mirror of
https://codeberg.org/forgejo/forgejo.git
synced 2024-12-25 07:43:36 +01:00
375fd15fbf
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>
68 lines
1.8 KiB
Go
68 lines
1.8 KiB
Go
// Copyright 2023 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package elasticsearch
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"time"
|
|
|
|
"code.gitea.io/gitea/modules/log"
|
|
|
|
"github.com/olivere/elastic/v7"
|
|
)
|
|
|
|
// VersionedIndexName returns the full index name with version
|
|
func (i *Indexer) VersionedIndexName() string {
|
|
return versionedIndexName(i.indexName, i.version)
|
|
}
|
|
|
|
func versionedIndexName(indexName string, version int) string {
|
|
if version == 0 {
|
|
// Old index name without version
|
|
return indexName
|
|
}
|
|
return fmt.Sprintf("%s.v%d", indexName, version)
|
|
}
|
|
|
|
func (i *Indexer) createIndex(ctx context.Context) error {
|
|
createIndex, err := i.Client.CreateIndex(i.VersionedIndexName()).BodyString(i.mapping).Do(ctx)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if !createIndex.Acknowledged {
|
|
return fmt.Errorf("create index %s with %s failed", i.VersionedIndexName(), i.mapping)
|
|
}
|
|
|
|
i.checkOldIndexes(ctx)
|
|
|
|
return nil
|
|
}
|
|
|
|
func (i *Indexer) initClient() (*elastic.Client, error) {
|
|
opts := []elastic.ClientOptionFunc{
|
|
elastic.SetURL(i.url),
|
|
elastic.SetSniff(false),
|
|
elastic.SetHealthcheckInterval(10 * time.Second),
|
|
elastic.SetGzip(false),
|
|
}
|
|
|
|
logger := log.GetLogger(log.DEFAULT)
|
|
|
|
opts = append(opts, elastic.SetTraceLog(&log.PrintfLogger{Logf: logger.Trace}))
|
|
opts = append(opts, elastic.SetInfoLog(&log.PrintfLogger{Logf: logger.Info}))
|
|
opts = append(opts, elastic.SetErrorLog(&log.PrintfLogger{Logf: logger.Error}))
|
|
|
|
return elastic.NewClient(opts...)
|
|
}
|
|
|
|
func (i *Indexer) checkOldIndexes(ctx context.Context) {
|
|
for v := 0; v < i.version; v++ {
|
|
indexName := versionedIndexName(i.indexName, v)
|
|
exists, err := i.Client.IndexExists(indexName).Do(ctx)
|
|
if err == nil && exists {
|
|
log.Warn("Found older elasticsearch index named %q, Gitea will keep the old NOT DELETED. You can delete the old version after the upgrade succeed.", indexName)
|
|
}
|
|
}
|
|
}
|