This repository has been archived on 2024-01-04. You can view files and clone it, but cannot push or open issues or pull requests.
forgejo/modules/queue/unique_queue_channel.go
zeripath c88547ce71
Add Goroutine stack inspector to admin/monitor (#19207)
Continues on from #19202.

Following the addition of pprof labels we can now more easily understand the relationship between a goroutine and the requests that spawn them. 

This PR takes advantage of the labels and adds a few others, then provides a mechanism for the monitoring page to query the pprof goroutine profile.

The binary profile that results from this profile is immediately piped in to the google library for parsing this and then stack traces are formed for the goroutines.

If the goroutine is within a context or has been created from a goroutine within a process context it will acquire the process description labels for that process. 

The goroutines are mapped with there associate pids and any that do not have an associated pid are placed in a group at the bottom as unbound.

In this way we should be able to more easily examine goroutines that have been stuck.

A manager command `gitea manager processes` is also provided that can export the processes (with or without stacktraces) to the command line.

Signed-off-by: Andrew Thornton <art27@cantab.net>
2022-03-31 19:01:43 +02:00

242 lines
6.4 KiB
Go

// Copyright 2020 The Gitea Authors. All rights reserved.
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.
package queue
import (
"context"
"fmt"
"runtime/pprof"
"sync"
"sync/atomic"
"time"
"code.gitea.io/gitea/modules/json"
"code.gitea.io/gitea/modules/log"
)
// ChannelUniqueQueueType is the type for channel queue
const ChannelUniqueQueueType Type = "unique-channel"
// ChannelUniqueQueueConfiguration is the configuration for a ChannelUniqueQueue
type ChannelUniqueQueueConfiguration ChannelQueueConfiguration
// ChannelUniqueQueue implements UniqueQueue
//
// It is basically a thin wrapper around a WorkerPool but keeps a store of
// what has been pushed within a table.
//
// Please note that this Queue does not guarantee that a particular
// task cannot be processed twice or more at the same time. Uniqueness is
// only guaranteed whilst the task is waiting in the queue.
type ChannelUniqueQueue struct {
*WorkerPool
lock sync.Mutex
table map[string]bool
shutdownCtx context.Context
shutdownCtxCancel context.CancelFunc
terminateCtx context.Context
terminateCtxCancel context.CancelFunc
exemplar interface{}
workers int
name string
}
// NewChannelUniqueQueue create a memory channel queue
func NewChannelUniqueQueue(handle HandlerFunc, cfg, exemplar interface{}) (Queue, error) {
configInterface, err := toConfig(ChannelUniqueQueueConfiguration{}, cfg)
if err != nil {
return nil, err
}
config := configInterface.(ChannelUniqueQueueConfiguration)
if config.BatchLength == 0 {
config.BatchLength = 1
}
terminateCtx, terminateCtxCancel := context.WithCancel(context.Background())
shutdownCtx, shutdownCtxCancel := context.WithCancel(terminateCtx)
queue := &ChannelUniqueQueue{
table: map[string]bool{},
shutdownCtx: shutdownCtx,
shutdownCtxCancel: shutdownCtxCancel,
terminateCtx: terminateCtx,
terminateCtxCancel: terminateCtxCancel,
exemplar: exemplar,
workers: config.Workers,
name: config.Name,
}
queue.WorkerPool = NewWorkerPool(func(data ...Data) (unhandled []Data) {
for _, datum := range data {
// No error is possible here because PushFunc ensures that this can be marshalled
bs, _ := json.Marshal(datum)
queue.lock.Lock()
delete(queue.table, string(bs))
queue.lock.Unlock()
if u := handle(datum); u != nil {
if queue.IsPaused() {
// We can only pushback to the channel if we're paused.
go func() {
if err := queue.Push(u[0]); err != nil {
