vbatts/cri-o
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Switch to github.com/golang/dep for vendoring

Browse source 
Signed-off-by: Mrunal Patel <mrunalp@gmail.com>
This commit is contained in:
Mrunal Patel 2017-01-31 16:45:59 -08:00
parent d6ab91be27
commit 8e5b17cf13
15431 changed files with 3971413 additions and 8881 deletions
Download patch file Download diff file Expand all files Collapse all files

839
vendor/k8s.io/kubernetes/examples/storage/cassandra/README.md generated vendored Normal file
View file

@ -0,0 +1,839 @@
# Cloud Native Deployments of Cassandra using Kubernetes
## Table of Contents
- [Prerequisites](#prerequisites)
- [Cassandra Docker](#cassandra-docker)
- [Quickstart](#quickstart)
- [Step 1: Create a Cassandra Headless Service](#step-1-create-a-cassandra-headless-service)
- [Step 2: Use a StatefulSet to create Cassandra Ring](#step-2-use-a-statefulset-to-create-cassandra-ring)
- [Step 3: Validate and Modify The Cassandra StatefulSet](#step-3-validate-and-modify-the-cassandra-statefulset)
- [Step 4: Delete Cassandra StatefulSet](#step-4-delete-cassandra-statefulset)
- [Step 5: Use a Replication Controller to create Cassandra node pods](#step-5-use-a-replication-controller-to-create-cassandra-node-pods)
- [Step 6: Scale up the Cassandra cluster](#step-6-scale-up-the-cassandra-cluster)
- [Step 7: Delete the Replication Controller](#step-7-delete-the-replication-controller)
- [Step 8: Use a DaemonSet instead of a Replication Controller](#step-8-use-a-daemonset-instead-of-a-replication-controller)
- [Step 9: Resource Cleanup](#step-9-resource-cleanup)
- [Seed Provider Source](#seed-provider-source)
The following document describes the development of a _cloud native_
[Cassandra](http://cassandra.apache.org/) deployment on Kubernetes. When we say
_cloud native_, we mean an application which understands that it is running
within a cluster manager, and uses this cluster management infrastructure to
help implement the application. In particular, in this instance, a custom
Cassandra `SeedProvider` is used to enable Cassandra to dynamically discover
new Cassandra nodes as they join the cluster.
This example also uses some of the core components of Kubernetes:
- [_Pods_](../../../docs/user-guide/pods.md)
- [ _Services_](../../../docs/user-guide/services.md)
- [_Replication Controllers_](../../../docs/user-guide/replication-controller.md)
- [_Stateful Sets_](http://kubernetes.io/docs/user-guide/petset/)
- [_Daemon Sets_](../../../docs/admin/daemons.md)
## Prerequisites
This example assumes that you have a Kubernetes version >=1.2 cluster installed and running,
and that you have installed the [`kubectl`](../../../docs/user-guide/kubectl/kubectl.md)
command line tool somewhere in your path. Please see the
[getting started guides](../../../docs/getting-started-guides/)
for installation instructions for your platform.
This example also has a few code and configuration files needed. To avoid
typing these out, you can `git clone` the Kubernetes repository to your local
computer.
## Cassandra Docker
The pods use the [```gcr.io/google-samples/cassandra:v11```](image/Dockerfile)
image from Google's [container registry](https://cloud.google.com/container-registry/docs/).
The docker is based on `debian:jessie` and includes OpenJDK 8. This image
includes a standard Cassandra installation from the Apache Debian repo. Through the use of environment variables you are able to change values that are inserted into the `cassandra.yaml`.
| ENV VAR | DEFAULT VALUE |
| ------------- |:-------------: |
| CASSANDRA_CLUSTER_NAME | 'Test Cluster' |
| CASSANDRA_NUM_TOKENS | 32 |
| CASSANDRA_RPC_ADDRESS | 0.0.0.0 |
## Quickstart
If you want to jump straight to the commands we will run,
here are the steps:
```sh
#
# StatefulSet
#
# create a service to track all cassandra statefulset nodes
kubectl create -f examples/storage/cassandra/cassandra-service.yaml
# create a statefulset
kubectl create -f examples/storage/cassandra/cassandra-statefulset.yaml
# validate the Cassandra cluster. Substitute the name of one of your pods.
kubectl exec -ti cassandra-0 -- nodetool status
# cleanup
grace=$(kubectl get po cassandra-0 --template '{{.spec.terminationGracePeriodSeconds}}') \
&& kubectl delete statefulset,po -l app=cassandra \
&& echo "Sleeping $grace" \
&& sleep $grace \
&& kubectl delete pvc -l app=cassandra
#
# Resource Controller Example
#
# create a replication controller to replicate cassandra nodes
kubectl create -f examples/storage/cassandra/cassandra-controller.yaml
# validate the Cassandra cluster. Substitute the name of one of your pods.
kubectl exec -ti cassandra-xxxxx -- nodetool status
# scale up the Cassandra cluster
kubectl scale rc cassandra --replicas=4
# delete the replication controller
kubectl delete rc cassandra
#
# Create a DaemonSet to place a cassandra node on each kubernetes node
#
kubectl create -f examples/storage/cassandra/cassandra-daemonset.yaml --validate=false
# resource cleanup
kubectl delete service -l app=cassandra
kubectl delete daemonset cassandra
```
## Step 1: Create a Cassandra Headless Service
A Kubernetes _[Service](../../../docs/user-guide/services.md)_ describes a set of
[_Pods_](../../../docs/user-guide/pods.md) that perform the same task. In
Kubernetes, the atomic unit of an application is a Pod: one or more containers
that _must_ be scheduled onto the same host.
The Service is used for DNS lookups between Cassandra Pods, and Cassandra clients
within the Kubernetes Cluster.
Here is the service description:
<!-- BEGIN MUNGE: EXAMPLE cassandra-service.yaml -->
```yaml
apiVersion: v1
kind: Service
metadata:
labels:
app: cassandra
name: cassandra
spec:
clusterIP: None
ports:
- port: 9042
selector:
app: cassandra
```
[Download example](cassandra-service.yaml?raw=true)
<!-- END MUNGE: EXAMPLE cassandra-service.yaml -->
Create the service for the StatefulSet:
```console
$ kubectl create -f examples/storage/cassandra/cassandra-service.yaml
```
The following command shows if the service has been created.
```console
$ kubectl get svc cassandra
```
The response should be like:
```console
NAME CLUSTER-IP EXTERNAL-IP PORT(S) AGE
cassandra None <none> 9042/TCP 45s
```
If an error is returned the service create failed.
## Step 2: Use a StatefulSet to create Cassandra Ring
StatefulSets (previously PetSets) are a new feature that was added as an <i>Alpha</i> component in
Kubernetes 1.3. Deploying stateful distributed applications, like Cassandra, within a clustered
environment can be challenging. We implemented StatefulSet to greatly simplify this
process. Multiple StatefulSet features are used within this example, but is out of
scope of this documentation. [Please refer to the PetSet documentation.](http://kubernetes.io/docs/user-guide/petset/)
The StatefulSet manifest that is included below, creates a Cassandra ring that consists
of three pods.
<!-- BEGIN MUNGE: EXAMPLE cassandra-statefulset.yaml -->
```yaml
apiVersion: "apps/v1beta1"
kind: StatefulSet
metadata:
name: cassandra
spec:
serviceName: cassandra
replicas: 3
template:
metadata:
labels:
app: cassandra
spec:
containers:
- name: cassandra
image: gcr.io/google-samples/cassandra:v11
imagePullPolicy: Always
ports:
- containerPort: 7000
name: intra-node
- containerPort: 7001
name: tls-intra-node
- containerPort: 7199
name: jmx
- containerPort: 9042
name: cql
resources:
limits:
cpu: "500m"
memory: 1Gi
requests:
cpu: "500m"
memory: 1Gi
securityContext:
capabilities:
add:
- IPC_LOCK
env:
- name: MAX_HEAP_SIZE
value: 512M
- name: HEAP_NEWSIZE
value: 100M
- name: CASSANDRA_SEEDS
value: "cassandra-0.cassandra.default.svc.cluster.local"
- name: CASSANDRA_CLUSTER_NAME
value: "K8Demo"
- name: CASSANDRA_DC
value: "DC1-K8Demo"
- name: CASSANDRA_RACK
value: "Rack1-K8Demo"
- name: CASSANDRA_AUTO_BOOTSTRAP
value: "false"
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
readinessProbe:
exec:
command:
- /bin/bash
- -c
- /ready-probe.sh
initialDelaySeconds: 15
timeoutSeconds: 5
# These volume mounts are persistent. They are like inline claims,
# but not exactly because the names need to match exactly one of
# the stateful pod volumes.
volumeMounts:
- name: cassandra-data
mountPath: /cassandra_data
# These are converted to volume claims by the controller
# and mounted at the paths mentioned above.
# do not use these in production until ssd GCEPersistentDisk or other ssd pd
volumeClaimTemplates:
- metadata:
name: cassandra-data
annotations:
volume.alpha.kubernetes.io/storage-class: anything
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 1Gi
```
[Download example](cassandra-statefulset.yaml?raw=true)
<!-- END MUNGE: EXAMPLE cassandra-statefulset.yaml -->
Create the Cassandra StatefulSet as follows:
```console
$ kubectl create -f examples/storage/cassandra/cassandra-statefulset.yaml
```
## Step 3: Validate and Modify The Cassandra StatefulSet
Deploying this StatefulSet shows off two of the new features that StatefulSets provides.
1. The pod names are known
2. The pods deploy in incremental order
First validate that the StatefulSet has deployed, by running `kubectl` command below.
```console
$ kubectl get statefulset cassandra
```
The command should respond like:
```console
NAME DESIRED CURRENT AGE
cassandra 3 3 13s
```
Next watch the Cassandra pods deploy, one after another. The StatefulSet resource
deploys pods in a number fashion: 1, 2, 3, etc. If you execute the following
command before the pods deploy you are able to see the ordered creation.
```console
$ kubectl get pods -l="app=cassandra"
NAME READY STATUS RESTARTS AGE
cassandra-0 1/1 Running 0 1m
cassandra-1 0/1 ContainerCreating 0 8s
```
The above example shows two of the three pods in the Cassandra StatefulSet deployed.
Once all of the pods are deployed the same command will respond with the full
StatefulSet.
```console
$ kubectl get pods -l="app=cassandra"
NAME READY STATUS RESTARTS AGE
cassandra-0 1/1 Running 0 10m
cassandra-1 1/1 Running 0 9m
cassandra-2 1/1 Running 0 8m
```
Running the Cassandra utility `nodetool` will display the status of the ring.
```console
$ kubectl exec cassandra-0 -- nodetool status
Datacenter: DC1-K8Demo
======================
Status=Up/Down
|/ State=Normal/Leaving/Joining/Moving
-- Address Load Tokens Owns (effective) Host ID Rack
UN 10.4.2.4 65.26 KiB 32 63.7% a9d27f81-6783-461d-8583-87de2589133e Rack1-K8Demo
UN 10.4.0.4 102.04 KiB 32 66.7% 5559a58c-8b03-47ad-bc32-c621708dc2e4 Rack1-K8Demo
UN 10.4.1.4 83.06 KiB 32 69.6% 9dce943c-581d-4c0e-9543-f519969cc805 Rack1-K8Demo
```
You can also run `cqlsh` to describe the keyspaces in the cluster.
```console
$ kubectl exec cassandra-0 -- cqlsh -e 'desc keyspaces'
system_traces system_schema system_auth system system_distributed
```
In order to increase or decrease the size of the Cassandra StatefulSet, you must use
`kubectl edit`. You can find more information about the edit command in the [documentation](../../../docs/user-guide/kubectl/kubectl_edit.md).
Use the following command to edit the StatefulSet.
```console
$ kubectl edit statefulset cassandra
```
This will create an editor in your terminal. The line you are looking to change is
`replicas`. The example does on contain the entire contents of the terminal window, and
the last line of the example below is the replicas line that you want to change.
```console
# Please edit the object below. Lines beginning with a '#' will be ignored,
# and an empty file will abort the edit. If an error occurs while saving this file will be
# reopened with the relevant failures.
#
apiVersion: apps/v1beta1
kind: StatefulSet
metadata:
creationTimestamp: 2016-08-13T18:40:58Z
generation: 1
labels:
app: cassandra
name: cassandra
namespace: default
resourceVersion: "323"
selfLink: /apis/apps/v1beta1/namespaces/default/statefulsets/cassandra
uid: 7a219483-6185-11e6-a910-42010a8a0fc0
spec:
replicas: 3
```
Modify the manifest to the following, and save the manifest.
```console
spec:
replicas: 4
```
The StatefulSet will now contain four pods.
```console
$ kubectl get statefulset cassandra
```
The command should respond like:
```console
NAME DESIRED CURRENT AGE
cassandra 4 4 36m
```
For the Kubernetes 1.5 release, the beta StatefulSet resource does not have `kubectl scale`
functionality, like a Deployment, ReplicaSet, Replication Controller, or Job.
## Step 4: Delete Cassandra StatefulSet
Deleting and/or scaling a StatefulSet down will not delete the volumes associated with the StatefulSet. This is done to ensure safety first, your data is more valuable than an auto purge of all related StatefulSet resources. Deleting the Persistent Volume Claims may result in a deletion of the associated volumes, depending on the storage class and reclaim policy. You should never assume ability to access a volume after claim deletion.
