gitea/modules/indexer/issues/meilisearch.go

174 lines
3.7 KiB
Go
Raw Normal View History

// Copyright 2023 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package issues
import (
"context"
"strconv"
"strings"
"sync"
"time"
"github.com/meilisearch/meilisearch-go"
)
var _ Indexer = &MeilisearchIndexer{}
// MeilisearchIndexer implements Indexer interface
type MeilisearchIndexer struct {
Rewrite queue (#24505) # ⚠️ Breaking Many deprecated queue config options are removed (actually, they should have been removed in 1.18/1.19). If you see the fatal message when starting Gitea: "Please update your app.ini to remove deprecated config options", please follow the error messages to remove these options from your app.ini. Example: ``` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].ISSUE_INDEXER_QUEUE_TYPE`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].UPDATE_BUFFER_LEN`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [F] Please update your app.ini to remove deprecated config options ``` Many options in `[queue]` are are dropped, including: `WRAP_IF_NECESSARY`, `MAX_ATTEMPTS`, `TIMEOUT`, `WORKERS`, `BLOCK_TIMEOUT`, `BOOST_TIMEOUT`, `BOOST_WORKERS`, they can be removed from app.ini. # The problem The old queue package has some legacy problems: * complexity: I doubt few people could tell how it works. * maintainability: Too many channels and mutex/cond are mixed together, too many different structs/interfaces depends each other. * stability: due to the complexity & maintainability, sometimes there are strange bugs and difficult to debug, and some code doesn't have test (indeed some code is difficult to test because a lot of things are mixed together). * general applicability: although it is called "queue", its behavior is not a well-known queue. * scalability: it doesn't seem easy to make it work with a cluster without breaking its behaviors. It came from some very old code to "avoid breaking", however, its technical debt is too heavy now. It's a good time to introduce a better "queue" package. # The new queue package It keeps using old config and concept as much as possible. * It only contains two major kinds of concepts: * The "base queue": channel, levelqueue, redis * They have the same abstraction, the same interface, and they are tested by the same testing code. * The "WokerPoolQueue", it uses the "base queue" to provide "worker pool" function, calls the "handler" to process the data in the base queue. * The new code doesn't do "PushBack" * Think about a queue with many workers, the "PushBack" can't guarantee the order for re-queued unhandled items, so in new code it just does "normal push" * The new code doesn't do "pause/resume" * The "pause/resume" was designed to handle some handler's failure: eg: document indexer (elasticsearch) is down * If a queue is paused for long time, either the producers blocks or the new items are dropped. * The new code doesn't do such "pause/resume" trick, it's not a common queue's behavior and it doesn't help much. * If there are unhandled items, the "push" function just blocks for a few seconds and then re-queue them and retry. * The new code doesn't do "worker booster" * Gitea's queue's handlers are light functions, the cost is only the go-routine, so it doesn't make sense to "boost" them. * The new code only use "max worker number" to limit the concurrent workers. * The new "Push" never blocks forever * Instead of creating more and more blocking goroutines, return an error is more friendly to the server and to the end user. There are more details in code comments: eg: the "Flush" problem, the strange "code.index" hanging problem, the "immediate" queue problem. Almost ready for review. TODO: * [x] add some necessary comments during review * [x] add some more tests if necessary * [x] update documents and config options * [x] test max worker / active worker * [x] re-run the CI tasks to see whether any test is flaky * [x] improve the `handleOldLengthConfiguration` to provide more friendly messages * [x] fine tune default config values (eg: length?) ## Code coverage: ![image](https://user-images.githubusercontent.com/2114189/236620635-55576955-f95d-4810-b12f-879026a3afdf.png)
2023-05-08 19:49:59 +08:00
client *meilisearch.Client
indexerName string
available bool
stopTimer chan struct{}
lock sync.RWMutex
}
// MeilisearchIndexer creates a new meilisearch indexer
func NewMeilisearchIndexer(url, apiKey, indexerName string) (*MeilisearchIndexer, error) {
client := meilisearch.NewClient(meilisearch.ClientConfig{
Host: url,
APIKey: apiKey,
})
indexer := &MeilisearchIndexer{
client: client,
indexerName: indexerName,
available: true,
stopTimer: make(chan struct{}),
}
ticker := time.NewTicker(10 * time.Second)
go func() {
for {
select {
case <-ticker.C:
indexer.checkAvailability()
case <-indexer.stopTimer:
ticker.Stop()
return
}
}
}()
return indexer, nil
}
// Init will initialize the indexer
func (b *MeilisearchIndexer) Init() (bool, error) {
_, err := b.client.GetIndex(b.indexerName)
if err == nil {
return true, nil
}
_, err = b.client.CreateIndex(&meilisearch.IndexConfig{
Uid: b.indexerName,
PrimaryKey: "id",
})
if err != nil {
return false, b.checkError(err)
}
_, err = b.client.Index(b.indexerName).UpdateFilterableAttributes(&[]string{"repo_id"})
return false, b.checkError(err)
}
// Ping checks if meilisearch is available
func (b *MeilisearchIndexer) Ping() bool {
b.lock.RLock()
defer b.lock.RUnlock()
return b.available
}
// Index will save the index data
func (b *MeilisearchIndexer) Index(issues []*IndexerData) error {
if len(issues) == 0 {
return nil
}
for _, issue := range issues {
_, err := b.client.Index(b.indexerName).AddDocuments(issue)
if err != nil {
return b.checkError(err)
}
}
// TODO: bulk send index data
return nil
}
// Delete deletes indexes by ids
func (b *MeilisearchIndexer) Delete(ids ...int64) error {
if len(ids) == 0 {
return nil
}
for _, id := range ids {
_, err := b.client.Index(b.indexerName).DeleteDocument(strconv.FormatInt(id, 10))
if err != nil {
return b.checkError(err)
}
}
// TODO: bulk send deletes
return nil
}
// Search searches for issues by given conditions.
// Returns the matching issue IDs
func (b *MeilisearchIndexer) Search(ctx context.Context, keyword string, repoIDs []int64, limit, start int) (*SearchResult, error) {
repoFilters := make([]string, 0, len(repoIDs))
for _, repoID := range repoIDs {
repoFilters = append(repoFilters, "repo_id = "+strconv.FormatInt(repoID, 10))
}
filter := strings.Join(repoFilters, " OR ")
searchRes, err := b.client.Index(b.indexerName).Search(keyword, &meilisearch.SearchRequest{
Filter: filter,
Limit: int64(limit),
Offset: int64(start),
})
if err != nil {
return nil, b.checkError(err)
}
hits := make([]Match, 0, len(searchRes.Hits))
for _, hit := range searchRes.Hits {
hits = append(hits, Match{
ID: int64(hit.(map[string]any)["id"].(float64)),
})
}
return &SearchResult{
Total: searchRes.TotalHits,
Hits: hits,
}, nil
}
// Close implements indexer
func (b *MeilisearchIndexer) Close() {
select {
case <-b.stopTimer:
default:
close(b.stopTimer)
}
}
func (b *MeilisearchIndexer) checkError(err error) error {
return err
}
func (b *MeilisearchIndexer) checkAvailability() {
_, err := b.client.Health()
if err != nil {
b.setAvailability(false)
return
}
b.setAvailability(true)
}
func (b *MeilisearchIndexer) setAvailability(available bool) {
b.lock.Lock()
defer b.lock.Unlock()
if b.available == available {
return
}
b.available = available
}