log.Error("Unable to push back to queue %d. Error: %v", queue.qid, err)
}
}()
} else {
unhandled = append(unhandled, u...)
}
}
}
return unhandled
}, config.WorkerPoolConfiguration)
queue.qid = GetManager().Add(queue, ChannelUniqueQueueType, config, exemplar)
return queue, nil
}
// Run starts to run the queue
func (q *ChannelUniqueQueue) Run(atShutdown, atTerminate func(func())) {
pprof.SetGoroutineLabels(q.baseCtx)
atShutdown(q.Shutdown)
atTerminate(q.Terminate)
log.Debug("ChannelUniqueQueue: %s Starting", q.name)
_ = q.AddWorkers(q.workers, 0)
}
// Push will push data into the queue if the data is not already in the queue
func (q *ChannelUniqueQueue) Push(data Data) error {
return q.PushFunc(data, nil)
}
// PushFunc will push data into the queue
func (q *ChannelUniqueQueue) PushFunc(data Data, fn func() error) error {
if !assignableTo(data, q.exemplar) {
return fmt.Errorf("unable to assign data: %v to same type as exemplar: %v in queue: %s", data, q.exemplar, q.name)
}
bs, err := json.Marshal(data)
if err != nil {
return err
}
q.lock.Lock()
locked := true
defer func() {
if locked {
q.lock.Unlock()
}
}()
if _, ok := q.table[string(bs)]; ok {
return ErrAlreadyInQueue
}
// FIXME: We probably need to implement some sort of limit here
// If the downstream queue blocks this table will grow without limit
q.table[string(bs)] = true
if fn != nil {
err := fn()
if err != nil {
delete(q.table, string(bs))
return err
}
}
locked = false
q.lock.Unlock()
q.WorkerPool.Push(data)
return nil
}
// Has checks if the data is in the queue
func (q *ChannelUniqueQueue) Has(data Data) (bool, error) {
bs, err := json.Marshal(data)
if err != nil {
return false, err
}
q.lock.Lock()
defer q.lock.Unlock()
_, has := q.table[string(bs)]
return has, nil
}
// Flush flushes the channel with a timeout - the Flush worker will be registered as a flush worker with the manager
func (q *ChannelUniqueQueue) Flush(timeout time.Duration) error {
if q.IsPaused() {
return nil
}
ctx, cancel := q.commonRegisterWorkers(1, timeout, true)
defer cancel()
return q.FlushWithContext(ctx)
}
// FlushWithContext is very similar to CleanUp but it will return as soon as the dataChan is empty
func (q *ChannelUniqueQueue) FlushWithContext(ctx context.Context) error {
log.Trace("ChannelUniqueQueue: %d Flush", q.qid)
paused, _ := q.IsPausedIsResumed()
for {
select {
case <-paused:
return nil
default:
}
select {
case data, ok := <-q.dataChan:
if !ok {
return nil
}
if unhandled := q.handle(data); unhandled != nil {
log.Error("Unhandled Data whilst flushing queue %d", q.qid)
}
atomic.AddInt64(&q.numInQueue, -1)
case <-q.baseCtx.Done():
return q.baseCtx.Err()
case <-ctx.Done():
return ctx.Err()
default:
return nil
}
}
}
// Shutdown processing from this queue
func (q *ChannelUniqueQueue) Shutdown() {
log.Trace("ChannelUniqueQueue: %s Shutting down", q.name)
select {
case <-q.shutdownCtx.Done():
return
default:
}
go func() {
log.Trace("ChannelUniqueQueue: %s Flushing", q.name)
if err := q.FlushWithContext(q.terminateCtx); err != nil {
log.Warn("ChannelUniqueQueue: %s Terminated before completed flushing", q.name)
return
}
log.Debug("ChannelUniqueQueue: %s Flushed", q.name)
}()
q.shutdownCtxCancel()
log.Debug("ChannelUniqueQueue: %s Shutdown", q.name)
}
// Terminate this queue and close the queue
func (q *ChannelUniqueQueue) Terminate() {
log.Trace("ChannelUniqueQueue: %s Terminating", q.name)
q.Shutdown()
select {
case <-q.terminateCtx.Done():
return
default:
}
q.terminateCtxCancel()
q.baseCtxFinished()
log.Debug("ChannelUniqueQueue: %s Terminated", q.name)
}
// Name returns the name of this queue
func (q *ChannelUniqueQueue) Name() string {
return q.name
}
func init() {
queuesMap[ChannelUniqueQueueType] = NewChannelUniqueQueue
}