Use the following commands to delete the StatefulSet.
```console
$ grace=$(kubectl get po cassandra-0 --template '{{.spec.terminationGracePeriodSeconds}}') \
&& kubectl delete statefulset -l app=cassandra \
&& echo "Sleeping $grace" \
&& sleep $grace \
&& kubectl delete pvc -l app=cassandra
```
## Step 5: Use a Replication Controller to create Cassandra node pods
A Kubernetes
_[Replication Controller](../../../docs/user-guide/replication-controller.md)_
is responsible for replicating sets of identical pods. Like a
Service, it has a selector query which identifies the members of its set.
Unlike a Service, it also has a desired number of replicas, and it will create
or delete Pods to ensure that the number of Pods matches up with its
desired state.
The Replication Controller, in conjunction with the Service we just defined,
will let us easily build a replicated, scalable Cassandra cluster.
Let's create a replication controller with two initial replicas.
<!-- BEGIN MUNGE: EXAMPLE cassandra-controller.yaml -->
```yaml
apiVersion: v1
kind: ReplicationController
metadata:
name: cassandra
# The labels will be applied automatically
# from the labels in the pod template, if not set
# labels:
# app: cassandra
spec:
replicas: 2
# The selector will be applied automatically
# from the labels in the pod template, if not set.
# selector:
# app: cassandra
template:
metadata:
labels:
app: cassandra
spec:
containers:
- command:
- /run.sh
resources:
limits:
cpu: 0.5
env:
- name: MAX_HEAP_SIZE
value: 512M
- name: HEAP_NEWSIZE
value: 100M
- name: CASSANDRA_SEED_PROVIDER
value: "io.k8s.cassandra.KubernetesSeedProvider"
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
image: gcr.io/google-samples/cassandra:v11
name: cassandra
ports:
- containerPort: 7000
name: intra-node
- containerPort: 7001
name: tls-intra-node
- containerPort: 7199
name: jmx
- containerPort: 9042
name: cql
volumeMounts:
- mountPath: /cassandra_data
name: data
volumes:
- name: data
emptyDir: {}
```
[Download example](cassandra-controller.yaml?raw=true)
<!-- END MUNGE: EXAMPLE cassandra-controller.yaml -->
There are a few things to note in this description.
The `selector` attribute contains the controller's selector query. It can be
explicitly specified, or applied automatically from the labels in the pod
template if not set, as is done here.
The pod template's label, `app:cassandra`, matches the Service selector
from Step 1. This is how pods created by this replication controller are picked up
by the Service."
The `replicas` attribute specifies the desired number of replicas, in this
case 2 initially. We'll scale up to more shortly.
Create the Replication Controller:
```console
$ kubectl create -f examples/storage/cassandra/cassandra-controller.yaml
```
You can list the new controller:
```console
$ kubectl get rc -o wide
NAME DESIRED CURRENT AGE CONTAINER(S) IMAGE(S) SELECTOR
cassandra 2 2 11s cassandra gcr.io/google-samples/cassandra:v11 app=cassandra
```
Now if you list the pods in your cluster, and filter to the label
`app=cassandra`, you should see two Cassandra pods. (The `wide` argument lets
you see which Kubernetes nodes the pods were scheduled onto.)
```console
$ kubectl get pods -l="app=cassandra" -o wide
NAME READY STATUS RESTARTS AGE NODE
cassandra-21qyy 1/1 Running 0 1m kubernetes-minion-b286
cassandra-q6sz7 1/1 Running 0 1m kubernetes-minion-9ye5
```
Because these pods have the label `app=cassandra`, they map to the service we
defined in Step 1.
You can check that the Pods are visible to the Service using the following service endpoints query:
```console
$ kubectl get endpoints cassandra -o yaml
apiVersion: v1
kind: Endpoints
metadata:
creationTimestamp: 2015-06-21T22:34:12Z
labels:
app: cassandra
name: cassandra
namespace: default
resourceVersion: "944373"
selfLink: /api/v1/namespaces/default/endpoints/cassandra
uid: a3d6c25f-1865-11e5-a34e-42010af01bcc
subsets:
- addresses:
- ip: 10.244.3.15
targetRef:
kind: Pod
name: cassandra
namespace: default
resourceVersion: "944372"
uid: 9ef9895d-1865-11e5-a34e-42010af01bcc
ports:
- port: 9042
protocol: TCP
```
To show that the `SeedProvider` logic is working as intended, you can use the
`nodetool` command to examine the status of the Cassandra cluster. To do this,
use the `kubectl exec` command, which lets you run `nodetool` in one of your
Cassandra pods. Again, substitute `cassandra-xxxxx` with the actual name of one
of your pods.
```console
$ kubectl exec -ti cassandra-xxxxx -- nodetool status
Datacenter: datacenter1
=======================
Status=Up/Down
|/ State=Normal/Leaving/Joining/Moving
-- Address Load Tokens Owns (effective) Host ID Rack
UN 10.244.0.5 74.09 KB 256 100.0% 86feda0f-f070-4a5b-bda1-2eeb0ad08b77 rack1
UN 10.244.3.3 51.28 KB 256 100.0% dafe3154-1d67-42e1-ac1d-78e7e80dce2b rack1
```
## Step 6: Scale up the Cassandra cluster
Now let's scale our Cassandra cluster to 4 pods. We do this by telling the
Replication Controller that we now want 4 replicas.
```sh
$ kubectl scale rc cassandra --replicas=4
```
You can see the new pods listed:
```console
$ kubectl get pods -l="app=cassandra" -o wide
NAME READY STATUS RESTARTS AGE NODE
cassandra-21qyy 1/1 Running 0 6m kubernetes-minion-b286
cassandra-81m2l 1/1 Running 0 47s kubernetes-minion-b286
cassandra-8qoyp 1/1 Running 0 47s kubernetes-minion-9ye5
cassandra-q6sz7 1/1 Running 0 6m kubernetes-minion-9ye5
```
In a few moments, you can examine the Cassandra cluster status again, and see
that the new pods have been detected by the custom `SeedProvider`:
```console
$ kubectl exec -ti cassandra-xxxxx -- nodetool status
Datacenter: datacenter1
=======================
Status=Up/Down
|/ State=Normal/Leaving/Joining/Moving
-- Address Load Tokens Owns (effective) Host ID Rack
UN 10.244.0.6 51.67 KB 256 48.9% d07b23a5-56a1-4b0b-952d-68ab95869163 rack1
UN 10.244.1.5 84.71 KB 256 50.7% e060df1f-faa2-470c-923d-ca049b0f3f38 rack1
UN 10.244.1.6 84.71 KB 256 47.0% 83ca1580-4f3c-4ec5-9b38-75036b7a297f rack1
UN 10.244.0.5 68.2 KB 256 53.4% 72ca27e2-c72c-402a-9313-1e4b61c2f839 rack1
```
## Step 7: Delete the Replication Controller
Before you start Step 5, __delete the replication controller__ you created above:
```sh
$ kubectl delete rc cassandra
```
## Step 8: Use a DaemonSet instead of a Replication Controller
In Kubernetes, a [_Daemon Set_](../../../docs/admin/daemons.md) can distribute pods
onto Kubernetes nodes, one-to-one. Like a _ReplicationController_, it has a
selector query which identifies the members of its set. Unlike a
_ReplicationController_, it has a node selector to limit which nodes are
scheduled with the templated pods, and replicates not based on a set target
number of pods, but rather assigns a single pod to each targeted node.
An example use case: when deploying to the cloud, the expectation is that
instances are ephemeral and might die at any time. Cassandra is built to
replicate data across the cluster to facilitate data redundancy, so that in the
case that an instance dies, the data stored on the instance does not, and the
cluster can react by re-replicating the data to other running nodes.
`DaemonSet` is designed to place a single pod on each node in the Kubernetes
cluster. That will give us data redundancy. Let's create a
DaemonSet to start our storage cluster:
<!-- BEGIN MUNGE: EXAMPLE cassandra-daemonset.yaml -->
```yaml
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
labels:
name: cassandra
name: cassandra
spec:
template:
metadata:
labels:
app: cassandra
spec:
# Filter to specific nodes:
# nodeSelector:
# app: cassandra
containers:
- command:
- /run.sh
env:
- name: MAX_HEAP_SIZE
value: 512M
- name: HEAP_NEWSIZE
value: 100M
- name: CASSANDRA_SEED_PROVIDER
value: "io.k8s.cassandra.KubernetesSeedProvider"
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
image: gcr.io/google-samples/cassandra:v11
name: cassandra
ports:
- containerPort: 7000
name: intra-node
- containerPort: 7001
name: tls-intra-node
- containerPort: 7199
name: jmx
- containerPort: 9042
name: cql
# If you need it it is going away in C* 4.0
#- containerPort: 9160
# name: thrift
resources:
requests:
cpu: 0.5
volumeMounts:
- mountPath: /cassandra_data
name: data
volumes:
- name: data
emptyDir: {}
```
[Download example](cassandra-daemonset.yaml?raw=true)
<!-- END MUNGE: EXAMPLE cassandra-daemonset.yaml -->
Most of this DaemonSet definition is identical to the ReplicationController
definition above; it simply gives the daemon set a recipe to use when it creates
new Cassandra pods, and targets all Cassandra nodes in the cluster.
Differentiating aspects are the `nodeSelector` attribute, which allows the
DaemonSet to target a specific subset of nodes (you can label nodes just like
other resources), and the lack of a `replicas` attribute due to the 1-to-1 node-
pod relationship.
Create this DaemonSet:
```console
$ kubectl create -f examples/storage/cassandra/cassandra-daemonset.yaml
```
You may need to disable config file validation, like so:
```console
$ kubectl create -f examples/storage/cassandra/cassandra-daemonset.yaml --validate=false
```
You can see the DaemonSet running:
```console
$ kubectl get daemonset
NAME DESIRED CURRENT NODE-SELECTOR
cassandra 3 3 <none>
```
Now, if you list the pods in your cluster, and filter to the label
`app=cassandra`, you should see one (and only one) new cassandra pod for each
node in your network.
```console
$ kubectl get pods -l="app=cassandra" -o wide
NAME READY STATUS RESTARTS AGE NODE
cassandra-ico4r 1/1 Running 0 4s kubernetes-minion-rpo1
cassandra-kitfh 1/1 Running 0 1s kubernetes-minion-9ye5
cassandra-tzw89 1/1 Running 0 2s kubernetes-minion-b286
```
To prove that this all worked as intended, you can again use the `nodetool`
command to examine the status of the cluster. To do this, use the `kubectl
exec` command to run `nodetool` in one of your newly-launched cassandra pods.
```console
$ kubectl exec -ti cassandra-xxxxx -- nodetool status
Datacenter: datacenter1
=======================
Status=Up/Down
|/ State=Normal/Leaving/Joining/Moving
-- Address Load Tokens Owns (effective) Host ID Rack
UN 10.244.0.5 74.09 KB 256 100.0% 86feda0f-f070-4a5b-bda1-2eeb0ad08b77 rack1
UN 10.244.4.2 32.45 KB 256 100.0% 0b1be71a-6ffb-4895-ac3e-b9791299c141 rack1
UN 10.244.3.3 51.28 KB 256 100.0% dafe3154-1d67-42e1-ac1d-78e7e80dce2b rack1
```
**Note**: This example had you delete the cassandra Replication Controller before
you created the DaemonSet. This is because – to keep this example simple – the
RC and the DaemonSet are using the same `app=cassandra` label (so that their pods map to the
service we created, and so that the SeedProvider can identify them).
If we didn't delete the RC first, the two resources would conflict with
respect to how many pods they wanted to have running. If we wanted, we could support running
both together by using additional labels and selectors.
## Step 9: Resource Cleanup
When you are ready to take down your resources, do the following:
```console
$ kubectl delete service -l app=cassandra
$ kubectl delete daemonset cassandra
```
### Custom Seed Provider
A custom [`SeedProvider`](https://svn.apache.org/repos/asf/cassandra/trunk/src/java/org/apache/cassandra/locator/SeedProvider.java)
is included for running Cassandra on top of Kubernetes. Only when you deploy Cassandra
via a replication control or a deamonset, you will need to use the custom seed provider.
In Cassandra, a `SeedProvider` bootstraps the gossip protocol that Cassandra uses to find other
Cassandra nodes. Seed addresses are hosts deemed as contact points. Cassandra
instances use the seed list to find each other and learn the topology of the
ring. The [`KubernetesSeedProvider`](java/src/main/java/io/k8s/cassandra/KubernetesSeedProvider.java)
discovers Cassandra seeds IP addresses via the Kubernetes API, those Cassandra
instances are defined within the Cassandra Service.
Refer to the custom seed provider [README](java/README.md) for further
`KubernetesSeedProvider` configurations. For this example you should not need
to customize the Seed Provider configurations.
See the [image](image/) directory of this example for specifics on
how the container docker image was built and what it contains.
You may also note that we are setting some Cassandra parameters (`MAX_HEAP_SIZE`
and `HEAP_NEWSIZE`), and adding information about the
[namespace](../../../docs/user-guide/namespaces.md).
We also tell Kubernetes that the container exposes
both the `CQL` and `Thrift` API ports. Finally, we tell the cluster
manager that we need 0.1 cpu (0.1 core).
<!-- BEGIN MUNGE: GENERATED_ANALYTICS -->
[![Analytics](https://kubernetes-site.appspot.com/UA-36037335-10/GitHub/examples/storage/cassandra/README.md?pixel)]()
<!-- END MUNGE: GENERATED_ANALYTICS -->

