Mailing-List: contact yarn-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Date: Wed, 12 Jul 2017 18:30:01 +0000 (UTC)
From: "Wangda Tan (JIRA)" <jira@apache.org>
To: yarn-issues@hadoop.apache.org
Message-ID: <JIRA.13012026.1476371202000.231429.1499884201142@Atlassian.JIRA>
In-Reply-To: <JIRA.13012026.1476371202000@Atlassian.JIRA>
References: <JIRA.13012026.1476371202000@Atlassian.JIRA> <JIRA.13012026.1476371202104@jira-lw-us.apache.org>
Subject: [jira] [Updated] (YARN-5731) Preemption does not work in few corner
 cases when reservations are placed
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
archived-at: Wed, 12 Jul 2017 18:30:07 -0000


     [ https://issues.apache.org/jira/browse/YARN-5731?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Wangda Tan updated YARN-5731:
-----------------------------
    Description: 
YARN Capacity Scheduler does not kick Preemption under below scenario.
Two queues A and B each with 50% capacity and 100% maximum capacity and user limit factor 2. Minimum Container size is 1536MB and total cluster resource is 40GB. Now submit the first job which needs 1536MB for AM and 9 task containers each 4.5GB to queue A. Job will get 8 containers total (AM 1536MB + 7 * 4.5GB = 33GB) and the cluster usage is 93.8% and the job has reserved a container of 4.5GB.
Now when next job (1536MB for AM and 9 task containers each 4.5GB) is submitted onto queue B. The job hangs in ACCEPTED state forever and RM scheduler never kicks in Preemption. (RM UI Image 2 attached)
Test Case:

./spark-submit --class org.apache.spark.examples.SparkPi --master yarn-client --queue A --executor-memory 4G --executor-cores 4 --num-executors 9 ../lib/spark-examples*.jar 1000000

After a minute..

./spark-submit --class org.apache.spark.examples.SparkPi --master yarn-client --queue B --executor-memory 4G --executor-cores 4 --num-executors 9 ../lib/spark-examples*.jar 1000000

Credit to: [~Prabhu Joseph] for bug investigation and troubleshooting.


  was:
YARN Capacity Scheduler does not kick Preemption under below scenario.
Two queues A and B each with 50% capacity and 100% maximum capacity and user limit factor 2. Minimum Container size is 1536MB and total cluster resource is 40GB. Now submit the first job which needs 1536MB for AM and 9 task containers each 4.5GB to queue A. Job will get 8 containers total (AM 1536MB + 7 * 4.5GB = 33GB) and the cluster usage is 93.8% and the job has reserved a container of 4.5GB.
Now when next job (1536MB for AM and 9 task containers each 4.5GB) is submitted onto queue B. The job hangs in ACCEPTED state forever and RM scheduler never kicks in Preemption. (RM UI Image 2 attached)
Test Case:

./spark-submit --class org.apache.spark.examples.SparkPi --master yarn-client --queue A --executor-memory 4G --executor-cores 4 --num-executors 9 ../lib/spark-examples*.jar 1000000

After a minute..

./spark-submit --class org.apache.spark.examples.SparkPi --master yarn-client --queue B --executor-memory 4G --executor-cores 4 --num-executors 9 ../lib/spark-examples*.jar 1000000


> Preemption does not work in few corner cases when reservations are placed
> -------------------------------------------------------------------------
>
>                 Key: YARN-5731
>                 URL: https://issues.apache.org/jira/browse/YARN-5731
>             Project: Hadoop YARN
>          Issue Type: Bug
>          Components: capacity scheduler
>    Affects Versions: 2.8.0
>            Reporter: Sunil G
>            Assignee: Sunil G
>         Attachments: YARN-5731-branch-2.8.001.patch
>
>
> YARN Capacity Scheduler does not kick Preemption under below scenario.
> Two queues A and B each with 50% capacity and 100% maximum capacity and user limit factor 2. Minimum Container size is 1536MB and total cluster resource is 40GB. Now submit the first job which needs 1536MB for AM and 9 task containers each 4.5GB to queue A. Job will get 8 containers total (AM 1536MB + 7 * 4.5GB = 33GB) and the cluster usage is 93.8% and the job has reserved a container of 4.5GB.
> Now when next job (1536MB for AM and 9 task containers each 4.5GB) is submitted onto queue B. The job hangs in ACCEPTED state forever and RM scheduler never kicks in Preemption. (RM UI Image 2 attached)
> Test Case:
> ./spark-submit --class org.apache.spark.examples.SparkPi --master yarn-client --queue A --executor-memory 4G --executor-cores 4 --num-executors 9 ../lib/spark-examples*.jar 1000000
> After a minute..
> ./spark-submit --class org.apache.spark.examples.SparkPi --master yarn-client --queue B --executor-memory 4G --executor-cores 4 --num-executors 9 ../lib/spark-examples*.jar 1000000
> Credit to: [~Prabhu Joseph] for bug investigation and troubleshooting.


--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

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