Skip to content

K
k3s
Commit bbfda4be authored by Eric Tune's avatar Eric Tune
Browse files
Options

Remove examples moved to docs site

Part of https://github.com/kubernetes/kubernetes/issues/23511 Left redirect in md files and deleted files intended for download.
parent d08a7226
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 4 additions and 830 deletions
examples/examples_test.go
View file @ bbfda4be
...@@ -401,14 +401,6 @@ func TestExampleObjectSchemas(t *testing.T) { ...@@ -401,14 +401,6 @@ func TestExampleObjectSchemas(t *testing.T) {
"javaweb": &api.Pod{}, "javaweb": &api.Pod{},
"javaweb-2": &api.Pod{}, "javaweb-2": &api.Pod{},
}, },
"../examples/job/work-queue-1": {
"job": &batch.Job{},
},
"../examples/job/work-queue-2": {
"redis-pod": &api.Pod{},
"redis-service": &api.Service{},
"job": &batch.Job{},
},
"../examples/volumes/azure_file": { "../examples/volumes/azure_file": {
"azure": &api.Pod{}, "azure": &api.Pod{},
}, },
......
examples/job/expansions/README.md
View file @ bbfda4be
<!-- BEGIN MUNGE: UNVERSIONED_WARNING --> <!-- BEGIN MUNGE: UNVERSIONED_WARNING -->
<!-- BEGIN STRIP_FOR_RELEASE --> <!-- BEGIN STRIP_FOR_RELEASE -->
...@@ -32,216 +33,7 @@ Documentation for other releases can be found at ...@@ -32,216 +33,7 @@ Documentation for other releases can be found at
<!-- END MUNGE: UNVERSIONED_WARNING --> <!-- END MUNGE: UNVERSIONED_WARNING -->
# Example: Multiple Job Objects from Template Expansion This file has moved to: http://kubernetes.io/docs/user-guide/jobs/
In this example, we will run multiple Kubernetes Jobs created from
a common template. You may want to be familiar with the basic,
non-parallel, use of [Job](../../../docs/user-guide/jobs.md) first.
## Basic Template Expansion
First, create a template of a Job object:
<!-- BEGIN MUNGE: EXAMPLE job.yaml.txt -->
```
apiVersion: batch/v1
kind: Job
metadata:
name: process-item-$ITEM
labels:
jobgroup: jobexample
spec:
template:
metadata:
name: jobexample
labels:
jobgroup: jobexample
spec:
containers:
- name: c
image: busybox
command: ["sh", "-c", "echo Processing item $ITEM && sleep 5"]
restartPolicy: Never
```
[Download example](job.yaml.txt?raw=true)
<!-- END MUNGE: EXAMPLE job.yaml.txt -->
Unlike a *pod template*, our *job template* is not a Kubernetes API type. It is just
a yaml representation of a Job object that has some placeholders that need to be filled
in before it can be used. The `$ITEM` syntax is not meaningful to Kubernetes.
In this example, the only processing the container does is to `echo` a string and sleep for a bit.
In a real use case, the processing would be some substantial computation, such as rendering a frame
of a movie, or processing a range of rows in a database. The "$ITEM" parameter would specify for
example, the frame number or the row range.
This Job and its Pod template have a label: `jobgroup=jobexample`. There is nothing special
to the system about this label. This label
makes it convenient to operate on all the jobs in this group at once.
We also put the same label on the pod template so that we can check on all Pods of these Jobs
with a single command.
After the job is created, the system will add more labels that distinguish one Job's pods
from another Job's pods.
Note that the label key `jobgroup` is not special to Kubernetes. you can pick your own label scheme.
Next, expand the template into multiple files, one for each item to be processed.
```console
# Expand files into a temporary directory
$ mkdir ./jobs
$ for i in apple banana cherry
do
cat job.yaml.txt | sed "s/\$ITEM/$i/" > ./jobs/job-$i.yaml
done
$ ls jobs/
job-apple.yaml
job-banana.yaml
job-cherry.yaml
```
Here, we used `sed` to replace the string `$ITEM` with the the loop variable.
You could use any type of template language (jinja2, erb) or write a program
to generate the Job objects.