57
vendor/k8s.io/kubernetes/examples/storage/cassandra/cassandra-controller.yaml generated vendored Normal file
View file

@ -0,0 +1,57 @@
apiVersion: v1
kind: ReplicationController
metadata:
name: cassandra
# The labels will be applied automatically
# from the labels in the pod template, if not set
# labels:
# app: cassandra
spec:
replicas: 2
# The selector will be applied automatically
# from the labels in the pod template, if not set.
# selector:
# app: cassandra
template:
metadata:
labels:
app: cassandra
spec:
containers:
- command:
- /run.sh
resources:
limits:
cpu: 0.5
env:
- name: MAX_HEAP_SIZE
value: 512M
- name: HEAP_NEWSIZE
value: 100M
- name: CASSANDRA_SEED_PROVIDER
value: "io.k8s.cassandra.KubernetesSeedProvider"
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
image: gcr.io/google-samples/cassandra:v11
name: cassandra
ports:
- containerPort: 7000
name: intra-node
- containerPort: 7001
name: tls-intra-node
- containerPort: 7199
name: jmx
- containerPort: 9042
name: cql
volumeMounts:
- mountPath: /cassandra_data
name: data
volumes:
- name: data
emptyDir: {}

56
vendor/k8s.io/kubernetes/examples/storage/cassandra/cassandra-daemonset.yaml generated vendored Normal file
View file

@ -0,0 +1,56 @@
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
labels:
name: cassandra
name: cassandra
spec:
template:
metadata:
labels:
app: cassandra
spec:
# Filter to specific nodes:
# nodeSelector:
# app: cassandra
containers:
- command:
- /run.sh
env:
- name: MAX_HEAP_SIZE
value: 512M
- name: HEAP_NEWSIZE
value: 100M
- name: CASSANDRA_SEED_PROVIDER
value: "io.k8s.cassandra.KubernetesSeedProvider"
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
image: gcr.io/google-samples/cassandra:v11
name: cassandra
ports:
- containerPort: 7000
name: intra-node
- containerPort: 7001
name: tls-intra-node
- containerPort: 7199
name: jmx
- containerPort: 9042
name: cql
# If you need it it is going away in C* 4.0
#- containerPort: 9160
# name: thrift
resources:
requests:
cpu: 0.5
volumeMounts:
- mountPath: /cassandra_data
name: data
volumes:
- name: data
emptyDir: {}

12
vendor/k8s.io/kubernetes/examples/storage/cassandra/cassandra-service.yaml generated vendored Normal file
View file

@ -0,0 +1,12 @@
apiVersion: v1
kind: Service
metadata:
labels:
app: cassandra
name: cassandra
spec:
clusterIP: None
ports:
- port: 9042
selector:
app: cassandra

82
vendor/k8s.io/kubernetes/examples/storage/cassandra/cassandra-statefulset.yaml generated vendored Normal file
View file

@ -0,0 +1,82 @@
apiVersion: "apps/v1beta1"
kind: StatefulSet
metadata:
name: cassandra
spec:
serviceName: cassandra
replicas: 3
template:
metadata:
labels:
app: cassandra
spec:
containers:
- name: cassandra
image: gcr.io/google-samples/cassandra:v11
imagePullPolicy: Always
ports:
- containerPort: 7000
name: intra-node
- containerPort: 7001
name: tls-intra-node
- containerPort: 7199
name: jmx
- containerPort: 9042
name: cql
resources:
limits:
cpu: "500m"
memory: 1Gi
requests:
cpu: "500m"
memory: 1Gi
securityContext:
capabilities:
add:
- IPC_LOCK
env:
- name: MAX_HEAP_SIZE
value: 512M
- name: HEAP_NEWSIZE
value: 100M
- name: CASSANDRA_SEEDS
value: "cassandra-0.cassandra.default.svc.cluster.local"
- name: CASSANDRA_CLUSTER_NAME
value: "K8Demo"
- name: CASSANDRA_DC
value: "DC1-K8Demo"
- name: CASSANDRA_RACK
value: "Rack1-K8Demo"
- name: CASSANDRA_AUTO_BOOTSTRAP
value: "false"
- name: POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
readinessProbe:
exec:
command:
- /bin/bash
- -c
- /ready-probe.sh
initialDelaySeconds: 15
timeoutSeconds: 5
# These volume mounts are persistent. They are like inline claims,
# but not exactly because the names need to match exactly one of
# the stateful pod volumes.
volumeMounts:
- name: cassandra-data
mountPath: /cassandra_data
# These are converted to volume claims by the controller
# and mounted at the paths mentioned above.
# do not use these in production until ssd GCEPersistentDisk or other ssd pd
volumeClaimTemplates:
- metadata:
name: cassandra-data
annotations:
volume.alpha.kubernetes.io/storage-class: anything
spec:
accessModes: [ "ReadWriteOnce" ]
resources:
requests:
storage: 1Gi

78
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/Dockerfile generated vendored Normal file
View file

@ -0,0 +1,78 @@
# 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 google/debian:jessie
ADD files /
ENV DI_VERSION="1.1.1" DI_SHA="dec8167091671df0dd3748a8938102479db5fffc"
RUN mv /java.list /etc/apt/sources.list.d/java.list \
&& apt-get update \
&& apt-get -qq -y --force-yes install --no-install-recommends procps openjdk-8-jre-headless libjemalloc1 curl localepurge \
&& curl -L https://github.com/Yelp/dumb-init/releases/download/v${DI_VERSION}/dumb-init_${DI_VERSION}_amd64 > /sbin/dumb-init \
&& echo "$DI_SHA /sbin/dumb-init" | sha1sum -c - \
&& mv /cassandra.list /etc/apt/sources.list.d/cassandra.list \
&& gpg --keyserver pgp.mit.edu --recv-keys F758CE318D77295D \
&& gpg --export --armor F758CE318D77295D | apt-key add - \
&& gpg --keyserver pgp.mit.edu --recv-keys 2B5C1B00 \
&& gpg --export --armor 2B5C1B00 | apt-key add - \
&& gpg --keyserver pgp.mit.edu --recv-keys 0353B12C \
&& gpg --export --armor 0353B12C | apt-key add - \
&& gpg --keyserver pool.sks-keyservers.net --recv-keys A278B781FE4B2BDA \
&& gpg --export --armor A278B781FE4B2BDA | apt-key add - \
&& apt-get update \
&& apt-get -qq -y --force-yes install --no-install-recommends curl cassandra localepurge \
&& chmod a+rx /run.sh /sbin/dumb-init /ready-probe.sh \
&& mkdir -p /cassandra_data/data \
&& mv /logback.xml /cassandra.yaml /jvm.options /etc/cassandra/ \
# Not able to run as cassandra until https://github.com/kubernetes/kubernetes/issues/2630 is resolved
# && chown -R cassandra: /etc/cassandra /cassandra_data /run.sh /kubernetes-cassandra.jar \
# && chmod o+w -R /etc/cassandra /cassandra_data \
&& apt-get -y purge curl localepurge \
&& apt-get clean \
&& rm -rf \
doc \
man \
info \
locale \
/var/lib/apt/lists/* \
/var/log/* \
/var/cache/debconf/* \
common-licenses \
~/.bashrc \
/etc/systemd \
/lib/lsb \
/lib/udev \
/usr/share/doc/ \
/usr/share/doc-base/ \
/usr/share/man/ \
/tmp/*
VOLUME ["/cassandra_data"]
# 7000: intra-node communication
# 7001: TLS intra-node communication
# 7199: JMX
# 9042: CQL
# 9160: thrift service not included cause it is going away
EXPOSE 7000 7001 7199 9042
# Not able to do this until https://github.com/kubernetes/kubernetes/issues/2630 is resolved
# if you are using attached storage
# USER cassandra
CMD ["/sbin/dumb-init", "/bin/bash", "/run.sh"]

34
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/Makefile generated vendored Normal file
View file

@ -0,0 +1,34 @@
# 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.
# build the cassandra image.
VERSION=v11
PROJECT_ID=google_samples
PROJECT=gcr.io/${PROJECT_ID}
all: build
kubernetes-cassandra.jar: ../java/* ../java/src/main/java/io/k8s/cassandra/*.java
cd ../java && mvn clean && mvn package
mv ../java/target/kubernetes-cassandra*.jar files/kubernetes-cassandra.jar
cd ../java && mvn clean
build: kubernetes-cassandra.jar
docker build --pull -t ${PROJECT}/cassandra:${VERSION} .
push: build
gcloud docker -- push ${PROJECT}/cassandra:${VERSION}
.PHONY: all build push

2
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/files/cassandra.list generated vendored Normal file
View file

@ -0,0 +1,2 @@
deb http://www.apache.org/dist/cassandra/debian 39x main
deb-src http://www.apache.org/dist/cassandra/debian 39x main

990
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/files/cassandra.yaml generated vendored Normal file
View file

