Bug 850474 - RFE add support to keep a claim alive for DAG Submissions.
Summary: RFE add support to keep a claim alive for DAG Submissions.
Keywords:
Status: CLOSED WONTFIX
Alias: None
Product: Red Hat Enterprise MRG
Classification: Red Hat
Component: condor
Version: Development
Hardware: All
OS: Linux
medium
high
Target Milestone: ---
: ---
Assignee: grid-maint-list
QA Contact: MRG Quality Engineering
URL:
Whiteboard:
Depends On:
Blocks: 845292
TreeView+ depends on / blocked
 
Reported: 2012-08-21 15:59 UTC by Timothy St. Clair
Modified: 2016-05-26 19:13 UTC (History)
3 users (show)

Fixed In Version: condor-7.8.2-0.3
Doc Type: Rebase: Enhancements Only
Doc Text:
Important: if this rebase also contains *bug fixes* (or contains only bug fixes), select the correct option from the Doc Type drop-down list. Rebase package(s) to version: condor-7.8 series Highlights and notable enhancements: When submitting DAGMan jobs users can now supply a +KeepClaimIdle parameter which allows a claim to stay active during the interim period where condor_dagman is submitting new jobs. This enables higher throughput in cases where claims are relinquished prior to new jobs being submitted.
Clone Of:
Environment:
Last Closed: 2016-05-26 19:13:01 UTC
Target Upstream Version:
Embargoed:

Attachments (Terms of Use)


Links
System ID Private Priority Status Summary Last Updated
Condor 2094 0 None None None 2012-08-21 15:59:05 UTC

Description Timothy St. Clair 2012-08-21 15:59:05 UTC 
A common use case which affects utilization is the case where the claim divy'd out to a DAG job was relinquished because DAGman had not submitted a new job in time for the it to be reused by the autocluster.  

This ticket is to capture the addition of 

  +KeepClaimIdle parameter 

which keeps the claim alive long enough so that it can be reused by a DAG
Comment 4 Anne-Louise Tangring 2016-05-26 19:13:01 UTC 
MRG-G is in maintenance only and only customer escalations will be addressed from this point forward. This issue can be re-opened if a customer escalation associated with this issue occurs.
Note You need to log in before you can comment on or make changes to this bug.