v0.8.2

startup

.gitignore

@@ -15,7 +15,7 @@
 /examples
 
 # Ignore command binary
-/tools/asynqmon/asynqmon
+/tools/asynq/asynq
 
-# Ignore asynqmon config file
+# Ignore asynq config file
-.asynqmon.*
+.asynq.*

CHANGELOG.md

@@ -7,6 +7,41 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.8.2] - 2020-05-03
+
+### Fixed
+
+- [Fixed cancelfunc leak](https://github.com/hibiken/asynq/pull/145)
+
+## [0.8.1] - 2020-04-27
+
+### Added
+
+- `ParseRedisURI` helper function is added to create a `RedisConnOpt` from a URI string.
+- `SetDefaultOptions` method is added to `Client`.
+
+## [0.8.0] - 2020-04-19
+
+### Changed
+
+- `Background` type is renamed to `Server`.
+- To upgrade from the previous version, Update `NewBackground` to `NewServer` and pass `Config` by value.
+- CLI is renamed to `asynq`.
+- To upgrade the CLI to the latest version run `go get -u github.com/hibiken/tools/asynq`
+- The `ps` command in CLI is renamed to `servers`
+- `Concurrency` defaults to the number of CPUs when unset or set to a negative value.
+
+### Added
+
+- `ShutdownTimeout` field is added to `Config` to speicfy timeout duration used during graceful shutdown.
+- New `Server` type exposes `Start`, `Stop`, and `Quiet` as well as `Run`.
+
+## [0.7.1] - 2020-04-05
+
+### Fixed
+
+- Fixed signal handling for windows.
+
 ## [0.7.0] - 2020-03-22
 
 ### Changed

README.md

@@ -7,12 +7,41 @@
 [![Gitter chat](https://badges.gitter.im/go-asynq/gitter.svg)](https://gitter.im/go-asynq/community)
 [![codecov](https://codecov.io/gh/hibiken/asynq/branch/master/graph/badge.svg)](https://codecov.io/gh/hibiken/asynq)
 
-Asynq is a simple Go library for queueing tasks and processing them in the background with workers.  
+## Overview
-It is backed by Redis and it is designed to have a low barrier to entry. It should be integrated in your web stack easily.
 
-**Important Note**: Current major version is zero (v0.x.x) to accomodate rapid development and fast iteration while getting early feedback from users. The public API could change without a major version update before v1.0.0 release.
+Asynq is a Go library for queueing tasks and processing them in the background with workers. It is backed by Redis and it is designed to have a low barrier to entry. It should be integrated in your web stack easily.
 
-![Task Queue Diagram](/docs/assets/task-queue.png)
+Highlevel overview of how Asynq works:
+
+- Client puts task on a queue
+- Server pulls task off queues and starts a worker goroutine for each task
+- Tasks are processed concurrently by multiple workers
+
+Task queues are used as a mechanism to distribute work across multiple machines.  
+A system can consist of multiple worker servers and brokers, giving way to high availability and horizontal scaling.
+
+![Task Queue Diagram](/docs/assets/overview.png)
+
+## Stability and Compatibility
+
+**Important Note**: Current major version is zero (v0.x.x) to accomodate rapid development and fast iteration while getting early feedback from users (Feedback on APIs are appreciated!). The public API could change without a major version update before v1.0.0 release.
+
+**Status**: The library is currently undergoing heavy development with frequent, breaking API changes.
+
+## Features
+
+- Guaranteed [at least one execution](https://www.cloudcomputingpatterns.org/at_least_once_delivery/) of a task
+- Scheduling of tasks
+- Durability since tasks are written to Redis
+- [Retries](https://github.com/hibiken/asynq/wiki/Task-Retry) of failed tasks
+- [Weighted priority queues](https://github.com/hibiken/asynq/wiki/Priority-Queues#weighted-priority-queues)
+- [Strict priority queues](https://github.com/hibiken/asynq/wiki/Priority-Queues#strict-priority-queues)
+- Low latency to add a task since writes are fast in Redis
+- De-duplication of tasks using [unique option](https://github.com/hibiken/asynq/wiki/Unique-Tasks)
+- Allow [timeout and deadline per task](https://github.com/hibiken/asynq/wiki/Task-Timeout-and-Cancelation)
+- [Flexible handler interface with support for middlewares](https://github.com/hibiken/asynq/wiki/Handler-Deep-Dive)
+- [Support Redis Sentinels](https://github.com/hibiken/asynq/wiki/Automatic-Failover) for HA
+- [CLI](#command-line-tool) to inspect and remote-control queues and tasks
 
 ## Quickstart
 
@@ -22,7 +51,7 @@ First, make sure you are running a Redis server locally.
 $ redis-server
 ```
 
-Next, write a package that encapslates task creation and task handling.
+Next, write a package that encapsulates task creation and task handling.
 
 ```go
 package tasks
@@ -33,13 +62,15 @@ import (
     "github.com/hibiken/asynq"
 )
 
-// A list of background task types.
+// A list of task types.
 const (
     EmailDelivery   = "email:deliver"
     ImageProcessing = "image:process"
 )
 
+//--------------------------------------------
 // Write function NewXXXTask to create a task.
+//--------------------------------------------
 
 func NewEmailDeliveryTask(userID int, tmplID string) *asynq.Task {
     payload := map[string]interface{}{"user_id": userID, "template_id": tmplID}
@@ -51,8 +82,13 @@ func NewImageProcessingTask(src, dst string) *asynq.Task {
     return asynq.NewTask(ImageProcessing, payload)
 }
 
+//-------------------------------------------------------------
 // Write function HandleXXXTask to handle the given task.
 // NOTE: It satisfies the asynq.HandlerFunc interface.
+// 
+// Handler doesn't need to be a function. You can define a type 
+// that satisfies asynq.Handler interface. See example below.
+//-------------------------------------------------------------
 
 func HandleEmailDeliveryTask(ctx context.Context, t *asynq.Task) error {
     userID, err := t.Payload.GetInt("user_id")
@@ -68,7 +104,12 @@ func HandleEmailDeliveryTask(ctx context.Context, t *asynq.Task) error {
     return nil
 }
 
-func HandleImageProcessingTask(ctx context.Context, t *asynq.Task) error {
+type ImageProcesser struct {
+    // ... fields for struct
+}
+
+// ImageProcessor implements asynq.Handler.
+func (p *ImageProcessor) ProcessTask(ctx context.Context, t *asynq.Task) error {
     src, err := t.Payload.GetString("src")
     if err != nil {
         return err
@@ -81,10 +122,14 @@ func HandleImageProcessingTask(ctx context.Context, t *asynq.Task) error {
     // Image processing logic ...
     return nil
 }
+
+func NewImageProcessor() *ImageProcessor {
+    // ... return an instance
+}
 ```
 
-In your web application code, import the above package and use [`Client`](https://pkg.go.dev/github.com/hibiken/asynq?tab=doc#Client) to enqueue tasks to the task queue.  
+In your web application code, import the above package and use [`Client`](https://pkg.go.dev/github.com/hibiken/asynq?tab=doc#Client) to put tasks on the queue.  
-A task will be processed by a background worker as soon as the task gets enqueued.  
+A task will be processed asynchronously by a background worker as soon as the task gets enqueued.  
 Scheduled tasks will be stored in Redis and will be enqueued at the specified time.
 
 ```go
@@ -100,10 +145,13 @@ import (
 const redisAddr = "127.0.0.1:6379"
 
 func main() {
-    r := &asynq.RedisClientOpt{Addr: redisAddr}
+    r := asynq.RedisClientOpt{Addr: redisAddr}
     c := asynq.NewClient(r)
 
+    // ----------------------------------------------------
     // Example 1: Enqueue task to be processed immediately.
+    //            Use (*Client).Enqueue method.
+    // ---------------------------------------------------- 
 
     t := tasks.NewEmailDeliveryTask(42, "some:template:id")
     err := c.Enqueue(t)
@@ -112,7 +160,10 @@ func main() {
     }
 
 
+    // ----------------------------------------------------------
     // Example 2: Schedule task to be processed in the future.
+    //            Use (*Client).EnqueueIn or (*Client).EnqueueAt.
+    // ----------------------------------------------------------
 
     t = tasks.NewEmailDeliveryTask(42, "other:template:id")
     err = c.EnqueueIn(24*time.Hour, t)
@@ -121,19 +172,34 @@ func main() {
     }
 
 
-    // Example 3: Pass options to tune task processing behavior.
+    // --------------------------------------------------------------------------
-    // Options include MaxRetry, Queue, Timeout, Deadline, etc.
+    // Example 3: Set options to tune task processing behavior.
+    //            Options include MaxRetry, Queue, Timeout, Deadline, Unique etc.
+    // --------------------------------------------------------------------------
+
+    c.SetDefaultOptions(tasks.ImageProcessing, asynq.MaxRetry(10), asynq.Timeout(time.Minute))
 
     t = tasks.NewImageProcessingTask("some/blobstore/url", "other/blobstore/url")
-    err = c.Enqueue(t, asynq.MaxRetry(10), asynq.Queue("critical"), asynq.Timeout(time.Minute))
+    err = c.Enqueue(t)
+    if err != nil {
+        log.Fatal("could not enqueue task: %v", err)
+    }
+
+    // --------------------------------------------------------------------------
+    // Example 4: Pass options to tune task processing behavior at enqueue time.
+    //            Options passed at enqueue time override default ones, if any.
+    // --------------------------------------------------------------------------
+
+    t = tasks.NewImageProcessingTask("some/blobstore/url", "other/blobstore/url")
+    err = c.Enqueue(t, asynq.Queue("critical"), asynq.Timeout(30*time.Second))
     if err != nil {
         log.Fatal("could not enqueue task: %v", err)
     }
 }
 ```
 
-Next, create a binary to process these tasks in the background.  
+Next, create a worker server to process these tasks in the background.  
-To start the background workers, use [`Background`](https://pkg.go.dev/github.com/hibiken/asynq?tab=doc#Background) and provide your [`Handler`](https://pkg.go.dev/github.com/hibiken/asynq?tab=doc#Handler) to process the tasks.
+To start the background workers, use [`Server`](https://pkg.go.dev/github.com/hibiken/asynq?tab=doc#Server) and provide your [`Handler`](https://pkg.go.dev/github.com/hibiken/asynq?tab=doc#Handler) to process the tasks.
 
 You can optionally use [`ServeMux`](https://pkg.go.dev/github.com/hibiken/asynq?tab=doc#ServeMux) to create a handler, just as you would with [`"net/http"`](https://golang.org/pkg/net/http/) Handler.
 
@@ -141,6 +207,8 @@ You can optionally use [`ServeMux`](https://pkg.go.dev/github.com/hibiken/asynq?
 package main
 
 import (
+    "log"
+
     "github.com/hibiken/asynq"
     "your/app/package/tasks"
 )
@@ -148,9 +216,9 @@ import (
 const redisAddr = "127.0.0.1:6379"
 
 func main() {
-    r := &asynq.RedisClientOpt{Addr: redisAddr}
+    r := asynq.RedisClientOpt{Addr: redisAddr}
 
-    bg := asynq.NewBackground(r, &asynq.Config{
+    srv := asynq.NewServer(r, asynq.Config{
         // Specify how many concurrent workers to use
         Concurrency: 10,
         // Optionally specify multiple queues with different priority.
@@ -165,10 +233,12 @@ func main() {
     // mux maps a type to a handler
     mux := asynq.NewServeMux()
     mux.HandleFunc(tasks.EmailDelivery, tasks.HandleEmailDeliveryTask)
-    mux.HandleFunc(tasks.ImageProcessing, tasks.HandleImageProcessingTask)
+    mux.Handle(tasks.ImageProcessing, tasks.NewImageProcessor())
     // ...register other handlers...
 
-    bg.Run(mux)
+    if err := srv.Run(mux); err != nil {
+        log.Fatalf("could not run server: %v", err)
+    }
 }
 ```
 
@@ -184,7 +254,7 @@ Here's an example of running the `stats` command.
 
 ![Gif](/docs/assets/demo.gif)
 
-For details on how to use the tool, refer to the tool's [README](/tools/asynqmon/README.md).
+For details on how to use the tool, refer to the tool's [README](/tools/asynq/README.md).
 
 ## Installation
 
@@ -197,7 +267,7 @@ go get -u github.com/hibiken/asynq
 To install the CLI tool, run the following command:
 
 ```sh
-go get -u github.com/hibiken/asynq/tools/asynqmon
+go get -u github.com/hibiken/asynq/tools/asynq
 ```
 
 ## Requirements
@@ -216,7 +286,7 @@ Please see the [Contribution Guide](/CONTRIBUTING.md) before contributing.
 
 - [Sidekiq](https://github.com/mperham/sidekiq) : Many of the design ideas are taken from sidekiq and its Web UI
 - [RQ](https://github.com/rq/rq) : Client APIs are inspired by rq library.
-- [Cobra](https://github.com/spf13/cobra) : Asynqmon CLI is built with cobra
+- [Cobra](https://github.com/spf13/cobra) : Asynq CLI is built with cobra
 
 ## License
 

asynq.go

@@ -7,6 +7,9 @@ package asynq
 import (
 	"crypto/tls"
 	"fmt"
+	"net/url"
+	"strconv"
+	"strings"
 
 	"github.com/go-redis/redis/v7"
 )
@@ -94,6 +97,79 @@ type RedisFailoverClientOpt struct {
 	TLSConfig *tls.Config
 }
 
+// ParseRedisURI parses redis uri string and returns RedisConnOpt if uri is valid.
+// It returns a non-nil error if uri cannot be parsed.
+//
+// Three URI schemes are supported, which are redis:, redis-socket:, and redis-sentinel:.
+// Supported formats are:
+//     redis://[:password@]host[:port][/dbnumber]
+//     redis-socket://[:password@]path[?db=dbnumber]
+//     redis-sentinel://[:password@]host1[:port][,host2:[:port]][,hostN:[:port]][?master=masterName]
+func ParseRedisURI(uri string) (RedisConnOpt, error) {
+	u, err := url.Parse(uri)
+	if err != nil {
+		return nil, fmt.Errorf("asynq: could not parse redis uri: %v", err)
+	}
+	switch u.Scheme {
+	case "redis":
+		return parseRedisURI(u)
+	case "redis-socket":
+		return parseRedisSocketURI(u)
+	case "redis-sentinel":
+		return parseRedisSentinelURI(u)
+	default:
+		return nil, fmt.Errorf("asynq: unsupported uri scheme: %q", u.Scheme)
+	}
+}
+
+func parseRedisURI(u *url.URL) (RedisConnOpt, error) {
+	var db int
+	var err error
+	if len(u.Path) > 0 {
+		xs := strings.Split(strings.Trim(u.Path, "/"), "/")
+		db, err = strconv.Atoi(xs[0])
+		if err != nil {
+			return nil, fmt.Errorf("asynq: could not parse redis uri: database number should be the first segment of the path")
+		}
+	}
+	var password string
+	if v, ok := u.User.Password(); ok {
+		password = v
+	}
+	return RedisClientOpt{Addr: u.Host, DB: db, Password: password}, nil
+}
+
+func parseRedisSocketURI(u *url.URL) (RedisConnOpt, error) {
+	const errPrefix = "asynq: could not parse redis socket uri"
+	if len(u.Path) == 0 {
+		return nil, fmt.Errorf("%s: path does not exist", errPrefix)
+	}
+	q := u.Query()
+	var db int
+	var err error
+	if n := q.Get("db"); n != "" {
+		db, err = strconv.Atoi(n)
+		if err != nil {
+			return nil, fmt.Errorf("%s: query param `db` should be a number", errPrefix)
+		}
+	}
+	var password string
+	if v, ok := u.User.Password(); ok {
+		password = v
+	}
+	return RedisClientOpt{Network: "unix", Addr: u.Path, DB: db, Password: password}, nil
+}
+
+func parseRedisSentinelURI(u *url.URL) (RedisConnOpt, error) {
+	addrs := strings.Split(u.Host, ",")
+	master := u.Query().Get("master")
+	var password string
+	if v, ok := u.User.Password(); ok {
+		password = v
+	}
+	return RedisFailoverClientOpt{MasterName: master, SentinelAddrs: addrs, Password: password}, nil
+}
+
 // createRedisClient returns a redis client given a redis connection configuration.
 //
 // Passing an unexpected type as a RedisConnOpt argument will cause panic.

asynq_test.go

@@ -44,3 +44,106 @@ var sortTaskOpt = cmp.Transformer("SortMsg", func(in []*Task) []*Task {
 	})
 	return out
 })
+
+func TestParseRedisURI(t *testing.T) {
+	tests := []struct {
+		uri  string
+		want RedisConnOpt
+	}{
+		{
+			"redis://localhost:6379",
+			RedisClientOpt{Addr: "localhost:6379"},
+		},
+		{
+			"redis://localhost:6379/3",
+			RedisClientOpt{Addr: "localhost:6379", DB: 3},
+		},
+		{
+			"redis://:mypassword@localhost:6379",
+			RedisClientOpt{Addr: "localhost:6379", Password: "mypassword"},
+		},
+		{
+			"redis://:mypassword@127.0.0.1:6379/11",
+			RedisClientOpt{Addr: "127.0.0.1:6379", Password: "mypassword", DB: 11},
+		},
+		{
+			"redis-socket:///var/run/redis/redis.sock",
+			RedisClientOpt{Network: "unix", Addr: "/var/run/redis/redis.sock"},
+		},
+		{
+			"redis-socket://:mypassword@/var/run/redis/redis.sock",
+			RedisClientOpt{Network: "unix", Addr: "/var/run/redis/redis.sock", Password: "mypassword"},
+		},
+		{
+			"redis-socket:///var/run/redis/redis.sock?db=7",
+			RedisClientOpt{Network: "unix", Addr: "/var/run/redis/redis.sock", DB: 7},
+		},
+		{
+			"redis-socket://:mypassword@/var/run/redis/redis.sock?db=12",
+			RedisClientOpt{Network: "unix", Addr: "/var/run/redis/redis.sock", Password: "mypassword", DB: 12},
+		},
+		{
+			"redis-sentinel://localhost:5000,localhost:5001,localhost:5002?master=mymaster",
+			RedisFailoverClientOpt{
+				MasterName:    "mymaster",
+				SentinelAddrs: []string{"localhost:5000", "localhost:5001", "localhost:5002"},
+			},
+		},
+		{
+			"redis-sentinel://:mypassword@localhost:5000,localhost:5001,localhost:5002?master=mymaster",
+			RedisFailoverClientOpt{
+				MasterName:    "mymaster",
+				SentinelAddrs: []string{"localhost:5000", "localhost:5001", "localhost:5002"},
+				Password:      "mypassword",
+			},
+		},
+	}
+
+	for _, tc := range tests {
+		got, err := ParseRedisURI(tc.uri)
+		if err != nil {
+			t.Errorf("ParseRedisURI(%q) returned an error: %v", tc.uri, err)
+			continue
+		}
+
+		if diff := cmp.Diff(tc.want, got); diff != "" {
+			t.Errorf("ParseRedisURI(%q) = %+v, want %+v\n(-want,+got)\n%s", tc.uri, got, tc.want, diff)
+		}
+	}
+}
+
+func TestParseRedisURIErrors(t *testing.T) {
+	tests := []struct {
+		desc string
+		uri  string
+	}{
+		{
+			"unsupported scheme",
+			"rdb://localhost:6379",
+		},
+		{
+			"missing scheme",
+			"localhost:6379",
+		},
+		{
+			"multiple db numbers",
+			"redis://localhost:6379/1,2,3",
+		},
+		{
+			"missing path for socket connection",
+			"redis-socket://?db=one",
+		},
+		{
+			"non integer for db numbers for socket",
+			"redis-socket:///some/path/to/redis?db=one",
+		},
+	}
+
+	for _, tc := range tests {
+		_, err := ParseRedisURI(tc.uri)
+		if err == nil {
+			t.Errorf("%s: ParseRedisURI(%q) succeeded for malformed input, want error",
+				tc.desc, tc.uri)
+		}
+	}
+}