@ -0,0 +1,990 @@
# Cassandra storage config YAML
# NOTE:
# See http://wiki.apache.org/cassandra/StorageConfiguration for
# full explanations of configuration directives
# /NOTE
# The name of the cluster. This is mainly used to prevent machines in
# one logical cluster from joining another.
cluster_name: 'Test Cluster'
# This defines the number of tokens randomly assigned to this node on the ring
# The more tokens, relative to other nodes, the larger the proportion of data
# that this node will store. You probably want all nodes to have the same number
# of tokens assuming they have equal hardware capability.
#
# If you leave this unspecified, Cassandra will use the default of 1 token for legacy compatibility,
# and will use the initial_token as described below.
#
# Specifying initial_token will override this setting on the node's initial start,
# on subsequent starts, this setting will apply even if initial token is set.
#
# If you already have a cluster with 1 token per node, and wish to migrate to
# multiple tokens per node, see http://wiki.apache.org/cassandra/Operations
num_tokens: 256
# Triggers automatic allocation of num_tokens tokens for this node. The allocation
# algorithm attempts to choose tokens in a way that optimizes replicated load over
# the nodes in the datacenter for the replication strategy used by the specified
# keyspace.
#
# The load assigned to each node will be close to proportional to its number of
# vnodes.
#
# Only supported with the Murmur3Partitioner.
# allocate_tokens_for_keyspace: KEYSPACE
# initial_token allows you to specify tokens manually. While you can use # it with
# vnodes (num_tokens > 1, above) -- in which case you should provide a
# comma-separated list -- it's primarily used when adding nodes # to legacy clusters
# that do not have vnodes enabled.
# initial_token:
# See http://wiki.apache.org/cassandra/HintedHandoff
# May either be "true" or "false" to enable globally
hinted_handoff_enabled: true
# When hinted_handoff_enabled is true, a black list of data centers that will not
# perform hinted handoff
# hinted_handoff_disabled_datacenters:
# - DC1
# - DC2
# this defines the maximum amount of time a dead host will have hints
# generated. After it has been dead this long, new hints for it will not be
# created until it has been seen alive and gone down again.
max_hint_window_in_ms: 10800000 # 3 hours
# Maximum throttle in KBs per second, per delivery thread. This will be
# reduced proportionally to the number of nodes in the cluster. (If there
# are two nodes in the cluster, each delivery thread will use the maximum
# rate; if there are three, each will throttle to half of the maximum,
# since we expect two nodes to be delivering hints simultaneously.)
hinted_handoff_throttle_in_kb: 1024
# Number of threads with which to deliver hints;
# Consider increasing this number when you have multi-dc deployments, since
# cross-dc handoff tends to be slower
max_hints_delivery_threads: 2
# Directory where Cassandra should store hints.
# If not set, the default directory is $CASSANDRA_HOME/data/hints.
# hints_directory: /var/lib/cassandra/hints
# How often hints should be flushed from the internal buffers to disk.
# Will *not* trigger fsync.
hints_flush_period_in_ms: 10000
# Maximum size for a single hints file, in megabytes.
max_hints_file_size_in_mb: 128
# Compression to apply to the hint files. If omitted, hints files
# will be written uncompressed. LZ4, Snappy, and Deflate compressors
# are supported.
#hints_compression:
# - class_name: LZ4Compressor
# parameters:
# -
# Maximum throttle in KBs per second, total. This will be
# reduced proportionally to the number of nodes in the cluster.
batchlog_replay_throttle_in_kb: 1024
# Authentication backend, implementing IAuthenticator; used to identify users
# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthenticator,
# PasswordAuthenticator}.
#
# - AllowAllAuthenticator performs no checks - set it to disable authentication.
# - PasswordAuthenticator relies on username/password pairs to authenticate
# users. It keeps usernames and hashed passwords in system_auth.credentials table.
# Please increase system_auth keyspace replication factor if you use this authenticator.
# If using PasswordAuthenticator, CassandraRoleManager must also be used (see below)
authenticator: AllowAllAuthenticator
# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions
# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthorizer,
# CassandraAuthorizer}.
#
# - AllowAllAuthorizer allows any action to any user - set it to disable authorization.
# - CassandraAuthorizer stores permissions in system_auth.permissions table. Please
# increase system_auth keyspace replication factor if you use this authorizer.
authorizer: AllowAllAuthorizer
# Part of the Authentication & Authorization backend, implementing IRoleManager; used
# to maintain grants and memberships between roles.
# Out of the box, Cassandra provides org.apache.cassandra.auth.CassandraRoleManager,
# which stores role information in the system_auth keyspace. Most functions of the
# IRoleManager require an authenticated login, so unless the configured IAuthenticator
# actually implements authentication, most of this functionality will be unavailable.
#
# - CassandraRoleManager stores role data in the system_auth keyspace. Please
# increase system_auth keyspace replication factor if you use this role manager.
role_manager: CassandraRoleManager
# Validity period for roles cache (fetching granted roles can be an expensive
# operation depending on the role manager, CassandraRoleManager is one example)
# Granted roles are cached for authenticated sessions in AuthenticatedUser and
# after the period specified here, become eligible for (async) reload.
# Defaults to 2000, set to 0 to disable caching entirely.
# Will be disabled automatically for AllowAllAuthenticator.
roles_validity_in_ms: 2000
# Refresh interval for roles cache (if enabled).
# After this interval, cache entries become eligible for refresh. Upon next
# access, an async reload is scheduled and the old value returned until it
# completes. If roles_validity_in_ms is non-zero, then this must be
# also.
# Defaults to the same value as roles_validity_in_ms.
# roles_update_interval_in_ms: 2000
# Validity period for permissions cache (fetching permissions can be an
# expensive operation depending on the authorizer, CassandraAuthorizer is
# one example). Defaults to 2000, set to 0 to disable.
# Will be disabled automatically for AllowAllAuthorizer.
permissions_validity_in_ms: 2000
# Refresh interval for permissions cache (if enabled).
# After this interval, cache entries become eligible for refresh. Upon next
# access, an async reload is scheduled and the old value returned until it
# completes. If permissions_validity_in_ms is non-zero, then this must be
# also.
# Defaults to the same value as permissions_validity_in_ms.
# permissions_update_interval_in_ms: 2000
# Validity period for credentials cache. This cache is tightly coupled to
# the provided PasswordAuthenticator implementation of IAuthenticator. If
# another IAuthenticator implementation is configured, this cache will not
# be automatically used and so the following settings will have no effect.
# Please note, credentials are cached in their encrypted form, so while
# activating this cache may reduce the number of queries made to the
# underlying table, it may not bring a significant reduction in the
# latency of individual authentication attempts.
# Defaults to 2000, set to 0 to disable credentials caching.
credentials_validity_in_ms: 2000
# Refresh interval for credentials cache (if enabled).
# After this interval, cache entries become eligible for refresh. Upon next
# access, an async reload is scheduled and the old value returned until it
# completes. If credentials_validity_in_ms is non-zero, then this must be
# also.
# Defaults to the same value as credentials_validity_in_ms.
# credentials_update_interval_in_ms: 2000
# The partitioner is responsible for distributing groups of rows (by
# partition key) across nodes in the cluster. You should leave this
# alone for new clusters. The partitioner can NOT be changed without
# reloading all data, so when upgrading you should set this to the
# same partitioner you were already using.
#
# Besides Murmur3Partitioner, partitioners included for backwards
# compatibility include RandomPartitioner, ByteOrderedPartitioner, and
# OrderPreservingPartitioner.
#
partitioner: org.apache.cassandra.dht.Murmur3Partitioner
# Directories where Cassandra should store data on disk. Cassandra
# will spread data evenly across them, subject to the granularity of
# the configured compaction strategy.
# If not set, the default directory is $CASSANDRA_HOME/data/data.
data_file_directories:
- /cassandra_data/data
# commit log. when running on magnetic HDD, this should be a
# separate spindle than the data directories.
# If not set, the default directory is $CASSANDRA_HOME/data/commitlog.
commitlog_directory: /cassandra_data/commitlog
# policy for data disk failures:
# die: shut down gossip and client transports and kill the JVM for any fs errors or
# single-sstable errors, so the node can be replaced.
# stop_paranoid: shut down gossip and client transports even for single-sstable errors,
# kill the JVM for errors during startup.
# stop: shut down gossip and client transports, leaving the node effectively dead, but
# can still be inspected via JMX, kill the JVM for errors during startup.
# best_effort: stop using the failed disk and respond to requests based on
# remaining available sstables. This means you WILL see obsolete
# data at CL.ONE!
# ignore: ignore fatal errors and let requests fail, as in pre-1.2 Cassandra
disk_failure_policy: stop
# policy for commit disk failures:
# die: shut down gossip and Thrift and kill the JVM, so the node can be replaced.
# stop: shut down gossip and Thrift, leaving the node effectively dead, but
# can still be inspected via JMX.
# stop_commit: shutdown the commit log, letting writes collect but
# continuing to service reads, as in pre-2.0.5 Cassandra
# ignore: ignore fatal errors and let the batches fail
commit_failure_policy: stop
# Maximum size of the key cache in memory.
#
# Each key cache hit saves 1 seek and each row cache hit saves 2 seeks at the
# minimum, sometimes more. The key cache is fairly tiny for the amount of
# time it saves, so it's worthwhile to use it at large numbers.
# The row cache saves even more time, but must contain the entire row,
# so it is extremely space-intensive. It's best to only use the
# row cache if you have hot rows or static rows.
#
# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup.
#
# Default value is empty to make it "auto" (min(5% of Heap (in MB), 100MB)). Set to 0 to disable key cache.
key_cache_size_in_mb:
# Duration in seconds after which Cassandra should
# save the key cache. Caches are saved to saved_caches_directory as
# specified in this configuration file.
#
# Saved caches greatly improve cold-start speeds, and is relatively cheap in
# terms of I/O for the key cache. Row cache saving is much more expensive and
# has limited use.
#
# Default is 14400 or 4 hours.
key_cache_save_period: 14400
# Number of keys from the key cache to save
# Disabled by default, meaning all keys are going to be saved
# key_cache_keys_to_save: 100
# Row cache implementation class name.
# Available implementations:
# org.apache.cassandra.cache.OHCProvider Fully off-heap row cache implementation (default).
# org.apache.cassandra.cache.SerializingCacheProvider This is the row cache implementation availabile
# in previous releases of Cassandra.
# row_cache_class_name: org.apache.cassandra.cache.OHCProvider
# Maximum size of the row cache in memory.
# Please note that OHC cache implementation requires some additional off-heap memory to manage
# the map structures and some in-flight memory during operations before/after cache entries can be
# accounted against the cache capacity. This overhead is usually small compared to the whole capacity.
# Do not specify more memory that the system can afford in the worst usual situation and leave some
# headroom for OS block level cache. Do never allow your system to swap.
#
# Default value is 0, to disable row caching.
row_cache_size_in_mb: 0
# Duration in seconds after which Cassandra should save the row cache.
# Caches are saved to saved_caches_directory as specified in this configuration file.
#
# Saved caches greatly improve cold-start speeds, and is relatively cheap in
# terms of I/O for the key cache. Row cache saving is much more expensive and
# has limited use.
#
# Default is 0 to disable saving the row cache.
row_cache_save_period: 0
# Number of keys from the row cache to save.
# Specify 0 (which is the default), meaning all keys are going to be saved
# row_cache_keys_to_save: 100
# Maximum size of the counter cache in memory.
#
# Counter cache helps to reduce counter locks' contention for hot counter cells.
# In case of RF = 1 a counter cache hit will cause Cassandra to skip the read before
# write entirely. With RF > 1 a counter cache hit will still help to reduce the duration
# of the lock hold, helping with hot counter cell updates, but will not allow skipping
# the read entirely. Only the local (clock, count) tuple of a counter cell is kept
# in memory, not the whole counter, so it's relatively cheap.
#
# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup.
#
# Default value is empty to make it "auto" (min(2.5% of Heap (in MB), 50MB)). Set to 0 to disable counter cache.
# NOTE: if you perform counter deletes and rely on low gcgs, you should disable the counter cache.
counter_cache_size_in_mb:
# Duration in seconds after which Cassandra should
# save the counter cache (keys only). Caches are saved to saved_caches_directory as
# specified in this configuration file.
#
# Default is 7200 or 2 hours.
counter_cache_save_period: 7200
# Number of keys from the counter cache to save
# Disabled by default, meaning all keys are going to be saved
# counter_cache_keys_to_save: 100
# saved caches
# If not set, the default directory is $CASSANDRA_HOME/data/saved_caches.
saved_caches_directory: /cassandra_data/saved_caches
# commitlog_sync may be either "periodic" or "batch."
#
# When in batch mode, Cassandra won't ack writes until the commit log
# has been fsynced to disk. It will wait
# commitlog_sync_batch_window_in_ms milliseconds between fsyncs.
# This window should be kept short because the writer threads will
# be unable to do extra work while waiting. (You may need to increase
# concurrent_writes for the same reason.)
#
# commitlog_sync: batch
# commitlog_sync_batch_window_in_ms: 2
#
# the other option is "periodic" where writes may be acked immediately
# and the CommitLog is simply synced every commitlog_sync_period_in_ms
# milliseconds.
commitlog_sync: periodic
commitlog_sync_period_in_ms: 10000
# The size of the individual commitlog file segments. A commitlog
# segment may be archived, deleted, or recycled once all the data
# in it (potentially from each columnfamily in the system) has been
# flushed to sstables.
#
# The default size is 32, which is almost always fine, but if you are
# archiving commitlog segments (see commitlog_archiving.properties),
# then you probably want a finer granularity of archiving; 8 or 16 MB
# is reasonable.
# Max mutation size is also configurable via max_mutation_size_in_kb setting in
# cassandra.yaml. The default is half the size commitlog_segment_size_in_mb * 1024.
#
# NOTE: If max_mutation_size_in_kb is set explicitly then commitlog_segment_size_in_mb must
# be set to at least twice the size of max_mutation_size_in_kb / 1024
#
commitlog_segment_size_in_mb: 32
# Compression to apply to the commit log. If omitted, the commit log
# will be written uncompressed. LZ4, Snappy, and Deflate compressors
# are supported.
#commitlog_compression:
# - class_name: LZ4Compressor
# parameters:
# -
# any class that implements the SeedProvider interface and has a
# constructor that takes a Map<String, String> of parameters will do.
seed_provider:
# Addresses of hosts that are deemed contact points.
# Cassandra nodes use this list of hosts to find each other and learn
# the topology of the ring. You must change this if you are running
# multiple nodes!
#- class_name: io.k8s.cassandra.KubernetesSeedProvider
- class_name: SEED_PROVIDER
parameters:
# seeds is actually a comma-delimited list of addresses.
# Ex: "<ip1>,<ip2>,<ip3>"
- seeds: "127.0.0.1"
# For workloads with more data than can fit in memory, Cassandra's
# bottleneck will be reads that need to fetch data from
# disk. "concurrent_reads" should be set to (16 * number_of_drives) in
# order to allow the operations to enqueue low enough in the stack
# that the OS and drives can reorder them. Same applies to
# "concurrent_counter_writes", since counter writes read the current
# values before incrementing and writing them back.
#
# On the other hand, since writes are almost never IO bound, the ideal
# number of "concurrent_writes" is dependent on the number of cores in
# your system; (8 * number_of_cores) is a good rule of thumb.
concurrent_reads: 32
concurrent_writes: 32
concurrent_counter_writes: 32
# For materialized view writes, as there is a read involved, so this should
# be limited by the less of concurrent reads or concurrent writes.
concurrent_materialized_view_writes: 32
# Maximum memory to use for pooling sstable buffers. Defaults to the smaller
# of 1/4 of heap or 512MB. This pool is allocated off-heap, so is in addition
# to the memory allocated for heap. Memory is only allocated as needed.
# file_cache_size_in_mb: 512
# Flag indicating whether to allocate on or off heap when the sstable buffer
# pool is exhausted, that is when it has exceeded the maximum memory
# file_cache_size_in_mb, beyond which it will not cache buffers but allocate on request.
# buffer_pool_use_heap_if_exhausted: true
# The strategy for optimizing disk read
# Possible values are:
# ssd (for solid state disks, the default)
# spinning (for spinning disks)
# disk_optimization_strategy: ssd
# Total permitted memory to use for memtables. Cassandra will stop
# accepting writes when the limit is exceeded until a flush completes,
# and will trigger a flush based on memtable_cleanup_threshold
# If omitted, Cassandra will set both to 1/4 the size of the heap.
# memtable_heap_space_in_mb: 2048
# memtable_offheap_space_in_mb: 2048
# Ratio of occupied non-flushing memtable size to total permitted size
# that will trigger a flush of the largest memtable. Larger mct will
# mean larger flushes and hence less compaction, but also less concurrent
# flush activity which can make it difficult to keep your disks fed
# under heavy write load.
#
# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1)
# memtable_cleanup_threshold: 0.11
# Specify the way Cassandra allocates and manages memtable memory.
# Options are:
# heap_buffers: on heap nio buffers
# offheap_buffers: off heap (direct) nio buffers
# offheap_objects: off heap objects
memtable_allocation_type: heap_buffers
# Total space to use for commit logs on disk.
#
# If space gets above this value, Cassandra will flush every dirty CF
# in the oldest segment and remove it. So a small total commitlog space
# will tend to cause more flush activity on less-active columnfamilies.
#
# The default value is the smaller of 8192, and 1/4 of the total space
# of the commitlog volume.
#
# commitlog_total_space_in_mb: 8192
# This sets the amount of memtable flush writer threads. These will
# be blocked by disk io, and each one will hold a memtable in memory
# while blocked.
#
# memtable_flush_writers defaults to one per data_file_directory.
#
# If your data directories are backed by SSD, you can increase this, but
# avoid having memtable_flush_writers * data_file_directories > number of cores
#memtable_flush_writers: 1
# A fixed memory pool size in MB for for SSTable index summaries. If left
# empty, this will default to 5% of the heap size. If the memory usage of
# all index summaries exceeds this limit, SSTables with low read rates will
# shrink their index summaries in order to meet this limit. However, this
# is a best-effort process. In extreme conditions Cassandra may need to use
# more than this amount of memory.
index_summary_capacity_in_mb:
# How frequently index summaries should be resampled. This is done
# periodically to redistribute memory from the fixed-size pool to sstables
# proportional their recent read rates. Setting to -1 will disable this
# process, leaving existing index summaries at their current sampling level.
index_summary_resize_interval_in_minutes: 60
# Whether to, when doing sequential writing, fsync() at intervals in
# order to force the operating system to flush the dirty
# buffers. Enable this to avoid sudden dirty buffer flushing from
# impacting read latencies. Almost always a good idea on SSDs; not
# necessarily on platters.
trickle_fsync: false
trickle_fsync_interval_in_kb: 10240
# TCP port, for commands and data
# For security reasons, you should not expose this port to the internet. Firewall it if needed.
storage_port: 7000
# SSL port, for encrypted communication. Unused unless enabled in
# encryption_options
# For security reasons, you should not expose this port to the internet. Firewall it if needed.
ssl_storage_port: 7001
# Address or interface to bind to and tell other Cassandra nodes to connect to.
# You _must_ change this if you want multiple nodes to be able to communicate!
#
# Set listen_address OR listen_interface, not both. Interfaces must correspond
# to a single address, IP aliasing is not supported.
#
# Leaving it blank leaves it up to InetAddress.getLocalHost(). This
# will always do the Right Thing _if_ the node is properly configured
# (hostname, name resolution, etc), and the Right Thing is to use the
# address associated with the hostname (it might not be).
#
# Setting listen_address to 0.0.0.0 is always wrong.
#
# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address
# you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4
# address will be used. If true the first ipv6 address will be used. Defaults to false preferring
# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6.
listen_address: localhost