Next, create all the jobs with one kubectl command:
```console
$ kubectl create -f ./jobs
job "process-item-apple" created
job "process-item-banana" created
job "process-item-cherry" created
```
Now, check on the jobs:
```console
$ kubectl get jobs -l app=jobexample
JOB CONTAINER(S) IMAGE(S) SELECTOR SUCCESSFUL
process-item-apple c busybox app in (jobexample),item in (apple) 1
process-item-banana c busybox app in (jobexample),item in (banana) 1
process-item-cherry c busybox app in (jobexample),item in (cherry) 1
```
Here we use the `-l` option to select all jobs that are part of this
group of jobs. (There might be other unrelated jobs in the system that we
do not care to see.)
We can check on the pods as well using the same label selector:
```console
$ kubectl get pods -l app=jobexample
NAME READY STATUS RESTARTS AGE
process-item-apple-kixwv 0/1 Completed 0 4m
process-item-banana-wrsf7 0/1 Completed 0 4m
process-item-cherry-dnfu9 0/1 Completed 0 4m
```
There is not a single command to check on the output of all jobs at once,
but looping over all the pods is pretty easy:
```console
$ for p in $(kubectl get pods -l app=jobexample -o name)
do
kubectl logs $p
done
Processing item apple
Processing item banana
Processing item cherry
```
## Multiple Template Parameters
In the first example, each instance of the template had one parameter, and that parameter was also
used as a label. However label keys are limited in [what characters they can
contain](labels.md#syntax-and-character-set).
This slightly more complex example uses a the jinja2 template language to generate our objects.
We will use a one-line python script to convert the template to a file.
First, download or paste the following template file to a file called `job.yaml.jinja2`:
<!-- BEGIN MUNGE: EXAMPLE job.yaml.jinja2 -->
```
{%- set params = [{ "name": "apple", "url": "http://www.orangepippin.com/apples", },
{ "name": "banana", "url": "https://en.wikipedia.org/wiki/Banana", },
{ "name": "raspberry", "url": "https://www.raspberrypi.org/" }]
%}
{%- for p in params %}
{%- set name = p["name"] %}
{%- set url = p["url"] %}
apiVersion: batch/v1
kind: Job
metadata:
name: jobexample-{{ name }}
labels:
jobgroup: jobexample
spec:
template:
name: jobexample
labels:
jobgroup: jobexample
spec:
containers:
- name: c
image: busybox
command: ["sh", "-c", "echo Processing URL {{ url }} && sleep 5"]
restartPolicy: Never
---
{%- endfor %}
```
[Download example](job.yaml.jinja2?raw=true)
<!-- END MUNGE: EXAMPLE job.yaml.jinja2 -->
The above template defines parameters for each job object using a list of
python dicts (lines 1-4). Then a for loop emits one job yaml object
for each set of parameters (remaining lines).
We take advantage of the fact that multiple yaml documents can be concatenated
with the `---` separator (second to last line).
.) We can pipe the output directly to kubectl to
create the objects.
You will need the jinja2 package if you do not already have it: `pip install --user jinja2`.
Now, use this one-line python program to expand the template:
```
$ alias render_template='python -c "from jinja2 import Template; import sys; print(Template(sys.stdin.read()).render());"'
```
The output can be saved to a file, like this:
```
$ cat job.yaml.jinja2 | render_template > jobs.yaml
```
or sent directly to kubectl, like this:
```
$ cat job.yaml.jinja2 | render_template | kubectl create -f -
```
## Alternatives
If you have a large number of job objects, you may find that:
- even using labels, managing so many Job objects is cumbersome.
- you exceed resource quota when creating all the Jobs at once,
and do not want to wait to create them incrementally.
- you need a way to easily scale the number of pods running
concurrently. One reason would be to avoid using too many
compute resources. Another would be to limit the number of
concurrent requests to a shared resource, such as a database,
used by all the pods in the job.
- very large numbers of jobs created at once overload the
kubernetes apiserver, controller, or scheduler.
In this case, you can consider one of the
other [job patterns](../../../docs/user-guide/jobs.md#job-patterns).