background_test.go

@@ -1,128 +0,0 @@
-// Copyright 2020 Kentaro Hibino. All rights reserved.
-// Use of this source code is governed by a MIT license
-// that can be found in the LICENSE file.
-
-package asynq
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/google/go-cmp/cmp"
-	"go.uber.org/goleak"
-)
-
-func TestBackground(t *testing.T) {
-	// https://github.com/go-redis/redis/issues/1029
-	ignoreOpt := goleak.IgnoreTopFunction("github.com/go-redis/redis/v7/internal/pool.(*ConnPool).reaper")
-	defer goleak.VerifyNoLeaks(t, ignoreOpt)
-
-	r := &RedisClientOpt{
-		Addr: "localhost:6379",
-		DB:   15,
-	}
-	client := NewClient(r)
-	bg := NewBackground(r, &Config{
-		Concurrency: 10,
-	})
-
-	// no-op handler
-	h := func(ctx context.Context, task *Task) error {
-		return nil
-	}
-
-	bg.start(HandlerFunc(h))
-
-	err := client.Enqueue(NewTask("send_email", map[string]interface{}{"recipient_id": 123}))
-	if err != nil {
-		t.Errorf("could not enqueue a task: %v", err)
-	}
-
-	err = client.EnqueueAt(time.Now().Add(time.Hour), NewTask("send_email", map[string]interface{}{"recipient_id": 456}))
-	if err != nil {
-		t.Errorf("could not enqueue a task: %v", err)
-	}
-
-	bg.stop()
-}
-
-func TestGCD(t *testing.T) {
-	tests := []struct {
-		input []int
-		want  int
-	}{
-		{[]int{6, 2, 12}, 2},
-		{[]int{3, 3, 3}, 3},
-		{[]int{6, 3, 1}, 1},
-		{[]int{1}, 1},
-		{[]int{1, 0, 2}, 1},
-		{[]int{8, 0, 4}, 4},
-		{[]int{9, 12, 18, 30}, 3},
-	}
-
-	for _, tc := range tests {
-		got := gcd(tc.input...)
-		if got != tc.want {
-			t.Errorf("gcd(%v) = %d, want %d", tc.input, got, tc.want)
-		}
-	}
-}
-
-func TestNormalizeQueueCfg(t *testing.T) {
-	tests := []struct {
-		input map[string]int
-		want  map[string]int
-	}{
-		{
-			input: map[string]int{
-				"high":    100,
-				"default": 20,
-				"low":     5,
-			},
-			want: map[string]int{
-				"high":    20,
-				"default": 4,
-				"low":     1,
-			},
-		},
-		{
-			input: map[string]int{
-				"default": 10,
-			},
-			want: map[string]int{
-				"default": 1,
-			},
-		},
-		{
-			input: map[string]int{
-				"critical": 5,
-				"default":  1,
-			},
-			want: map[string]int{
-				"critical": 5,
-				"default":  1,
-			},
-		},
-		{
-			input: map[string]int{
-				"critical": 6,
-				"default":  3,
-				"low":      0,
-			},
-			want: map[string]int{
-				"critical": 2,
-				"default":  1,
-				"low":      0,
-			},
-		},
-	}
-
-	for _, tc := range tests {
-		got := normalizeQueueCfg(tc.input)
-		if diff := cmp.Diff(tc.want, got); diff != "" {
-			t.Errorf("normalizeQueueCfg(%v) = %v, want %v; (-want, +got):\n%s",
-				tc.input, got, tc.want, diff)
-		}
-	}
-}

benchmark_test.go

@@ -24,7 +24,7 @@ func BenchmarkEndToEndSimple(b *testing.B) {
 			DB:   redisDB,
 		}
 		client := NewClient(redis)
-		bg := NewBackground(redis, &Config{
+		srv := NewServer(redis, Config{
 			Concurrency: 10,
 			RetryDelayFunc: func(n int, err error, t *Task) time.Duration {
 				return time.Second
@@ -46,11 +46,11 @@ func BenchmarkEndToEndSimple(b *testing.B) {
 		}
 		b.StartTimer() // end setup
 
-		bg.start(HandlerFunc(handler))
+		srv.Start(HandlerFunc(handler))
 		wg.Wait()
 
 		b.StopTimer() // begin teardown
-		bg.stop()
+		srv.Stop()
 		b.StartTimer() // end teardown
 	}
 }
@@ -67,7 +67,7 @@ func BenchmarkEndToEnd(b *testing.B) {
 			DB:   redisDB,
 		}
 		client := NewClient(redis)
-		bg := NewBackground(redis, &Config{
+		srv := NewServer(redis, Config{
 			Concurrency: 10,
 			RetryDelayFunc: func(n int, err error, t *Task) time.Duration {
 				return time.Second
@@ -99,11 +99,11 @@ func BenchmarkEndToEnd(b *testing.B) {
 		}
 		b.StartTimer() // end setup
 
-		bg.start(HandlerFunc(handler))
+		srv.Start(HandlerFunc(handler))
 		wg.Wait()
 
 		b.StopTimer() // begin teardown
-		bg.stop()
+		srv.Stop()
 		b.StartTimer() // end teardown
 	}
 }
@@ -124,7 +124,7 @@ func BenchmarkEndToEndMultipleQueues(b *testing.B) {
 			DB:   redisDB,
 		}
 		client := NewClient(redis)
-		bg := NewBackground(redis, &Config{
+		srv := NewServer(redis, Config{
 			Concurrency: 10,
 			Queues: map[string]int{
 				"high":    6,
@@ -160,11 +160,11 @@ func BenchmarkEndToEndMultipleQueues(b *testing.B) {
 		}
 		b.StartTimer() // end setup
 
-		bg.start(HandlerFunc(handler))
+		srv.Start(HandlerFunc(handler))
 		wg.Wait()
 
 		b.StopTimer() // begin teardown
-		bg.stop()
+		srv.Stop()
 		b.StartTimer() // end teardown
 	}
 }

client.go

@@ -9,6 +9,7 @@ import (
 	"fmt"
 	"sort"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/hibiken/asynq/internal/base"
@@ -23,13 +24,18 @@ import (
 //
 // Clients are safe for concurrent use by multiple goroutines.
 type Client struct {
+	mu   sync.Mutex
+	opts map[string][]Option
 	rdb  *rdb.RDB
 }
 
 // NewClient and returns a new Client given a redis connection option.
 func NewClient(r RedisConnOpt) *Client {
 	rdb := rdb.NewRDB(createRedisClient(r))
-	return &Client{rdb}
+	return &Client{
+		opts: make(map[string][]Option),
+		rdb:  rdb,
+	}
 }
 
 // Option specifies the task processing behavior.
@@ -159,10 +165,19 @@ func serializePayload(payload map[string]interface{}) string {
 	return b.String()
 }
 
-const (
+// Default max retry count used if nothing is specified.
-	// Max retry count by default
+const defaultMaxRetry = 25
-	defaultMaxRetry = 25
+
-)
+// SetDefaultOptions sets options to be used for a given task type.
+// The argument opts specifies the behavior of task processing.
+// If there are conflicting Option values the last one overrides others.
+//
+// Default options can be overridden by options passed at enqueue time.
+func (c *Client) SetDefaultOptions(taskType string, opts ...Option) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	c.opts[taskType] = opts
+}
 
 // EnqueueAt schedules task to be enqueued at the specified time.
 //
@@ -171,6 +186,35 @@ const (
 // The argument opts specifies the behavior of task processing.
 // If there are conflicting Option values the last one overrides others.
 func (c *Client) EnqueueAt(t time.Time, task *Task, opts ...Option) error {
+	return c.enqueueAt(t, task, opts...)
+}
+
+// Enqueue enqueues task to be processed immediately.
+//
+// Enqueue returns nil if the task is enqueued successfully, otherwise returns a non-nil error.
+//
+// The argument opts specifies the behavior of task processing.
+// If there are conflicting Option values the last one overrides others.
+func (c *Client) Enqueue(task *Task, opts ...Option) error {
+	return c.enqueueAt(time.Now(), task, opts...)
+}
+
+// EnqueueIn schedules task to be enqueued after the specified delay.
+//
+// EnqueueIn returns nil if the task is scheduled successfully, otherwise returns a non-nil error.
+//
+// The argument opts specifies the behavior of task processing.
+// If there are conflicting Option values the last one overrides others.
+func (c *Client) EnqueueIn(d time.Duration, task *Task, opts ...Option) error {
+	return c.enqueueAt(time.Now().Add(d), task, opts...)
+}
+
+func (c *Client) enqueueAt(t time.Time, task *Task, opts ...Option) error {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	if defaults, ok := c.opts[task.Type]; ok {
+		opts = append(defaults, opts...)
+	}
 	opt := composeOptions(opts...)
 	msg := &base.TaskMessage{
 		ID:        xid.New(),
@@ -194,26 +238,6 @@ func (c *Client) EnqueueAt(t time.Time, task *Task, opts ...Option) error {
 	return err
 }
 
-// Enqueue enqueues task to be processed immediately.
-//
-// Enqueue returns nil if the task is enqueued successfully, otherwise returns a non-nil error.
-//
-// The argument opts specifies the behavior of task processing.
-// If there are conflicting Option values the last one overrides others.
-func (c *Client) Enqueue(task *Task, opts ...Option) error {
-	return c.EnqueueAt(time.Now(), task, opts...)
-}
-
-// EnqueueIn schedules task to be enqueued after the specified delay.
-//
-// EnqueueIn returns nil if the task is scheduled successfully, otherwise returns a non-nil error.
-//
-// The argument opts specifies the behavior of task processing.
-// If there are conflicting Option values the last one overrides others.
-func (c *Client) EnqueueIn(d time.Duration, task *Task, opts ...Option) error {
-	return c.EnqueueAt(time.Now().Add(d), task, opts...)
-}
-
 func (c *Client) enqueue(msg *base.TaskMessage, uniqueTTL time.Duration) error {
 	if uniqueTTL > 0 {
 		return c.rdb.EnqueueUnique(msg, uniqueTTL)

client_test.go

@@ -15,6 +15,11 @@ import (
 	"github.com/hibiken/asynq/internal/base"
 )
 
+var (
+	noTimeout  = time.Duration(0).String()
+	noDeadline = time.Time{}.Format(time.RFC3339)
+)
+
 func TestClientEnqueueAt(t *testing.T) {
 	r := setup(t)
 	client := NewClient(RedisClientOpt{
@@ -27,9 +32,6 @@ func TestClientEnqueueAt(t *testing.T) {
 	var (
 		now          = time.Now()
 		oneHourLater = now.Add(time.Hour)
-
-		noTimeout  = time.Duration(0).String()
-		noDeadline = time.Time{}.Format(time.RFC3339)
 	)
 
 	tests := []struct {
@@ -113,11 +115,6 @@ func TestClientEnqueue(t *testing.T) {
 
 	task := NewTask("send_email", map[string]interface{}{"to": "customer@gmail.com", "from": "merchant@example.com"})
 
-	var (
-		noTimeout  = time.Duration(0).String()
-		noDeadline = time.Time{}.Format(time.RFC3339)
-	)
-
 	tests := []struct {
 		desc         string
 		task         *Task
@@ -287,11 +284,6 @@ func TestClientEnqueueIn(t *testing.T) {
 
 	task := NewTask("send_email", map[string]interface{}{"to": "customer@gmail.com", "from": "merchant@example.com"})
 
-	var (
-		noTimeout  = time.Duration(0).String()
-		noDeadline = time.Time{}.Format(time.RFC3339)
-	)
-
 	tests := []struct {
 		desc          string
 		task          *Task
@@ -364,6 +356,86 @@ func TestClientEnqueueIn(t *testing.T) {
 	}
 }
 
+func TestClientDefaultOptions(t *testing.T) {
+	r := setup(t)
+
+	tests := []struct {
+		desc        string
+		defaultOpts []Option // options set at the client level.
+		opts        []Option // options used at enqueue time.
+		task        *Task
+		queue       string // queue that the message should go into.
+		want        *base.TaskMessage
+	}{
+		{
+			desc:        "With queue routing option",
+			defaultOpts: []Option{Queue("feed")},
+			opts:        []Option{},
+			task:        NewTask("feed:import", nil),
+			queue:       "feed",
+			want: &base.TaskMessage{
+				Type:     "feed:import",
+				Payload:  nil,
+				Retry:    defaultMaxRetry,
+				Queue:    "feed",
+				Timeout:  noTimeout,
+				Deadline: noDeadline,
+			},
+		},
+		{
+			desc:        "With multiple options",
+			defaultOpts: []Option{Queue("feed"), MaxRetry(5)},
+			opts:        []Option{},
+			task:        NewTask("feed:import", nil),
+			queue:       "feed",
+			want: &base.TaskMessage{
+				Type:     "feed:import",
+				Payload:  nil,
+				Retry:    5,
+				Queue:    "feed",
+				Timeout:  noTimeout,
+				Deadline: noDeadline,
+			},
+		},
+		{
+			desc:        "With overriding options at enqueue time",
+			defaultOpts: []Option{Queue("feed"), MaxRetry(5)},
+			opts:        []Option{Queue("critical")},
+			task:        NewTask("feed:import", nil),
+			queue:       "critical",
+			want: &base.TaskMessage{
+				Type:     "feed:import",
+				Payload:  nil,
+				Retry:    5,
+				Queue:    "critical",
+				Timeout:  noTimeout,
+				Deadline: noDeadline,
+			},
+		},
+	}
+
+	for _, tc := range tests {
+		h.FlushDB(t, r)
+		c := NewClient(RedisClientOpt{Addr: redisAddr, DB: redisDB})
+		c.SetDefaultOptions(tc.task.Type, tc.defaultOpts...)
+		err := c.Enqueue(tc.task, tc.opts...)
+		if err != nil {
+			t.Fatal(err)
+		}
+		enqueued := h.GetEnqueuedMessages(t, r, tc.queue)
+		if len(enqueued) != 1 {
+			t.Errorf("%s;\nexpected queue %q to have one message; got %d messages in the queue.",
+				tc.desc, tc.queue, len(enqueued))
+			continue
+		}
+		got := enqueued[0]
+		if diff := cmp.Diff(tc.want, got, h.IgnoreIDOpt); diff != "" {
+			t.Errorf("%s;\nmismatch found in enqueued task message; (-want,+got)\n%s",
+				tc.desc, diff)
+		}
+	}
+}
+
 func TestUniqueKey(t *testing.T) {
 	tests := []struct {
 		desc  string

doc.go

@@ -14,7 +14,7 @@ specify the options using one of RedisConnOpt types.
         DB:       3,
     }
 
-The Client is used to register a task to be processed at the specified time.
+The Client is used to enqueue a task to be processed at the specified time.
 
 Task is created with two parameters: its type and payload.
 
@@ -27,18 +27,18 @@ Task is created with two parameters: its type and payload.
     // Enqueue the task to be processed immediately.
     err := client.Enqueue(t)
 
-    // Schedule the task to be processed in one minute.
+    // Schedule the task to be processed after one minute.
     err = client.EnqueueIn(time.Minute, t)
 
-The Background is used to run the background task processing with a given
+The Server is used to run the background task processing with a given
 handler.
-    bg := asynq.NewBackground(redis, &asynq.Config{
+    srv := asynq.NewServer(redis, asynq.Config{
         Concurrency: 10,
     })
 
-    bg.Run(handler)
+    srv.Run(handler)
 
-Handler is an interface with one method ProcessTask which
+Handler is an interface type with a method which
 takes a task and returns an error. Handler should return nil if
 the processing is successful, otherwise return a non-nil error.
 If handler panics or returns a non-nil error, the task will be retried in the future.

example_test.go

@@ -0,0 +1,95 @@
+// Copyright 2020 Kentaro Hibino. All rights reserved.
+// Use of this source code is governed by a MIT license
+// that can be found in the LICENSE file.
+
+package asynq_test
+
+import (
+	"fmt"
+	"log"
+	"os"
+	"os/signal"
+
+	"github.com/hibiken/asynq"
+	"golang.org/x/sys/unix"
+)
+
+func ExampleServer_Run() {
+	srv := asynq.NewServer(
+		asynq.RedisClientOpt{Addr: ":6379"},
+		asynq.Config{Concurrency: 20},
+	)
+
+	h := asynq.NewServeMux()
+	// ... Register handlers
+
+	// Run blocks and waits for os signal to terminate the program.
+	if err := srv.Run(h); err != nil {
+		log.Fatal(err)
+	}
+}
+
+func ExampleServer_Stop() {
+	srv := asynq.NewServer(
+		asynq.RedisClientOpt{Addr: ":6379"},
+		asynq.Config{Concurrency: 20},
+	)
+
+	h := asynq.NewServeMux()
+	// ... Register handlers
+
+	if err := srv.Start(h); err != nil {
+		log.Fatal(err)
+	}
+
+	sigs := make(chan os.Signal, 1)
+	signal.Notify(sigs, unix.SIGTERM, unix.SIGINT)
+	<-sigs // wait for termination signal
+
+	srv.Stop()
+}
+
+func ExampleServer_Quiet() {
+	srv := asynq.NewServer(
+		asynq.RedisClientOpt{Addr: ":6379"},
+		asynq.Config{Concurrency: 20},
+	)
+
+	h := asynq.NewServeMux()
+	// ... Register handlers
+
+	if err := srv.Start(h); err != nil {
+		log.Fatal(err)
+	}
+
+	sigs := make(chan os.Signal, 1)
+	signal.Notify(sigs, unix.SIGTERM, unix.SIGINT, unix.SIGTSTP)
+	// Handle SIGTERM, SIGINT to exit the program.
+	// Handle SIGTSTP to stop processing new tasks.
+	for {
+		s := <-sigs
+		if s == unix.SIGTSTP {
+			srv.Quiet() // stop processing new tasks
+			continue
+		}
+		break
+	}
+
+	srv.Stop()
+}
+
+func ExampleParseRedisURI() {
+	rconn, err := asynq.ParseRedisURI("redis://localhost:6379/10")
+	if err != nil {
+		log.Fatal(err)
+	}
+	r, ok := rconn.(asynq.RedisClientOpt)
+	if !ok {
+		log.Fatal("unexpected type")
+	}
+	fmt.Println(r.Addr)
+	fmt.Println(r.DB)
+	// Output:
+	// localhost:6379
+	// 10
+}

go.mod

@@ -8,7 +8,7 @@ require (
 	github.com/rs/xid v1.2.1
 	github.com/spf13/cast v1.3.1
 	go.uber.org/goleak v0.10.0
-	golang.org/x/sys v0.0.0-20191204072324-ce4227a45e2e // indirect
+	golang.org/x/sys v0.0.0-20191204072324-ce4227a45e2e
 	golang.org/x/time v0.0.0-20190308202827-9d24e82272b4
 	gopkg.in/yaml.v2 v2.2.7 // indirect
 )

heartbeat.go

@@ -9,16 +9,15 @@ import (
 	"time"
 