# listen_interface: eth0
# listen_interface_prefer_ipv6: false
# Address to broadcast to other Cassandra nodes
# Leaving this blank will set it to the same value as listen_address
# broadcast_address: 1.2.3.4
# When using multiple physical network interfaces, set this
# to true to listen on broadcast_address in addition to
# the listen_address, allowing nodes to communicate in both
# interfaces.
# Ignore this property if the network configuration automatically
# routes between the public and private networks such as EC2.
# listen_on_broadcast_address: false
# Internode authentication backend, implementing IInternodeAuthenticator;
# used to allow/disallow connections from peer nodes.
# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator
# Whether to start the native transport server.
# Please note that the address on which the native transport is bound is the
# same as the rpc_address. The port however is different and specified below.
start_native_transport: true
# port for the CQL native transport to listen for clients on
# For security reasons, you should not expose this port to the internet. Firewall it if needed.
native_transport_port: 9042
# Enabling native transport encryption in client_encryption_options allows you to either use
# encryption for the standard port or to use a dedicated, additional port along with the unencrypted
# standard native_transport_port.
# Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption
# for native_transport_port. Setting native_transport_port_ssl to a different value
# from native_transport_port will use encryption for native_transport_port_ssl while
# keeping native_transport_port unencrypted.
# native_transport_port_ssl: 9142
# The maximum threads for handling requests when the native transport is used.
# This is similar to rpc_max_threads though the default differs slightly (and
# there is no native_transport_min_threads, idle threads will always be stopped
# after 30 seconds).
# native_transport_max_threads: 128
#
# The maximum size of allowed frame. Frame (requests) larger than this will
# be rejected as invalid. The default is 256MB.
# native_transport_max_frame_size_in_mb: 256
# The maximum number of concurrent client connections.
# The default is -1, which means unlimited.
# native_transport_max_concurrent_connections: -1
# The maximum number of concurrent client connections per source ip.
# The default is -1, which means unlimited.
# native_transport_max_concurrent_connections_per_ip: -1
# Whether to start the thrift rpc server.
start_rpc: false
# The address or interface to bind the Thrift RPC service and native transport
# server to.
#
# Set rpc_address OR rpc_interface, not both. Interfaces must correspond
# to a single address, IP aliasing is not supported.
#
# Leaving rpc_address blank has the same effect as on listen_address
# (i.e. it will be based on the configured hostname of the node).
#
# Note that unlike listen_address, you can specify 0.0.0.0, but you must also
# set broadcast_rpc_address to a value other than 0.0.0.0.
#
# For security reasons, you should not expose this port to the internet. Firewall it if needed.
#
# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address
# you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4
# address will be used. If true the first ipv6 address will be used. Defaults to false preferring
# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6.
rpc_address: localhost
# rpc_interface: eth1
# rpc_interface_prefer_ipv6: false
# port for Thrift to listen for clients on
rpc_port: 9160
# RPC address to broadcast to drivers and other Cassandra nodes. This cannot
# be set to 0.0.0.0. If left blank, this will be set to the value of
# rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must
# be set.
# broadcast_rpc_address: 1.2.3.4
# enable or disable keepalive on rpc/native connections
rpc_keepalive: true
# Cassandra provides two out-of-the-box options for the RPC Server:
#
# sync -> One thread per thrift connection. For a very large number of clients, memory
# will be your limiting factor. On a 64 bit JVM, 180KB is the minimum stack size
# per thread, and that will correspond to your use of virtual memory (but physical memory
# may be limited depending on use of stack space).
#
# hsha -> Stands for "half synchronous, half asynchronous." All thrift clients are handled
# asynchronously using a small number of threads that does not vary with the amount
# of thrift clients (and thus scales well to many clients). The rpc requests are still
# synchronous (one thread per active request). If hsha is selected then it is essential
# that rpc_max_threads is changed from the default value of unlimited.
#
# The default is sync because on Windows hsha is about 30% slower. On Linux,
# sync/hsha performance is about the same, with hsha of course using less memory.
#
# Alternatively, can provide your own RPC server by providing the fully-qualified class name
# of an o.a.c.t.TServerFactory that can create an instance of it.
rpc_server_type: sync
# Uncomment rpc_min|max_thread to set request pool size limits.
#
# Regardless of your choice of RPC server (see above), the number of maximum requests in the
# RPC thread pool dictates how many concurrent requests are possible (but if you are using the sync
# RPC server, it also dictates the number of clients that can be connected at all).
#
# The default is unlimited and thus provides no protection against clients overwhelming the server. You are
# encouraged to set a maximum that makes sense for you in production, but do keep in mind that
# rpc_max_threads represents the maximum number of client requests this server may execute concurrently.
#
# rpc_min_threads: 16
# rpc_max_threads: 2048
# uncomment to set socket buffer sizes on rpc connections
# rpc_send_buff_size_in_bytes:
# rpc_recv_buff_size_in_bytes:
# Uncomment to set socket buffer size for internode communication
# Note that when setting this, the buffer size is limited by net.core.wmem_max
# and when not setting it it is defined by net.ipv4.tcp_wmem
# See:
# /proc/sys/net/core/wmem_max
# /proc/sys/net/core/rmem_max
# /proc/sys/net/ipv4/tcp_wmem
# /proc/sys/net/ipv4/tcp_wmem
# and: man tcp
# internode_send_buff_size_in_bytes:
# internode_recv_buff_size_in_bytes:
# Frame size for thrift (maximum message length).
thrift_framed_transport_size_in_mb: 15
# Set to true to have Cassandra create a hard link to each sstable
# flushed or streamed locally in a backups/ subdirectory of the
# keyspace data. Removing these links is the operator's
# responsibility.
incremental_backups: false
# Whether or not to take a snapshot before each compaction. Be
# careful using this option, since Cassandra won't clean up the
# snapshots for you. Mostly useful if you're paranoid when there
# is a data format change.
snapshot_before_compaction: false
# Whether or not a snapshot is taken of the data before keyspace truncation
# or dropping of column families. The STRONGLY advised default of true
# should be used to provide data safety. If you set this flag to false, you will
# lose data on truncation or drop.
auto_snapshot: true
# When executing a scan, within or across a partition, we need to keep the
# tombstones seen in memory so we can return them to the coordinator, which
# will use them to make sure other replicas also know about the deleted rows.
# With workloads that generate a lot of tombstones, this can cause performance
# problems and even exaust the server heap.
# (http://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets)
# Adjust the thresholds here if you understand the dangers and want to
# scan more tombstones anyway. These thresholds may also be adjusted at runtime
# using the StorageService mbean.
tombstone_warn_threshold: 1000
tombstone_failure_threshold: 100000
# Granularity of the collation index of rows within a partition.
# Increase if your rows are large, or if you have a very large
# number of rows per partition. The competing goals are these:
# 1) a smaller granularity means more index entries are generated
# and looking up rows within the partition by collation column
# is faster
# 2) but, Cassandra will keep the collation index in memory for hot
# rows (as part of the key cache), so a larger granularity means
# you can cache more hot rows
column_index_size_in_kb: 64
# Log WARN on any batch size exceeding this value. 5kb per batch by default.
# Caution should be taken on increasing the size of this threshold as it can lead to node instability.
batch_size_warn_threshold_in_kb: 5
# Fail any batch exceeding this value. 50kb (10x warn threshold) by default.
batch_size_fail_threshold_in_kb: 50
# Number of simultaneous compactions to allow, NOT including
# validation "compactions" for anti-entropy repair. Simultaneous
# compactions can help preserve read performance in a mixed read/write
# workload, by mitigating the tendency of small sstables to accumulate
# during a single long running compactions. The default is usually
# fine and if you experience problems with compaction running too
# slowly or too fast, you should look at
# compaction_throughput_mb_per_sec first.
#
# concurrent_compactors defaults to the smaller of (number of disks,
# number of cores), with a minimum of 2 and a maximum of 8.
#
# If your data directories are backed by SSD, you should increase this
# to the number of cores.
#concurrent_compactors: 1
# Throttles compaction to the given total throughput across the entire
# system. The faster you insert data, the faster you need to compact in
# order to keep the sstable count down, but in general, setting this to
# 16 to 32 times the rate you are inserting data is more than sufficient.
# Setting this to 0 disables throttling. Note that this account for all types
# of compaction, including validation compaction.
compaction_throughput_mb_per_sec: 16
# Log a warning when compacting partitions larger than this value
compaction_large_partition_warning_threshold_mb: 100
# When compacting, the replacement sstable(s) can be opened before they
# are completely written, and used in place of the prior sstables for
# any range that has been written. This helps to smoothly transfer reads
# between the sstables, reducing page cache churn and keeping hot rows hot
sstable_preemptive_open_interval_in_mb: 50
# Throttles all outbound streaming file transfers on this node to the
# given total throughput in Mbps. This is necessary because Cassandra does
# mostly sequential IO when streaming data during bootstrap or repair, which
# can lead to saturating the network connection and degrading rpc performance.
# When unset, the default is 200 Mbps or 25 MB/s.
# stream_throughput_outbound_megabits_per_sec: 200
# Throttles all streaming file transfer between the datacenters,
# this setting allows users to throttle inter dc stream throughput in addition
# to throttling all network stream traffic as configured with
# stream_throughput_outbound_megabits_per_sec
# When unset, the default is 200 Mbps or 25 MB/s
# inter_dc_stream_throughput_outbound_megabits_per_sec: 200
# How long the coordinator should wait for read operations to complete
read_request_timeout_in_ms: 5000
# How long the coordinator should wait for seq or index scans to complete
range_request_timeout_in_ms: 10000
# How long the coordinator should wait for writes to complete
write_request_timeout_in_ms: 2000
# How long the coordinator should wait for counter writes to complete
counter_write_request_timeout_in_ms: 5000
# How long a coordinator should continue to retry a CAS operation
# that contends with other proposals for the same row
cas_contention_timeout_in_ms: 1000
# How long the coordinator should wait for truncates to complete
# (This can be much longer, because unless auto_snapshot is disabled
# we need to flush first so we can snapshot before removing the data.)
truncate_request_timeout_in_ms: 60000
# The default timeout for other, miscellaneous operations
request_timeout_in_ms: 10000
# Enable operation timeout information exchange between nodes to accurately
# measure request timeouts. If disabled, replicas will assume that requests
# were forwarded to them instantly by the coordinator, which means that
# under overload conditions we will waste that much extra time processing
# already-timed-out requests.
#
# Warning: before enabling this property make sure to ntp is installed
# and the times are synchronized between the nodes.
cross_node_timeout: false
# Set socket timeout for streaming operation.
# The stream session is failed if no data is received by any of the
# participants within that period.
# Default value is 3600000, which means streams timeout after an hour.
# streaming_socket_timeout_in_ms: 3600000
# phi value that must be reached for a host to be marked down.
# most users should never need to adjust this.
# phi_convict_threshold: 8
# endpoint_snitch -- Set this to a class that implements
# IEndpointSnitch. The snitch has two functions:
# - it teaches Cassandra enough about your network topology to route
# requests efficiently
# - it allows Cassandra to spread replicas around your cluster to avoid
# correlated failures. It does this by grouping machines into
# "datacenters" and "racks." Cassandra will do its best not to have
# more than one replica on the same "rack" (which may not actually
# be a physical location)
#
# IF YOU CHANGE THE SNITCH AFTER DATA IS INSERTED INTO THE CLUSTER,
# YOU MUST RUN A FULL REPAIR, SINCE THE SNITCH AFFECTS WHERE REPLICAS
# ARE PLACED.
#
# IF THE RACK A REPLICA IS PLACED IN CHANGES AFTER THE REPLICA HAS BEEN
# ADDED TO A RING, THE NODE MUST BE DECOMMISSIONED AND REBOOTSTRAPPED.
#
# Out of the box, Cassandra provides
# - SimpleSnitch:
# Treats Strategy order as proximity. This can improve cache
# locality when disabling read repair. Only appropriate for
# single-datacenter deployments.
# - GossipingPropertyFileSnitch
# This should be your go-to snitch for production use. The rack
# and datacenter for the local node are defined in
# cassandra-rackdc.properties and propagated to other nodes via
# gossip. If cassandra-topology.properties exists, it is used as a
# fallback, allowing migration from the PropertyFileSnitch.
# - PropertyFileSnitch:
# Proximity is determined by rack and data center, which are
# explicitly configured in cassandra-topology.properties.
# - Ec2Snitch:
# Appropriate for EC2 deployments in a single Region. Loads Region
# and Availability Zone information from the EC2 API. The Region is
# treated as the datacenter, and the Availability Zone as the rack.
# Only private IPs are used, so this will not work across multiple
# Regions.
# - Ec2MultiRegionSnitch:
# Uses public IPs as broadcast_address to allow cross-region
# connectivity. (Thus, you should set seed addresses to the public
# IP as well.) You will need to open the storage_port or
# ssl_storage_port on the public IP firewall. (For intra-Region
# traffic, Cassandra will switch to the private IP after
# establishing a connection.)
# - RackInferringSnitch:
# Proximity is determined by rack and data center, which are
# assumed to correspond to the 3rd and 2nd octet of each node's IP
# address, respectively. Unless this happens to match your
# deployment conventions, this is best used as an example of
# writing a custom Snitch class and is provided in that spirit.
#
# You can use a custom Snitch by setting this to the full class name
# of the snitch, which will be assumed to be on your classpath.
endpoint_snitch: SimpleSnitch
# controls how often to perform the more expensive part of host score
# calculation
dynamic_snitch_update_interval_in_ms: 100
# controls how often to reset all host scores, allowing a bad host to
# possibly recover
dynamic_snitch_reset_interval_in_ms: 600000
# if set greater than zero and read_repair_chance is < 1.0, this will allow
# 'pinning' of replicas to hosts in order to increase cache capacity.
# The badness threshold will control how much worse the pinned host has to be
# before the dynamic snitch will prefer other replicas over it. This is
# expressed as a double which represents a percentage. Thus, a value of
# 0.2 means Cassandra would continue to prefer the static snitch values
# until the pinned host was 20% worse than the fastest.
dynamic_snitch_badness_threshold: 0.1
# request_scheduler -- Set this to a class that implements
# RequestScheduler, which will schedule incoming client requests
# according to the specific policy. This is useful for multi-tenancy
# with a single Cassandra cluster.
# NOTE: This is specifically for requests from the client and does
# not affect inter node communication.
# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place
# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of
# client requests to a node with a separate queue for each
# request_scheduler_id. The scheduler is further customized by
# request_scheduler_options as described below.
request_scheduler: org.apache.cassandra.scheduler.NoScheduler
# Scheduler Options vary based on the type of scheduler
# NoScheduler - Has no options
# RoundRobin
# - throttle_limit -- The throttle_limit is the number of in-flight
# requests per client. Requests beyond
# that limit are queued up until
# running requests can complete.
# The value of 80 here is twice the number of
# concurrent_reads + concurrent_writes.
# - default_weight -- default_weight is optional and allows for
# overriding the default which is 1.
# - weights -- Weights are optional and will default to 1 or the
# overridden default_weight. The weight translates into how
# many requests are handled during each turn of the
# RoundRobin, based on the scheduler id.
#
# request_scheduler_options:
# throttle_limit: 80
# default_weight: 5
# weights:
# Keyspace1: 1
# Keyspace2: 5
# request_scheduler_id -- An identifier based on which to perform
# the request scheduling. Currently the only valid option is keyspace.
# request_scheduler_id: keyspace
# Enable or disable inter-node encryption
# Default settings are TLS v1, RSA 1024-bit keys (it is imperative that
# users generate their own keys) TLS_RSA_WITH_AES_128_CBC_SHA as the cipher
# suite for authentication, key exchange and encryption of the actual data transfers.
# Use the DHE/ECDHE ciphers if running in FIPS 140 compliant mode.
# NOTE: No custom encryption options are enabled at the moment
# The available internode options are : all, none, dc, rack
#
# If set to dc cassandra will encrypt the traffic between the DCs
# If set to rack cassandra will encrypt the traffic between the racks
#
# The passwords used in these options must match the passwords used when generating
# the keystore and truststore. For instructions on generating these files, see:
# http://download.oracle.com/javase/6/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore
#
server_encryption_options:
internode_encryption: none
keystore: conf/.keystore
keystore_password: cassandra
truststore: conf/.truststore
truststore_password: cassandra
# More advanced defaults below:
# protocol: TLS
# algorithm: SunX509
# store_type: JKS
# cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA]
# require_client_auth: false
# enable or disable client/server encryption.
client_encryption_options:
enabled: false
# If enabled and optional is set to true encrypted and unencrypted connections are handled.
optional: false
keystore: conf/.keystore
keystore_password: cassandra
# require_client_auth: false
# Set trustore and truststore_password if require_client_auth is true
# truststore: conf/.truststore
# truststore_password: cassandra
# More advanced defaults below:
# protocol: TLS
# algorithm: SunX509
# store_type: JKS
# cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA]
# internode_compression controls whether traffic between nodes is
# compressed.
# can be: all - all traffic is compressed
# dc - traffic between different datacenters is compressed
# none - nothing is compressed.
internode_compression: all
# Enable or disable tcp_nodelay for inter-dc communication.
# Disabling it will result in larger (but fewer) network packets being sent,
# reducing overhead from the TCP protocol itself, at the cost of increasing
# latency if you block for cross-datacenter responses.
inter_dc_tcp_nodelay: false
# TTL for different trace types used during logging of the repair process.
tracetype_query_ttl: 86400
tracetype_repair_ttl: 604800
# GC Pauses greater than gc_warn_threshold_in_ms will be logged at WARN level
# Adjust the threshold based on your application throughput requirement
# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level
gc_warn_threshold_in_ms: 1000
# UDFs (user defined functions) are disabled by default.
# As of Cassandra 3.0 there is a sandbox in place that should prevent execution of evil code.
enable_user_defined_functions: false
# Enables scripted UDFs (JavaScript UDFs).
# Java UDFs are always enabled, if enable_user_defined_functions is true.
# Enable this option to be able to use UDFs with "language javascript" or any custom JSR-223 provider.
# This option has no effect, if enable_user_defined_functions is false.
enable_scripted_user_defined_functions: false
# The default Windows kernel timer and scheduling resolution is 15.6ms for power conservation.
# Lowering this value on Windows can provide much tighter latency and better throughput, however
# some virtualized environments may see a negative performance impact from changing this setting
# below their system default. The sysinternals 'clockres' tool can confirm your system's default
# setting.
windows_timer_interval: 1
# Enables encrypting data at-rest (on disk). Different key providers can be plugged in, but the default reads from
# a JCE-style keystore. A single keystore can hold multiple keys, but the one referenced by
# the "key_alias" is the only key that will be used for encrypt opertaions; previously used keys
# can still (and should!) be in the keystore and will be used on decrypt operations
# (to handle the case of key rotation).
#
# It is strongly recommended to download and install Java Cryptography Extension (JCE)
# Unlimited Strength Jurisdiction Policy Files for your version of the JDK.
# (current link: http://www.oracle.com/technetwork/java/javase/downloads/jce8-download-2133166.html)
#
# Currently, only the following file types are supported for transparent data encryption, although
# more are coming in future cassandra releases: commitlog, hints
transparent_data_encryption_options:
enabled: false
chunk_length_kb: 64
cipher: AES/CBC/PKCS5Padding
key_alias: testing:1
# CBC IV length for AES needs to be 16 bytes (which is also the default size)
# iv_length: 16
key_provider:
- class_name: org.apache.cassandra.security.JKSKeyProvider
parameters:
- keystore: conf/.keystore
keystore_password: cassandra
store_type: JCEKS
key_password: cassandra

