forgejo/modules/queue/base_channel.go

124 lines
2.2 KiB
Go
Raw Normal View History

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 20:49:59 +09:00
// Copyright 2023 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package queue
import (
"context"
"errors"
"sync"
"time"
"code.gitea.io/gitea/modules/container"
)
var errChannelClosed = errors.New("channel is closed")
type baseChannel struct {
c chan []byte
set container.Set[string]
mu sync.Mutex
isUnique bool
}
var _ baseQueue = (*baseChannel)(nil)
func newBaseChannelGeneric(cfg *BaseConfig, unique bool) (baseQueue, error) {
q := &baseChannel{c: make(chan []byte, cfg.Length), isUnique: unique}
if unique {
q.set = container.Set[string]{}
}
return q, nil
}
func newBaseChannelSimple(cfg *BaseConfig) (baseQueue, error) {
return newBaseChannelGeneric(cfg, false)
}
func newBaseChannelUnique(cfg *BaseConfig) (baseQueue, error) {
return newBaseChannelGeneric(cfg, true)
}
func (q *baseChannel) PushItem(ctx context.Context, data []byte) error {
if q.c == nil {
return errChannelClosed
}
if q.isUnique {
q.mu.Lock()
has := q.set.Contains(string(data))
q.mu.Unlock()
if has {
return ErrAlreadyInQueue
}
}
select {
case q.c <- data:
if q.isUnique {
q.mu.Lock()
q.set.Add(string(data))
q.mu.Unlock()
}
return nil
case <-time.After(pushBlockTime):
return context.DeadlineExceeded
case <-ctx.Done():
return ctx.Err()
}
}
func (q *baseChannel) PopItem(ctx context.Context) ([]byte, error) {
select {
case data, ok := <-q.c:
if !ok {
return nil, errChannelClosed
}
q.mu.Lock()
q.set.Remove(string(data))
q.mu.Unlock()
return data, nil
case <-ctx.Done():
return nil, ctx.Err()
}
}
func (q *baseChannel) HasItem(ctx context.Context, data []byte) (bool, error) {
q.mu.Lock()
defer q.mu.Unlock()
return q.set.Contains(string(data)), nil
}
func (q *baseChannel) Len(ctx context.Context) (int, error) {
q.mu.Lock()
defer q.mu.Unlock()
if q.c == nil {
return 0, errChannelClosed
}
return len(q.c), nil
}
func (q *baseChannel) Close() error {
q.mu.Lock()
defer q.mu.Unlock()
close(q.c)
q.set = container.Set[string]{}
return nil
}
func (q *baseChannel) RemoveAll(ctx context.Context) error {
q.mu.Lock()
defer q.mu.Unlock()
for q.c != nil && len(q.c) > 0 {
<-q.c
}
return nil
}