<!-- BEGIN MUNGE: GENERATED_ANALYTICS --> <!-- BEGIN MUNGE: GENERATED_ANALYTICS -->
......
examples/job/expansions/job.yaml.jinja2 deleted 100644 → 0
View file @ d08a7226
{%- set params = [{ "name": "apple", "url": "http://www.orangepippin.com/apples", },
{ "name": "banana", "url": "https://en.wikipedia.org/wiki/Banana", },
{ "name": "raspberry", "url": "https://www.raspberrypi.org/" }]
%}
{%- for p in params %}
{%- set name = p["name"] %}
{%- set url = p["url"] %}
apiVersion: batch/v1
kind: Job
metadata:
name: jobexample-{{ name }}
labels:
jobgroup: jobexample
spec:
template:
name: jobexample
labels:
jobgroup: jobexample
spec:
containers:
- name: c
image: busybox
command: ["sh", "-c", "echo Processing URL {{ url }} && sleep 5"]
restartPolicy: Never
---
{%- endfor %}
examples/job/expansions/job.yaml.txt deleted 100644 → 0
View file @ d08a7226
apiVersion: batch/v1
kind: Job
metadata:
name: process-item-$ITEM
labels:
jobgroup: jobexample
spec:
template:
metadata:
name: jobexample
labels:
jobgroup: jobexample
spec:
containers:
- name: c
image: busybox
command: ["sh", "-c", "echo Processing item $ITEM && sleep 5"]
restartPolicy: Never
examples/job/work-queue-1/Dockerfile deleted 100644 → 0
View file @ d08a7226
# Copyright 2016 The Kubernetes Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Specify BROKER_URL and QUEUE when running
FROM ubuntu:14.04
RUN apt-get update && \
apt-get install -y curl ca-certificates amqp-tools python \
--no-install-recommends \
&& rm -rf /var/lib/apt/lists/*
COPY ./worker.py /worker.py
CMD /usr/bin/amqp-consume --url=$BROKER_URL -q $QUEUE -c 1 /worker.py
examples/job/work-queue-1/job.yaml deleted 100644 → 0
View file @ d08a7226
apiVersion: batch/v1
kind: Job
metadata:
name: job-wq-1
spec:
completions: 8
parallelism: 2
template:
metadata:
name: job-wq-1
spec:
containers:
- name: c
image: gcr.io/<project>/job-wq-1
restartPolicy: OnFailure
examples/job/work-queue-1/worker.py deleted 100755 → 0
View file @ d08a7226
#!/usr/bin/env python
# Copyright 2015 The Kubernetes Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Just prints standard out and sleeps for 10 seconds.
import sys
import time
print("Processing " + sys.stdin.lines())
time.sleep(10)
examples/job/work-queue-2/Dockerfile deleted 100644 → 0
View file @ d08a7226
# Copyright 2016 The Kubernetes Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
FROM python
RUN pip install redis
COPY ./worker.py /worker.py
COPY ./rediswq.py /rediswq.py
CMD python worker.py
examples/job/work-queue-2/README.md
View file @ bbfda4be
<!-- BEGIN MUNGE: UNVERSIONED_WARNING --> <!-- BEGIN MUNGE: UNVERSIONED_WARNING -->
<!-- BEGIN STRIP_FOR_RELEASE --> <!-- BEGIN STRIP_FOR_RELEASE -->
...@@ -32,274 +33,7 @@ Documentation for other releases can be found at ...@@ -32,274 +33,7 @@ Documentation for other releases can be found at
<!-- END MUNGE: UNVERSIONED_WARNING --> <!-- END MUNGE: UNVERSIONED_WARNING -->
# Example: Job with Work Queue with Pod Per Work Item This file has moved to: http://kubernetes.io/docs/user-guide/jobs/
In this example, we will run a Kubernetes Job with multiple parallel
worker processes. You may want to be familiar with the basic,
non-parallel, use of [Job](../../../docs/user-guide/jobs.md) first.
In this example, as each pod is created, it picks up one unit of work
from a task queue, completes it, deletes it from the queue, and exits.
Here is an overview of the steps in this example:
1. **Start a storage service to hold the work queue.** In this example, we use Redis to store
our work items. In the previous example, we used RabbitMQ. In this example, we use Redis and
a custom work-queue client library because AMQP does not provide a good way for clients to
detect when a finite-length work queue is empty. In practice you would set up a store such
as Redis once and reuse it for the work queues of many jobs, and other things.
1. **Create a queue, and fill it with messages.** Each message represents one task to be done. In
this example, a message is just an integer that we will do a lengthy computation on.
1. **Start a Job that works on tasks from the queue**. The Job starts several pods. Each pod takes
one task from the message queue, processes it, and repeats until the end of the queue is reached.
## Starting Redis
For this example, for simplicitly, we will start a single instance of Redis.