 	"github.com/hibiken/asynq/internal/base"
-	"github.com/hibiken/asynq/internal/rdb"
 )
 
 // heartbeater is responsible for writing process info to redis periodically to
 // indicate that the background worker process is up.
 type heartbeater struct {
 	logger Logger
-	rdb    *rdb.RDB
+	broker base.Broker
 
-	ps *base.ProcessState
+	ss *base.ServerState
 
 	// channel to communicate back to the long running "heartbeater" goroutine.
 	done chan struct{}
@@ -27,11 +26,11 @@ type heartbeater struct {
 	interval time.Duration
 }
 
-func newHeartbeater(l Logger, rdb *rdb.RDB, ps *base.ProcessState, interval time.Duration) *heartbeater {
+func newHeartbeater(l Logger, b base.Broker, ss *base.ServerState, interval time.Duration) *heartbeater {
 	return &heartbeater{
 		logger:   l,
-		rdb:      rdb,
+		broker:   b,
-		ps:       ps,
+		ss:       ss,
 		done:     make(chan struct{}),
 		interval: interval,
 	}
@@ -44,8 +43,8 @@ func (h *heartbeater) terminate() {
 }
 
 func (h *heartbeater) start(wg *sync.WaitGroup) {
-	h.ps.SetStarted(time.Now())
+	h.ss.SetStarted(time.Now())
-	h.ps.SetStatus(base.StatusRunning)
+	h.ss.SetStatus(base.StatusRunning)
 	wg.Add(1)
 	go func() {
 		defer wg.Done()
@@ -53,7 +52,7 @@ func (h *heartbeater) start(wg *sync.WaitGroup) {
 		for {
 			select {
 			case <-h.done:
-				h.rdb.ClearProcessState(h.ps)
+				h.broker.ClearServerState(h.ss)
 				h.logger.Info("Heartbeater done")
 				return
 			case <-time.After(h.interval):
@@ -66,7 +65,7 @@ func (h *heartbeater) start(wg *sync.WaitGroup) {
 func (h *heartbeater) beat() {
 	// Note: Set TTL to be long enough so that it won't expire before we write again
 	// and short enough to expire quickly once the process is shut down or killed.
-	err := h.rdb.WriteProcessState(h.ps, h.interval*2)
+	err := h.broker.WriteServerState(h.ss, h.interval*2)
 	if err != nil {
 		h.logger.Error("could not write heartbeat data: %v", err)
 	}

heartbeat_test.go

@@ -14,6 +14,7 @@ import (
 	h "github.com/hibiken/asynq/internal/asynqtest"
 	"github.com/hibiken/asynq/internal/base"
 	"github.com/hibiken/asynq/internal/rdb"
+	"github.com/hibiken/asynq/internal/testbroker"
 )
 
 func TestHeartbeater(t *testing.T) {
@@ -31,17 +32,18 @@ func TestHeartbeater(t *testing.T) {
 	}
 
 	timeCmpOpt := cmpopts.EquateApproxTime(10 * time.Millisecond)
-	ignoreOpt := cmpopts.IgnoreUnexported(base.ProcessInfo{})
+	ignoreOpt := cmpopts.IgnoreUnexported(base.ServerInfo{})
+	ignoreFieldOpt := cmpopts.IgnoreFields(base.ServerInfo{}, "ServerID")
 	for _, tc := range tests {
 		h.FlushDB(t, r)
 
-		state := base.NewProcessState(tc.host, tc.pid, tc.concurrency, tc.queues, false)
+		state := base.NewServerState(tc.host, tc.pid, tc.concurrency, tc.queues, false)
 		hb := newHeartbeater(testLogger, rdbClient, state, tc.interval)
 
 		var wg sync.WaitGroup
 		hb.start(&wg)
 
-		want := &base.ProcessInfo{
+		want := &base.ServerInfo{
 			Host:        tc.host,
 			PID:         tc.pid,
 			Queues:      tc.queues,
@@ -53,21 +55,21 @@ func TestHeartbeater(t *testing.T) {
 		// allow for heartbeater to write to redis
 		time.Sleep(tc.interval * 2)
 
-		ps, err := rdbClient.ListProcesses()
+		ss, err := rdbClient.ListServers()
 		if err != nil {
-			t.Errorf("could not read process status from redis: %v", err)
+			t.Errorf("could not read server info from redis: %v", err)
 			hb.terminate()
 			continue
 		}
 
-		if len(ps) != 1 {
+		if len(ss) != 1 {
-			t.Errorf("(*RDB).ListProcesses returned %d process info, want 1", len(ps))
+			t.Errorf("(*RDB).ListServers returned %d process info, want 1", len(ss))
 			hb.terminate()
 			continue
 		}
 
-		if diff := cmp.Diff(want, ps[0], timeCmpOpt, ignoreOpt); diff != "" {
+		if diff := cmp.Diff(want, ss[0], timeCmpOpt, ignoreOpt, ignoreFieldOpt); diff != "" {
-			t.Errorf("redis stored process status %+v, want %+v; (-want, +got)\n%s", ps[0], want, diff)
+			t.Errorf("redis stored process status %+v, want %+v; (-want, +got)\n%s", ss[0], want, diff)
 			hb.terminate()
 			continue
 		}
@@ -79,21 +81,21 @@ func TestHeartbeater(t *testing.T) {
 		time.Sleep(tc.interval * 2)
 
 		want.Status = "stopped"
-		ps, err = rdbClient.ListProcesses()
+		ss, err = rdbClient.ListServers()
 		if err != nil {
 			t.Errorf("could not read process status from redis: %v", err)
 			hb.terminate()
 			continue
 		}
 
-		if len(ps) != 1 {
+		if len(ss) != 1 {
-			t.Errorf("(*RDB).ListProcesses returned %d process info, want 1", len(ps))
+			t.Errorf("(*RDB).ListProcesses returned %d process info, want 1", len(ss))
 			hb.terminate()
 			continue
 		}
 
-		if diff := cmp.Diff(want, ps[0], timeCmpOpt, ignoreOpt); diff != "" {
+		if diff := cmp.Diff(want, ss[0], timeCmpOpt, ignoreOpt, ignoreFieldOpt); diff != "" {
-			t.Errorf("redis stored process status %+v, want %+v; (-want, +got)\n%s", ps[0], want, diff)
+			t.Errorf("redis stored process status %+v, want %+v; (-want, +got)\n%s", ss[0], want, diff)
 			hb.terminate()
 			continue
 		}
@@ -101,3 +103,26 @@ func TestHeartbeater(t *testing.T) {
 		hb.terminate()
 	}
 }
+
+func TestHeartbeaterWithRedisDown(t *testing.T) {
+	// Make sure that heartbeater goroutine doesn't panic
+	// if it cannot connect to redis.
+	defer func() {
+		if r := recover(); r != nil {
+			t.Errorf("panic occurred: %v", r)
+		}
+	}()
+	r := rdb.NewRDB(setup(t))
+	testBroker := testbroker.NewTestBroker(r)
+	ss := base.NewServerState("localhost", 1234, 10, map[string]int{"default": 1}, false)
+	hb := newHeartbeater(testLogger, testBroker, ss, time.Second)
+
+	testBroker.Sleep()
+	var wg sync.WaitGroup
+	hb.start(&wg)
+
+	// wait for heartbeater to try writing data to redis
+	time.Sleep(2 * time.Second)
+
+	hb.terminate()
+}

internal/asynqtest/asynqtest.go

@@ -41,9 +41,9 @@ var SortZSetEntryOpt = cmp.Transformer("SortZSetEntries", func(in []ZSetEntry) [
 	return out
 })
 
-// SortProcessInfoOpt is a cmp.Option to sort base.ProcessInfo for comparing slice of process info.
+// SortServerInfoOpt is a cmp.Option to sort base.ServerInfo for comparing slice of process info.
-var SortProcessInfoOpt = cmp.Transformer("SortProcessInfo", func(in []*base.ProcessInfo) []*base.ProcessInfo {
+var SortServerInfoOpt = cmp.Transformer("SortServerInfo", func(in []*base.ServerInfo) []*base.ServerInfo {
-	out := append([]*base.ProcessInfo(nil), in...) // Copy input to avoid mutating it
+	out := append([]*base.ServerInfo(nil), in...) // Copy input to avoid mutating it
 	sort.Slice(out, func(i, j int) bool {
 		if out[i].Host != out[j].Host {
 			return out[i].Host < out[j].Host

internal/base/base.go

@@ -12,6 +12,7 @@ import (
 	"sync"
 	"time"
 
+	"github.com/go-redis/redis/v7"
 	"github.com/rs/xid"
 )
 
@@ -20,10 +21,10 @@ const DefaultQueueName = "default"
 
 // Redis keys
 const (
-	AllProcesses    = "asynq:ps"                     // ZSET
+	AllServers      = "asynq:servers"                // ZSET
-	psPrefix        = "asynq:ps:"                    // STRING - asynq:ps:<host>:<pid>
+	serversPrefix   = "asynq:servers:"               // STRING - asynq:ps:<host>:<pid>:<serverid>
 	AllWorkers      = "asynq:workers"                // ZSET
-	workersPrefix   = "asynq:workers:"               // HASH   - asynq:workers:<host:<pid>
+	workersPrefix   = "asynq:workers:"               // HASH   - asynq:workers:<host:<pid>:<serverid>
 	processedPrefix = "asynq:processed:"             // STRING - asynq:processed:<yyyy-mm-dd>
 	failurePrefix   = "asynq:failure:"               // STRING - asynq:failure:<yyyy-mm-dd>
 	QueuePrefix     = "asynq:queues:"                // LIST   - asynq:queues:<qname>
@@ -51,14 +52,14 @@ func FailureKey(t time.Time) string {
 	return failurePrefix + t.UTC().Format("2006-01-02")
 }
 
-// ProcessInfoKey returns a redis key for process info.
+// ServerInfoKey returns a redis key for process info.
-func ProcessInfoKey(hostname string, pid int) string {
+func ServerInfoKey(hostname string, pid int, sid string) string {
-	return fmt.Sprintf("%s%s:%d", psPrefix, hostname, pid)
+	return fmt.Sprintf("%s%s:%d:%s", serversPrefix, hostname, pid, sid)
 }
 
-// WorkersKey returns a redis key for the workers given hostname and pid.
+// WorkersKey returns a redis key for the workers given hostname, pid, and server ID.
-func WorkersKey(hostname string, pid int) string {
+func WorkersKey(hostname string, pid int, sid string) string {
-	return fmt.Sprintf("%s%s:%d", workersPrefix, hostname, pid)
+	return fmt.Sprintf("%s%s:%d:%s", workersPrefix, hostname, pid, sid)
 }
 
 // TaskMessage is the internal representation of a task with additional metadata fields.
@@ -104,42 +105,47 @@ type TaskMessage struct {
 	UniqueKey string
 }
 
-// ProcessState holds process level information.
+// ServerState holds process level information.
 //
-// ProcessStates are safe for concurrent use by multiple goroutines.
+// ServerStates are safe for concurrent use by multiple goroutines.
-type ProcessState struct {
+type ServerState struct {
 	mu             sync.Mutex // guards all data fields
+	id             xid.ID
 	concurrency    int
 	queues         map[string]int
 	strictPriority bool
 	pid            int
 	host           string
-	status         PStatus
+	status         ServerStatus
 	started        time.Time
 	workers        map[string]*workerStats
 }
 
-// PStatus represents status of a process.
+// ServerStatus represents status of a server.
-type PStatus int
+type ServerStatus int
 
 const (
-	// StatusIdle indicates process is in idle state.
+	// StatusIdle indicates the server is in idle state.
-	StatusIdle PStatus = iota
+	StatusIdle ServerStatus = iota
 
-	// StatusRunning indicates process is up and processing tasks.
+	// StatusRunning indicates the servier is up and processing tasks.
 	StatusRunning
 
-	// StatusStopped indicates process is up but not processing new tasks.
+	// StatusQuiet indicates the server is up but not processing new tasks.
+	StatusQuiet
+
+	// StatusStopped indicates the server server has been stopped.
 	StatusStopped
 )
 
 var statuses = []string{
 	"idle",
 	"running",
+	"quiet",
 	"stopped",
 }
 
-func (s PStatus) String() string {
+func (s ServerStatus) String() string {
 	if StatusIdle <= s && s <= StatusStopped {
 		return statuses[s]
 	}
@@ -151,11 +157,12 @@ type workerStats struct {
 	started time.Time
 }
 
-// NewProcessState returns a new instance of ProcessState.
+// NewServerState returns a new instance of ServerState.
-func NewProcessState(host string, pid, concurrency int, queues map[string]int, strict bool) *ProcessState {
+func NewServerState(host string, pid, concurrency int, queues map[string]int, strict bool) *ServerState {
-	return &ProcessState{
+	return &ServerState{
 		host:           host,
 		pid:            pid,
+		id:             xid.New(),
 		concurrency:    concurrency,
 		queues:         cloneQueueConfig(queues),
 		strictPriority: strict,
@@ -164,59 +171,67 @@ func NewProcessState(host string, pid, concurrency int, queues map[string]int, s
 	}
 }
 
-// SetStatus updates the state of process.
+// SetStatus updates the status of server.
-func (ps *ProcessState) SetStatus(status PStatus) {
+func (ss *ServerState) SetStatus(status ServerStatus) {
-	ps.mu.Lock()
+	ss.mu.Lock()
-	defer ps.mu.Unlock()
+	defer ss.mu.Unlock()
-	ps.status = status
+	ss.status = status
+}
+
+// Status returns the status of server.
+func (ss *ServerState) Status() ServerStatus {
+	ss.mu.Lock()
+	defer ss.mu.Unlock()
+	return ss.status
 }
 
 // SetStarted records when the process started processing.
-func (ps *ProcessState) SetStarted(t time.Time) {
+func (ss *ServerState) SetStarted(t time.Time) {
-	ps.mu.Lock()
+	ss.mu.Lock()
-	defer ps.mu.Unlock()
+	defer ss.mu.Unlock()
-	ps.started = t
+	ss.started = t
 }
 
 // AddWorkerStats records when a worker started and which task it's processing.
-func (ps *ProcessState) AddWorkerStats(msg *TaskMessage, started time.Time) {
+func (ss *ServerState) AddWorkerStats(msg *TaskMessage, started time.Time) {
-	ps.mu.Lock()
+	ss.mu.Lock()
-	defer ps.mu.Unlock()
+	defer ss.mu.Unlock()
-	ps.workers[msg.ID.String()] = &workerStats{msg, started}
+	ss.workers[msg.ID.String()] = &workerStats{msg, started}
 }
 
 // DeleteWorkerStats removes a worker's entry from the process state.
-func (ps *ProcessState) DeleteWorkerStats(msg *TaskMessage) {
+func (ss *ServerState) DeleteWorkerStats(msg *TaskMessage) {
-	ps.mu.Lock()
+	ss.mu.Lock()
-	defer ps.mu.Unlock()
+	defer ss.mu.Unlock()
-	delete(ps.workers, msg.ID.String())
+	delete(ss.workers, msg.ID.String())
 }
 
-// Get returns current state of process as a ProcessInfo.
+// GetInfo returns current state of server as a ServerInfo.
-func (ps *ProcessState) Get() *ProcessInfo {
+func (ss *ServerState) GetInfo() *ServerInfo {
-	ps.mu.Lock()
+	ss.mu.Lock()
-	defer ps.mu.Unlock()
+	defer ss.mu.Unlock()
-	return &ProcessInfo{
+	return &ServerInfo{
-		Host:              ps.host,
+		Host:              ss.host,
-		PID:               ps.pid,
+		PID:               ss.pid,
-		Concurrency:       ps.concurrency,
+		ServerID:          ss.id.String(),
-		Queues:            cloneQueueConfig(ps.queues),
+		Concurrency:       ss.concurrency,
-		StrictPriority:    ps.strictPriority,
+		Queues:            cloneQueueConfig(ss.queues),
-		Status:            ps.status.String(),
+		StrictPriority:    ss.strictPriority,
-		Started:           ps.started,
+		Status:            ss.status.String(),
-		ActiveWorkerCount: len(ps.workers),
+		Started:           ss.started,
+		ActiveWorkerCount: len(ss.workers),
 	}
 }
 
 // GetWorkers returns a list of currently running workers' info.
-func (ps *ProcessState) GetWorkers() []*WorkerInfo {
+func (ss *ServerState) GetWorkers() []*WorkerInfo {
-	ps.mu.Lock()
+	ss.mu.Lock()
-	defer ps.mu.Unlock()
+	defer ss.mu.Unlock()
 	var res []*WorkerInfo
-	for _, w := range ps.workers {
+	for _, w := range ss.workers {
 		res = append(res, &WorkerInfo{
-			Host:    ps.host,
+			Host:    ss.host,
-			PID:     ps.pid,
+			PID:     ss.pid,
 			ID:      w.msg.ID,
 			Type:    w.msg.Type,
 			Queue:   w.msg.Queue,
@@ -243,10 +258,11 @@ func clonePayload(payload map[string]interface{}) map[string]interface{} {
 	return res
 }
 
-// ProcessInfo holds information about a running background worker process.
+// ServerInfo holds information about a running server.
-type ProcessInfo struct {
+type ServerInfo struct {
 	Host              string
 	PID               int
+	ServerID          string
 	Concurrency       int
 	Queues            map[string]int
 	StrictPriority    bool
@@ -313,3 +329,25 @@ func (c *Cancelations) GetAll() []context.CancelFunc {
 	}
 	return res
 }
+
+// Broker is a message broker that supports operations to manage task queues.
+//
+// See rdb.RDB as a reference implementation.
+type Broker interface {
+	Enqueue(msg *TaskMessage) error
+	EnqueueUnique(msg *TaskMessage, ttl time.Duration) error
+	Dequeue(qnames ...string) (*TaskMessage, error)
+	Done(msg *TaskMessage) error
+	Requeue(msg *TaskMessage) error
+	Schedule(msg *TaskMessage, processAt time.Time) error
+	ScheduleUnique(msg *TaskMessage, processAt time.Time, ttl time.Duration) error
+	Retry(msg *TaskMessage, processAt time.Time, errMsg string) error
+	Kill(msg *TaskMessage, errMsg string) error
+	RequeueAll() (int64, error)
+	CheckAndEnqueue(qnames ...string) error
+	WriteServerState(ss *ServerState, ttl time.Duration) error
+	ClearServerState(ss *ServerState) error
+	CancelationPubSub() (*redis.PubSub, error) // TODO: Need to decouple from redis to support other brokers
+	PublishCancelation(id string) error
+	Close() error
+}

internal/base/base_test.go

@@ -12,6 +12,7 @@ import (
 	"time"
 
 	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
 	"github.com/rs/xid"
 )
 