2
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/files/java.list generated vendored Normal file
View file

@ -0,0 +1,2 @@
# for jre8
deb http://http.debian.net/debian jessie-backports main

240
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/files/jvm.options generated vendored Normal file
View file

@ -0,0 +1,240 @@
###########################################################################
# jvm.options #
# #
# - all flags defined here will be used by cassandra to startup the JVM #
# - one flag should be specified per line #
# - lines that do not start with '-' will be ignored #
# - only static flags are accepted (no variables or parameters) #
# - dynamic flags will be appended to these on cassandra-env #
###########################################################################
######################
# STARTUP PARAMETERS #
######################
# Uncomment any of the following properties to enable specific startup parameters
# In a multi-instance deployment, multiple Cassandra instances will independently assume that all
# CPU processors are available to it. This setting allows you to specify a smaller set of processors
# and perhaps have affinity.
#-Dcassandra.available_processors=number_of_processors
# The directory location of the cassandra.yaml file.
#-Dcassandra.config=directory
# Sets the initial partitioner token for a node the first time the node is started.
#-Dcassandra.initial_token=token
# Set to false to start Cassandra on a node but not have the node join the cluster.
#-Dcassandra.join_ring=true|false
# Set to false to clear all gossip state for the node on restart. Use when you have changed node
# information in cassandra.yaml (such as listen_address).
#-Dcassandra.load_ring_state=true|false
# Enable pluggable metrics reporter. See Pluggable metrics reporting in Cassandra 2.0.2.
#-Dcassandra.metricsReporterConfigFile=file
# Set the port on which the CQL native transport listens for clients. (Default: 9042)
#-Dcassandra.native_transport_port=port
# Overrides the partitioner. (Default: org.apache.cassandra.dht.Murmur3Partitioner)
#-Dcassandra.partitioner=partitioner
# To replace a node that has died, restart a new node in its place specifying the address of the
# dead node. The new node must not have any data in its data directory, that is, it must be in the
# same state as before bootstrapping.
#-Dcassandra.replace_address=listen_address or broadcast_address of dead node
# Allow restoring specific tables from an archived commit log.
#-Dcassandra.replayList=table
# Allows overriding of the default RING_DELAY (1000ms), which is the amount of time a node waits
# before joining the ring.
#-Dcassandra.ring_delay_ms=ms
# Set the port for the Thrift RPC service, which is used for client connections. (Default: 9160)
#-Dcassandra.rpc_port=port
# Set the SSL port for encrypted communication. (Default: 7001)
#-Dcassandra.ssl_storage_port=port
# Enable or disable the native transport server. See start_native_transport in cassandra.yaml.
# cassandra.start_native_transport=true|false
# Enable or disable the Thrift RPC server. (Default: true)
#-Dcassandra.start_rpc=true/false
# Set the port for inter-node communication. (Default: 7000)
#-Dcassandra.storage_port=port
# Set the default location for the trigger JARs. (Default: conf/triggers)
#-Dcassandra.triggers_dir=directory
# For testing new compaction and compression strategies. It allows you to experiment with different
# strategies and benchmark write performance differences without affecting the production workload.
#-Dcassandra.write_survey=true
# To disable configuration via JMX of auth caches (such as those for credentials, permissions and
# roles). This will mean those config options can only be set (persistently) in cassandra.yaml
# and will require a restart for new values to take effect.
#-Dcassandra.disable_auth_caches_remote_configuration=true
########################
# GENERAL JVM SETTINGS #
########################
# enable assertions. disabling this in production will give a modest
# performance benefit (around 5%).
-ea
# enable thread priorities, primarily so we can give periodic tasks
# a lower priority to avoid interfering with client workload
-XX:+UseThreadPriorities
# allows lowering thread priority without being root on linux - probably
# not necessary on Windows but doesn't harm anything.
# see http://tech.stolsvik.com/2010/01/linux-java-thread-priorities-workar
-XX:ThreadPriorityPolicy=42
# Enable heap-dump if there's an OOM
-XX:+HeapDumpOnOutOfMemoryError
# Per-thread stack size.
-Xss256k
# Larger interned string table, for gossip's benefit (CASSANDRA-6410)
-XX:StringTableSize=1000003
# Make sure all memory is faulted and zeroed on startup.
# This helps prevent soft faults in containers and makes
# transparent hugepage allocation more effective.
-XX:+AlwaysPreTouch
# Disable biased locking as it does not benefit Cassandra.
-XX:-UseBiasedLocking
# Enable thread-local allocation blocks and allow the JVM to automatically
# resize them at runtime.
-XX:+UseTLAB
-XX:+ResizeTLAB
# http://www.evanjones.ca/jvm-mmap-pause.html
-XX:+PerfDisableSharedMem
# Prefer binding to IPv4 network intefaces (when net.ipv6.bindv6only=1). See
# http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=6342561 (short version:
# comment out this entry to enable IPv6 support).
-Djava.net.preferIPv4Stack=true
### Debug options
# uncomment to enable flight recorder
#-XX:+UnlockCommercialFeatures
#-XX:+FlightRecorder
# uncomment to have Cassandra JVM listen for remote debuggers/profilers on port 1414
#-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=1414
# uncomment to have Cassandra JVM log internal method compilation (developers only)
#-XX:+UnlockDiagnosticVMOptions
#-XX:+LogCompilation
#################
# HEAP SETTINGS #
#################
# Heap size is automatically calculated by cassandra-env based on this
# formula: max(min(1/2 ram, 1024MB), min(1/4 ram, 8GB))
# That is:
# - calculate 1/2 ram and cap to 1024MB
# - calculate 1/4 ram and cap to 8192MB
# - pick the max
#
# For production use you may wish to adjust this for your environment.
# If that's the case, uncomment the -Xmx and Xms options below to override the
# automatic calculation of JVM heap memory.
#
# It is recommended to set min (-Xms) and max (-Xmx) heap sizes to
# the same value to avoid stop-the-world GC pauses during resize, and
# so that we can lock the heap in memory on startup to prevent any
# of it from being swapped out.
#-Xms4G
#-Xmx4G
# Young generation size is automatically calculated by cassandra-env
# based on this formula: min(100 * num_cores, 1/4 * heap size)
#
# The main trade-off for the young generation is that the larger it
# is, the longer GC pause times will be. The shorter it is, the more
# expensive GC will be (usually).
#
# It is not recommended to set the young generation size if using the
# G1 GC, since that will override the target pause-time goal.
# More info: http://www.oracle.com/technetwork/articles/java/g1gc-1984535.html
#
# The example below assumes a modern 8-core+ machine for decent
# times. If in doubt, and if you do not particularly want to tweak, go
# 100 MB per physical CPU core.
#-Xmn800M
#################
# GC SETTINGS #
#################
### CMS Settings
#-XX:+UseParNewGC
#-XX:+UseConcMarkSweepGC
#-XX:+CMSParallelRemarkEnabled
#-XX:SurvivorRatio=8
#-XX:MaxTenuringThreshold=1
#-XX:CMSInitiatingOccupancyFraction=75
#-XX:+UseCMSInitiatingOccupancyOnly
#-XX:CMSWaitDuration=10000
#-XX:+CMSParallelInitialMarkEnabled
#-XX:+CMSEdenChunksRecordAlways
# some JVMs will fill up their heap when accessed via JMX, see CASSANDRA-6541
#-XX:+CMSClassUnloadingEnabled
### G1 Settings (experimental, comment previous section and uncomment section below to enable)
## Use the Hotspot garbage-first collector.
-XX:+UseG1GC
#
## Have the JVM do less remembered set work during STW, instead
## preferring concurrent GC. Reduces p99.9 latency.
-XX:G1RSetUpdatingPauseTimePercent=5
#
## Main G1GC tunable: lowering the pause target will lower throughput and vise versa.
## 200ms is the JVM default and lowest viable setting
## 1000ms increases throughput. Keep it smaller than the timeouts in cassandra.yaml.
#-XX:MaxGCPauseMillis=500
## Optional G1 Settings
# Save CPU time on large (>= 16GB) heaps by delaying region scanning
# until the heap is 70% full. The default in Hotspot 8u40 is 40%.
#-XX:InitiatingHeapOccupancyPercent=70
# For systems with > 8 cores, the default ParallelGCThreads is 5/8 the number of logical cores.
# Otherwise equal to the number of cores when 8 or less.
# Machines with > 10 cores should try setting these to <= full cores.
#-XX:ParallelGCThreads=16
# By default, ConcGCThreads is 1/4 of ParallelGCThreads.
# Setting both to the same value can reduce STW durations.
#-XX:ConcGCThreads=16
### GC logging options -- uncomment to enable
-XX:+PrintGCDetails
-XX:+PrintGCDateStamps
-XX:+PrintHeapAtGC
-XX:+PrintTenuringDistribution
-XX:+PrintGCApplicationStoppedTime
-XX:+PrintPromotionFailure
#-XX:PrintFLSStatistics=1
#-Xloggc:/var/log/cassandra/gc.log
-XX:+UseGCLogFileRotation
-XX:NumberOfGCLogFiles=10
-XX:GCLogFileSize=10M

BIN
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/files/kubernetes-cassandra.jar generated vendored Normal file
View file

Binary file not shown.

