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: 
72 lines
1.7 KiB
Go
72 lines
1.7 KiB
Go
// Copyright 2023 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package queue
|
|
|
|
import (
|
|
"context"
|
|
"os"
|
|
"os/exec"
|
|
"testing"
|
|
"time"
|
|
|
|
"code.gitea.io/gitea/modules/nosql"
|
|
"code.gitea.io/gitea/modules/setting"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
)
|
|
|
|
func waitRedisReady(conn string, dur time.Duration) (ready bool) {
|
|
ctxTimed, cancel := context.WithTimeout(context.Background(), time.Second*5)
|
|
defer cancel()
|
|
for t := time.Now(); ; time.Sleep(50 * time.Millisecond) {
|
|
ret := nosql.GetManager().GetRedisClient(conn).Ping(ctxTimed)
|
|
if ret.Err() == nil {
|
|
return true
|
|
}
|
|
if time.Since(t) > dur {
|
|
return false
|
|
}
|
|
}
|
|
}
|
|
|
|
func redisServerCmd(t *testing.T) *exec.Cmd {
|
|
redisServerProg, err := exec.LookPath("redis-server")
|
|
if err != nil {
|
|
return nil
|
|
}
|
|
c := &exec.Cmd{
|
|
Path: redisServerProg,
|
|
Args: []string{redisServerProg, "--bind", "127.0.0.1", "--port", "6379"},
|
|
Dir: t.TempDir(),
|
|
Stdin: os.Stdin,
|
|
Stdout: os.Stdout,
|
|
Stderr: os.Stderr,
|
|
}
|
|
return c
|
|
}
|
|
|
|
func TestBaseRedis(t *testing.T) {
|
|
var redisServer *exec.Cmd
|
|
defer func() {
|
|
if redisServer != nil {
|
|
_ = redisServer.Process.Signal(os.Interrupt)
|
|
_ = redisServer.Wait()
|
|
}
|
|
}()
|
|
if !waitRedisReady("redis://127.0.0.1:6379/0", 0) {
|
|
redisServer = redisServerCmd(t)
|
|
if redisServer == nil && os.Getenv("CI") != "" {
|
|
t.Skip("redis-server not found")
|
|
return
|
|
}
|
|
assert.NoError(t, redisServer.Start())
|
|
if !assert.True(t, waitRedisReady("redis://127.0.0.1:6379/0", 5*time.Second), "start redis-server") {
|
|
return
|
|
}
|
|
}
|
|
|
|
testQueueBasic(t, newBaseRedisSimple, toBaseConfig("baseRedis", setting.QueueSettings{Length: 10}), false)
|
|
testQueueBasic(t, newBaseRedisUnique, toBaseConfig("baseRedisUnique", setting.QueueSettings{Length: 10}), true)
|
|
}
|