hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Sunil G (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-4576) Enhancement for tracking Blacklist in AM Launching
Date Thu, 21 Jan 2016 17:30:40 GMT

    [ https://issues.apache.org/jira/browse/YARN-4576?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15110961#comment-15110961

Sunil G commented on YARN-4576:

Thanks [~djp] for sharing the proposal fast. Skimmed through the doc and it looks fine. I
have few doubts in this.

1. Time Window for Blacklist
>> For AM launch failure, we can get diagnostics and error code as “DISKS_FAILED​”.
With a timer/service, RM may not be able to poke NM to give latest disk status, correct .
It can get this information via NM heartbeat. So  event trigger can be only NM heartbeat.
In this case do we need  timer thread to monitor. Coudl you pls help to elaborate. Pls correct
me if missed something.

2. Feature of Whitelist
>> This will be helpful. I think along with nodes, we can also support node-labels.
It may give more better use case scenario. 

I think rules for strict/loose whitelisting also to be clearly mentioned. Because same node
may be in app's blacklist or in global blacklist. Such cases, how the behavior should be for
strict/loose will be important.

> Enhancement for tracking Blacklist in AM Launching
> --------------------------------------------------
>                 Key: YARN-4576
>                 URL: https://issues.apache.org/jira/browse/YARN-4576
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: resourcemanager
>            Reporter: Junping Du
>            Assignee: Junping Du
>            Priority: Critical
>         Attachments: EnhancementAMLaunchingBlacklist.pdf
> Before YARN-2005, YARN blacklist mechanism is to track the bad nodes by AM:  If AM tried
to launch containers on a specific node get failed for several times, AM will blacklist this
node in future resource asking. This mechanism works fine for normal containers. However,
from our observation on behaviors of several clusters: if this problematic node launch AM
failed, then RM could pickup this problematic node to launch next AM attempts again and again
that cause application failure in case other functional nodes are busy. In normal case, the
customized healthy checker script cannot be so sensitive to mark node as unhealthy when one
or two containers get launched failed. 
> After YARN-2005, we can have a BlacklistManager in each RMapp, so those nodes who launching
AM attempts failed for specific application before will get blacklisted. To get rid of potential
risks that all nodes being blacklisted by BlacklistManager, a disable-failure-threshold is
involved to stop adding more nodes into blacklist if hit certain ratio already. 
> There are already some enhancements for this AM blacklist mechanism: YARN-4284 is to
address the more wider case for AM container get launched failure and YARN-4389 tries to make
configuration settings available for change by App to meet app specific requirement. However,
there are still several gaps to address more scenarios:
> 1. We may need a global blacklist instead of each app maintain a separated one. The reason
is: AM could get more chance to fail if other AM get failed before. A quick example is: in
a busy cluster, all nodes are busy except two problematic nodes: node a and node b, app1 already
submit and get failed in two AM attempts on a and b. app2 and other apps should wait for other
busy nodes rather than waste attempts on these two problematic nodes.
> 2. If AM container failure is recognized as global event instead app own issue, we should
consider the blacklist is not a permanent thing but with a specific time window. 
> 3. We could have user defined black list polices to address more possible cases and scenarios,
so it reasonable to make blacklist policy pluggable.
> 4. For some test scenario, we could have whitelist mechanism for AM launching.
> 5. Some minor issues: it sounds like NM reconnect won't refresh blacklist so far.
> Will try to address all issues here.

This message was sent by Atlassian JIRA

View raw message