1
0
Fork 0
mirror of https://codeberg.org/forgejo/forgejo.git synced 2024-11-22 08:42:32 -05:00
forgejo/modules/setting/queue.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

113 lines
3.5 KiB
Go

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package setting
import (
"path/filepath"
"code.gitea.io/gitea/modules/json"
"code.gitea.io/gitea/modules/log"
)
// QueueSettings represent the settings for a queue from the ini
type QueueSettings struct {
Name string // not an INI option, it is the name for [queue.the-name] section
Type string
Datadir string
ConnStr string // for leveldb or redis
Length int // max queue length before blocking
QueueName, SetName string // the name suffix for storage (db key, redis key), "set" is for unique queue
BatchLength int
MaxWorkers int
}
var queueSettingsDefault = QueueSettings{
Type: "level", // dummy, channel, level, redis
Datadir: "queues/common", // relative to AppDataPath
Length: 100, // queue length before a channel queue will block
QueueName: "_queue",
SetName: "_unique",
BatchLength: 20,
MaxWorkers: 10,
}
func GetQueueSettings(rootCfg ConfigProvider, name string) (QueueSettings, error) {
// deep copy default settings
cfg := QueueSettings{}
if cfgBs, err := json.Marshal(queueSettingsDefault); err != nil {
return cfg, err
} else if err = json.Unmarshal(cfgBs, &cfg); err != nil {
return cfg, err
}
cfg.Name = name
if sec, err := rootCfg.GetSection("queue"); err == nil {
if err = sec.MapTo(&cfg); err != nil {
log.Error("Failed to map queue common config for %q: %v", name, err)
return cfg, nil
}
}
if sec, err := rootCfg.GetSection("queue." + name); err == nil {
if err = sec.MapTo(&cfg); err != nil {
log.Error("Failed to map queue spec config for %q: %v", name, err)
return cfg, nil
}
if sec.HasKey("CONN_STR") {
cfg.ConnStr = sec.Key("CONN_STR").String()
}
}
if cfg.Datadir == "" {
cfg.Datadir = queueSettingsDefault.Datadir
}
if !filepath.IsAbs(cfg.Datadir) {
cfg.Datadir = filepath.Join(AppDataPath, cfg.Datadir)
}
cfg.Datadir = filepath.ToSlash(cfg.Datadir)
if cfg.Type == "redis" && cfg.ConnStr == "" {
cfg.ConnStr = "redis://127.0.0.1:6379/0"
}
if cfg.Length <= 0 {
cfg.Length = queueSettingsDefault.Length
}
if cfg.MaxWorkers <= 0 {
cfg.MaxWorkers = queueSettingsDefault.MaxWorkers
}
if cfg.BatchLength <= 0 {
cfg.BatchLength = queueSettingsDefault.BatchLength
}
return cfg, nil
}
func LoadQueueSettings() {
loadQueueFrom(CfgProvider)
}
func loadQueueFrom(rootCfg ConfigProvider) {
hasOld := false
handleOldLengthConfiguration := func(rootCfg ConfigProvider, newQueueName, oldSection, oldKey string) {
if rootCfg.Section(oldSection).HasKey(oldKey) {
hasOld = true
log.Error("Removed queue option: `[%s].%s`. Use new options in `[queue.%s]`", oldSection, oldKey, newQueueName)
}
}
handleOldLengthConfiguration(rootCfg, "issue_indexer", "indexer", "ISSUE_INDEXER_QUEUE_TYPE")
handleOldLengthConfiguration(rootCfg, "issue_indexer", "indexer", "ISSUE_INDEXER_QUEUE_BATCH_NUMBER")
handleOldLengthConfiguration(rootCfg, "issue_indexer", "indexer", "ISSUE_INDEXER_QUEUE_DIR")
handleOldLengthConfiguration(rootCfg, "issue_indexer", "indexer", "ISSUE_INDEXER_QUEUE_CONN_STR")
handleOldLengthConfiguration(rootCfg, "issue_indexer", "indexer", "UPDATE_BUFFER_LEN")
handleOldLengthConfiguration(rootCfg, "mailer", "mailer", "SEND_BUFFER_LEN")
handleOldLengthConfiguration(rootCfg, "pr_patch_checker", "repository", "PULL_REQUEST_QUEUE_LENGTH")
handleOldLengthConfiguration(rootCfg, "mirror", "repository", "MIRROR_QUEUE_LENGTH")
if hasOld {
log.Fatal("Please update your app.ini to remove deprecated config options")
}
}