Bug 1036065

Summary: IRQBALANCE_BANNED_CPUS doesn't work
Product: Red Hat Enterprise Linux 6 Reporter: James Hogarth <james.hogarth>
Component: irqbalanceAssignee: Petr Holasek <pholasek>
Status: CLOSED DUPLICATE QA Contact: Red Hat Kernel QE team <kernel-qe>
Severity: urgent Docs Contact:
Priority: urgent    
Version: 6.5CC: dhoward, dsulliva, jeder
Target Milestone: rc   
Target Release: ---   
Hardware: Unspecified   
OS: Unspecified   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2014-01-23 13:40:55 UTC Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:

Description James Hogarth 2013-11-29 10:32:52 UTC 
Description of problem:
The issue is that in activate.c, applied_mask variable gets set to the cpu mask of the "local_cpus" value of the device. This ignores anything in banned_cpus.

So, made the change in the attached patch, which basically just does a cpus_andnot and makes sure that the resulting mask isn't 0.

Version-Release number of selected component (if applicable):
1.0.4-4

How reproducible:
Always

Steps to Reproduce:
1. Follow steps upstream


Actual results:
Specific CPU's won't be banned in a NUMA setup

Expected results:
Specific CPU's be banned in a NUMA setup

Additional info:
https://code.google.com/p/irqbalance/issues/detail?id=43
Fixed upstream in 1.0.6 git commit 1d8948271e2e81a7155ebe6c1b0abbead75416a