@@ -67,20 +68,22 @@ func TestFailureKey(t *testing.T) {
 	}
 }
 
-func TestProcessInfoKey(t *testing.T) {
+func TestServerInfoKey(t *testing.T) {
 	tests := []struct {
 		hostname string
 		pid      int
+		sid      string
 		want     string
 	}{
-		{"localhost", 9876, "asynq:ps:localhost:9876"},
+		{"localhost", 9876, "server123", "asynq:servers:localhost:9876:server123"},
-		{"127.0.0.1", 1234, "asynq:ps:127.0.0.1:1234"},
+		{"127.0.0.1", 1234, "server987", "asynq:servers:127.0.0.1:1234:server987"},
 	}
 
 	for _, tc := range tests {
-		got := ProcessInfoKey(tc.hostname, tc.pid)
+		got := ServerInfoKey(tc.hostname, tc.pid, tc.sid)
 		if got != tc.want {
-			t.Errorf("ProcessInfoKey(%q, %d) = %q, want %q", tc.hostname, tc.pid, got, tc.want)
+			t.Errorf("ServerInfoKey(%q, %d, %q) = %q, want %q",
+				tc.hostname, tc.pid, tc.sid, got, tc.want)
 		}
 	}
 }
@@ -89,24 +92,26 @@ func TestWorkersKey(t *testing.T) {
 	tests := []struct {
 		hostname string
 		pid      int
+		sid      string
 		want     string
 	}{
-		{"localhost", 9876, "asynq:workers:localhost:9876"},
+		{"localhost", 9876, "server1", "asynq:workers:localhost:9876:server1"},
-		{"127.0.0.1", 1234, "asynq:workers:127.0.0.1:1234"},
+		{"127.0.0.1", 1234, "server2", "asynq:workers:127.0.0.1:1234:server2"},
 	}
 
 	for _, tc := range tests {
-		got := WorkersKey(tc.hostname, tc.pid)
+		got := WorkersKey(tc.hostname, tc.pid, tc.sid)
 		if got != tc.want {
-			t.Errorf("WorkersKey(%q, %d) = %q, want = %q", tc.hostname, tc.pid, got, tc.want)
+			t.Errorf("WorkersKey(%q, %d, %q) = %q, want = %q",
+				tc.hostname, tc.pid, tc.sid, got, tc.want)
 		}
 	}
 }
 
-// Test for process state being accessed by multiple goroutines.
+// Test for server state being accessed by multiple goroutines.
 // Run with -race flag to check for data race.
-func TestProcessStateConcurrentAccess(t *testing.T) {
+func TestServerStateConcurrentAccess(t *testing.T) {
-	ps := NewProcessState("127.0.0.1", 1234, 10, map[string]int{"default": 1}, false)
+	ss := NewServerState("127.0.0.1", 1234, 10, map[string]int{"default": 1}, false)
 	var wg sync.WaitGroup
 	started := time.Now()
 	msgs := []*TaskMessage{
@@ -119,18 +124,21 @@ func TestProcessStateConcurrentAccess(t *testing.T) {
 	wg.Add(1)
 	go func() {
 		defer wg.Done()
-		ps.SetStarted(started)
+		ss.SetStarted(started)
-		ps.SetStatus(StatusRunning)
+		ss.SetStatus(StatusRunning)
+		if status := ss.Status(); status != StatusRunning {
+			t.Errorf("(*ServerState).Status() = %v, want %v", status, StatusRunning)
+		}
 	}()
 
 	// Simulate processor starting worker goroutines.
 	for _, msg := range msgs {
 		wg.Add(1)
-		ps.AddWorkerStats(msg, time.Now())
+		ss.AddWorkerStats(msg, time.Now())
 		go func(msg *TaskMessage) {
 			defer wg.Done()
 			time.Sleep(time.Duration(rand.Intn(500)) * time.Millisecond)
-			ps.DeleteWorkerStats(msg)
+			ss.DeleteWorkerStats(msg)
 		}(msg)
 	}
 
@@ -139,15 +147,15 @@ func TestProcessStateConcurrentAccess(t *testing.T) {
 	go func() {
 		wg.Done()
 		for i := 0; i < 5; i++ {
-			ps.Get()
+			ss.GetInfo()
-			ps.GetWorkers()
+			ss.GetWorkers()
 			time.Sleep(time.Duration(rand.Intn(100)) * time.Millisecond)
 		}
 	}()
 
 	wg.Wait()
 
-	want := &ProcessInfo{
+	want := &ServerInfo{
 		Host:              "127.0.0.1",
 		PID:               1234,
 		Concurrency:       10,
@@ -158,9 +166,9 @@ func TestProcessStateConcurrentAccess(t *testing.T) {
 		ActiveWorkerCount: 0,
 	}
 
-	got := ps.Get()
+	got := ss.GetInfo()
-	if diff := cmp.Diff(want, got); diff != "" {
+	if diff := cmp.Diff(want, got, cmpopts.IgnoreFields(ServerInfo{}, "ServerID")); diff != "" {
-		t.Errorf("(*ProcessState).Get() = %+v, want %+v; (-want,+got)\n%s",
+		t.Errorf("(*ServerState).GetInfo() = %+v, want %+v; (-want,+got)\n%s",
 			got, want, diff)
 	}
 }

internal/rdb/inspect.go

@@ -759,23 +759,23 @@ func (r *RDB) RemoveQueue(qname string, force bool) error {
 }
 
 // Note: Script also removes stale keys.
-var listProcessesCmd = redis.NewScript(`
+var listServersCmd = redis.NewScript(`
 local res = {}
 local now = tonumber(ARGV[1])
 local keys = redis.call("ZRANGEBYSCORE", KEYS[1], now, "+inf")
 for _, key in ipairs(keys) do
-	local ps = redis.call("GET", key)
+	local s = redis.call("GET", key)
-	if ps then
+	if s then
-		table.insert(res, ps)
+		table.insert(res, s)
 	end  
 end
 redis.call("ZREMRANGEBYSCORE", KEYS[1], "-inf", now-1)
 return res`)
 
-// ListProcesses returns the list of process statuses.
+// ListServers returns the list of server info.
-func (r *RDB) ListProcesses() ([]*base.ProcessInfo, error) {
+func (r *RDB) ListServers() ([]*base.ServerInfo, error) {
-	res, err := listProcessesCmd.Run(r.client,
+	res, err := listServersCmd.Run(r.client,
-		[]string{base.AllProcesses}, time.Now().UTC().Unix()).Result()
+		[]string{base.AllServers}, time.Now().UTC().Unix()).Result()
 	if err != nil {
 		return nil, err
 	}
@@ -783,16 +783,16 @@ func (r *RDB) ListProcesses() ([]*base.ProcessInfo, error) {
 	if err != nil {
 		return nil, err
 	}
-	var processes []*base.ProcessInfo
+	var servers []*base.ServerInfo
 	for _, s := range data {
-		var ps base.ProcessInfo
+		var info base.ServerInfo
-		err := json.Unmarshal([]byte(s), &ps)
+		err := json.Unmarshal([]byte(s), &info)
 		if err != nil {
 			continue // skip bad data
 		}
-		processes = append(processes, &ps)
+		servers = append(servers, &info)
 	}
-	return processes, nil
+	return servers, nil
 }
 
 // Note: Script also removes stale keys.

internal/rdb/inspect_test.go

@@ -2051,14 +2051,14 @@ func TestRemoveQueueError(t *testing.T) {
 	}
 }
 
-func TestListProcesses(t *testing.T) {
+func TestListServers(t *testing.T) {
 	r := setup(t)
 
 	started1 := time.Now().Add(-time.Hour)
-	ps1 := base.NewProcessState("do.droplet1", 1234, 10, map[string]int{"default": 1}, false)
+	ss1 := base.NewServerState("do.droplet1", 1234, 10, map[string]int{"default": 1}, false)
-	ps1.SetStarted(started1)
+	ss1.SetStarted(started1)
-	ps1.SetStatus(base.StatusRunning)
+	ss1.SetStatus(base.StatusRunning)
-	info1 := &base.ProcessInfo{
+	info1 := &base.ServerInfo{
 		Concurrency:       10,
 		Queues:            map[string]int{"default": 1},
 		Host:              "do.droplet1",
@@ -2069,11 +2069,11 @@ func TestListProcesses(t *testing.T) {
 	}
 
 	started2 := time.Now().Add(-2 * time.Hour)
-	ps2 := base.NewProcessState("do.droplet2", 9876, 20, map[string]int{"email": 1}, false)
+	ss2 := base.NewServerState("do.droplet2", 9876, 20, map[string]int{"email": 1}, false)
-	ps2.SetStarted(started2)
+	ss2.SetStarted(started2)
-	ps2.SetStatus(base.StatusStopped)
+	ss2.SetStatus(base.StatusStopped)
-	ps2.AddWorkerStats(h.NewTaskMessage("send_email", nil), time.Now())
+	ss2.AddWorkerStats(h.NewTaskMessage("send_email", nil), time.Now())
-	info2 := &base.ProcessInfo{
+	info2 := &base.ServerInfo{
 		Concurrency:       20,
 		Queues:            map[string]int{"email": 1},
 		Host:              "do.droplet2",
@@ -2084,41 +2084,42 @@ func TestListProcesses(t *testing.T) {
 	}
 
 	tests := []struct {
-		processes []*base.ProcessState
+		serverStates []*base.ServerState
-		want      []*base.ProcessInfo
+		want         []*base.ServerInfo
 	}{
 		{
-			processes: []*base.ProcessState{},
+			serverStates: []*base.ServerState{},
-			want:      []*base.ProcessInfo{},
+			want:         []*base.ServerInfo{},
 		},
 		{
-			processes: []*base.ProcessState{ps1},
+			serverStates: []*base.ServerState{ss1},
-			want:      []*base.ProcessInfo{info1},
+			want:         []*base.ServerInfo{info1},
 		},
 		{
-			processes: []*base.ProcessState{ps1, ps2},
+			serverStates: []*base.ServerState{ss1, ss2},
-			want:      []*base.ProcessInfo{info1, info2},
+			want:         []*base.ServerInfo{info1, info2},
 		},
 	}
 
-	ignoreOpt := cmpopts.IgnoreUnexported(base.ProcessInfo{})
+	ignoreOpt := cmpopts.IgnoreUnexported(base.ServerInfo{})
+	ignoreFieldOpt := cmpopts.IgnoreFields(base.ServerInfo{}, "ServerID")
 
 	for _, tc := range tests {
 		h.FlushDB(t, r.client)
 
-		for _, ps := range tc.processes {
+		for _, ss := range tc.serverStates {
-			if err := r.WriteProcessState(ps, 5*time.Second); err != nil {
+			if err := r.WriteServerState(ss, 5*time.Second); err != nil {
 				t.Fatal(err)
 			}
 		}
 
-		got, err := r.ListProcesses()
+		got, err := r.ListServers()
 		if err != nil {
-			t.Errorf("r.ListProcesses returned an error: %v", err)
+			t.Errorf("r.ListServers returned an error: %v", err)
 		}
-		if diff := cmp.Diff(tc.want, got, h.SortProcessInfoOpt, ignoreOpt); diff != "" {
+		if diff := cmp.Diff(tc.want, got, h.SortServerInfoOpt, ignoreOpt, ignoreFieldOpt); diff != "" {
-			t.Errorf("r.ListProcesses returned %v, want %v; (-want,+got)\n%s",
+			t.Errorf("r.ListServers returned %v, want %v; (-want,+got)\n%s",
-				got, tc.processes, diff)
+				got, tc.serverStates, diff)
 		}
 	}
 }
@@ -2164,15 +2165,15 @@ func TestListWorkers(t *testing.T) {
 	for _, tc := range tests {
 		h.FlushDB(t, r.client)
 
-		ps := base.NewProcessState(host, pid, 10, map[string]int{"default": 1}, false)
+		ss := base.NewServerState(host, pid, 10, map[string]int{"default": 1}, false)
 
 		for _, w := range tc.workers {
-			ps.AddWorkerStats(w.msg, w.started)
+			ss.AddWorkerStats(w.msg, w.started)
 		}
 
-		err := r.WriteProcessState(ps, time.Minute)
+		err := r.WriteServerState(ss, time.Minute)
 		if err != nil {
-			t.Errorf("could not write process state to redis: %v", err)
+			t.Errorf("could not write server state to redis: %v", err)
 			continue
 		}
 

internal/rdb/rdb.go

@@ -463,9 +463,9 @@ func (r *RDB) forwardSingle(src, dst string) error {
 		[]string{src, dst}, now).Err()
 }
 
-// KEYS[1]  -> asynq:ps:<host:pid>
+// KEYS[1]  -> asynq:servers:<host:pid:sid>
-// KEYS[2]  -> asynq:ps
+// KEYS[2]  -> asynq:servers
-// KEYS[3]  -> asynq:workers<host:pid>
+// KEYS[3]  -> asynq:workers<host:pid:sid>
 // keys[4]  -> asynq:workers
 // ARGV[1]  -> expiration time
 // ARGV[2]  -> TTL in seconds
@@ -484,16 +484,16 @@ redis.call("EXPIRE", KEYS[3], ARGV[2])
 redis.call("ZADD", KEYS[4], ARGV[1], KEYS[3])
 return redis.status_reply("OK")`)
 
-// WriteProcessState writes process state data to redis with expiration  set to the value ttl.
+// WriteServerState writes server state data to redis with expiration  set to the value ttl.
-func (r *RDB) WriteProcessState(ps *base.ProcessState, ttl time.Duration) error {
+func (r *RDB) WriteServerState(ss *base.ServerState, ttl time.Duration) error {
-	info := ps.Get()
+	info := ss.GetInfo()
 	bytes, err := json.Marshal(info)
 	if err != nil {
 		return err
 	}
 	var args []interface{} // args to the lua script
 	exp := time.Now().Add(ttl).UTC()
-	workers := ps.GetWorkers()
+	workers := ss.GetWorkers()
 	args = append(args, float64(exp.Unix()), ttl.Seconds(), bytes)
 	for _, w := range workers {
 		bytes, err := json.Marshal(w)
@@ -502,17 +502,17 @@ func (r *RDB) WriteProcessState(ps *base.ProcessState, ttl time.Duration) error
 		}
 		args = append(args, w.ID.String(), bytes)
 	}
-	pkey := base.ProcessInfoKey(info.Host, info.PID)
+	skey := base.ServerInfoKey(info.Host, info.PID, info.ServerID)
-	wkey := base.WorkersKey(info.Host, info.PID)
+	wkey := base.WorkersKey(info.Host, info.PID, info.ServerID)
 	return writeProcessInfoCmd.Run(r.client,
-		[]string{pkey, base.AllProcesses, wkey, base.AllWorkers},
+		[]string{skey, base.AllServers, wkey, base.AllWorkers},
 		args...).Err()
 }
 
-// KEYS[1] -> asynq:ps
+// KEYS[1] -> asynq:servers
-// KEYS[2] -> asynq:ps:<host:pid>
+// KEYS[2] -> asynq:servers:<host:pid:sid>
 // KEYS[3] -> asynq:workers
-// KEYS[4] -> asynq:workers<host:pid>
+// KEYS[4] -> asynq:workers<host:pid:sid>
 var clearProcessInfoCmd = redis.NewScript(`
 redis.call("ZREM", KEYS[1], KEYS[2])
 redis.call("DEL", KEYS[2])
@@ -520,14 +520,14 @@ redis.call("ZREM", KEYS[3], KEYS[4])
 redis.call("DEL", KEYS[4])
 return redis.status_reply("OK")`)
 
-// ClearProcessState deletes process state data from redis.
+// ClearServerState deletes server state data from redis.
-func (r *RDB) ClearProcessState(ps *base.ProcessState) error {
+func (r *RDB) ClearServerState(ss *base.ServerState) error {
-	info := ps.Get()
+	info := ss.GetInfo()
-	host, pid := info.Host, info.PID
+	host, pid, id := info.Host, info.PID, info.ServerID
-	pkey := base.ProcessInfoKey(host, pid)
+	skey := base.ServerInfoKey(host, pid, id)
-	wkey := base.WorkersKey(host, pid)
+	wkey := base.WorkersKey(host, pid, id)
 	return clearProcessInfoCmd.Run(r.client,
-		[]string{base.AllProcesses, pkey, base.AllWorkers, wkey}).Err()
+		[]string{base.AllServers, skey, base.AllWorkers, wkey}).Err()
 }
 
 // CancelationPubSub returns a pubsub for cancelation messages.

internal/rdb/rdb_test.go

@@ -862,60 +862,61 @@ func TestCheckAndEnqueue(t *testing.T) {
 	}
 }
 
-func TestWriteProcessState(t *testing.T) {
+func TestWriteServerState(t *testing.T) {
 	r := setup(t)
-	host, pid := "localhost", 98765
 	queues := map[string]int{"default": 2, "email": 5, "low": 1}
 
 	started := time.Now()
-	ps := base.NewProcessState(host, pid, 10, queues, false)
+	ss := base.NewServerState("localhost", 4242, 10, queues, false)
-	ps.SetStarted(started)
+	ss.SetStarted(started)
-	ps.SetStatus(base.StatusRunning)
+	ss.SetStatus(base.StatusRunning)
 	ttl := 5 * time.Second
 
 	h.FlushDB(t, r.client)
 
-	err := r.WriteProcessState(ps, ttl)
+	err := r.WriteServerState(ss, ttl)
 	if err != nil {
-		t.Errorf("r.WriteProcessState returned an error: %v", err)
+		t.Errorf("r.WriteServerState returned an error: %v", err)
 	}
 
-	// Check ProcessInfo was written correctly
+	// Check ServerInfo was written correctly
-	pkey := base.ProcessInfoKey(host, pid)
+	info := ss.GetInfo()
-	data := r.client.Get(pkey).Val()
+	skey := base.ServerInfoKey(info.Host, info.PID, info.ServerID)
-	var got base.ProcessInfo
+	data := r.client.Get(skey).Val()
+	var got base.ServerInfo
 	err = json.Unmarshal([]byte(data), &got)
 	if err != nil {
 		t.Fatalf("could not decode json: %v", err)
 	}
-	want := base.ProcessInfo{
+	want := base.ServerInfo{
-		Host:              "localhost",
+		Host:              info.Host,
-		PID:               98765,
+		PID:               info.PID,
-		Concurrency:       10,
+		Concurrency:       info.Concurrency,
 		Queues:            map[string]int{"default": 2, "email": 5, "low": 1},
 		StrictPriority:    false,
 		Status:            "running",
 		Started:           started,
 		ActiveWorkerCount: 0,
 	}
-	if diff := cmp.Diff(want, got); diff != "" {
+	ignoreOpt := cmpopts.IgnoreFields(base.ServerInfo{}, "ServerID")
-		t.Errorf("persisted ProcessInfo was %v, want %v; (-want,+got)\n%s",
+	if diff := cmp.Diff(want, got, ignoreOpt); diff != "" {
+		t.Errorf("persisted ServerInfo was %v, want %v; (-want,+got)\n%s",
 			got, want, diff)
 	}
-	// Check ProcessInfo TTL was set correctly
+	// Check ServerInfo TTL was set correctly
-	gotTTL := r.client.TTL(pkey).Val()
+	gotTTL := r.client.TTL(skey).Val()
 	if !cmp.Equal(ttl.Seconds(), gotTTL.Seconds(), cmpopts.EquateApprox(0, 1)) {
-		t.Errorf("TTL of %q was %v, want %v", pkey, gotTTL, ttl)
+		t.Errorf("TTL of %q was %v, want %v", skey, gotTTL, ttl)
 	}
-	// Check ProcessInfo key was added to the set correctly
+	// Check ServerInfo key was added to the set correctly
-	gotProcesses := r.client.ZRange(base.AllProcesses, 0, -1).Val()
+	gotProcesses := r.client.ZRange(base.AllServers, 0, -1).Val()
-	wantProcesses := []string{pkey}
+	wantProcesses := []string{skey}
 	if diff := cmp.Diff(wantProcesses, gotProcesses); diff != "" {
-		t.Errorf("%q contained %v, want %v", base.AllProcesses, gotProcesses, wantProcesses)
+		t.Errorf("%q contained %v, want %v", base.AllServers, gotProcesses, wantProcesses)
 	}
 