13
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/files/logback.xml generated vendored Normal file
View file

@ -0,0 +1,13 @@
<?xml version="1.0"?>
<configuration scan="true">
<jmxConfigurator/>
<appender name="STDOUT" class="ch.qos.logback.core.ConsoleAppender">
<encoder>
<pattern>%-5level %date{HH:mm:ss,SSS} %msg%n</pattern>
</encoder>
</appender>
<root level="INFO">
<appender-ref ref="STDOUT"/>
</root>
<logger name="com.thinkaurelius.thrift" level="ERROR"/>
</configuration>

27
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/files/ready-probe.sh generated vendored Normal file
View file

@ -0,0 +1,27 @@
#!/bin/bash
# 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.
if [[ $(nodetool status | grep $POD_IP) == *"UN"* ]]; then
if [[ $DEBUG ]]; then
echo "Not Up";
fi
exit 0;
else
if [[ $DEBUG ]]; then
echo "UN";
fi
exit 1;
fi

171
vendor/k8s.io/kubernetes/examples/storage/cassandra/image/files/run.sh generated vendored Normal file
View file

@ -0,0 +1,171 @@
#!/bin/bash
# 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.
set -e
CASSANDRA_CONF_DIR=/etc/cassandra
CASSANDRA_CFG=$CASSANDRA_CONF_DIR/cassandra.yaml
# we are doing StatefulSet or just setting our seeds
if [ -z "$CASSANDRA_SEEDS" ]; then
HOSTNAME=$(hostname -f)
fi
# The following vars relate to there counter parts in $CASSANDRA_CFG
# for instance rpc_address
CASSANDRA_RPC_ADDRESS="${CASSANDRA_RPC_ADDRESS:-0.0.0.0}"
CASSANDRA_NUM_TOKENS="${CASSANDRA_NUM_TOKENS:-32}"
CASSANDRA_CLUSTER_NAME="${CASSANDRA_CLUSTER_NAME:='Test Cluster'}"
CASSANDRA_LISTEN_ADDRESS=${POD_IP:-$HOSTNAME}
CASSANDRA_BROADCAST_ADDRESS=${POD_IP:-$HOSTNAME}
CASSANDRA_BROADCAST_RPC_ADDRESS=${POD_IP:-$HOSTNAME}
CASSANDRA_DISK_OPTIMIZATION_STRATEGY="${CASSANDRA_DISK_OPTIMIZATION_STRATEGY:-ssd}"
CASSANDRA_MIGRATION_WAIT="${CASSANDRA_MIGRATION_WAIT:-1}"
CASSANDRA_ENDPOINT_SNITCH="${CASSANDRA_ENDPOINT_SNITCH:-SimpleSnitch}"
CASSANDRA_DC="${CASSANDRA_DC}"
CASSANDRA_RACK="${CASSANDRA_RACK}"
CASSANDRA_RING_DELAY="${CASSANDRA_RING_DELAY:-30000}"
CASSANDRA_AUTO_BOOTSTRAP="${CASSANDRA_AUTO_BOOTSTRAP:-true}"
CASSANDRA_SEEDS="${CASSANDRA_SEEDS:false}"
CASSANDRA_SEED_PROVIDER="${CASSANDRA_SEED_PROVIDER:-org.apache.cassandra.locator.SimpleSeedProvider}"
CASSANDRA_AUTO_BOOTSTRAP="${CASSANDRA_AUTO_BOOTSTRAP:false}"
# Turn off JMX auth
CASSANDRA_OPEN_JMX="${CASSANDRA_OPEN_JMX:-false}"
# send GC to STDOUT
CASSANDRA_GC_STDOUT="${CASSANDRA_GC_STDOUT:-false}"
echo Starting Cassandra on ${CASSANDRA_LISTEN_ADDRESS}
echo CASSANDRA_CONF_DIR ${CASSANDRA_CONF_DIR}
echo CASSANDRA_CFG ${CASSANDRA_CFG}
echo CASSANDRA_AUTO_BOOTSTRAP ${CASSANDRA_AUTO_BOOTSTRAP}
echo CASSANDRA_BROADCAST_ADDRESS ${CASSANDRA_BROADCAST_ADDRESS}
echo CASSANDRA_BROADCAST_RPC_ADDRESS ${CASSANDRA_BROADCAST_RPC_ADDRESS}
echo CASSANDRA_CLUSTER_NAME ${CASSANDRA_CLUSTER_NAME}
echo CASSANDRA_COMPACTION_THROUGHPUT_MB_PER_SEC ${CASSANDRA_COMPACTION_THROUGHPUT_MB_PER_SEC}
echo CASSANDRA_CONCURRENT_COMPACTORS ${CASSANDRA_CONCURRENT_COMPACTORS}
echo CASSANDRA_CONCURRENT_READS ${CASSANDRA_CONCURRENT_READS}
echo CASSANDRA_CONCURRENT_WRITES ${CASSANDRA_CONCURRENT_WRITES}
echo CASSANDRA_COUNTER_CACHE_SIZE_IN_MB ${CASSANDRA_COUNTER_CACHE_SIZE_IN_MB}
echo CASSANDRA_DC ${CASSANDRA_DC}
echo CASSANDRA_DISK_OPTIMIZATION_STRATEGY ${CASSANDRA_DISK_OPTIMIZATION_STRATEGY}
echo CASSANDRA_ENDPOINT_SNITCH ${CASSANDRA_ENDPOINT_SNITCH}
echo CASSANDRA_GC_WARN_THRESHOLD_IN_MS ${CASSANDRA_GC_WARN_THRESHOLD_IN_MS}
echo CASSANDRA_INTERNODE_COMPRESSION ${CASSANDRA_INTERNODE_COMPRESSION}
echo CASSANDRA_KEY_CACHE_SIZE_IN_MB ${CASSANDRA_KEY_CACHE_SIZE_IN_MB}
echo CASSANDRA_LISTEN_ADDRESS ${CASSANDRA_LISTEN_ADDRESS}
echo CASSANDRA_LISTEN_INTERFACE ${CASSANDRA_LISTEN_INTERFACE}
echo CASSANDRA_MEMTABLE_ALLOCATION_TYPE ${CASSANDRA_MEMTABLE_ALLOCATION_TYPE}
echo CASSANDRA_MEMTABLE_CLEANUP_THRESHOLD ${CASSANDRA_MEMTABLE_CLEANUP_THRESHOLD}
echo CASSANDRA_MEMTABLE_FLUSH_WRITERS ${CASSANDRA_MEMTABLE_FLUSH_WRITERS}
echo CASSANDRA_MIGRATION_WAIT ${CASSANDRA_MIGRATION_WAIT}
echo CASSANDRA_NUM_TOKENS ${CASSANDRA_NUM_TOKENS}
echo CASSANDRA_RACK ${CASSANDRA_RACK}
echo CASSANDRA_RING_DELAY ${CASSANDRA_RING_DELAY}
echo CASSANDRA_RPC_ADDRESS ${CASSANDRA_RPC_ADDRESS}
echo CASSANDRA_RPC_INTERFACE ${CASSANDRA_RPC_INTERFACE}
echo CASSANDRA_SEEDS ${CASSANDRA_SEEDS}
echo CASSANDRA_SEED_PROVIDER ${CASSANDRA_SEED_PROVIDER}
# if DC and RACK are set, use GossipingPropertyFileSnitch
if [[ $CASSANDRA_DC && $CASSANDRA_RACK ]]; then
echo "dc=$CASSANDRA_DC" > $CASSANDRA_CONF_DIR/cassandra-rackdc.properties
echo "rack=$CASSANDRA_RACK" >> $CASSANDRA_CONF_DIR/cassandra-rackdc.properties
CASSANDRA_ENDPOINT_SNITCH="GossipingPropertyFileSnitch"
fi
if [ -n "$CASSANDRA_MAX_HEAP" ]; then
sed -ri "s/^(#)?-Xmx[0-9]+.*/-Xmx$CASSANDRA_MAX_HEAP/" "$CASSANDRA_CONF_DIR/jvm.options"
sed -ri "s/^(#)?-Xms[0-9]+.*/-Xms$CASSANDRA_MAX_HEAP/" "$CASSANDRA_CONF_DIR/jvm.options"
fi
if [ -n "$CASSANDRA_REPLACE_NODE" ]; then
echo "-Dcassandra.replace_address=$CASSANDRA_REPLACE_NODE/" >> "$CASSANDRA_CONF_DIR/jvm.options"
fi
for rackdc in dc rack; do
var="CASSANDRA_${rackdc^^}"
val="${!var}"
if [ "$val" ]; then
sed -ri 's/^('"$rackdc"'=).*/\1 '"$val"'/' "$CASSANDRA_CONF_DIR/cassandra-rackdc.properties"
fi
done
# TODO what else needs to be modified
for yaml in \
broadcast_address \
broadcast_rpc_address \
cluster_name \
disk_optimization_strategy \
endpoint_snitch \
listen_address \
num_tokens \
rpc_address \
start_rpc \
key_cache_size_in_mb \
concurrent_reads \
concurrent_writes \
memtable_cleanup_threshold \
memtable_allocation_type \
memtable_flush_writers \
concurrent_compactors \
compaction_throughput_mb_per_sec \
counter_cache_size_in_mb \
internode_compression \
endpoint_snitch \
gc_warn_threshold_in_ms \
listen_interface \
rpc_interface \
; do
var="CASSANDRA_${yaml^^}"
val="${!var}"
if [ "$val" ]; then
sed -ri 's/^(# )?('"$yaml"':).*/\2 '"$val"'/' "$CASSANDRA_CFG"
fi
done
echo "auto_bootstrap: ${CASSANDRA_AUTO_BOOTSTRAP}" >> $CASSANDRA_CFG
# set the seed to itself. This is only for the first pod, otherwise
# it will be able to get seeds from the seed provider
if [[ $CASSANDRA_SEEDS == 'false' ]]; then
sed -ri 's/- seeds:.*/- seeds: "'"$POD_IP"'"/' $CASSANDRA_CFG
else # if we have seeds set them. Probably StatefulSet
sed -ri 's/- seeds:.*/- seeds: "'"$CASSANDRA_SEEDS"'"/' $CASSANDRA_CFG
fi
sed -ri 's/- class_name: SEED_PROVIDER/- class_name: '"$CASSANDRA_SEED_PROVIDER"'/' $CASSANDRA_CFG
# send gc to stdout
if [[ $CASSANDRA_GC_STDOUT == 'true' ]]; then
sed -ri 's/ -Xloggc:\/var\/log\/cassandra\/gc\.log//' $CASSANDRA_CONF_DIR/cassandra-env.sh
fi
# enable RMI and JMX to work on one port
echo "JVM_OPTS=\"\$JVM_OPTS -Djava.rmi.server.hostname=$POD_IP\"" >> $CASSANDRA_CONF_DIR/cassandra-env.sh
# getting WARNING messages with Migration Service
echo "-Dcassandra.migration_task_wait_in_seconds=${CASSANDRA_MIGRATION_WAIT}" >> $CASSANDRA_CONF_DIR/jvm.options
echo "-Dcassandra.ring_delay_ms=${CASSANDRA_RING_DELAY}" >> $CASSANDRA_CONF_DIR/jvm.options
if [[ $CASSANDRA_OPEN_JMX == 'true' ]]; then
export LOCAL_JMX=no
sed -ri 's/ -Dcom\.sun\.management\.jmxremote\.authenticate=true/ -Dcom\.sun\.management\.jmxremote\.authenticate=false/' $CASSANDRA_CONF_DIR/cassandra-env.sh
sed -ri 's/ -Dcom\.sun\.management\.jmxremote\.password\.file=\/etc\/cassandra\/jmxremote\.password//' $CASSANDRA_CONF_DIR/cassandra-env.sh
fi
export CLASSPATH=/kubernetes-cassandra.jar
cassandra -R -f

1
vendor/k8s.io/kubernetes/examples/storage/cassandra/java/.gitignore generated vendored Normal file
View file

@ -0,0 +1 @@
target

34
vendor/k8s.io/kubernetes/examples/storage/cassandra/java/README.md generated vendored Normal file
View file

@ -0,0 +1,34 @@
# Cassandra on Kubernetes Custom Seed Provider: releases.k8s.io/HEAD
Within any deployment of Cassandra a Seed Provider is used to for node discovery and communication. When a Cassandra node first starts it must discover which nodes, or seeds, for the information about the Cassandra nodes in the ring / rack / datacenter.
This Java project provides a custom Seed Provider which communicates with the Kubernetes API to discover the required information. This provider is bundled with the Docker provided in this example.
# Configuring the Seed Provider
The following environment variables may be used to override the default configurations:
| ENV VAR | DEFAULT VALUE | NOTES |
| ------------- |:-------------: |:-------------:|
| KUBERNETES_PORT_443_TCP_ADDR | kubernetes.default.svc.cluster.local | The hostname of the API server |
| KUBERNETES_PORT_443_TCP_PORT | 443 | API port number |
| CASSANDRA_SERVICE | cassandra | Default service name for lookup |
| POD_NAMESPACE | default | Default pod service namespace |
| K8S_ACCOUNT_TOKEN | /var/run/secrets/kubernetes.io/serviceaccount/token | Default path to service token |
# Using
If no endpoints are discovered from the API the seeds configured in the cassandra.yaml file are used.
# Provider limitations
This Cassandra Provider implements `SeedProvider`. and utilizes `SimpleSnitch`. This limits a Cassandra Ring to a single Cassandra Datacenter and ignores Rack setup. Datastax provides more documentation on the use of [_SNITCHES_](https://docs.datastax.com/en/cassandra/3.x/cassandra/architecture/archSnitchesAbout.html). Further development is planned to
expand this capability.
This in affect makes every node a seed provider, which is not a recommended best practice. This increases maintenance and reduces gossip performance.
<!-- BEGIN MUNGE: GENERATED_ANALYTICS -->
[![Analytics](https://kubernetes-site.appspot.com/UA-36037335-10/GitHub/examples/storage/cassandra/java/README.md?pixel)]()
<!-- END MUNGE: GENERATED_ANALYTICS -->

