[
https://issues.apache.org/jira/browse/TEZ-1752?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14529464#comment-14529464
]
Hitesh Shah edited comment on TEZ-1752 at 5/5/15 10:49 PM:
-----------------------------------------------------------
bq. Spoke to Rajesh offline about committing the patch into TEZ-2003 instead of
master for now, and hardening it there.
Given the earlier comment on this ( and also accounting for the patch splitting
comment ), does it make sense to back this out of 0.7 ? Is there any
dependency/reason for this to go into 0.7? May be worth waiting for 0.8 unless
this is a very safe change?
[~sseth] [~rajesh.balamohan] comments?
was (Author: hitesh):
bq. Spoke to Rajesh offline about committing the patch into TEZ-2003 instead of
master for now, and hardening it there.
Given the earlier comment on this ( and also accounting for the patch splitting
comment ), does it make sense to back this out of 0.7 ? Is there any
dependency/reason for this to go into 0.7? May be worth waiting for 0.8 unless
this is a very safe change?
> Inputs / Outputs in the Runtime library should be interruptable
> ---------------------------------------------------------------
>
> Key: TEZ-1752
> URL: https://issues.apache.org/jira/browse/TEZ-1752
> Project: Apache Tez
> Issue Type: Improvement
> Reporter: Siddharth Seth
> Assignee: Rajesh Balamohan
> Fix For: 0.7.0
>
> Attachments: TEZ-1752.1.patch, TEZ-1752.2.patch, TEZ-1752.3.patch,
> TEZ-1752.4.patch, TEZ-1752.5.patch, TEZ-1752.master.patch
>
>
> Not possible to preempt tasks without killing containers without this.
> There's still the problem of Processors not supporting interrupts. We may
> need API enhancements to either query IPOs on whether they are interrupbtible.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
