1
0
Fork 0
mirror of https://codeberg.org/forgejo/forgejo.git synced 2024-12-04 10:30:19 -05:00
forgejo/services/actions/job_emitter.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

143 lines
3.4 KiB
Go

// Copyright 2022 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package actions
import (
"context"
"errors"
"fmt"
actions_model "code.gitea.io/gitea/models/actions"
"code.gitea.io/gitea/models/db"
"code.gitea.io/gitea/modules/graceful"
"code.gitea.io/gitea/modules/queue"
"xorm.io/builder"
)
var jobEmitterQueue *queue.WorkerPoolQueue[*jobUpdate]
type jobUpdate struct {
RunID int64
}
func EmitJobsIfReady(runID int64) error {
err := jobEmitterQueue.Push(&jobUpdate{
RunID: runID,
})
if errors.Is(err, queue.ErrAlreadyInQueue) {
return nil
}
return err
}
func jobEmitterQueueHandler(items ...*jobUpdate) []*jobUpdate {
ctx := graceful.GetManager().ShutdownContext()
var ret []*jobUpdate
for _, update := range items {
if err := checkJobsOfRun(ctx, update.RunID); err != nil {
ret = append(ret, update)
}
}
return ret
}
func checkJobsOfRun(ctx context.Context, runID int64) error {
jobs, _, err := actions_model.FindRunJobs(ctx, actions_model.FindRunJobOptions{RunID: runID})
if err != nil {
return err
}
if err := db.WithTx(ctx, func(ctx context.Context) error {
idToJobs := make(map[string][]*actions_model.ActionRunJob, len(jobs))
for _, job := range jobs {
idToJobs[job.JobID] = append(idToJobs[job.JobID], job)
}
updates := newJobStatusResolver(jobs).Resolve()
for _, job := range jobs {
if status, ok := updates[job.ID]; ok {
job.Status = status
if n, err := actions_model.UpdateRunJob(ctx, job, builder.Eq{"status": actions_model.StatusBlocked}, "status"); err != nil {
return err
} else if n != 1 {
return fmt.Errorf("no affected for updating blocked job %v", job.ID)
}
}
}
return nil
}); err != nil {
return err
}
CreateCommitStatus(ctx, jobs...)
return nil
}
type jobStatusResolver struct {
statuses map[int64]actions_model.Status
needs map[int64][]int64
}
func newJobStatusResolver(jobs actions_model.ActionJobList) *jobStatusResolver {
idToJobs := make(map[string][]*actions_model.ActionRunJob, len(jobs))
for _, job := range jobs {
idToJobs[job.JobID] = append(idToJobs[job.JobID], job)
}
statuses := make(map[int64]actions_model.Status, len(jobs))
needs := make(map[int64][]int64, len(jobs))
for _, job := range jobs {
statuses[job.ID] = job.Status
for _, need := range job.Needs {
for _, v := range idToJobs[need] {
needs[job.ID] = append(needs[job.ID], v.ID)
}
}
}
return &jobStatusResolver{
statuses: statuses,
needs: needs,
}
}
func (r *jobStatusResolver) Resolve() map[int64]actions_model.Status {
ret := map[int64]actions_model.Status{}
for i := 0; i < len(r.statuses); i++ {
updated := r.resolve()
if len(updated) == 0 {
return ret
}
for k, v := range updated {
ret[k] = v
r.statuses[k] = v
}
}
return ret
}
func (r *jobStatusResolver) resolve() map[int64]actions_model.Status {
ret := map[int64]actions_model.Status{}
for id, status := range r.statuses {
if status != actions_model.StatusBlocked {
continue
}
allDone, allSucceed := true, true
for _, need := range r.needs[id] {
needStatus := r.statuses[need]
if !needStatus.IsDone() {
allDone = false
}
if needStatus.In(actions_model.StatusFailure, actions_model.StatusCancelled, actions_model.StatusSkipped) {
allSucceed = false
}
}
if allDone {
if allSucceed {
ret[id] = actions_model.StatusWaiting
} else {
ret[id] = actions_model.StatusSkipped
}
}
}
return ret
}