94
vendor/k8s.io/kubernetes/examples/storage/cassandra/java/pom.xml generated vendored Normal file
View file

@ -0,0 +1,94 @@
<!--
Copyright (C) 2015 Google Inc.
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.
-->
<project>
<modelVersion>4.0.0</modelVersion>
<groupId>io.k8s.cassandra</groupId>
<artifactId>kubernetes-cassandra</artifactId>
<version>1.0.2</version>
<build>
<plugins>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
</plugins>
</build>
<properties>
<logback.version>1.1.3</logback.version>
<cassandra.version>3.9</cassandra.version>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.hamcrest</groupId>
<artifactId>hamcrest-all</artifactId>
<version>1.3</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<version>1.7.5</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>ch.qos.logback</groupId>
<artifactId>logback-classic</artifactId>
<version>${logback.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>ch.qos.logback</groupId>
<artifactId>logback-core</artifactId>
<version>${logback.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.codehaus.jackson</groupId>
<artifactId>jackson-core-asl</artifactId>
<version>1.6.3</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.codehaus.jackson</groupId>
<artifactId>jackson-mapper-asl</artifactId>
<version>1.6.3</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.cassandra</groupId>
<artifactId>cassandra-all</artifactId>
<version>${cassandra.version}</version>
<scope>provided</scope>
</dependency>
</dependencies>
</project>

254
vendor/k8s.io/kubernetes/examples/storage/cassandra/java/src/main/java/io/k8s/cassandra/KubernetesSeedProvider.java generated vendored Normal file
View file

@ -0,0 +1,254 @@
/*
* Copyright (C) 2015 Google Inc.
*
* 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.
*/
package io.k8s.cassandra;
import org.apache.cassandra.config.Config;
import org.apache.cassandra.config.ConfigurationLoader;
import org.apache.cassandra.config.YamlConfigurationLoader;
import org.apache.cassandra.exceptions.ConfigurationException;
import org.apache.cassandra.locator.SeedProvider;
import org.apache.cassandra.locator.SimpleSeedProvider;
import org.apache.cassandra.utils.FBUtilities;
import org.codehaus.jackson.annotate.JsonIgnoreProperties;
import org.codehaus.jackson.map.ObjectMapper;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import javax.net.ssl.*;
import java.io.IOException;
import java.net.InetAddress;
import java.net.URL;
import java.net.UnknownHostException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.security.KeyManagementException;
import java.security.NoSuchAlgorithmException;
import java.security.SecureRandom;
import java.security.cert.X509Certificate;
import java.util.ArrayList;
import java.util.Collections;
import java.util.List;
import java.util.Map;
/**
* Self discovery {@link SeedProvider} that creates a list of Cassandra Seeds by
* communicating with the Kubernetes API.
* <p>Various System Variable can be used to configure this provider:
* <ul>
* <li>KUBERNETES_PORT_443_TCP_ADDR defaults to kubernetes.default.svc.cluster.local</li>
* <li>KUBERNETES_PORT_443_TCP_PORT defaults to 443</li>
* <li>CASSANDRA_SERVICE defaults to cassandra</li>
* <li>POD_NAMESPACE defaults to 'default'</li>
* <li>CASSANDRA_SERVICE_NUM_SEEDS defaults to 8 seeds</li>
* <li>K8S_ACCOUNT_TOKEN defaults to the path for the default token</li>
* </ul>
*/
public class KubernetesSeedProvider implements SeedProvider {
private static final Logger logger = LoggerFactory.getLogger(KubernetesSeedProvider.class);
/**
* default seeds to fall back on
*/
private List<InetAddress> defaultSeeds;
private TrustManager[] trustAll;
private HostnameVerifier trustAllHosts;
/**
* Create new Seeds
* @param params
*/
public KubernetesSeedProvider(Map<String, String> params) {
// Create default seeds
defaultSeeds = createDefaultSeeds();
// TODO: Load the CA cert when it is available on all platforms.
trustAll = new TrustManager[] {
new X509TrustManager() {
public void checkServerTrusted(X509Certificate[] certs, String authType) {}
public void checkClientTrusted(X509Certificate[] certs, String authType) {}
public X509Certificate[] getAcceptedIssuers() { return null; }
}
};
trustAllHosts = new HostnameVerifier() {
public boolean verify(String hostname, SSLSession session) {
return true;
}
};
}
/**
* Call kubernetes API to collect a list of seed providers
* @return list of seed providers
*/
public List<InetAddress> getSeeds() {
String host = getEnvOrDefault("KUBERNETES_PORT_443_TCP_ADDR", "kubernetes.default.svc.cluster.local");
String port = getEnvOrDefault("KUBERNETES_PORT_443_TCP_PORT", "443");
String serviceName = getEnvOrDefault("CASSANDRA_SERVICE", "cassandra");
String podNamespace = getEnvOrDefault("POD_NAMESPACE", "default");
String path = String.format("/api/v1/namespaces/%s/endpoints/", podNamespace);
String seedSizeVar = getEnvOrDefault("CASSANDRA_SERVICE_NUM_SEEDS", "8");
Integer seedSize = Integer.valueOf(seedSizeVar);
String accountToken = getEnvOrDefault("K8S_ACCOUNT_TOKEN", "/var/run/secrets/kubernetes.io/serviceaccount/token");
List<InetAddress> seeds = new ArrayList<InetAddress>();
try {
String token = getServiceAccountToken(accountToken);
SSLContext ctx = SSLContext.getInstance("SSL");
ctx.init(null, trustAll, new SecureRandom());
String PROTO = "https://";
URL url = new URL(PROTO + host + ":" + port + path + serviceName);
logger.info("Getting endpoints from " + url);
HttpsURLConnection conn = (HttpsURLConnection)url.openConnection();
// TODO: Remove this once the CA cert is propagated everywhere, and replace
// with loading the CA cert.
conn.setHostnameVerifier(trustAllHosts);
conn.setSSLSocketFactory(ctx.getSocketFactory());
conn.addRequestProperty("Authorization", "Bearer " + token);
ObjectMapper mapper = new ObjectMapper();
Endpoints endpoints = mapper.readValue(conn.getInputStream(), Endpoints.class);
if (endpoints != null) {
// Here is a problem point, endpoints.subsets can be null in first node cases.
if (endpoints.subsets != null && !endpoints.subsets.isEmpty()){
for (Subset subset : endpoints.subsets) {
if (subset.addresses != null && !subset.addresses.isEmpty()) {
for (Address address : subset.addresses) {
seeds.add(InetAddress.getByName(address.ip));
if(seeds.size() >= seedSize) {
logger.info("Available num endpoints: " + seeds.size());
return Collections.unmodifiableList(seeds);
}
}
}
}
}
logger.info("Available num endpoints: " + seeds.size());
} else {
logger.warn("Endpoints are not available using default seeds in cassandra.yaml");
return Collections.unmodifiableList(defaultSeeds);
}
} catch (Exception ex) {
logger.warn("Request to kubernetes apiserver failed, using default seeds in cassandra.yaml", ex);
return Collections.unmodifiableList(defaultSeeds);
}
if (seeds.size() == 0) {
// If we got nothing, we might be the first instance, in that case
// fall back on the seeds that were passed in cassandra.yaml.
logger.warn("Seeds are not available using default seeds in cassandra.yaml");
return Collections.unmodifiableList(defaultSeeds);
}
return Collections.unmodifiableList(seeds);
}
/**
* Code taken from {@link SimpleSeedProvider}. This is used as a fall back
* incase we don't find seeds
* @return
*/
protected List<InetAddress> createDefaultSeeds()
{
Config conf;
try {
conf = loadConfig();
}
catch (Exception e) {
throw new AssertionError(e);
}
String[] hosts = conf.seed_provider.parameters.get("seeds").split(",", -1);
List<InetAddress> seeds = new ArrayList<InetAddress>();
for (String host : hosts) {
try {
seeds.add(InetAddress.getByName(host.trim()));
}
catch (UnknownHostException ex) {
// not fatal... DD will bark if there end up being zero seeds.
logger.warn("Seed provider couldn't lookup host {}", host);
}
}
if(seeds.size() == 0) {
try {
seeds.add(InetAddress.getLocalHost());
} catch (UnknownHostException e) {
logger.warn("Seed provider couldn't lookup localhost");
}
}
return Collections.unmodifiableList(seeds);
}
/**
* Code taken from {@link SimpleSeedProvider}
* @return
*/
protected static Config loadConfig() throws ConfigurationException
{
String loaderClass = System.getProperty("cassandra.config.loader");
ConfigurationLoader loader = loaderClass == null
? new YamlConfigurationLoader()
: FBUtilities.<ConfigurationLoader>construct(loaderClass, "configuration loading");
return loader.loadConfig();
}
private static String getEnvOrDefault(String var, String def) {
String val = System.getenv(var);
if (val == null) {
val = def;
}
return val;
}
private static String getServiceAccountToken(String file) {
try {
return new String(Files.readAllBytes(Paths.get(file)));
} catch (IOException e) {
logger.warn("unable to load service account token" + file);
throw new RuntimeException("Unable to load services account token " + file);
}
}
protected List<InetAddress> getDefaultSeeds() {
return defaultSeeds;
}
@JsonIgnoreProperties(ignoreUnknown = true)
static class Address {
public String ip;
}
@JsonIgnoreProperties(ignoreUnknown = true)
static class Subset {
public List<Address> addresses;
}
@JsonIgnoreProperties(ignoreUnknown = true)
static class Endpoints {
public List<Subset> subsets;
}
}

64
vendor/k8s.io/kubernetes/examples/storage/cassandra/java/src/test/java/io/k8s/cassandra/KubernetesSeedProviderTest.java generated vendored Normal file
View file

@ -0,0 +1,64 @@
/*
* Copyright (C) 2015 Google Inc.
*
* 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.
*/
package io.k8s.cassandra;
import com.google.common.collect.ImmutableMap;
import org.apache.cassandra.locator.SeedProvider;
import org.junit.Ignore;
import org.junit.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import static org.hamcrest.Matchers.*;
import java.net.InetAddress;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import static org.junit.Assert.*;
public class KubernetesSeedProviderTest {
private static final Logger logger = LoggerFactory.getLogger(KubernetesSeedProviderTest.class);
@Test
@Ignore("has to be run inside of a kube cluster")
public void getSeeds() throws Exception {
SeedProvider provider = new KubernetesSeedProvider(new HashMap<String, String>());
List<InetAddress> seeds = provider.getSeeds();
assertThat(seeds, is(not(empty())));
}
@Test
public void testDefaultSeeds() throws Exception {
KubernetesSeedProvider provider = new KubernetesSeedProvider(new HashMap<String,String>());
List<InetAddress> seeds = provider.getDefaultSeeds();
List<InetAddress> seedsTest = new ArrayList<>();
seedsTest.add(InetAddress.getByName("8.4.4.4"));
seedsTest.add(InetAddress.getByName("8.8.8.8"));
assertThat(seeds, is(not(empty())));
assertThat(seeds, is(seedsTest));
logger.debug("seeds loaded {}", seeds);
}
}

57
vendor/k8s.io/kubernetes/examples/storage/cassandra/java/src/test/resources/cassandra.yaml generated vendored Normal file
View file

@ -0,0 +1,57 @@
# Copyright (C) 2015 Google Inc.
#
# 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.
#
# Warning!
# Consider the effects on 'o.a.c.i.s.LegacySSTableTest' before changing schemas in this file.
#
cluster_name: Test Cluster
# memtable_allocation_type: heap_buffers
memtable_allocation_type: offheap_objects
commitlog_sync: batch
commitlog_sync_batch_window_in_ms: 1.0
commitlog_segment_size_in_mb: 5
commitlog_directory: target/cassandra/commitlog
hints_directory: target/cassandra/hints
partitioner: org.apache.cassandra.dht.ByteOrderedPartitioner
listen_address: 127.0.0.1
storage_port: 7010
rpc_port: 9170
start_native_transport: true
native_transport_port: 9042
column_index_size_in_kb: 4
saved_caches_directory: target/cassandra/saved_caches
data_file_directories:
- target/cassandra/data
disk_access_mode: mmap
seed_provider:
- class_name: io.k8s.cassandra.KubernetesSeedProvider
parameters:
- seeds: "8.4.4.4,8.8.8.8"
endpoint_snitch: org.apache.cassandra.locator.SimpleSnitch
dynamic_snitch: true
request_scheduler: org.apache.cassandra.scheduler.RoundRobinScheduler
request_scheduler_id: keyspace
server_encryption_options:
internode_encryption: none
keystore: conf/.keystore
keystore_password: cassandra
truststore: conf/.truststore
truststore_password: cassandra
incremental_backups: true
concurrent_compactors: 4
compaction_throughput_mb_per_sec: 0
row_cache_class_name: org.apache.cassandra.cache.OHCProvider
row_cache_size_in_mb: 16
enable_user_defined_functions: true
enable_scripted_user_defined_functions: true

34
vendor/k8s.io/kubernetes/examples/storage/cassandra/java/src/test/resources/logback-test.xml generated vendored Normal file
View file

@ -0,0 +1,34 @@
<!--
Copyright (C) 2015 Google Inc.
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.
-->
<configuration debug="false" scan="true">
<appender name="STDOUT" target="System.out" class="ch.qos.logback.core.ConsoleAppender">
<encoder>
<pattern>%-5level %date{HH:mm:ss,SSS} %msg%n</pattern>
</encoder>
<filter class="ch.qos.logback.classic.filter.ThresholdFilter">
<level>DEBUG</level>
</filter>
</appender>
<logger name="io.k8s.cassandra" level="DEBUG"/>
<root level="INFO">
<appender-ref ref="STDOUT" />
</root>
</configuration>