summaryrefslogtreecommitdiffstats
path: root/services/pull
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/pull
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/pull')
-rw-r--r--services/pull/check.go35
-rw-r--r--services/pull/check_test.go29
2 files changed, 26 insertions, 38 deletions
diff --git a/services/pull/check.go b/services/pull/check.go
index 02d9015414..8bc2bdff1d 100644
--- a/services/pull/check.go
+++ b/services/pull/check.go
@@ -30,7 +30,7 @@ import (
)
// prPatchCheckerQueue represents a queue to handle update pull request tests
-var prPatchCheckerQueue queue.UniqueQueue
+var prPatchCheckerQueue *queue.WorkerPoolQueue[string]
var (
ErrIsClosed = errors.New("pull is closed")
@@ -44,16 +44,14 @@ var (
// AddToTaskQueue adds itself to pull request test task queue.
func AddToTaskQueue(pr *issues_model.PullRequest) {
- err := prPatchCheckerQueue.PushFunc(strconv.FormatInt(pr.ID, 10), func() error {
- pr.Status = issues_model.PullRequestStatusChecking
- err := pr.UpdateColsIfNotMerged(db.DefaultContext, "status")
- if err != nil {
- log.Error("AddToTaskQueue(%-v).UpdateCols.(add to queue): %v", pr, err)
- } else {
- log.Trace("Adding %-v to the test pull requests queue", pr)
- }
- return err
- })
+ pr.Status = issues_model.PullRequestStatusChecking
+ err := pr.UpdateColsIfNotMerged(db.DefaultContext, "status")
+ if err != nil {
+ log.Error("AddToTaskQueue(%-v).UpdateCols.(add to queue): %v", pr, err)
+ return
+ }
+ log.Trace("Adding %-v to the test pull requests queue", pr)
+ err = prPatchCheckerQueue.Push(strconv.FormatInt(pr.ID, 10))
if err != nil && err != queue.ErrAlreadyInQueue {
log.Error("Error adding %-v to the test pull requests queue: %v", pr, err)
}
@@ -315,10 +313,8 @@ func InitializePullRequests(ctx context.Context) {
case <-ctx.Done():
return
default:
- if err := prPatchCheckerQueue.PushFunc(strconv.FormatInt(prID, 10), func() error {
- log.Trace("Adding PR[%d] to the pull requests patch checking queue", prID)
- return nil
- }); err != nil {
+ log.Trace("Adding PR[%d] to the pull requests patch checking queue", prID)
+ if err := prPatchCheckerQueue.Push(strconv.FormatInt(prID, 10)); err != nil {
log.Error("Error adding PR[%d] to the pull requests patch checking queue %v", prID, err)
}
}
@@ -326,10 +322,9 @@ func InitializePullRequests(ctx context.Context) {
}
// handle passed PR IDs and test the PRs
-func handle(data ...queue.Data) []queue.Data {
- for _, datum := range data {
- id, _ := strconv.ParseInt(datum.(string), 10, 64)
-
+func handler(items ...string) []string {
+ for _, s := range items {
+ id, _ := strconv.ParseInt(s, 10, 64)
testPR(id)
}
return nil
@@ -389,7 +384,7 @@ func CheckPRsForBaseBranch(baseRepo *repo_model.Repository, baseBranchName strin
// Init runs the task queue to test all the checking status pull requests
func Init() error {
- prPatchCheckerQueue = queue.CreateUniqueQueue("pr_patch_checker", handle, "")
+ prPatchCheckerQueue = queue.CreateUniqueQueue("pr_patch_checker", handler)
if prPatchCheckerQueue == nil {
return fmt.Errorf("Unable to create pr_patch_checker Queue")
diff --git a/services/pull/check_test.go b/services/pull/check_test.go
index 590065250f..52209b4d35 100644
--- a/services/pull/check_test.go
+++ b/services/pull/check_test.go
@@ -12,6 +12,7 @@ import (
issues_model "code.gitea.io/gitea/models/issues"
"code.gitea.io/gitea/models/unittest"
"code.gitea.io/gitea/modules/queue"
+ "code.gitea.io/gitea/modules/setting"
"github.com/stretchr/testify/assert"
)
@@ -20,27 +21,18 @@ func TestPullRequest_AddToTaskQueue(t *testing.T) {
assert.NoError(t, unittest.PrepareTestDatabase())
idChan := make(chan int64, 10)
-
- q, err := queue.NewChannelUniqueQueue(func(data ...queue.Data) []queue.Data {
- for _, datum := range data {
- id, _ := strconv.ParseInt(datum.(string), 10, 64)
+ testHandler := func(items ...string) []string {
+ for _, s := range items {
+ id, _ := strconv.ParseInt(s, 10, 64)
idChan <- id
}
return nil
- }, queue.ChannelUniqueQueueConfiguration{
- WorkerPoolConfiguration: queue.WorkerPoolConfiguration{
- QueueLength: 10,
- BatchLength: 1,
- Name: "temporary-queue",
- },
- Workers: 1,
- }, "")
- assert.NoError(t, err)
-
- queueShutdown := []func(){}
- queueTerminate := []func(){}
+ }
- prPatchCheckerQueue = q.(queue.UniqueQueue)
+ cfg, err := setting.GetQueueSettings(setting.CfgProvider, "pr_patch_checker")
+ assert.NoError(t, err)
+ prPatchCheckerQueue, err = queue.NewWorkerPoolQueueBySetting("pr_patch_checker", cfg, testHandler, true)
+ assert.NoError(t, err)
pr := unittest.AssertExistsAndLoadBean(t, &issues_model.PullRequest{ID: 2})
AddToTaskQueue(pr)
@@ -54,7 +46,8 @@ func TestPullRequest_AddToTaskQueue(t *testing.T) {
assert.True(t, has)
assert.NoError(t, err)
- prPatchCheckerQueue.Run(func(shutdown func()) {
+ var queueShutdown, queueTerminate []func()
+ go prPatchCheckerQueue.Run(func(shutdown func()) {
queueShutdown = append(queueShutdown, shutdown)
}, func(terminate func()) {
queueTerminate = append(queueTerminate, terminate)