("populateRepoIndexer: %v", err)
  56. return
  57. } else if len(ids) == 0 {
  58. break
  59. }
  60. for _, id := range ids {
  61. select {
  62. case <-isShutdown:
  63. log.Info("Repository Stats Indexer population shutdown before completion")
  64. return
  65. default:
  66. }
  67. if err := statsQueue.Push(id); err != nil {
  68. log.Error("statsQueue.Push: %v", err)
  69. }
  70. maxRepoID = id - 1
  71. }
  72. }
  73. log.Info("Done (re)populating the repo stats indexer with existing repositories")
  74. }