Mailing-List: contact yarn-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Date: Sat, 4 Feb 2017 01:45:51 +0000 (UTC)
From: "He Tianyi (JIRA)" <jira@apache.org>
To: yarn-issues@hadoop.apache.org
Message-ID: <JIRA.13035439.1484644028000.31969.1486172751648@Atlassian.JIRA>
In-Reply-To: <JIRA.13035439.1484644028000@Atlassian.JIRA>
References: <JIRA.13035439.1484644028000@Atlassian.JIRA> <JIRA.13035439.1484644028106@jira-lw-us.apache.org>
Subject: [jira] [Updated] (YARN-6101) Delay scheduling for node resource
 balance
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
archived-at: Sat, 04 Feb 2017 01:45:57 -0000


     [ https://issues.apache.org/jira/browse/YARN-6101?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

He Tianyi updated YARN-6101:
----------------------------
    Description: 
We observed that, in today's cluster, usage of Spark has dramatically increased. 
This introduced a new issue that CPU/MEM utilization for single node may become imbalanced due to Spark is generally more memory intensive. For example, after a node with capability (48 cores, 192 GB memory) cannot satisfy a (1 core, 2 GB memory) request if current used resource is (20 cores, 191 GB memory), with plenty of total available resource across the whole cluster.
A thought for avoiding the situation is to introduce some strategy during scheduling.
This JIRA proposes a delay-scheduling-alike approach to achieve better balance between different type of resources on each node.
The basic idea is consider dominant resource for each node, and when a scheduling opportunity on a particular node is offered to a resource request, better make sure the allocation is changing dominant resource of the node, or, in worst case, allocate at once when number of offered scheduling opportunities exceeds a certain number.
With YARN SLS and a simulation file with hybrid workload (MR+Spark), the approach improved cluster resource usage by nearly 5%. And after deployed to production, we observed a 8% improvement.

  was:
We observed that, in today's cluster, usage of Spark has dramatically increased. 
This introduced a new issue that CPU/MEM utilization for single node may become imbalanced due to Spark is generally more memory intensive. For example, after a node with capability (48 cores, 192 GB memory) cannot satisfy a (1 core, 2 GB memory) request if current used resource is (20 cores, 190 GB memory), with plenty of total available resource across the whole cluster.
A thought for avoiding the situation is to introduce some strategy during scheduling.
This JIRA proposes a delay-scheduling-alike approach to achieve better balance between different type of resources on each node.
The basic idea is consider dominant resource for each node, and when a scheduling opportunity on a particular node is offered to a resource request, better make sure the allocation is changing dominant resource of the node, or, in worst case, allocate at once when number of offered scheduling opportunities exceeds a certain number.
With YARN SLS and a simulation file with hybrid workload (MR+Spark), the approach improved cluster resource usage by nearly 5%. And after deployed to production, we observed a 8% improvement.


> Delay scheduling for node resource balance
> ------------------------------------------
>
>                 Key: YARN-6101
>                 URL: https://issues.apache.org/jira/browse/YARN-6101
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: fairscheduler
>            Reporter: He Tianyi
>            Priority: Minor
>         Attachments: YARN-6101.preliminary.0000.patch
>
>
> We observed that, in today's cluster, usage of Spark has dramatically increased. 
> This introduced a new issue that CPU/MEM utilization for single node may become imbalanced due to Spark is generally more memory intensive. For example, after a node with capability (48 cores, 192 GB memory) cannot satisfy a (1 core, 2 GB memory) request if current used resource is (20 cores, 191 GB memory), with plenty of total available resource across the whole cluster.
> A thought for avoiding the situation is to introduce some strategy during scheduling.
> This JIRA proposes a delay-scheduling-alike approach to achieve better balance between different type of resources on each node.
> The basic idea is consider dominant resource for each node, and when a scheduling opportunity on a particular node is offered to a resource request, better make sure the allocation is changing dominant resource of the node, or, in worst case, allocate at once when number of offered scheduling opportunities exceeds a certain number.
> With YARN SLS and a simulation file with hybrid workload (MR+Spark), the approach improved cluster resource usage by nearly 5%. And after deployed to production, we observed a 8% improvement.


--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org