0
Fork 0
mirror of https://codeberg.org/forgejo/forgejo.git synced 2024-12-23 15:53:07 -05:00
forgejo/modules/queue/manager_test.go
wxiaoguang 6f9c278559
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

124 lines
4 KiB
Go

// Copyright 2023 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package queue
import (
"context"
"path/filepath"
"testing"
"code.gitea.io/gitea/modules/setting"
"github.com/stretchr/testify/assert"
)
func TestManager(t *testing.T) {
oldAppDataPath := setting.AppDataPath
setting.AppDataPath = t.TempDir()
defer func() {
setting.AppDataPath = oldAppDataPath
}()
newQueueFromConfig := func(name, cfg string) (*WorkerPoolQueue[int], error) {
cfgProvider, err := setting.NewConfigProviderFromData(cfg)
if err != nil {
return nil, err
}
qs, err := setting.GetQueueSettings(cfgProvider, name)
if err != nil {
return nil, err
}
return NewWorkerPoolQueueBySetting(name, qs, func(s ...int) (unhandled []int) { return nil }, false)
}
// test invalid CONN_STR
_, err := newQueueFromConfig("default", `
[queue]
DATADIR = temp-dir
CONN_STR = redis://
`)
assert.ErrorContains(t, err, "invalid leveldb connection string")
// test default config
q, err := newQueueFromConfig("default", "")
assert.NoError(t, err)
assert.Equal(t, "default", q.GetName())
assert.Equal(t, "level", q.GetType())
assert.Equal(t, filepath.Join(setting.AppDataPath, "queues/common"), q.baseConfig.DataFullDir)
assert.Equal(t, 100, q.baseConfig.Length)
assert.Equal(t, 20, q.batchLength)
assert.Equal(t, "", q.baseConfig.ConnStr)
assert.Equal(t, "default_queue", q.baseConfig.QueueFullName)
assert.Equal(t, "default_queue_unique", q.baseConfig.SetFullName)
assert.Equal(t, 10, q.GetWorkerMaxNumber())
assert.Equal(t, 0, q.GetWorkerNumber())
assert.Equal(t, 0, q.GetWorkerActiveNumber())
assert.Equal(t, 0, q.GetQueueItemNumber())
assert.Equal(t, "int", q.GetItemTypeName())
// test inherited config
cfgProvider, err := setting.NewConfigProviderFromData(`
[queue]
TYPE = channel
DATADIR = queues/dir1
LENGTH = 100
BATCH_LENGTH = 20
CONN_STR = "addrs=127.0.0.1:6379 db=0"
QUEUE_NAME = _queue1
[queue.sub]
TYPE = level
DATADIR = queues/dir2
LENGTH = 102
BATCH_LENGTH = 22
CONN_STR =
QUEUE_NAME = _q2
SET_NAME = _u2
MAX_WORKERS = 2
`)
assert.NoError(t, err)
q1 := createWorkerPoolQueue[string]("no-such", cfgProvider, nil, false)
assert.Equal(t, "no-such", q1.GetName())
assert.Equal(t, "dummy", q1.GetType()) // no handler, so it becomes dummy
assert.Equal(t, filepath.Join(setting.AppDataPath, "queues/dir1"), q1.baseConfig.DataFullDir)
assert.Equal(t, 100, q1.baseConfig.Length)
assert.Equal(t, 20, q1.batchLength)
assert.Equal(t, "addrs=127.0.0.1:6379 db=0", q1.baseConfig.ConnStr)
assert.Equal(t, "no-such_queue1", q1.baseConfig.QueueFullName)
assert.Equal(t, "no-such_queue1_unique", q1.baseConfig.SetFullName)
assert.Equal(t, 10, q1.GetWorkerMaxNumber())
assert.Equal(t, 0, q1.GetWorkerNumber())
assert.Equal(t, 0, q1.GetWorkerActiveNumber())
assert.Equal(t, 0, q1.GetQueueItemNumber())
assert.Equal(t, "string", q1.GetItemTypeName())
qid1 := GetManager().qidCounter
q2 := createWorkerPoolQueue("sub", cfgProvider, func(s ...int) (unhandled []int) { return nil }, false)
assert.Equal(t, "sub", q2.GetName())
assert.Equal(t, "level", q2.GetType())
assert.Equal(t, filepath.Join(setting.AppDataPath, "queues/dir2"), q2.baseConfig.DataFullDir)
assert.Equal(t, 102, q2.baseConfig.Length)
assert.Equal(t, 22, q2.batchLength)
assert.Equal(t, "", q2.baseConfig.ConnStr)
assert.Equal(t, "sub_q2", q2.baseConfig.QueueFullName)
assert.Equal(t, "sub_q2_u2", q2.baseConfig.SetFullName)
assert.Equal(t, 2, q2.GetWorkerMaxNumber())
assert.Equal(t, 0, q2.GetWorkerNumber())
assert.Equal(t, 0, q2.GetWorkerActiveNumber())
assert.Equal(t, 0, q2.GetQueueItemNumber())
assert.Equal(t, "int", q2.GetItemTypeName())
qid2 := GetManager().qidCounter
assert.Equal(t, q1, GetManager().ManagedQueues()[qid1])
GetManager().GetManagedQueue(qid1).SetWorkerMaxNumber(120)
assert.Equal(t, 120, q1.workerMaxNum)
stop := runWorkerPoolQueue(q2)
assert.NoError(t, GetManager().GetManagedQueue(qid2).FlushWithContext(context.Background(), 0))
assert.NoError(t, GetManager().FlushAll(context.Background(), 0))
stop()
}