See the [Redis Example](../../../examples/storage/redis/README.md) for an example
of deploying Redis scaleably and redundantly.
Start a temporary Pod running Redis and a service so we can find it.
```console
$ kubectl create -f examples/job/work-queue-2/redis-pod.yaml
pod "redis-master" created
$ kubectl create -f examples/job/work-queue-2/redis-service.yaml
service "redis" created
```
## Filling the Queue with tasks
Now lets fill the queue with some "tasks". In our example, our tasks are just strings to be
printed.
Start a temporary interactive pod for running the Redis CLI
```console
$ kubectl run -i --tty temp --image redis --command "/bin/sh"
Waiting for pod default/redis2-c7h78 to be running, status is Pending, pod ready: false
Hit enter for command prompt
```
Now hit enter, start the redis CLI, and create a list with some work items in it.
```
# redis-cli -h redis
redis:6379> rpush job2 "apple"
(integer) 1
redis:6379> rpush job2 "banana"
(integer) 2
redis:6379> rpush job2 "cherry"
(integer) 3
redis:6379> rpush job2 "date"
(integer) 4
redis:6379> rpush job2 "fig"
(integer) 5
redis:6379> rpush job2 "grape"
(integer) 6
redis:6379> rpush job2 "lemon"
(integer) 7
redis:6379> rpush job2 "melon"
(integer) 8
redis:6379> rpush job2 "orange"
(integer) 9
redis:6379> lrange job2 0 -1
1) "apple"
2) "banana"
3) "cherry"
4) "date"
5) "fig"
6) "grape"
7) "lemon"
8) "melon"
9) "orange"
```
So, the list with key `job2` will be our work queue.
Note: if you do not have Kube DNS setup correctly, you may need to change
the first step of the above block to `redis-cli -h $REDIS_SERVICE_HOST`.
## Create an Image
Now we are ready to create an image that we will run.
We will use a python worker program with a redis client to read
the messages from the message queue.
A simple Redis work queue client library is provided,
called rediswq.py ([Download](rediswq.py?raw=true)).
The "worker" program in each Pod of the Job uses the work queue
client library to get work. Here it is:
<!-- BEGIN MUNGE: EXAMPLE worker.py -->
```
#!/usr/bin/env python
# Copyright 2015 The Kubernetes Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import time
import rediswq
host="redis"
# Uncomment next two lines if you do not have Kube-DNS working.
# import os
# host = os.getenv("REDIS_SERVICE_HOST")
q = rediswq.RedisWQ(name="job2", host="redis")
print("Worker with sessionID: " + q.sessionID())
print("Initial queue state: empty=" + str(q.empty()))
while not q.empty():
item = q.lease(lease_secs=10, block=True, timeout=2)
if item is not None:
itemstr = item.decode("utf=8")
print("Working on " + itemstr)
time.sleep(10) # Put your actual work here instead of sleep.
q.complete(item)
else:
print("Waiting for work")
print("Queue empty, exiting")
```
[Download example](worker.py?raw=true)
<!-- END MUNGE: EXAMPLE worker.py -->
If you are working from the source tree,
change directory to the `examples/job/work-queue-2` directory.
Otherwise, download [`worker.py`](worker.py?raw=true), [`rediswq.py`](rediswq.py?raw=true), and [`Dockerfile`](Dockerfile?raw=true)
using above links. Then build the image:
```console
$ docker build -t job-wq-2 .
```
### Push the image
For the [Docker Hub](https://hub.docker.com/), tag your app image with
your username and push to the Hub with the below commands. Replace
`<username>` with your Hub username.
```
docker tag job-wq-2 <username>/job-wq-2
docker push <username>/job-wq-2
```
You need to push to a public repository or [configure your cluster to be able to access
your private repository](../../../docs/user-guide/images.md).
If you are using [Google Container
Registry](https://cloud.google.com/tools/container-registry/), tag
your app image with your project ID, and push to GCR. Replace
`<project>` with your project ID.
```
docker tag job-wq-2 gcr.io/<project>/job-wq-2
gcloud docker push gcr.io/<project>/job-wq-2
```
## Defining a Job
Here is the job definition:
<!-- BEGIN MUNGE: EXAMPLE job.yaml -->
```yaml
apiVersion: batch/v1
kind: Job
metadata:
name: job-wq-2
spec:
parallelism: 2
template:
metadata:
name: job-wq-2
spec:
containers:
- name: c
image: gcr.io/myproject/job-wq-2
restartPolicy: OnFailure
```
[Download example](job.yaml?raw=true)
<!-- END MUNGE: EXAMPLE job.yaml -->
Be sure to edit the job template to
change `gcr.io/myproject` to your own path.