 	// Check WorkersInfo was written correctly
-	wkey := base.WorkersKey(host, pid)
+	wkey := base.WorkersKey(info.Host, info.PID, info.ServerID)
 	workerExist := r.client.Exists(wkey).Val()
 	if workerExist != 0 {
 		t.Errorf("%q key exists", wkey)
@@ -928,9 +929,8 @@ func TestWriteProcessState(t *testing.T) {
 	}
 }
 
-func TestWriteProcessStateWithWorkers(t *testing.T) {
+func TestWriteServerStateWithWorkers(t *testing.T) {
 	r := setup(t)
-	host, pid := "localhost", 98765
 	queues := map[string]int{"default": 2, "email": 5, "low": 1}
 	concurrency := 10
 
@@ -939,31 +939,33 @@ func TestWriteProcessStateWithWorkers(t *testing.T) {
 	w2Started := time.Now().Add(-time.Second)
 	msg1 := h.NewTaskMessage("send_email", map[string]interface{}{"user_id": "123"})
 	msg2 := h.NewTaskMessage("gen_thumbnail", map[string]interface{}{"path": "some/path/to/imgfile"})
-	ps := base.NewProcessState(host, pid, concurrency, queues, false)
+	ss := base.NewServerState("127.0.01", 4242, concurrency, queues, false)
-	ps.SetStarted(started)
+	ss.SetStarted(started)
-	ps.SetStatus(base.StatusRunning)
+	ss.SetStatus(base.StatusRunning)
-	ps.AddWorkerStats(msg1, w1Started)
+	ss.AddWorkerStats(msg1, w1Started)
-	ps.AddWorkerStats(msg2, w2Started)
+	ss.AddWorkerStats(msg2, w2Started)
 	ttl := 5 * time.Second
 
 	h.FlushDB(t, r.client)
 
-	err := r.WriteProcessState(ps, ttl)
+	err := r.WriteServerState(ss, ttl)
 	if err != nil {
-		t.Errorf("r.WriteProcessState returned an error: %v", err)
+		t.Errorf("r.WriteServerState returned an error: %v", err)
 	}
 
-	// Check ProcessInfo was written correctly
+	// Check ServerInfo was written correctly
-	pkey := base.ProcessInfoKey(host, pid)
+	info := ss.GetInfo()
-	data := r.client.Get(pkey).Val()
+	skey := base.ServerInfoKey(info.Host, info.PID, info.ServerID)
-	var got base.ProcessInfo
+	data := r.client.Get(skey).Val()
+	var got base.ServerInfo
 	err = json.Unmarshal([]byte(data), &got)
 	if err != nil {
 		t.Fatalf("could not decode json: %v", err)
 	}
-	want := base.ProcessInfo{
+	want := base.ServerInfo{
-		Host:              host,
+		Host:              info.Host,
-		PID:               pid,
+		PID:               info.PID,
+		ServerID:          info.ServerID,
 		Concurrency:       concurrency,
 		Queues:            queues,
 		StrictPriority:    false,
@@ -972,23 +974,23 @@ func TestWriteProcessStateWithWorkers(t *testing.T) {
 		ActiveWorkerCount: 2,
 	}
 	if diff := cmp.Diff(want, got); diff != "" {
-		t.Errorf("persisted ProcessInfo was %v, want %v; (-want,+got)\n%s",
+		t.Errorf("persisted ServerInfo was %v, want %v; (-want,+got)\n%s",
 			got, want, diff)
 	}
-	// Check ProcessInfo TTL was set correctly
+	// Check ServerInfo TTL was set correctly
-	gotTTL := r.client.TTL(pkey).Val()
+	gotTTL := r.client.TTL(skey).Val()
 	if !cmp.Equal(ttl.Seconds(), gotTTL.Seconds(), cmpopts.EquateApprox(0, 1)) {
-		t.Errorf("TTL of %q was %v, want %v", pkey, gotTTL, ttl)
+		t.Errorf("TTL of %q was %v, want %v", skey, gotTTL, ttl)
 	}
-	// Check ProcessInfo key was added to the set correctly
+	// Check ServerInfo key was added to the set correctly
-	gotProcesses := r.client.ZRange(base.AllProcesses, 0, -1).Val()
+	gotProcesses := r.client.ZRange(base.AllServers, 0, -1).Val()
-	wantProcesses := []string{pkey}
+	wantProcesses := []string{skey}
 	if diff := cmp.Diff(wantProcesses, gotProcesses); diff != "" {
-		t.Errorf("%q contained %v, want %v", base.AllProcesses, gotProcesses, wantProcesses)
+		t.Errorf("%q contained %v, want %v", base.AllServers, gotProcesses, wantProcesses)
 	}
 
 	// Check WorkersInfo was written correctly
-	wkey := base.WorkersKey(host, pid)
+	wkey := base.WorkersKey(info.Host, info.PID, info.ServerID)
 	wdata := r.client.HGetAll(wkey).Val()
 	if len(wdata) != 2 {
 		t.Fatalf("HGETALL %q returned a hash of size %d, want 2", wkey, len(wdata))
@@ -1003,8 +1005,8 @@ func TestWriteProcessStateWithWorkers(t *testing.T) {
 	}
 	wantWorkers := map[string]*base.WorkerInfo{
 		msg1.ID.String(): {
-			Host:    host,
+			Host:    info.Host,
-			PID:     pid,
+			PID:     info.PID,
 			ID:      msg1.ID,
 			Type:    msg1.Type,
 			Queue:   msg1.Queue,
@@ -1012,8 +1014,8 @@ func TestWriteProcessStateWithWorkers(t *testing.T) {
 			Started: w1Started,
 		},
 		msg2.ID.String(): {
-			Host:    host,
+			Host:    info.Host,
-			PID:     pid,
+			PID:     info.PID,
 			ID:      msg2.ID,
 			Type:    msg2.Type,
 			Queue:   msg2.Queue,
@@ -1039,27 +1041,28 @@ func TestWriteProcessStateWithWorkers(t *testing.T) {
 	}
 }
 
-func TestClearProcessState(t *testing.T) {
+func TestClearServerState(t *testing.T) {
 	r := setup(t)
-	host, pid := "127.0.0.1", 1234
+	ss := base.NewServerState("127.0.01", 4242, 10, map[string]int{"default": 1}, false)
+	info := ss.GetInfo()
 
 	h.FlushDB(t, r.client)
 
-	pkey := base.ProcessInfoKey(host, pid)
+	skey := base.ServerInfoKey(info.Host, info.PID, info.ServerID)
-	wkey := base.WorkersKey(host, pid)
+	wkey := base.WorkersKey(info.Host, info.PID, info.ServerID)
-	otherPKey := base.ProcessInfoKey("otherhost", 12345)
+	otherSKey := base.ServerInfoKey("otherhost", 12345, "server98")
-	otherWKey := base.WorkersKey("otherhost", 12345)
+	otherWKey := base.WorkersKey("otherhost", 12345, "server98")
 	// Populate the keys.
-	if err := r.client.Set(pkey, "process-info", 0).Err(); err != nil {
+	if err := r.client.Set(skey, "process-info", 0).Err(); err != nil {
 		t.Fatal(err)
 	}
 	if err := r.client.HSet(wkey, "worker-key", "worker-info").Err(); err != nil {
 		t.Fatal(err)
 	}
-	if err := r.client.ZAdd(base.AllProcesses, &redis.Z{Member: pkey}).Err(); err != nil {
+	if err := r.client.ZAdd(base.AllServers, &redis.Z{Member: skey}).Err(); err != nil {
 		t.Fatal(err)
 	}
-	if err := r.client.ZAdd(base.AllProcesses, &redis.Z{Member: otherPKey}).Err(); err != nil {
+	if err := r.client.ZAdd(base.AllServers, &redis.Z{Member: otherSKey}).Err(); err != nil {
 		t.Fatal(err)
 	}
 	if err := r.client.ZAdd(base.AllWorkers, &redis.Z{Member: wkey}).Err(); err != nil {
@@ -1069,24 +1072,22 @@ func TestClearProcessState(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	ps := base.NewProcessState(host, pid, 10, map[string]int{"default": 1}, false)
+	err := r.ClearServerState(ss)
-
-	err := r.ClearProcessState(ps)
 	if err != nil {
-		t.Fatalf("(*RDB).ClearProcessState failed: %v", err)
+		t.Fatalf("(*RDB).ClearServerState failed: %v", err)
 	}
 
 	// Check all keys are cleared
-	if r.client.Exists(pkey).Val() != 0 {
+	if r.client.Exists(skey).Val() != 0 {
-		t.Errorf("Redis key %q exists", pkey)
+		t.Errorf("Redis key %q exists", skey)
 	}
 	if r.client.Exists(wkey).Val() != 0 {
 		t.Errorf("Redis key %q exists", wkey)
 	}
-	gotProcessKeys := r.client.ZRange(base.AllProcesses, 0, -1).Val()
+	gotProcessKeys := r.client.ZRange(base.AllServers, 0, -1).Val()
-	wantProcessKeys := []string{otherPKey}
+	wantProcessKeys := []string{otherSKey}
 	if diff := cmp.Diff(wantProcessKeys, gotProcessKeys); diff != "" {
-		t.Errorf("%q contained %v, want %v", base.AllProcesses, gotProcessKeys, wantProcessKeys)
+		t.Errorf("%q contained %v, want %v", base.AllServers, gotProcessKeys, wantProcessKeys)
 	}
 	gotWorkerKeys := r.client.ZRange(base.AllWorkers, 0, -1).Val()
 	wantWorkerKeys := []string{otherWKey}

internal/testbroker/testbroker.go

@@ -0,0 +1,187 @@
+// Copyright 2020 Kentaro Hibino. All rights reserved.
+// Use of this source code is governed by a MIT license
+// that can be found in the LICENSE file.
+
+// Package testbroker exports a broker implementation that should be used in package testing.
+package testbroker
+
+import (
+	"errors"
+	"sync"
+	"time"
+
+	"github.com/go-redis/redis/v7"
+	"github.com/hibiken/asynq/internal/base"
+)
+
+var errRedisDown = errors.New("asynqtest: redis is down")
+
+// TestBroker is a broker implementation which enables
+// to simulate Redis failure in tests.
+type TestBroker struct {
+	mu       sync.Mutex
+	sleeping bool
+
+	// real broker
+	real base.Broker
+}
+
+func NewTestBroker(b base.Broker) *TestBroker {
+	return &TestBroker{real: b}
+}
+
+func (tb *TestBroker) Sleep() {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	tb.sleeping = true
+}
+
+func (tb *TestBroker) Wakeup() {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	tb.sleeping = false
+}
+
+func (tb *TestBroker) Enqueue(msg *base.TaskMessage) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.Enqueue(msg)
+}
+
+func (tb *TestBroker) EnqueueUnique(msg *base.TaskMessage, ttl time.Duration) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.EnqueueUnique(msg, ttl)
+}
+
+func (tb *TestBroker) Dequeue(qnames ...string) (*base.TaskMessage, error) {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return nil, errRedisDown
+	}
+	return tb.real.Dequeue(qnames...)
+}
+
+func (tb *TestBroker) Done(msg *base.TaskMessage) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.Done(msg)
+}
+
+func (tb *TestBroker) Requeue(msg *base.TaskMessage) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.Requeue(msg)
+}
+
+func (tb *TestBroker) Schedule(msg *base.TaskMessage, processAt time.Time) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.Schedule(msg, processAt)
+}
+
+func (tb *TestBroker) ScheduleUnique(msg *base.TaskMessage, processAt time.Time, ttl time.Duration) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.ScheduleUnique(msg, processAt, ttl)
+}
+
+func (tb *TestBroker) Retry(msg *base.TaskMessage, processAt time.Time, errMsg string) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.Retry(msg, processAt, errMsg)
+}
+
+func (tb *TestBroker) Kill(msg *base.TaskMessage, errMsg string) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.Kill(msg, errMsg)
+}
+
+func (tb *TestBroker) RequeueAll() (int64, error) {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return 0, errRedisDown
+	}
+	return tb.real.RequeueAll()
+}
+
+func (tb *TestBroker) CheckAndEnqueue(qnames ...string) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.CheckAndEnqueue()
+}
+
+func (tb *TestBroker) WriteServerState(ss *base.ServerState, ttl time.Duration) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.WriteServerState(ss, ttl)
+}
+
+func (tb *TestBroker) ClearServerState(ss *base.ServerState) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.ClearServerState(ss)
+}
+
+func (tb *TestBroker) CancelationPubSub() (*redis.PubSub, error) {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return nil, errRedisDown
+	}
+	return tb.real.CancelationPubSub()
+}
+
+func (tb *TestBroker) PublishCancelation(id string) error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.PublishCancelation(id)
+}
+
+func (tb *TestBroker) Close() error {
+	tb.mu.Lock()
+	defer tb.mu.Unlock()
+	if tb.sleeping {
+		return errRedisDown
+	}
+	return tb.real.Close()
+}

processor.go

@@ -19,9 +19,9 @@ import (
 
 type processor struct {
 	logger Logger
-	rdb    *rdb.RDB
+	broker base.Broker
 
-	ps *base.ProcessState
+	ss *base.ServerState
 
 	handler Handler
 
@@ -34,6 +34,8 @@ type processor struct {
 
 	errHandler ErrorHandler
 
+	shutdownTimeout time.Duration
+
 	// channel via which to send sync requests to syncer.
 	syncRequestCh chan<- *syncRequest
 
@@ -61,30 +63,40 @@ type processor struct {
 
 type retryDelayFunc func(n int, err error, task *Task) time.Duration
 
+type newProcessorParams struct {
+	logger          Logger
+	broker          base.Broker
+	ss              *base.ServerState
+	retryDelayFunc  retryDelayFunc
+	syncCh          chan<- *syncRequest
+	cancelations    *base.Cancelations
+	errHandler      ErrorHandler
+	shutdownTimeout time.Duration
+}
+
 // newProcessor constructs a new processor.
-func newProcessor(l Logger, r *rdb.RDB, ps *base.ProcessState, fn retryDelayFunc,
+func newProcessor(params newProcessorParams) *processor {
-	syncCh chan<- *syncRequest, c *base.Cancelations, errHandler ErrorHandler) *processor {
+	info := params.ss.GetInfo()
-	info := ps.Get()
 	qcfg := normalizeQueueCfg(info.Queues)
 	orderedQueues := []string(nil)
 	if info.StrictPriority {
 		orderedQueues = sortByPriority(qcfg)
 	}
 	return &processor{
-		logger:         l,
+		logger:         params.logger,
-		rdb:            r,
+		broker:         params.broker,
-		ps:             ps,
+		ss:             params.ss,
 		queueConfig:    qcfg,
 		orderedQueues:  orderedQueues,
-		retryDelayFunc: fn,
+		retryDelayFunc: params.retryDelayFunc,
-		syncRequestCh:  syncCh,
+		syncRequestCh:  params.syncCh,
-		cancelations:   c,
+		cancelations:   params.cancelations,
 		errLogLimiter:  rate.NewLimiter(rate.Every(3*time.Second), 1),
 		sema:           make(chan struct{}, info.Concurrency),
 		done:           make(chan struct{}),
 		abort:          make(chan struct{}),
 		quit:           make(chan struct{}),
-		errHandler:     errHandler,
+		errHandler:     params.errHandler,
 		handler:        HandlerFunc(func(ctx context.Context, t *Task) error { return fmt.Errorf("handler not set") }),
 	}
 }
@@ -106,9 +118,7 @@ func (p *processor) stop() {
 func (p *processor) terminate() {
 	p.stop()
 
-	// IDEA: Allow user to customize this timeout value.
+	time.AfterFunc(p.shutdownTimeout, func() { close(p.quit) })
-	const timeout = 8 * time.Second
-	time.AfterFunc(timeout, func() { close(p.quit) })
 	p.logger.Info("Waiting for all workers to finish...")
 
 	// send cancellation signal to all in-progress task handlers
@@ -147,8 +157,8 @@ func (p *processor) start(wg *sync.WaitGroup) {
 // process the task.
 func (p *processor) exec() {
 	qnames := p.queues()
-	msg, err := p.rdb.Dequeue(qnames...)
+	msg, err := p.broker.Dequeue(qnames...)
-	if err == rdb.ErrNoProcessableTask {
+	if err == rdb.ErrNoProcessableTask { // TODO: Need to decouple this error from rdb to support other brokers
 		// queues are empty, this is a normal behavior.
 		if len(p.queueConfig) > 1 {
 			// sleep to avoid slamming redis and let scheduler move tasks into queues.
@@ -171,21 +181,23 @@ func (p *processor) exec() {
 		p.requeue(msg)
 		return
 	case p.sema <- struct{}{}: // acquire token
-		p.ps.AddWorkerStats(msg, time.Now())
+		p.ss.AddWorkerStats(msg, time.Now())
 		go func() {
 			defer func() {
-				p.ps.DeleteWorkerStats(msg)
+				p.ss.DeleteWorkerStats(msg)
 				<-p.sema /* release token */
 			}()
 
