YARN-11524. Improve the Policy Description in Federation.md. (#5797)
This commit is contained in:
slfan1989
GitHub
parent
c13d92996d
commit
33b1677e9e
@ -157,7 +157,7 @@ Configuration
|
||||
|
||||
To configure the `YARN` to use the `Federation`, set the following property in the **conf/yarn-site.xml**:
|
||||
|
||||
###EVERYWHERE:
|
||||
### EVERYWHERE:
|
||||
|
||||
These are common configurations that should appear in the **conf/yarn-site.xml** at each machine in the federation.
|
||||
|
||||
@ -167,7 +167,7 @@ These are common configurations that should appear in the **conf/yarn-site.xml**
|
||||
|`yarn.federation.enabled` | `true` | Whether federation is enabled or not |
|
||||
|`yarn.resourcemanager.cluster-id` | `<unique-subcluster-id>` | The unique subcluster identifier for this RM (same as the one used for HA). |
|
||||
|
||||
####State-Store:
|
||||
#### State-Store:
|
||||
|
||||
Currently, we support ZooKeeper and SQL based implementations of the state-store.
|
||||
|
||||
@ -192,7 +192,7 @@ SQL: one must setup the following parameters:
|
||||
|
||||
We provide scripts for **MySQL** and **Microsoft SQL Server**.
|
||||
|
||||
> MySQL
|
||||
- MySQL
|
||||
|
||||
For MySQL, one must download the latest jar version 5.x from [MVN Repository](https://mvnrepository.com/artifact/mysql/mysql-connector-java) and add it to the CLASSPATH.
|
||||
Then the DB schema is created by executing the following SQL scripts in the database:
|
||||
@ -211,7 +211,7 @@ In the same directory we provide scripts to drop the Stored Procedures, the Tabl
|
||||
1. MySQL 5.7
|
||||
2. MySQL 8.0
|
||||
|
||||
> Microsoft SQL Server
|
||||
- Microsoft SQL Server
|
||||
|
||||
For SQL-Server, the process is similar, but the jdbc driver is already included.
|
||||
SQL-Server scripts are located in **sbin/FederationStateStore/SQLServer/**.
|
||||
@ -221,10 +221,10 @@ SQL-Server scripts are located in **sbin/FederationStateStore/SQLServer/**.
|
||||
1. SQL Server 2008 R2 Enterprise
|
||||
2. SQL Server 2012 Enterprise
|
||||
3. SQL Server 2016 Enterprise
|
||||
4. SQL Server 2017 Enterprise
|
||||
4. SQL Server 2017 Enterprise
|
||||
5. SQL Server 2019 Enterprise
|
||||
|
||||
####Optional:
|
||||
#### Optional:
|
||||
|
||||
| Property | Example | Description |
|
||||
|:---- |:---- |:---- |
|
||||
@ -235,7 +235,88 @@ SQL-Server scripts are located in **sbin/FederationStateStore/SQLServer/**.
|
||||
|`yarn.federation.subcluster-resolver.class` | `org.apache.hadoop.yarn.server.federation.resolver.DefaultSubClusterResolverImpl` | The class used to resolve which subcluster a node belongs to, and which subcluster(s) a rack belongs to. |
|
||||
|`yarn.federation.machine-list` | `<path of machine-list file>` | Path of machine-list file used by `SubClusterResolver`. Each line of the file is a node with sub-cluster and rack information. Below is the example: <br/> <br/> node1, subcluster1, rack1 <br/> node2, subcluster2, rack1 <br/> node3, subcluster3, rack2 <br/> node4, subcluster3, rack2 |
|
||||
|
||||
###ON RMs:
|
||||
**How to configure the policy-manager?**
|
||||
|
||||
- Router Policy
|
||||
|
||||
Router Policy defines the logic for determining the routing of an application submission and determines the HomeSubCluster for the application.
|
||||
|
||||
- HashBasedRouterPolicy
|
||||
- This policy selects a sub-cluster based on the hash of the job's queue name. It is particularly useful when dealing with a large number of queues in a system, providing a default behavior. Furthermore, it ensures that all jobs belonging to the same queue are consistently mapped to the same sub-cluster, which can improve locality and performance.
|
||||
- LoadBasedRouterPolicy
|
||||
- This is a simplified load-balancing policy implementation. The policy utilizes binary weights (0/1 values) to enable or disable each sub-cluster. It selects the sub-cluster with the least load to forward the application traffic, ensuring optimal distribution.
|
||||
- LocalityRouterPolicy
|
||||
- This policy selects the sub-cluster based on the node specified by the client for running its application. Follows these conditions:
|
||||
- It succeeds if
|
||||
- There are three AMContainerResourceRequests in the order NODE, RACK, ANY
|
||||
- Falls back to WeightedRandomRouterPolicy
|
||||
- Null or empty AMContainerResourceRequests;
|
||||
- One AMContainerResourceRequests and it has ANY as ResourceName;
|
||||
- The node is in blacklisted SubClusters.