In this example, each pod works on several items from the queue and then exits when there are no more items.
Since the workers themselves detect when the workqueue is empty, and the Job controller does not
know about the workqueue, it relies on the workers to signal when they are done working.
The workers signal that the queue is empty by exiting with success. So, as soon as any worker
exits with success, the controller knows the work is done, and the Pods will exit soon.
So, we set the completion count of the Job to 1. The job controller will wait for the other pods to complete
too.
## Running the Job
So, now run the Job:
```console
$ kubectl create -f ./job.yaml
```
Now wait a bit, then check on the job.
```console
$ ./kubectl describe jobs/job-wq-2
Name: job-wq-2
Namespace: default
Image(s): gcr.io/exampleproject/job-wq-2
Selector: app in (job-wq-2)
Parallelism: 2
Completions: Unset
Start Time: Mon, 11 Jan 2016 17:07:59 -0800
Labels: app=job-wq-2
Pods Statuses: 1 Running / 0 Succeeded / 0 Failed
No volumes.
Events:
FirstSeen LastSeen Count From SubobjectPath Type Reason Message
--------- -------- ----- ---- ------------- -------- ------ -------
33s 33s 1 {job-controller } Normal SuccessfulCreate Created pod: job-wq-2-lglf8
$ kubectl logs pods/job-wq-2-7r7b2
Worker with sessionID: bbd72d0a-9e5c-4dd6-abf6-416cc267991f
Initial queue state: empty=False
Working on banana
Working on date
Working on lemon
```
As you can see, one of our pods worked on several work units.
## Alternatives
If running a queue service or modifying your containers to use a work queue is inconvenient, you may
want to consider one of the other [job patterns](../../../docs/user-guide/jobs.md#job-patterns).
If you have a continuous stream of background processing work to run, then
consider running your background workers with a `replicationController` instead,
and consider running a background processing library such as
https://github.com/resque/resque.
<!-- BEGIN MUNGE: GENERATED_ANALYTICS --> <!-- BEGIN MUNGE: GENERATED_ANALYTICS -->
......
examples/job/work-queue-2/job.yaml deleted 100644 → 0
View file @ d08a7226
apiVersion: batch/v1
kind: Job
metadata:
name: job-wq-2
spec:
parallelism: 2
template:
metadata:
name: job-wq-2
spec:
containers:
- name: c
image: gcr.io/myproject/job-wq-2
restartPolicy: OnFailure
examples/job/work-queue-2/redis-pod.yaml deleted 100644 → 0
View file @ d08a7226
apiVersion: v1
kind: Pod
metadata:
name: redis-master
labels:
app: redis
spec:
containers:
- name: master
image: redis
env:
- name: MASTER
value: "true"
ports:
- containerPort: 6379
examples/job/work-queue-2/redis-service.yaml deleted 100644 → 0
View file @ d08a7226
apiVersion: v1
kind: Service
metadata:
name: redis
spec:
ports:
- port: 6379
targetPort: 6379
selector:
app: redis
examples/job/work-queue-2/rediswq.py deleted 100644 → 0
View file @ d08a7226
#!/usr/bin/env python
# Copyright 2015 The Kubernetes Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Based on http://peter-hoffmann.com/2012/python-simple-queue-redis-queue.html
# and the suggestion in the redis documentation for RPOPLPUSH, at
# http://redis.io/commands/rpoplpush, which suggests how to implement a work-queue.
import redis
import uuid
import hashlib
class RedisWQ(object):
"""Simple Finite Work Queue with Redis Backend
This work queue is finite: as long as no more work is added
after workers start, the workers can detect when the queue
is completely empty.
The items in the work queue are assumed to have unique values.
This object is not intended to be used by multiple threads
concurrently.
"""
def __init__(self, name, **redis_kwargs):
"""The default connection parameters are: host='localhost', port=6379, db=0
The work queue is identified by "name". The library may create other
keys with "name" as a prefix.
