1
1
mirror of https://github.com/go-gitea/gitea synced 2024-11-15 22:54:24 +00:00
gitea/modules/setting/indexer.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

104 lines
3.4 KiB
Go

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package setting
import (
"net/url"
"path/filepath"
"strings"
"time"
"code.gitea.io/gitea/modules/log"
"github.com/gobwas/glob"
)
// Indexer settings
var Indexer = struct {
IssueType string
IssuePath string
IssueConnStr string
IssueConnAuth string
IssueIndexerName string
StartupTimeout time.Duration
RepoIndexerEnabled bool
RepoType string
RepoPath string
RepoConnStr string
RepoIndexerName string
MaxIndexerFileSize int64
IncludePatterns []glob.Glob
ExcludePatterns []glob.Glob
ExcludeVendored bool
}{
IssueType: "bleve",
IssuePath: "indexers/issues.bleve",
IssueConnStr: "",
IssueConnAuth: "",
IssueIndexerName: "gitea_issues",
RepoIndexerEnabled: false,
RepoType: "bleve",
RepoPath: "indexers/repos.bleve",
RepoConnStr: "",
RepoIndexerName: "gitea_codes",
MaxIndexerFileSize: 1024 * 1024,
ExcludeVendored: true,
}
func loadIndexerFrom(rootCfg ConfigProvider) {
sec := rootCfg.Section("indexer")
Indexer.IssueType = sec.Key("ISSUE_INDEXER_TYPE").MustString("bleve")
Indexer.IssuePath = filepath.ToSlash(sec.Key("ISSUE_INDEXER_PATH").MustString(filepath.ToSlash(filepath.Join(AppDataPath, "indexers/issues.bleve"))))
if !filepath.IsAbs(Indexer.IssuePath) {
Indexer.IssuePath = filepath.ToSlash(filepath.Join(AppWorkPath, Indexer.IssuePath))
}
Indexer.IssueConnStr = sec.Key("ISSUE_INDEXER_CONN_STR").MustString(Indexer.IssueConnStr)
if Indexer.IssueType == "meilisearch" {
u, err := url.Parse(Indexer.IssueConnStr)
if err != nil {
log.Warn("Failed to parse ISSUE_INDEXER_CONN_STR: %v", err)
u = &url.URL{}
}
Indexer.IssueConnAuth, _ = u.User.Password()
u.User = nil
Indexer.IssueConnStr = u.String()
}
Indexer.IssueIndexerName = sec.Key("ISSUE_INDEXER_NAME").MustString(Indexer.IssueIndexerName)
Indexer.RepoIndexerEnabled = sec.Key("REPO_INDEXER_ENABLED").MustBool(false)
Indexer.RepoType = sec.Key("REPO_INDEXER_TYPE").MustString("bleve")
Indexer.RepoPath = filepath.ToSlash(sec.Key("REPO_INDEXER_PATH").MustString(filepath.ToSlash(filepath.Join(AppDataPath, "indexers/repos.bleve"))))
if !filepath.IsAbs(Indexer.RepoPath) {
Indexer.RepoPath = filepath.ToSlash(filepath.Join(AppWorkPath, Indexer.RepoPath))
}
Indexer.RepoConnStr = sec.Key("REPO_INDEXER_CONN_STR").MustString("")
Indexer.RepoIndexerName = sec.Key("REPO_INDEXER_NAME").MustString("gitea_codes")
Indexer.IncludePatterns = IndexerGlobFromString(sec.Key("REPO_INDEXER_INCLUDE").MustString(""))
Indexer.ExcludePatterns = IndexerGlobFromString(sec.Key("REPO_INDEXER_EXCLUDE").MustString(""))
Indexer.ExcludeVendored = sec.Key("REPO_INDEXER_EXCLUDE_VENDORED").MustBool(true)
Indexer.MaxIndexerFileSize = sec.Key("MAX_FILE_SIZE").MustInt64(1024 * 1024)
Indexer.StartupTimeout = sec.Key("STARTUP_TIMEOUT").MustDuration(30 * time.Second)
}
// IndexerGlobFromString parses a comma separated list of patterns and returns a glob.Glob slice suited for repo indexing
func IndexerGlobFromString(globstr string) []glob.Glob {
extarr := make([]glob.Glob, 0, 10)
for _, expr := range strings.Split(strings.ToLower(globstr), ",") {
expr = strings.TrimSpace(expr)
if expr != "" {
if g, err := glob.Compile(expr, '.', '/'); err != nil {
log.Info("Invalid glob expression '%s' (skipped): %v", expr, err)
} else {
extarr = append(extarr, g)
}
}
}
return extarr
}