|
||||
- It fails if
|
||||
- The node does not exist and RelaxLocality is False;
|
||||
- We have an invalid number (not 0, 1 or 3) resource requests
|
||||
- RejectRouterPolicy
|
||||
- This policy simply rejects all incoming requests.
|
||||
- UniformRandomRouterPolicy
|
||||
- This simple policy picks at uniform random among any of the currently active sub-clusters. This policy is easy to use and good for testing.
|
||||
- WeightedRandomRouterPolicy
|
||||
- This policy implements a weighted random sample among currently active sub-clusters.
|
||||
|
||||
- AMRM Policy
|
||||
|
||||
AMRM Proxy defines the logic to split the resource request list received by AM among RMs.
|
||||
|
||||
- BroadcastAMRMProxyPolicy
|
||||
- This policy simply broadcasts each ResourceRequest to all the available sub-clusters.
|
||||
- HomeAMRMProxyPolicy
|
||||
- This policy simply sends the ResourceRequest to the home sub-cluster.
|
||||
- LocalityMulticastAMRMProxyPolicy
|
||||
- Host localized ResourceRequests are always forwarded to the RM that owns the corresponding node, based on the feedback of a SubClusterResolver
|
||||
If the SubClusterResolver cannot resolve this node we default to forwarding the ResourceRequest to the home sub-cluster.
|
||||
- Rack localized ResourceRequests are forwarded to the RMs that owns the corresponding rack. Note that in some deployments each rack could be
|
||||
striped across multiple RMs. This policy respects that. If the SubClusterResolver cannot resolve this rack we default to forwarding
|
||||
the ResourceRequest to the home sub-cluster.
|
||||
- ANY requests corresponding to node/rack local requests are forwarded only to the set of RMs that owns the corresponding localized requests. The number of
|
||||
containers listed in each ANY is proportional to the number of localized container requests (associated to this ANY via the same allocateRequestId).
|
||||
- RejectAMRMProxyPolicy
|
||||
- This policy simply rejects all requests. Useful to prevent apps from accessing any sub-cluster.
|
||||
|
||||
- Policy Manager
|
||||
|
||||
The PolicyManager is providing a combination of RouterPolicy and AMRMPolicy.
|
||||
|
||||
We can set policy-manager like this:
|
||||
```xml
|
||||
<!--
|
||||
We provide 6 PolicyManagers, They have a common prefix: org.apache.hadoop.yarn.server.federation.policies.manager
|
||||
1. HashBroadcastPolicyManager
|
||||
2. HomePolicyManager
|
||||
3. PriorityBroadcastPolicyManager
|
||||
4. RejectAllPolicyManager
|
||||
5. UniformBroadcastPolicyManager
|
||||
6. WeightedLocalityPolicyManager
|
||||
-->
|
||||
<property>
|
||||
<name>yarn.federation.policy-manager</name>
|
||||
<value>org.apache.hadoop.yarn.server.federation.policies.manager.HashBroadcastPolicyManager</value>
|
||||
</property>
|
||||
```
|
||||
|
||||
- HashBroadcastPolicyManager
|
||||
- Policy that routes applications via hashing of their queuename, and broadcast resource requests. This picks a HashBasedRouterPolicy for the router and a BroadcastAMRMProxyPolicy for the amrmproxy as they are designed to work together.
|
||||
- HomePolicyManager
|
||||
- Policy manager which uses the UniformRandomRouterPolicy for the Router and HomeAMRMProxyPolicy as the AMRMProxy policy to find the RM.
|
||||
- PriorityBroadcastPolicyManager
|
||||
- Policy that allows operator to configure "weights" for routing. This picks a PriorityRouterPolicy for the router and a BroadcastAMRMProxyPolicy for the amrmproxy as they are designed to work together.
|
||||
- RejectAllPolicyManager
|
||||
- This policy rejects all requests for both router and amrmproxy routing. This picks a RejectRouterPolicy for the router and a RejectAMRMProxyPolicy for the amrmproxy as they are designed to work together.
|
||||
- UniformBroadcastPolicyManager
|
||||
- It combines the basic policies: UniformRandomRouterPolicy and BroadcastAMRMProxyPolicy, which are designed to work together and "spread" the load among sub-clusters uniformly. This simple policy might impose heavy load on the RMs and return more containers than a job requested as all requests are (replicated and) broadcasted.
|
||||
- WeightedLocalityPolicyManager
|
||||
- Policy that allows operator to configure "weights" for routing. This picks a LocalityRouterPolicy for the router and a LocalityMulticastAMRMProxyPolicy for the amrmproxy as they are designed to work together.
|
||||
|
||||
### ON RMs:
|
||||
|
||||
These are extra configurations that should appear in the **conf/yarn-site.xml** at each ResourceManager.
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user