"""
self._db = redis.StrictRedis(**redis_kwargs)
# The session ID will uniquely identify this "worker".
self._session = str(uuid.uuid4())
# Work queue is implemented as two queues: main, and processing.
# Work is initially in main, and moved to processing when a client picks it up.
self._main_q_key = name
self._processing_q_key = name + ":processing"
self._lease_key_prefix = name + ":leased_by_session:"
def sessionID(self):
"""Return the ID for this session."""
return self._session
def _main_qsize(self):
"""Return the size of the main queue."""
return self._db.llen(self._main_q_key)
def _processing_qsize(self):
"""Return the size of the main queue."""
return self._db.llen(self._processing_q_key)
def empty(self):
"""Return True if the queue is empty, including work being done, False otherwise.
False does not necessarily mean that there is work available to work on right now,
"""
return self._main_qsize() == 0 and self._processing_qsize() == 0
# TODO: implement this
# def check_expired_leases(self):
# """Return to the work queueReturn True if the queue is empty, False otherwise."""
# # Processing list should not be _too_ long since it is approximately as long
# # as the number of active and recently active workers.
# processing = self._db.lrange(self._processing_q_key, 0, -1)
# for item in processing:
# # If the lease key is not present for an item (it expired or was
# # never created because the client crashed before creating it)
# # then move the item back to the main queue so others can work on it.
# if not self._lease_exists(item):
# TODO: transactionally move the key from processing queue to
# to main queue, while detecting if a new lease is created
# or if either queue is modified.
def _itemkey(self, item):
"""Returns a string that uniquely identifies an item (bytes)."""
return hashlib.sha224(item).hexdigest()
def _lease_exists(self, item):
"""True if a lease on 'item' exists."""
return self._db.exists(self._lease_key_prefix + self._itemkey(item))
def lease(self, lease_secs=60, block=True, timeout=None):
"""Begin working on an item the work queue.
Lease the item for lease_secs. After that time, other
workers may consider this client to have crashed or stalled
and pick up the item instead.
If optional args block is true and timeout is None (the default), block
if necessary until an item is available."""
if block:
item = self._db.brpoplpush(self._main_q_key, self._processing_q_key, timeout=timeout)
else:
item = self._db.rpoplpush(self._main_q_key, self._processing_q_key)
if item:
# Record that we (this session id) are working on a key. Expire that
# note after the lease timeout.
# Note: if we crash at this line of the program, then GC will see no lease
# for this item an later return it to the main queue.
itemkey = self._itemkey(item)
self._db.setex(self._lease_key_prefix + itemkey, lease_secs, self._session)
return item
def complete(self, value):
"""Complete working on the item with 'value'.
If the lease expired, the item may not have completed, and some
other worker may have picked it up. There is no indication
of what happened.
"""
self._db.lrem(self._processing_q_key, 0, value)
# If we crash here, then the GC code will try to move the value, but it will
# not be here, which is fine. So this does not need to be a transaction.
itemkey = self._itemkey(value)
self._db.delete(self._lease_key_prefix + itemkey, self._session)
# TODO: add functions to clean up all keys associated with "name" when
# processing is complete.
# TODO: add a function to add an item to the queue. Atomically
# check if the queue is empty and if so fail to add the item
# since other workers might think work is done and be in the process
# of exiting.
# TODO(etune): move to my own github for hosting, e.g. github.com/erictune/rediswq-py and
# make it so it can be pip installed by anyone (see
# http://stackoverflow.com/questions/8247605/configuring-so-that-pip-install-can-work-from-github)
# TODO(etune): finish code to GC expired leases, and call periodically
# e.g. each time lease times out.
examples/job/work-queue-2/worker.py deleted 100755 → 0
View file @ d08a7226
#!/usr/bin/env python
# Copyright 2015 The Kubernetes Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import time
import rediswq
host="redis"
# Uncomment next two lines if you do not have Kube-DNS working.
# import os
# host = os.getenv("REDIS_SERVICE_HOST")
q = rediswq.RedisWQ(name="job2", host="redis")
print("Worker with sessionID: " + q.sessionID())
print("Initial queue state: empty=" + str(q.empty()))
while not q.empty():
item = q.lease(lease_secs=10, block=True, timeout=2)
if item is not None:
itemstr = item.decode("utf=8")
print("Working on " + itemstr)
time.sleep(10) # Put your actual work here instead of sleep.
q.complete(item)
else:
print("Waiting for work")
print("Queue empty, exiting")
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment