aboutsummaryrefslogtreecommitdiffstats
path: root/services/repository
diff options
context:
space:
mode:
authorwxiaoguang <wxiaoguang@gmail.com>2023-05-08 19:49:59 +0800
committerGitHub <noreply@github.com>2023-05-08 19:49:59 +0800
commit6f9c278559789066aa831c1df25b0d866103d02d (patch)
treee3a1880e0d4cf88916f9d1b65d82fbd4c41ea47f /services/repository
parentcb700aedd1e670fb47b8cf0cd67fb117a1ad88a2 (diff)
downloadgitea-6f9c278559789066aa831c1df25b0d866103d02d.tar.gz
gitea-6f9c278559789066aa831c1df25b0d866103d02d.zip
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)
Diffstat (limited to 'services/repository')
-rw-r--r--services/repository/archiver/archiver.go15
-rw-r--r--services/repository/push.go9
2 files changed, 9 insertions, 15 deletions
diff --git a/services/repository/archiver/archiver.go b/services/repository/archiver/archiver.go
index 1da4425cfc..1c514a4112 100644
--- a/services/repository/archiver/archiver.go
+++ b/services/repository/archiver/archiver.go
@@ -295,26 +295,21 @@ func ArchiveRepository(request *ArchiveRequest) (*repo_model.RepoArchiver, error
return doArchive(request)
}
-var archiverQueue queue.UniqueQueue
+var archiverQueue *queue.WorkerPoolQueue[*ArchiveRequest]
// Init initlize archive
func Init() error {
- handler := func(data ...queue.Data) []queue.Data {
- for _, datum := range data {
- archiveReq, ok := datum.(*ArchiveRequest)
- if !ok {
- log.Error("Unable to process provided datum: %v - not possible to cast to IndexerData", datum)
- continue
- }
+ handler := func(items ...*ArchiveRequest) []*ArchiveRequest {
+ for _, archiveReq := range items {
log.Trace("ArchiverData Process: %#v", archiveReq)
if _, err := doArchive(archiveReq); err != nil {
- log.Error("Archive %v failed: %v", datum, err)
+ log.Error("Archive %v failed: %v", archiveReq, err)
}
}
return nil
}
- archiverQueue = queue.CreateUniqueQueue("repo-archive", handler, new(ArchiveRequest))
+ archiverQueue = queue.CreateUniqueQueue("repo-archive", handler)
if archiverQueue == nil {
return errors.New("unable to create codes indexer queue")
}
diff --git a/services/repository/push.go b/services/repository/push.go
index 7f174c71b3..c7ea8f336e 100644
--- a/services/repository/push.go
+++ b/services/repository/push.go
@@ -29,12 +29,11 @@ import (
)
// pushQueue represents a queue to handle update pull request tests
-var pushQueue queue.Queue
+var pushQueue *queue.WorkerPoolQueue[[]*repo_module.PushUpdateOptions]
// handle passed PR IDs and test the PRs
-func handle(data ...queue.Data) []queue.Data {
- for _, datum := range data {
- opts := datum.([]*repo_module.PushUpdateOptions)
+func handler(items ...[]*repo_module.PushUpdateOptions) [][]*repo_module.PushUpdateOptions {
+ for _, opts := range items {
if err := pushUpdates(opts); err != nil {
log.Error("pushUpdate failed: %v", err)
}
@@ -43,7 +42,7 @@ func handle(data ...queue.Data) []queue.Data {
}
func initPushQueue() error {
- pushQueue = queue.CreateQueue("push_update", handle, []*repo_module.PushUpdateOptions{})
+ pushQueue = queue.CreateSimpleQueue("push_update", handler)
if pushQueue == nil {
return errors.New("unable to create push_update Queue")
}