mirror of
https://codeberg.org/forgejo/forgejo.git
synced 2024-12-15 22:16:14 +00:00
6f9c278559
# ⚠️ 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)
105 lines
2.2 KiB
Go
105 lines
2.2 KiB
Go
// Copyright 2019 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package code
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"sync"
|
|
|
|
repo_model "code.gitea.io/gitea/models/repo"
|
|
"code.gitea.io/gitea/modules/log"
|
|
)
|
|
|
|
var indexer = newWrappedIndexer()
|
|
|
|
// ErrWrappedIndexerClosed is the error returned if the indexer was closed before it was ready
|
|
var ErrWrappedIndexerClosed = fmt.Errorf("Indexer closed before ready")
|
|
|
|
type wrappedIndexer struct {
|
|
internal Indexer
|
|
lock sync.RWMutex
|
|
cond *sync.Cond
|
|
closed bool
|
|
}
|
|
|
|
func newWrappedIndexer() *wrappedIndexer {
|
|
w := &wrappedIndexer{}
|
|
w.cond = sync.NewCond(w.lock.RLocker())
|
|
return w
|
|
}
|
|
|
|
func (w *wrappedIndexer) set(indexer Indexer) {
|
|
w.lock.Lock()
|
|
defer w.lock.Unlock()
|
|
if w.closed {
|
|
// Too late!
|
|
indexer.Close()
|
|
}
|
|
w.internal = indexer
|
|
w.cond.Broadcast()
|
|
}
|
|
|
|
func (w *wrappedIndexer) get() (Indexer, error) {
|
|
w.lock.RLock()
|
|
defer w.lock.RUnlock()
|
|
if w.internal == nil {
|
|
if w.closed {
|
|
return nil, ErrWrappedIndexerClosed
|
|
}
|
|
w.cond.Wait()
|
|
if w.closed {
|
|
return nil, ErrWrappedIndexerClosed
|
|
}
|
|
}
|
|
return w.internal, nil
|
|
}
|
|
|
|
// Ping checks if elastic is available
|
|
func (w *wrappedIndexer) Ping() bool {
|
|
indexer, err := w.get()
|
|
if err != nil {
|
|
log.Warn("Failed to get indexer: %v", err)
|
|
return false
|
|
}
|
|
return indexer.Ping()
|
|
}
|
|
|
|
func (w *wrappedIndexer) Index(ctx context.Context, repo *repo_model.Repository, sha string, changes *repoChanges) error {
|
|
indexer, err := w.get()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return indexer.Index(ctx, repo, sha, changes)
|
|
}
|
|
|
|
func (w *wrappedIndexer) Delete(repoID int64) error {
|
|
indexer, err := w.get()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return indexer.Delete(repoID)
|
|
}
|
|
|
|
func (w *wrappedIndexer) Search(ctx context.Context, repoIDs []int64, language, keyword string, page, pageSize int, isMatch bool) (int64, []*SearchResult, []*SearchResultLanguages, error) {
|
|
indexer, err := w.get()
|
|
if err != nil {
|
|
return 0, nil, nil, err
|
|
}
|
|
return indexer.Search(ctx, repoIDs, language, keyword, page, pageSize, isMatch)
|
|
}
|
|
|
|
func (w *wrappedIndexer) Close() {
|
|
w.lock.Lock()
|
|
defer w.lock.Unlock()
|
|
if w.closed {
|
|
return
|
|
}
|
|
w.closed = true
|
|
w.cond.Broadcast()
|
|
if w.internal != nil {
|
|
w.internal.Close()
|
|
}
|
|
}
|