+			ctx, cancel := createContext(msg)
+			p.cancelations.Add(msg.ID.String(), cancel)
+			defer func() {
+				cancel()
+				p.cancelations.Delete(msg.ID.String())
+			}()
+
 			resCh := make(chan error, 1)
 			task := NewTask(msg.Type, msg.Payload)
-			ctx, cancel := createContext(msg)
+			go func() { resCh <- perform(ctx, task, p.handler) }()
-			p.cancelations.Add(msg.ID.String(), cancel)
-			go func() {
-				resCh <- perform(ctx, task, p.handler)
-				p.cancelations.Delete(msg.ID.String())
-			}()
 
 			select {
 			case <-p.quit:
@@ -217,7 +229,7 @@ func (p *processor) exec() {
 // restore moves all tasks from "in-progress" back to queue
 // to restore all unfinished tasks.
 func (p *processor) restore() {
-	n, err := p.rdb.RequeueAll()
+	n, err := p.broker.RequeueAll()
 	if err != nil {
 		p.logger.Error("Could not restore unfinished tasks: %v", err)
 	}
@@ -227,20 +239,20 @@ func (p *processor) restore() {
 }
 
 func (p *processor) requeue(msg *base.TaskMessage) {
-	err := p.rdb.Requeue(msg)
+	err := p.broker.Requeue(msg)
 	if err != nil {
 		p.logger.Error("Could not push task id=%s back to queue: %v", msg.ID, err)
 	}
 }
 
 func (p *processor) markAsDone(msg *base.TaskMessage) {
-	err := p.rdb.Done(msg)
+	err := p.broker.Done(msg)
 	if err != nil {
 		errMsg := fmt.Sprintf("Could not remove task id=%s from %q", msg.ID, base.InProgressQueue)
 		p.logger.Warn("%s; Will retry syncing", errMsg)
 		p.syncRequestCh <- &syncRequest{
 			fn: func() error {
-				return p.rdb.Done(msg)
+				return p.broker.Done(msg)
 			},
 			errMsg: errMsg,
 		}
@@ -250,13 +262,13 @@ func (p *processor) markAsDone(msg *base.TaskMessage) {
 func (p *processor) retry(msg *base.TaskMessage, e error) {
 	d := p.retryDelayFunc(msg.Retried, e, NewTask(msg.Type, msg.Payload))
 	retryAt := time.Now().Add(d)
-	err := p.rdb.Retry(msg, retryAt, e.Error())
+	err := p.broker.Retry(msg, retryAt, e.Error())
 	if err != nil {
 		errMsg := fmt.Sprintf("Could not move task id=%s from %q to %q", msg.ID, base.InProgressQueue, base.RetryQueue)
 		p.logger.Warn("%s; Will retry syncing", errMsg)
 		p.syncRequestCh <- &syncRequest{
 			fn: func() error {
-				return p.rdb.Retry(msg, retryAt, e.Error())
+				return p.broker.Retry(msg, retryAt, e.Error())
 			},
 			errMsg: errMsg,
 		}
@@ -265,13 +277,13 @@ func (p *processor) retry(msg *base.TaskMessage, e error) {
 
 func (p *processor) kill(msg *base.TaskMessage, e error) {
 	p.logger.Warn("Retry exhausted for task id=%s", msg.ID)
-	err := p.rdb.Kill(msg, e.Error())
+	err := p.broker.Kill(msg, e.Error())
 	if err != nil {
 		errMsg := fmt.Sprintf("Could not move task id=%s from %q to %q", msg.ID, base.InProgressQueue, base.DeadQueue)
 		p.logger.Warn("%s; Will retry syncing", errMsg)
 		p.syncRequestCh <- &syncRequest{
 			fn: func() error {
-				return p.rdb.Kill(msg, e.Error())
+				return p.broker.Kill(msg, e.Error())
 			},
 			errMsg: errMsg,
 		}

processor_test.go

@@ -37,19 +37,16 @@ func TestProcessorSuccess(t *testing.T) {
 	tests := []struct {
 		enqueued      []*base.TaskMessage // initial default queue state
 		incoming      []*base.TaskMessage // tasks to be enqueued during run
-		wait          time.Duration       // wait duration between starting and stopping processor for this test case
 		wantProcessed []*Task             // tasks to be processed at the end
 	}{
 		{
 			enqueued:      []*base.TaskMessage{m1},
 			incoming:      []*base.TaskMessage{m2, m3, m4},
-			wait:          time.Second,
 			wantProcessed: []*Task{t1, t2, t3, t4},
 		},
 		{
 			enqueued:      []*base.TaskMessage{},
 			incoming:      []*base.TaskMessage{m1},
-			wait:          time.Second,
 			wantProcessed: []*Task{t1},
 		},
 	}
@@ -67,13 +64,20 @@ func TestProcessorSuccess(t *testing.T) {
 			processed = append(processed, task)
 			return nil
 		}
-		ps := base.NewProcessState("localhost", 1234, 10, defaultQueueConfig, false)
+		ss := base.NewServerState("localhost", 1234, 10, defaultQueueConfig, false)
-		cancelations := base.NewCancelations()
+		p := newProcessor(newProcessorParams{
-		p := newProcessor(testLogger, rdbClient, ps, defaultDelayFunc, nil, cancelations, nil)
+			logger:          testLogger,
+			broker:          rdbClient,
+			ss:              ss,
+			retryDelayFunc:  defaultDelayFunc,
+			syncCh:          nil,
+			cancelations:    base.NewCancelations(),
+			errHandler:      nil,
+			shutdownTimeout: defaultShutdownTimeout,
+		})
 		p.handler = HandlerFunc(handler)
 
-		var wg sync.WaitGroup
+		p.start(&sync.WaitGroup{})
-		p.start(&wg)
 		for _, msg := range tc.incoming {
 			err := rdbClient.Enqueue(msg)
 			if err != nil {
@@ -81,7 +85,7 @@ func TestProcessorSuccess(t *testing.T) {
 				t.Fatal(err)
 			}
 		}
-		time.Sleep(tc.wait)
+		time.Sleep(time.Second) // wait for one second to allow all enqueued tasks to be processed.
 		p.terminate()
 
 		if diff := cmp.Diff(tc.wantProcessed, processed, sortTaskOpt, cmp.AllowUnexported(Payload{})); diff != "" {
@@ -165,13 +169,20 @@ func TestProcessorRetry(t *testing.T) {
 			defer mu.Unlock()
 			n++
 		}
-		ps := base.NewProcessState("localhost", 1234, 10, defaultQueueConfig, false)
+		ss := base.NewServerState("localhost", 1234, 10, defaultQueueConfig, false)
-		cancelations := base.NewCancelations()
+		p := newProcessor(newProcessorParams{
-		p := newProcessor(testLogger, rdbClient, ps, delayFunc, nil, cancelations, ErrorHandlerFunc(errHandler))
+			logger:          testLogger,
+			broker:          rdbClient,
+			ss:              ss,
+			retryDelayFunc:  delayFunc,
+			syncCh:          nil,
+			cancelations:    base.NewCancelations(),
+			errHandler:      ErrorHandlerFunc(errHandler),
+			shutdownTimeout: defaultShutdownTimeout,
+		})
 		p.handler = tc.handler
 
-		var wg sync.WaitGroup
+		p.start(&sync.WaitGroup{})
-		p.start(&wg)
 		for _, msg := range tc.incoming {
 			err := rdbClient.Enqueue(msg)
 			if err != nil {
@@ -182,7 +193,7 @@ func TestProcessorRetry(t *testing.T) {
 		time.Sleep(tc.wait)
 		p.terminate()
 
-		cmpOpt := cmpopts.EquateApprox(0, float64(time.Second)) // allow up to second difference in zset score
+		cmpOpt := cmpopts.EquateApprox(0, float64(time.Second)) // allow up to a second difference in zset score
 		gotRetry := h.GetRetryEntries(t, r)
 		if diff := cmp.Diff(tc.wantRetry, gotRetry, h.SortZSetEntryOpt, cmpOpt); diff != "" {
 			t.Errorf("mismatch found in %q after running processor; (-want, +got)\n%s", base.RetryQueue, diff)
@@ -231,9 +242,17 @@ func TestProcessorQueues(t *testing.T) {
 	}
 
 	for _, tc := range tests {
-		cancelations := base.NewCancelations()
+		ss := base.NewServerState("localhost", 1234, 10, tc.queueCfg, false)
-		ps := base.NewProcessState("localhost", 1234, 10, tc.queueCfg, false)
+		p := newProcessor(newProcessorParams{
-		p := newProcessor(testLogger, nil, ps, defaultDelayFunc, nil, cancelations, nil)
+			logger:          testLogger,
+			broker:          nil,
+			ss:              ss,
+			retryDelayFunc:  defaultDelayFunc,
+			syncCh:          nil,
+			cancelations:    base.NewCancelations(),
+			errHandler:      nil,
+			shutdownTimeout: defaultShutdownTimeout,
+		})
 		got := p.queues()
 		if diff := cmp.Diff(tc.want, got, sortOpt); diff != "" {
 			t.Errorf("with queue config: %v\n(*processor).queues() = %v, want %v\n(-want,+got):\n%s",
@@ -299,13 +318,20 @@ func TestProcessorWithStrictPriority(t *testing.T) {
 			"low":                 1,
 		}
 		// Note: Set concurrency to 1 to make sure tasks are processed one at a time.
-		cancelations := base.NewCancelations()
+		ss := base.NewServerState("localhost", 1234, 1 /* concurrency */, queueCfg, true /*strict*/)
-		ps := base.NewProcessState("localhost", 1234, 1 /* concurrency */, queueCfg, true /*strict*/)
+		p := newProcessor(newProcessorParams{
-		p := newProcessor(testLogger, rdbClient, ps, defaultDelayFunc, nil, cancelations, nil)
+			logger:          testLogger,
+			broker:          rdbClient,
+			ss:              ss,
+			retryDelayFunc:  defaultDelayFunc,
+			syncCh:          nil,
+			cancelations:    base.NewCancelations(),
+			errHandler:      nil,
+			shutdownTimeout: defaultShutdownTimeout,
+		})
 		p.handler = HandlerFunc(handler)
 
-		var wg sync.WaitGroup
+		p.start(&sync.WaitGroup{})
-		p.start(&wg)
 		time.Sleep(tc.wait)
 		p.terminate()
 
@@ -446,3 +472,83 @@ func TestCreateContextWithoutTimeRestrictions(t *testing.T) {
 		t.Error("ctx.Done() blocked, want it to be non-blocking")
 	}
 }
+
+func TestGCD(t *testing.T) {
+	tests := []struct {
+		input []int
+		want  int
+	}{
+		{[]int{6, 2, 12}, 2},
+		{[]int{3, 3, 3}, 3},
+		{[]int{6, 3, 1}, 1},
+		{[]int{1}, 1},
+		{[]int{1, 0, 2}, 1},
+		{[]int{8, 0, 4}, 4},
+		{[]int{9, 12, 18, 30}, 3},
+	}
+
+	for _, tc := range tests {
+		got := gcd(tc.input...)
+		if got != tc.want {
+			t.Errorf("gcd(%v) = %d, want %d", tc.input, got, tc.want)
+		}
+	}
+}
+
+func TestNormalizeQueueCfg(t *testing.T) {
+	tests := []struct {
+		input map[string]int
+		want  map[string]int
+	}{
+		{
+			input: map[string]int{
+				"high":    100,
+				"default": 20,
+				"low":     5,
+			},
+			want: map[string]int{
+				"high":    20,
+				"default": 4,
+				"low":     1,
+			},
+		},
+		{
+			input: map[string]int{
+				"default": 10,
+			},
+			want: map[string]int{
+				"default": 1,
+			},
+		},
+		{
+			input: map[string]int{
+				"critical": 5,
+				"default":  1,
+			},
+			want: map[string]int{
+				"critical": 5,
+				"default":  1,
+			},
+		},
+		{
+			input: map[string]int{
+				"critical": 6,
+				"default":  3,
+				"low":      0,
+			},
+			want: map[string]int{
+				"critical": 2,
+				"default":  1,
+				"low":      0,
+			},
+		},
+	}
+
+	for _, tc := range tests {
+		got := normalizeQueueCfg(tc.input)
+		if diff := cmp.Diff(tc.want, got); diff != "" {
+			t.Errorf("normalizeQueueCfg(%v) = %v, want %v; (-want, +got):\n%s",
+				tc.input, got, tc.want, diff)
+		}
+	}
+}

scheduler.go

@@ -8,12 +8,12 @@ import (
 	"sync"
 	"time"
 
-	"github.com/hibiken/asynq/internal/rdb"
+	"github.com/hibiken/asynq/internal/base"
 )
 
 type scheduler struct {
 	logger Logger
-	rdb    *rdb.RDB
+	broker base.Broker
 
 	// channel to communicate back to the long running "scheduler" goroutine.
 	done chan struct{}
@@ -25,14 +25,14 @@ type scheduler struct {
 	qnames []string
 }
 
-func newScheduler(l Logger, r *rdb.RDB, avgInterval time.Duration, qcfg map[string]int) *scheduler {
+func newScheduler(l Logger, b base.Broker, avgInterval time.Duration, qcfg map[string]int) *scheduler {
 	var qnames []string
 	for q := range qcfg {
 		qnames = append(qnames, q)
 	}
 	return &scheduler{
 		logger:      l,
-		rdb:         r,
+		broker:      b,
 		done:        make(chan struct{}),
 		avgInterval: avgInterval,
 		qnames:      qnames,
@@ -63,7 +63,7 @@ func (s *scheduler) start(wg *sync.WaitGroup) {
 }
 
 func (s *scheduler) exec() {
-	if err := s.rdb.CheckAndEnqueue(s.qnames...); err != nil {
+	if err := s.broker.CheckAndEnqueue(s.qnames...); err != nil {
 		s.logger.Error("Could not enqueue scheduled tasks: %v", err)
 	}
 }

server.go

@@ -6,13 +6,13 @@ package asynq
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"math"
 	"math/rand"
 	"os"
-	"os/signal"
+	"runtime"
 	"sync"
-	"syscall"
 	"time"
 
 	"github.com/hibiken/asynq/internal/base"
@@ -20,29 +20,27 @@ import (
 	"github.com/hibiken/asynq/internal/rdb"
 )
 
-// Background is responsible for managing the background-task processing.
+// Server is responsible for managing the background-task processing.
 //
-// Background manages task queues to process tasks.
+// Server pulls tasks off queues and processes them.
-// If the processing of a task is unsuccessful, background will
+// If the processing of a task is unsuccessful, server will
-// schedule it for a retry until either the task gets processed successfully
+// schedule it for a retry.
-// or it exhausts its max retry count.
+// A task will be retried until either the task gets processed successfully
+// or until it reaches its max retry count.
 //
-// Once a task exhausts its retries, it will be moved to the "dead" queue and
+// If a task exhausts its retries, it will be moved to the "dead" queue and
 // will be kept in the queue for some time until a certain condition is met
 // (e.g., queue size reaches a certain limit, or the task has been in the
 // queue for a certain amount of time).
-type Background struct {
+type Server struct {
-	mu      sync.Mutex
+	ss *base.ServerState
-	running bool
-
-	ps *base.ProcessState
-
-	// wait group to wait for all goroutines to finish.
-	wg sync.WaitGroup
 
 	logger Logger
 
-	rdb         *rdb.RDB
+	broker base.Broker
+
+	// wait group to wait for all goroutines to finish.
+	wg          sync.WaitGroup
 	scheduler   *scheduler
 	processor   *processor
 	syncer      *syncer
@@ -50,11 +48,12 @@ type Background struct {
 	subscriber  *subscriber
 }
 
-// Config specifies the background-task processing behavior.
+// Config specifies the server's background-task processing behavior.
 type Config struct {
 	// Maximum number of concurrent processing of tasks.
 	//
-	// If set to a zero or negative value, NewBackground will overwrite the value to one.
+	// If set to a zero or negative value, NewServer will overwrite the value
+	// to the number of CPUs usable by the currennt process.
 	Concurrency int
 
 	// Function to calculate retry delay for a failed task.
@@ -69,7 +68,7 @@ type Config struct {
 	// List of queues to process with given priority value. Keys are the names of the
 	// queues and values are associated priority value.
 	//
-	// If set to nil or not specified, the background will process only the "default" queue.
+	// If set to nil or not specified, the server will process only the "default" queue.
 	//
 	// Priority is treated as follows to avoid starving low priority queues.
 	//
@@ -108,10 +107,16 @@ type Config struct {
 	// ErrorHandler: asynq.ErrorHandlerFunc(reportError)
 	ErrorHandler ErrorHandler
 
-	// Logger specifies the logger used by the background instance.
+	// Logger specifies the logger used by the server instance.
 	//
 	// If unset, default logger is used.
 	Logger Logger
+
+	// ShutdownTimeout specifies the duration to wait to let workers finish their tasks
+	// before forcing them to abort when stopping the server.
+	//
+	// If unset or zero, default timeout of 8 seconds is used.
+	ShutdownTimeout time.Duration
 }
 
 // An ErrorHandler handles errors returned by the task handler.
@@ -158,12 +163,14 @@ var defaultQueueConfig = map[string]int{
 	base.DefaultQueueName: 1,
 }
 
-// NewBackground returns a new Background given a redis connection option
+const defaultShutdownTimeout = 8 * time.Second
+
+// NewServer returns a new Server given a redis connection option
 // and background processing configuration.
-func NewBackground(r RedisConnOpt, cfg *Config) *Background {
+func NewServer(r RedisConnOpt, cfg Config) *Server {
 	n := cfg.Concurrency
 	if n < 1 {
-		n = 1
+		n = runtime.NumCPU()
 	}
 	delayFunc := cfg.RetryDelayFunc
 	if delayFunc == nil {
@@ -182,6 +189,10 @@ func NewBackground(r RedisConnOpt, cfg *Config) *Background {
 	if logger == nil {
 		logger = log.NewLogger(os.Stderr)
 	}
+	shutdownTimeout := cfg.ShutdownTimeout
+	if shutdownTimeout == 0 {
+		shutdownTimeout = defaultShutdownTimeout
+	}
 
 	host, err := os.Hostname()
 	if err != nil {
@@ -190,18 +201,27 @@ func NewBackground(r RedisConnOpt, cfg *Config) *Background {
 	pid := os.Getpid()
 
 	rdb := rdb.NewRDB(createRedisClient(r))
-	ps := base.NewProcessState(host, pid, n, queues, cfg.StrictPriority)
+	ss := base.NewServerState(host, pid, n, queues, cfg.StrictPriority)
 	syncCh := make(chan *syncRequest)
 	cancels := base.NewCancelations()
 	syncer := newSyncer(logger, syncCh, 5*time.Second)
-	heartbeater := newHeartbeater(logger, rdb, ps, 5*time.Second)
+	heartbeater := newHeartbeater(logger, rdb, ss, 5*time.Second)
 	scheduler := newScheduler(logger, rdb, 5*time.Second, queues)
-	processor := newProcessor(logger, rdb, ps, delayFunc, syncCh, cancels, cfg.ErrorHandler)
 	subscriber := newSubscriber(logger, rdb, cancels)
-	return &Background{
+	processor := newProcessor(newProcessorParams{
 		logger:          logger,
-		rdb:         rdb,
+		broker:          rdb,
-		ps:          ps,
+		ss:              ss,
+		retryDelayFunc:  delayFunc,
+		syncCh:          syncCh,
+		cancelations:    cancels,
+		errHandler:      cfg.ErrorHandler,
+		shutdownTimeout: shutdownTimeout,
+	})
+	return &Server{
+		ss:          ss,
+		logger:      logger,
+		broker:      rdb,
 		scheduler:   scheduler,
 		processor:   processor,
 		syncer:      syncer,
@@ -232,82 +252,95 @@ func (fn HandlerFunc) ProcessTask(ctx context.Context, task *Task) error {
 	return fn(ctx, task)
 }
 
+// ErrServerStopped indicates that the operation is now illegal because of the server being stopped.
+var ErrServerStopped = errors.New("asynq: the server has been stopped")
+
 // Run starts the background-task processing and blocks until
 // an os signal to exit the program is received. Once it receives
-// a signal, it gracefully shuts down all pending workers and other
+// a signal, it gracefully shuts down all active workers and other
 // goroutines to process the tasks.
-func (bg *Background) Run(handler Handler) {
+//
+// Run returns any error encountered during server startup time.
+// If the server has already been stopped, ErrServerStopped is returned.
+func (srv *Server) Run(handler Handler) error {
+	if err := srv.Start(handler); err != nil {
+		return err
+	}
+	srv.waitForSignals()
+	srv.Stop()
+	return nil
+}
+
+// Start starts the worker server. Once the server has started,
+// it pulls tasks off queues and starts a worker goroutine for each task.
+// Tasks are processed concurrently by the workers  up to the number of
+// concurrency specified at the initialization time.
+//
+// Start returns any error encountered during server startup time.
+// If the server has already been stopped, ErrServerStopped is returned.
+func (srv *Server) Start(handler Handler) error {
+	if handler == nil {
+		return fmt.Errorf("asynq: server cannot run with nil handler")
+	}
+	switch srv.ss.Status() {
+	case base.StatusRunning:
+		return fmt.Errorf("asynq: the server is already running")
+	case base.StatusStopped:
+		return ErrServerStopped
+	}
+	srv.ss.SetStatus(base.StatusRunning)
+	srv.processor.handler = handler
+
 	type prefixLogger interface {
 		SetPrefix(prefix string)
 	}
 	// If logger supports setting prefix, then set prefix for log output.
-	if l, ok := bg.logger.(prefixLogger); ok {
+	if l, ok := srv.logger.(prefixLogger); ok {
 		l.SetPrefix(fmt.Sprintf("asynq: pid=%d ", os.Getpid()))
 	}
-	bg.logger.Info("Starting processing")
+	srv.logger.Info("Starting processing")
 
-	bg.start(handler)
+	srv.heartbeater.start(&srv.wg)
-	defer bg.stop()
+	srv.subscriber.start(&srv.wg)
-
+	srv.syncer.start(&srv.wg)
-	bg.logger.Info("Send signal TSTP to stop processing new tasks")
+	srv.scheduler.start(&srv.wg)
-	bg.logger.Info("Send signal TERM or INT to terminate the process")
+	srv.processor.start(&srv.wg)
-
+	return nil
-	// Wait for a signal to terminate.
-	sigs := make(chan os.Signal, 1)
-	signal.Notify(sigs, syscall.SIGTERM, syscall.SIGINT, syscall.SIGTSTP)
-	for {
-		sig := <-sigs
-		if sig == syscall.SIGTSTP {
-			bg.processor.stop()
-			bg.ps.SetStatus(base.StatusStopped)
-			continue
-		}
-		break
-	}
-	fmt.Println()
-	bg.logger.Info("Starting graceful shutdown")
 }
 
-// starts the background-task processing.
+// Stop stops the worker server.
-func (bg *Background) start(handler Handler) {
+// It gracefully closes all active workers. The server will wait for
-	bg.mu.Lock()
+// active workers to finish processing tasks for duration specified in Config.ShutdownTimeout.
-	defer bg.mu.Unlock()
+// If worker didn't finish processing a task during the timeout, the task will be pushed back to Redis.
-	if bg.running {
+func (srv *Server) Stop() {
-		return
+	switch srv.ss.Status() {
-	}
+	case base.StatusIdle, base.StatusStopped:
-
+		// server is not running, do nothing and return.
-	bg.running = true
-	bg.processor.handler = handler
-
-	bg.heartbeater.start(&bg.wg)
-	bg.subscriber.start(&bg.wg)
-	bg.syncer.start(&bg.wg)
-	bg.scheduler.start(&bg.wg)
-	bg.processor.start(&bg.wg)
-}
-
-// stops the background-task processing.
-func (bg *Background) stop() {
-	bg.mu.Lock()
-	defer bg.mu.Unlock()
-	if !bg.running {
 		return
 	}
 
+	fmt.Println() // print newline for prettier log.
+	srv.logger.Info("Starting graceful shutdown")
 	// Note: The order of termination is important.
 	// Sender goroutines should be terminated before the receiver goroutines.
-	//
 	// processor -> syncer (via syncCh)
-	bg.scheduler.terminate()
+	srv.scheduler.terminate()
-	bg.processor.terminate()
+	srv.processor.terminate()
-	bg.syncer.terminate()
+	srv.syncer.terminate()
-	bg.subscriber.terminate()
+	srv.subscriber.terminate()
-	bg.heartbeater.terminate()
+	srv.heartbeater.terminate()
 
-	bg.wg.Wait()
+	srv.wg.Wait()
 
-	bg.rdb.Close()
+	srv.broker.Close()
-	bg.running = false
+	srv.ss.SetStatus(base.StatusStopped)
 
-	bg.logger.Info("Bye!")
+	srv.logger.Info("Bye!")
+}
+
+// Quiet signals the server to stop pulling new tasks off queues.
+// Quiet should be used before stopping the server.
+func (srv *Server) Quiet() {
+	srv.processor.stop()
+	srv.ss.SetStatus(base.StatusQuiet)
 }

server_test.go

@@ -0,0 +1,210 @@
+// Copyright 2020 Kentaro Hibino. All rights reserved.
+// Use of this source code is governed by a MIT license
+// that can be found in the LICENSE file.
+
+package asynq
+
+import (
+	"context"
+	"fmt"
+	"syscall"
+	"testing"
+	"time"
+
+	"github.com/hibiken/asynq/internal/rdb"
+	"github.com/hibiken/asynq/internal/testbroker"
+	"go.uber.org/goleak"
+)
+
+func TestServer(t *testing.T) {
+	// https://github.com/go-redis/redis/issues/1029
+	ignoreOpt := goleak.IgnoreTopFunction("github.com/go-redis/redis/v7/internal/pool.(*ConnPool).reaper")
+	defer goleak.VerifyNoLeaks(t, ignoreOpt)
+
+	r := &RedisClientOpt{
+		Addr: "localhost:6379",
+		DB:   15,
+	}
+	c := NewClient(r)
+	srv := NewServer(r, Config{
+		Concurrency: 10,
+	})
+
+	// no-op handler
+	h := func(ctx context.Context, task *Task) error {
+		return nil
+	}
+
+	err := srv.Start(HandlerFunc(h))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	err = c.Enqueue(NewTask("send_email", map[string]interface{}{"recipient_id": 123}))
+	if err != nil {
+		t.Errorf("could not enqueue a task: %v", err)
+	}
+
+	err = c.EnqueueAt(time.Now().Add(time.Hour), NewTask("send_email", map[string]interface{}{"recipient_id": 456}))
+	if err != nil {
+		t.Errorf("could not enqueue a task: %v", err)
+	}
+
+	srv.Stop()
+}
+
+func TestServerRun(t *testing.T) {
+	// https://github.com/go-redis/redis/issues/1029
+	ignoreOpt := goleak.IgnoreTopFunction("github.com/go-redis/redis/v7/internal/pool.(*ConnPool).reaper")
+	defer goleak.VerifyNoLeaks(t, ignoreOpt)
+
+	srv := NewServer(RedisClientOpt{Addr: ":6379"}, Config{})
+
+	done := make(chan struct{})
+	// Make sure server exits when receiving TERM signal.
+	go func() {
+		time.Sleep(2 * time.Second)
+		syscall.Kill(syscall.Getpid(), syscall.SIGTERM)
+		done <- struct{}{}
+	}()
+
+	go func() {
+		select {
+		case <-time.After(10 * time.Second):
+			t.Fatal("server did not stop after receiving TERM signal")
+		case <-done:
+		}
+	}()
+
+	mux := NewServeMux()
+	if err := srv.Run(mux); err != nil {
+		t.Fatal(err)
+	}
+}
+
+func TestServerErrServerStopped(t *testing.T) {
+	srv := NewServer(RedisClientOpt{Addr: ":6379"}, Config{})
+	handler := NewServeMux()
+	if err := srv.Start(handler); err != nil {
+		t.Fatal(err)
+	}
+	srv.Stop()
+	err := srv.Start(handler)
+	if err != ErrServerStopped {
+		t.Errorf("Restarting server: (*Server).Start(handler) = %v, want ErrServerStopped error", err)
+	}
+}
+
+func TestServerErrNilHandler(t *testing.T) {
+	srv := NewServer(RedisClientOpt{Addr: ":6379"}, Config{})
+	err := srv.Start(nil)
+	if err == nil {
+		t.Error("Starting server with nil handler: (*Server).Start(nil) did not return error")
+		srv.Stop()
+	}
+}
+
+func TestServerErrServerRunning(t *testing.T) {
+	srv := NewServer(RedisClientOpt{Addr: ":6379"}, Config{})
+	handler := NewServeMux()
+	if err := srv.Start(handler); err != nil {
+		t.Fatal(err)
+	}
+	err := srv.Start(handler)
+	if err == nil {
+		t.Error("Calling (*Server).Start(handler) on already running server did not return error")
+	}
+	srv.Stop()
+}
+
+func TestServerWithRedisDown(t *testing.T) {
+	// Make sure that server does not panic and exit if redis is down.
+	defer func() {
+		if r := recover(); r != nil {
+			t.Errorf("panic occurred: %v", r)
+		}
+	}()
+	r := rdb.NewRDB(setup(t))
+	testBroker := testbroker.NewTestBroker(r)
+	srv := NewServer(RedisClientOpt{Addr: ":6379"}, Config{})
+	srv.broker = testBroker
+	srv.scheduler.broker = testBroker
+	srv.heartbeater.broker = testBroker
+	srv.processor.broker = testBroker
+	srv.subscriber.broker = testBroker
+	testBroker.Sleep()
+
+	// no-op handler
+	h := func(ctx context.Context, task *Task) error {
+		return nil
+	}
+
+	err := srv.Start(HandlerFunc(h))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	time.Sleep(3 * time.Second)
+
+	srv.Stop()
+}
+
+func TestServerWithFlakyBroker(t *testing.T) {
+	// Make sure that server does not panic and exit if redis is down.
+	defer func() {
+		if r := recover(); r != nil {
+			t.Errorf("panic occurred: %v", r)
+		}
+	}()
+	r := rdb.NewRDB(setup(t))
+	testBroker := testbroker.NewTestBroker(r)
+	srv := NewServer(RedisClientOpt{Addr: redisAddr, DB: redisDB}, Config{})
+	srv.broker = testBroker
+	srv.scheduler.broker = testBroker
+	srv.heartbeater.broker = testBroker
+	srv.processor.broker = testBroker
+	srv.subscriber.broker = testBroker
+
+	c := NewClient(RedisClientOpt{Addr: redisAddr, DB: redisDB})
+
+	h := func(ctx context.Context, task *Task) error {
+		// force task retry.
+		if task.Type == "bad_task" {
+			return fmt.Errorf("could not process %q", task.Type)
+		}
+		time.Sleep(2 * time.Second)
+		return nil
+	}
+
+	err := srv.Start(HandlerFunc(h))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	for i := 0; i < 10; i++ {
+		err := c.Enqueue(NewTask("enqueued", nil), MaxRetry(i))
+		if err != nil {
+			t.Fatal(err)
+		}
+		err = c.Enqueue(NewTask("bad_task", nil))
+		if err != nil {
+			t.Fatal(err)
+		}
+		err = c.EnqueueIn(time.Duration(i)*time.Second, NewTask("scheduled", nil))
+		if err != nil {
+			t.Fatal(err)
+		}
+	}
+
+	// simulate redis going down.
+	testBroker.Sleep()
+
+	time.Sleep(3 * time.Second)
+
+	// simulate redis comes back online.
+	testBroker.Wakeup()
+
+	time.Sleep(3 * time.Second)
+
+	srv.Stop()
+}

signals_unix.go

@@ -0,0 +1,30 @@
+// +build linux bsd darwin
+
+package asynq
+
+import (
+	"os"
+	"os/signal"
+
+	"golang.org/x/sys/unix"
+)
+
+// waitForSignals waits for signals and handles them.
+// It handles SIGTERM, SIGINT, and SIGTSTP.
+// SIGTERM and SIGINT will signal the process to exit.
+// SIGTSTP will signal the process to stop processing new tasks.
+func (srv *Server) waitForSignals() {
+	srv.logger.Info("Send signal TSTP to stop processing new tasks")
+	srv.logger.Info("Send signal TERM or INT to terminate the process")
+
+	sigs := make(chan os.Signal, 1)
+	signal.Notify(sigs, unix.SIGTERM, unix.SIGINT, unix.SIGTSTP)
+	for {
+		sig := <-sigs
+		if sig == unix.SIGTSTP {
+			srv.Quiet()
+			continue
+		}
+		break
+	}
+}

signals_windows.go

@@ -0,0 +1,22 @@
+// +build windows
+
+package asynq
+
+import (
+	"os"
+	"os/signal"
+
+	"golang.org/x/sys/windows"
+)
+
+// waitForSignals waits for signals and handles them.
+// It handles SIGTERM and SIGINT.
+// SIGTERM and SIGINT will signal the process to exit.
+//
+// Note: Currently SIGTSTP is not supported for windows build.
+func (srv *Server) waitForSignals() {
+	srv.logger.Info("Send signal TERM or INT to terminate the process")
+	sigs := make(chan os.Signal, 1)
+	signal.Notify(sigs, windows.SIGTERM, windows.SIGINT)
+	<-sigs
+}

subscriber.go

@@ -6,28 +6,33 @@ package asynq
 
 import (
 	"sync"
+	"time"
 
+	"github.com/go-redis/redis/v7"
 	"github.com/hibiken/asynq/internal/base"
-	"github.com/hibiken/asynq/internal/rdb"
 )
 
 type subscriber struct {
 	logger Logger
-	rdb    *rdb.RDB
+	broker base.Broker
 
 	// channel to communicate back to the long running "subscriber" goroutine.
 	done chan struct{}
 
 	// cancelations hold cancel functions for all in-progress tasks.
 	cancelations *base.Cancelations
+
+	// time to wait before retrying to connect to redis.
+	retryTimeout time.Duration
 }
 
-func newSubscriber(l Logger, rdb *rdb.RDB, cancelations *base.Cancelations) *subscriber {
+func newSubscriber(l Logger, b base.Broker, cancelations *base.Cancelations) *subscriber {
 	return &subscriber{
 		logger:       l,
-		rdb:          rdb,
+		broker:       b,
 		done:         make(chan struct{}),
 		cancelations: cancelations,
+		retryTimeout: 5 * time.Second,
 	}
 }
 
@@ -38,15 +43,29 @@ func (s *subscriber) terminate() {
 }
 
 func (s *subscriber) start(wg *sync.WaitGroup) {
-	pubsub, err := s.rdb.CancelationPubSub()
-	cancelCh := pubsub.Channel()
-	if err != nil {
-		s.logger.Error("cannot subscribe to cancelation channel: %v", err)
-		return
-	}
 	wg.Add(1)
 	go func() {
 		defer wg.Done()
+		var (
+			pubsub *redis.PubSub
+			err    error
+		)
+		// Try until successfully connect to Redis.
+		for {
+			pubsub, err = s.broker.CancelationPubSub()
+			if err != nil {
+				s.logger.Error("cannot subscribe to cancelation channel: %v", err)
+				select {
+				case <-time.After(s.retryTimeout):
+					continue
+				case <-s.done:
+					s.logger.Info("Subscriber done")
+					return
+				}
+			}
+			break
+		}
+		cancelCh := pubsub.Channel()
 		for {
 			select {
 			case <-s.done:

subscriber_test.go

@@ -11,6 +11,7 @@ import (
 
 	"github.com/hibiken/asynq/internal/base"
 	"github.com/hibiken/asynq/internal/rdb"
+	"github.com/hibiken/asynq/internal/testbroker"
 )
 
 func TestSubscriber(t *testing.T) {
@@ -40,13 +41,16 @@ func TestSubscriber(t *testing.T) {
 		subscriber := newSubscriber(testLogger, rdbClient, cancelations)
 		var wg sync.WaitGroup
 		subscriber.start(&wg)
+		defer subscriber.terminate()
+
+		// wait for subscriber to establish connection to pubsub channel
+		time.Sleep(time.Second)
 
 		if err := rdbClient.PublishCancelation(tc.publishID); err != nil {
-			subscriber.terminate()
 			t.Fatalf("could not publish cancelation message: %v", err)
 		}
 
-		// allow for redis to publish message
+		// wait for redis to publish message
 		time.Sleep(time.Second)
 
 		mu.Lock()
@@ -58,7 +62,53 @@ func TestSubscriber(t *testing.T) {
 			}
 		}
 		mu.Unlock()
+	}
+}
 
-		subscriber.terminate()
+func TestSubscriberWithRedisDown(t *testing.T) {
+	defer func() {
+		if r := recover(); r != nil {
+			t.Errorf("panic occurred: %v", r)
 		}
+	}()
+	r := rdb.NewRDB(setup(t))
+	testBroker := testbroker.NewTestBroker(r)
+
+	cancelations := base.NewCancelations()
+	subscriber := newSubscriber(testLogger, testBroker, cancelations)
+	subscriber.retryTimeout = 1 * time.Second // set shorter retry timeout for testing purpose.
+
+	testBroker.Sleep() // simulate a situation where subscriber cannot connect to redis.
+	var wg sync.WaitGroup
+	subscriber.start(&wg)
+	defer subscriber.terminate()
+
+	time.Sleep(2 * time.Second) // subscriber should wait and retry connecting to redis.
+
+	testBroker.Wakeup() // simulate a situation where redis server is back online.
+
+	time.Sleep(2 * time.Second) // allow subscriber to establish pubsub channel.
+
+	const id = "test"
+	var (
+		mu     sync.Mutex
+		called bool
+	)
+	cancelations.Add(id, func() {
+		mu.Lock()
+		defer mu.Unlock()
+		called = true
+	})
+
+	if err := r.PublishCancelation(id); err != nil {
+		t.Fatalf("could not publish cancelation message: %v", err)
+	}
+
+	time.Sleep(time.Second) // wait for redis to publish message.
+
+	mu.Lock()
+	if !called {
+		t.Errorf("cancel function was not called")
+	}
+	mu.Unlock()
 }

tools/asynq/README.md

@@ -1,6 +1,6 @@
-# Asynqmon
+# Asynq CLI
 
-Asynqmon is a command line tool to monitor the tasks managed by `asynq` package.
+Asynq CLI is a command line tool to monitor the tasks managed by `asynq` package.
 
 ## Table of Contents
 
@@ -8,7 +8,7 @@ Asynqmon is a command line tool to monitor the tasks managed by `asynq` package.
 - [Quick Start](#quick-start)
   - [Stats](#stats)
   - [History](#history)
-  - [Process Status](#process-status)
+  - [Servers](#servers)
   - [List](#list)
   - [Enqueue](#enqueue)
   - [Delete](#delete)
@@ -20,19 +20,19 @@ Asynqmon is a command line tool to monitor the tasks managed by `asynq` package.
 
 In order to use the tool, compile it using the following command:
 
-    go get github.com/hibiken/asynq/tools/asynqmon
+    go get github.com/hibiken/asynq/tools/asynq
 
-This will create the asynqmon executable under your `$GOPATH/bin` directory.
+This will create the asynq executable under your `$GOPATH/bin` directory.
 
 ## Quickstart
 
 The tool has a few commands to inspect the state of tasks and queues.
 
-Run `asynqmon help` to see all the available commands.
+Run `asynq help` to see all the available commands.
 
-Asynqmon needs to connect to a redis-server to inspect the state of queues and tasks. Use flags to specify the options to connect to the redis-server used by your application.
+Asynq CLI needs to connect to a redis-server to inspect the state of queues and tasks. Use flags to specify the options to connect to the redis-server used by your application.
 
-By default, Asynqmon will try to connect to a redis server running at `localhost:6379`.
+By default, CLI will try to connect to a redis server running at `localhost:6379`.
 
 ### Stats
 
@@ -40,11 +40,11 @@ Stats command gives the overview of the current state of tasks and queues. You c
 
 Example:
 
-    watch -n 3 asynqmon stats
+    watch -n 3 asynq stats
 
-This will run `asynqmon stats` command every 3 seconds.
+This will run `asynq stats` command every 3 seconds.
 
-![Gif](/docs/assets/asynqmon_stats.gif)
+![Gif](/docs/assets/asynq_stats.gif)
 
 ### History
 
@@ -54,19 +54,17 @@ By default, it shows the stats from the last 10 days. Use `--days` to specify th
 
 Example:
 
-    asynqmon history --days=30
+    asynq history --days=30
 
-![Gif](/docs/assets/asynqmon_history.gif)
+![Gif](/docs/assets/asynq_history.gif)
 
-### Process Status
+### Servers
 
-PS (ProcessStatus) command shows the list of running worker processes.
+Servers command shows the list of running worker servers pulling tasks from the given redis instance.
 
 Example:
 
-    asynqmon ps
+    asynq servers
-
-![Gif](/docs/assets/asynqmon_ps.gif)
 
 ### List
 
@@ -74,11 +72,11 @@ List command shows all tasks in the specified state in a table format
 
 Example:
 
-    asynqmon ls retry
+    asynq ls retry
-    asynqmon ls scheduled
+    asynq ls scheduled
-    asynqmon ls dead
+    asynq ls dead
-    asynqmon ls enqueued:default
+    asynq ls enqueued:default
-    asynqmon ls inprogress
+    asynq ls inprogress
 
 ### Enqueue
 
@@ -88,13 +86,13 @@ Command `enq` takes a task ID and moves the task to **Enqueued** state. You can
 
 Example:
 
-    asynqmon enq d:1575732274:bnogo8gt6toe23vhef0g
+    asynq enq d:1575732274:bnogo8gt6toe23vhef0g
 
 Command `enqall` moves all tasks to **Enqueued** state from the specified state.
 
 Example:
 
-    asynqmon enqall retry
+    asynq enqall retry
 
 Running the above command will move all **Retry** tasks to **Enqueued** state.
 
@@ -106,13 +104,13 @@ Command `del` takes a task ID and deletes the task. You can obtain the task ID b
 
 Example:
 
-    asynqmon del r:1575732274:bnogo8gt6toe23vhef0g
+    asynq del r:1575732274:bnogo8gt6toe23vhef0g
 
 Command `delall` deletes all tasks which are in the specified state.
 
 Example:
 
-    asynqmon delall retry
+    asynq delall retry
 
 Running the above command will delete all **Retry** tasks.
 
@@ -124,13 +122,13 @@ Command `kill` takes a task ID and kills the task. You can obtain the task ID by
 
 Example:
 
-    asynqmon kill r:1575732274:bnogo8gt6toe23vhef0g
+    asynq kill r:1575732274:bnogo8gt6toe23vhef0g
 
 Command `killall` kills all tasks which are in the specified state.
 
 Example:
 
-    asynqmon killall retry
+    asynq killall retry
 
 Running the above command will move all **Retry** tasks to **Dead** state.
 
@@ -144,15 +142,15 @@ Handler implementation needs to be context aware in order to actually stop proce
 
 Example:
 
-    asynqmon cancel bnogo8gt6toe23vhef0g
+    asynq cancel bnogo8gt6toe23vhef0g
 
 ## Config File
 
 You can use a config file to set default values for the flags.
 This is useful, for example when you have to connect to a remote redis server.
 
-By default, `asynqmon` will try to read config file located in
+By default, `asynq` will try to read config file located in
-`$HOME/.asynqmon.(yaml|json)`. You can specify the file location via `--config` flag.
+`$HOME/.asynq.(yaml|json)`. You can specify the file location via `--config` flag.
 
 Config file example:
 

tools/asynq/cmd/cancel.go

@@ -18,17 +18,17 @@ import (
 var cancelCmd = &cobra.Command{
 	Use:   "cancel [task id]",
 	Short: "Sends a cancelation signal to the goroutine processing the specified task",
-	Long: `Cancel (asynqmon cancel) will send a cancelation signal to the goroutine processing 
+	Long: `Cancel (asynq cancel) will send a cancelation signal to the goroutine processing 
 the specified task. 
 
 The command takes one argument which specifies the task to cancel.
 The task should be in in-progress state.
-Identifier for a task should be obtained by running "asynqmon ls" command.
+Identifier for a task should be obtained by running "asynq ls" command.
 
 Handler implementation needs to be context aware for cancelation signal to
 actually cancel the processing.
 
-Example: asynqmon cancel bnogo8gt6toe23vhef0g`,
+Example: asynq cancel bnogo8gt6toe23vhef0g`,
 	Args: cobra.ExactArgs(1),
 	Run:  cancel,
 }

tools/asynq/cmd/del.go

@@ -18,13 +18,13 @@ import (
 var delCmd = &cobra.Command{
 	Use:   "del [task id]",
 	Short: "Deletes a task given an identifier",
-	Long: `Del (asynqmon del) will delete a task given an identifier.
+	Long: `Del (asynq del) will delete a task given an identifier.
 
 The command takes one argument which specifies the task to delete.
 The task should be in either scheduled, retry or dead state.
-Identifier for a task should be obtained by running "asynqmon ls" command.
+Identifier for a task should be obtained by running "asynq ls" command.
 
-Example: asynqmon enq d:1575732274:bnogo8gt6toe23vhef0g`,
+Example: asynq enq d:1575732274:bnogo8gt6toe23vhef0g`,
 	Args: cobra.ExactArgs(1),
 	Run:  del,
 }

tools/asynq/cmd/delall.go

@@ -20,11 +20,11 @@ var delallValidArgs = []string{"scheduled", "retry", "dead"}
 var delallCmd = &cobra.Command{
 	Use:   "delall [state]",
 	Short: "Deletes all tasks in the specified state",
-	Long: `Delall (asynqmon delall) will delete all tasks in the specified state.
+	Long: `Delall (asynq delall) will delete all tasks in the specified state.
 
 The argument should be one of "scheduled", "retry", or "dead".
 
-Example: asynqmon delall dead -> Deletes all dead tasks`,
+Example: asynq delall dead -> Deletes all dead tasks`,
 	ValidArgs: delallValidArgs,
 	Args:      cobra.ExactValidArgs(1),
 	Run:       delall,
@@ -60,7 +60,7 @@ func delall(cmd *cobra.Command, args []string) {
 	case "dead":
 		err = r.DeleteAllDeadTasks()
 	default:
-		fmt.Printf("error: `asynqmon delall [state]` only accepts %v as the argument.\n", delallValidArgs)
+		fmt.Printf("error: `asynq delall [state]` only accepts %v as the argument.\n", delallValidArgs)
 		os.Exit(1)
 	}
 	if err != nil {

tools/asynq/cmd/enq.go

@@ -18,16 +18,16 @@ import (
 var enqCmd = &cobra.Command{
 	Use:   "enq [task id]",
 	Short: "Enqueues a task given an identifier",
-	Long: `Enq (asynqmon enq) will enqueue a task given an identifier.
+	Long: `Enq (asynq enq) will enqueue a task given an identifier.
 
 The command takes one argument which specifies the task to enqueue.
 The task should be in either scheduled, retry or dead state.
-Identifier for a task should be obtained by running "asynqmon ls" command.
+Identifier for a task should be obtained by running "asynq ls" command.
 
 The task enqueued by this command will be processed as soon as the task 
 gets dequeued by a processor.
 
-Example: asynqmon enq d:1575732274:bnogo8gt6toe23vhef0g`,
+Example: asynq enq d:1575732274:bnogo8gt6toe23vhef0g`,
 	Args: cobra.ExactArgs(1),
 	Run:  enq,
 }

tools/asynq/cmd/enqall.go

@@ -20,14 +20,14 @@ var enqallValidArgs = []string{"scheduled", "retry", "dead"}
 var enqallCmd = &cobra.Command{
 	Use:   "enqall [state]",
 	Short: "Enqueues all tasks in the specified state",
-	Long: `Enqall (asynqmon enqall) will enqueue all tasks in the specified state.
+	Long: `Enqall (asynq enqall) will enqueue all tasks in the specified state.
 
 The argument should be one of "scheduled", "retry", or "dead".
 
 The tasks enqueued by this command will be processed as soon as it
 gets dequeued by a processor.
 
-Example: asynqmon enqall dead -> Enqueues all dead tasks`,
+Example: asynq enqall dead -> Enqueues all dead tasks`,
 	ValidArgs: enqallValidArgs,
 	Args:      cobra.ExactValidArgs(1),
 	Run:       enqall,
@@ -64,7 +64,7 @@ func enqall(cmd *cobra.Command, args []string) {
 	case "dead":
 		n, err = r.EnqueueAllDeadTasks()
 	default:
-		fmt.Printf("error: `asynqmon enqall [state]` only accepts %v as the argument.\n", enqallValidArgs)
+		fmt.Printf("error: `asynq enqall [state]` only accepts %v as the argument.\n", enqallValidArgs)
 		os.Exit(1)
 	}
 	if err != nil {

tools/asynq/cmd/history.go

@@ -22,12 +22,12 @@ var days int
 var historyCmd = &cobra.Command{
 	Use:   "history",
 	Short: "Shows historical aggregate data",
-	Long: `History (asynqmon history) will show the number of processed and failed tasks
+	Long: `History (asynq history) will show the number of processed and failed tasks
 from the last x days.
 
 By default, it will show the data from the last 10 days.
 
-Example: asynqmon history -x=30 -> Shows stats from the last 30 days`,
+Example: asynq history -x=30 -> Shows stats from the last 30 days`,
 	Args: cobra.NoArgs,
 	Run:  history,
 }

tools/asynq/cmd/kill.go

@@ -18,13 +18,13 @@ import (
 var killCmd = &cobra.Command{
 	Use:   "kill [task id]",
 	Short: "Kills a task given an identifier",
-	Long: `Kill (asynqmon kill) will put a task in dead state given an identifier.
+	Long: `Kill (asynq kill) will put a task in dead state given an identifier.
 
 The command takes one argument which specifies the task to kill.
 The task should be in either scheduled or retry state.
-Identifier for a task should be obtained by running "asynqmon ls" command.
+Identifier for a task should be obtained by running "asynq ls" command.
 
-Example: asynqmon kill r:1575732274:bnogo8gt6toe23vhef0g`,
+Example: asynq kill r:1575732274:bnogo8gt6toe23vhef0g`,
 	Args: cobra.ExactArgs(1),
 	Run:  kill,
 }

tools/asynq/cmd/killall.go

@@ -20,11 +20,11 @@ var killallValidArgs = []string{"scheduled", "retry"}
 var killallCmd = &cobra.Command{
 	Use:   "killall [state]",
 	Short: "Kills all tasks in the specified state",
-	Long: `Killall (asynqmon killall) will update all tasks from the specified state to dead state.
+	Long: `Killall (asynq killall) will update all tasks from the specified state to dead state.
 
 The argument should be either "scheduled" or "retry".
 
-Example: asynqmon killall retry -> Update all retry tasks to dead tasks`,
+Example: asynq killall retry -> Update all retry tasks to dead tasks`,
 	ValidArgs: killallValidArgs,
 	Args:      cobra.ExactValidArgs(1),
 	Run:       killall,
@@ -59,7 +59,7 @@ func killall(cmd *cobra.Command, args []string) {
 	case "retry":
 		n, err = r.KillAllRetryTasks()
 	default:
-		fmt.Printf("error: `asynqmon killall [state]` only accepts %v as the argument.\n", killallValidArgs)
+		fmt.Printf("error: `asynq killall [state]` only accepts %v as the argument.\n", killallValidArgs)
 		os.Exit(1)
 	}
 	if err != nil {

tools/asynq/cmd/ls.go

@@ -25,19 +25,19 @@ var lsValidArgs = []string{"enqueued", "inprogress", "scheduled", "retry", "dead
 var lsCmd = &cobra.Command{
 	Use:   "ls [state]",
 	Short: "Lists tasks in the specified state",
-	Long: `Ls (asynqmon ls) will list all tasks in the specified state in a table format.
+	Long: `Ls (asynq ls) will list all tasks in the specified state in a table format.
 
 The command takes one argument which specifies the state of tasks.
 The argument value should be one of "enqueued", "inprogress", "scheduled",
 "retry", or "dead".
 
 Example:
-asynqmon ls dead -> Lists all tasks in dead state
+asynq ls dead -> Lists all tasks in dead state
 
 Enqueued tasks requires a queue name after ":"
 Example:
-asynqmon ls enqueued:default  -> List tasks from default queue
+asynq ls enqueued:default  -> List tasks from default queue
-asynqmon ls enqueued:critical -> List tasks from critical queue 
+asynq ls enqueued:critical -> List tasks from critical queue 
 `,
 	Args: cobra.ExactValidArgs(1),
 	Run:  ls,
@@ -72,7 +72,7 @@ func ls(cmd *cobra.Command, args []string) {
 	switch parts[0] {
 	case "enqueued":
 		if len(parts) != 2 {
-			fmt.Printf("error: Missing queue name\n`asynqmon ls enqueued:[queue name]`\n")
+			fmt.Printf("error: Missing queue name\n`asynq ls enqueued:[queue name]`\n")
 			os.Exit(1)
 		}
 		listEnqueued(r, parts[1])
@@ -85,7 +85,7 @@ func ls(cmd *cobra.Command, args []string) {
 	case "dead":
 		listDead(r)
 	default:
-		fmt.Printf("error: `asynqmon ls [state]`\nonly accepts %v as the argument.\n", lsValidArgs)
+		fmt.Printf("error: `asynq ls [state]`\nonly accepts %v as the argument.\n", lsValidArgs)
 		os.Exit(1)
 	}
 }

tools/asynq/cmd/rmq.go

@@ -18,11 +18,11 @@ import (
 var rmqCmd = &cobra.Command{
 	Use:   "rmq [queue name]",
 	Short: "Removes the specified queue",
-	Long: `Rmq (asynqmon rmq) will remove the specified queue.
+	Long: `Rmq (asynq rmq) will remove the specified queue.
 By default, it will remove the queue only if it's empty.
 Use --force option to override this behavior.
 
-Example: asynqmon rmq low -> Removes "low" queue`,
+Example: asynq rmq low -> Removes "low" queue`,
 	Args: cobra.ExactValidArgs(1),
 	Run:  rmq,
 }
@@ -44,7 +44,7 @@ func rmq(cmd *cobra.Command, args []string) {
 	err := r.RemoveQueue(args[0], rmqForce)
 	if err != nil {
 		if _, ok := err.(*rdb.ErrQueueNotEmpty); ok {
-			fmt.Printf("error: %v\nIf you are sure you want to delete it, run 'asynqmon rmq --force %s'\n", err, args[0])
+			fmt.Printf("error: %v\nIf you are sure you want to delete it, run 'asynq rmq --force %s'\n", err, args[0])
 			os.Exit(1)
 		}
 		fmt.Printf("error: %v", err)

tools/asynq/cmd/root.go

@@ -26,9 +26,9 @@ var password string
 
 // rootCmd represents the base command when called without any subcommands
 var rootCmd = &cobra.Command{
-	Use:   "asynqmon",
+	Use:   "asynq",
 	Short: "A monitoring tool for asynq queues",
-	Long:  `Asynqmon is a montoring CLI to inspect tasks and queues managed by asynq.`,
+	Long:  `Asynq is a montoring CLI to inspect tasks and queues managed by asynq.`,
 }
 
 // Execute adds all child commands to the root command and sets flags appropriately.
@@ -43,7 +43,7 @@ func Execute() {
 func init() {
 	cobra.OnInitialize(initConfig)
 
-	rootCmd.PersistentFlags().StringVar(&cfgFile, "config", "", "config file to set flag defaut values (default is $HOME/.asynqmon.yaml)")
+	rootCmd.PersistentFlags().StringVar(&cfgFile, "config", "", "config file to set flag defaut values (default is $HOME/.asynq.yaml)")
 	rootCmd.PersistentFlags().StringVarP(&uri, "uri", "u", "127.0.0.1:6379", "redis server URI")
 	rootCmd.PersistentFlags().IntVarP(&db, "db", "n", 0, "redis database number (default is 0)")
 	rootCmd.PersistentFlags().StringVarP(&password, "password", "p", "", "password to use when connecting to redis server")
@@ -65,9 +65,9 @@ func initConfig() {
 			os.Exit(1)
 		}
 
-		// Search config in home directory with name ".asynqmon" (without extension).
+		// Search config in home directory with name ".asynq" (without extension).
 		viper.AddConfigPath(home)
-		viper.SetConfigName(".asynqmon")
+		viper.SetConfigName(".asynq")
 	}
 
 	viper.AutomaticEnv() // read in environment variables that match

tools/asynq/cmd/servers.go

@@ -18,64 +18,64 @@ import (
 	"github.com/spf13/viper"
 )
 
-// psCmd represents the ps command
+// serversCmd represents the servers command
-var psCmd = &cobra.Command{
+var serversCmd = &cobra.Command{
-	Use:   "ps",
+	Use:   "servers",
-	Short: "Shows all background worker processes",
+	Short: "Shows all running worker servers",
-	Long: `Ps (asynqmon ps) will show all background worker processes
+	Long: `Servers (asynq servers) will show all running worker servers
-backed by the specified redis instance.
+pulling tasks from the specified redis instance.
 
-The command shows the following for each process:
+The command shows the following for each server:
-* Host and PID of the process
+* Host and PID of the process in which the server is running
 * Number of active workers out of worker pool
 * Queue configuration
-* State of the worker process ("running" | "stopped")
+* State of the worker server ("running" | "quiet")
-* Time the process was started
+* Time the server was started
 
-A "running" process is processing tasks in queues.
+A "running" server is pulling tasks from queues and processing them.
-A "stopped" process is no longer processing new tasks.`,
+A "quiet" server is no longer pulling new tasks from queues`,
 	Args: cobra.NoArgs,
-	Run:  ps,
+	Run:  servers,
 }
 
 func init() {
-	rootCmd.AddCommand(psCmd)
+	rootCmd.AddCommand(serversCmd)
 }
 
-func ps(cmd *cobra.Command, args []string) {
+func servers(cmd *cobra.Command, args []string) {
 	r := rdb.NewRDB(redis.NewClient(&redis.Options{
 		Addr:     viper.GetString("uri"),
 		DB:       viper.GetInt("db"),
 		Password: viper.GetString("password"),
 	}))
 
-	processes, err := r.ListProcesses()
+	servers, err := r.ListServers()
 	if err != nil {
 		fmt.Println(err)
 		os.Exit(1)
 	}
-	if len(processes) == 0 {
+	if len(servers) == 0 {
-		fmt.Println("No processes")
+		fmt.Println("No running servers")
 		return
 	}
 
 	// sort by hostname and pid
-	sort.Slice(processes, func(i, j int) bool {
+	sort.Slice(servers, func(i, j int) bool {
-		x, y := processes[i], processes[j]
+		x, y := servers[i], servers[j]
 		if x.Host != y.Host {
 			return x.Host < y.Host
 		}
 		return x.PID < y.PID
 	})
 
-	// print processes
+	// print server info
 	cols := []string{"Host", "PID", "State", "Active Workers", "Queues", "Started"}
 	printRows := func(w io.Writer, tmpl string) {
-		for _, ps := range processes {
+		for _, info := range servers {
 			fmt.Fprintf(w, tmpl,
-				ps.Host, ps.PID, ps.Status,
+				info.Host, info.PID, info.Status,
-				fmt.Sprintf("%d/%d", ps.ActiveWorkerCount, ps.Concurrency),
+				fmt.Sprintf("%d/%d", info.ActiveWorkerCount, info.Concurrency),
-				formatQueues(ps.Queues), timeAgo(ps.Started))
+				formatQueues(info.Queues), timeAgo(info.Started))
 		}
 	}
 	printTable(cols, printRows)

tools/asynq/cmd/stats.go

@@ -33,7 +33,7 @@ Specifically, the command shows the following:
 To monitor the tasks continuously, it's recommended that you run this
 command in conjunction with the watch command.
 
-Example: watch -n 3 asynqmon stats -> Shows current state of tasks every three seconds`,
+Example: watch -n 3 asynq stats -> Shows current state of tasks every three seconds`,
 	Args: cobra.NoArgs,
 	Run:  stats,
 }

tools/asynq/cmd/workers.go

@@ -20,7 +20,7 @@ import (
 var workersCmd = &cobra.Command{
 	Use:   "workers",
 	Short: "Shows all running workers information",
-	Long: `Workers (asynqmon workers) will show all running workers information.
+	Long: `Workers (asynq workers) will show all running workers information.
 
 The command shows the following for each worker:
 * Process in which the worker is running

tools/asynq/main.go

@@ -4,7 +4,7 @@
 
 package main
 
-import "github.com/hibiken/asynq/tools/asynqmon/cmd"
+import "github.com/hibiken/asynq/tools/asynq/cmd"
 
 func main() {
 	cmd.Execute()