Bug 696422 - [SGI 6.2 FEAT] UV: add smp_affinity_list
Summary: [SGI 6.2 FEAT] UV: add smp_affinity_list
Keywords:
Status: CLOSED ERRATA
Alias: None
Product: Red Hat Enterprise Linux 6
Classification: Red Hat
Component: kernel
Version: 6.2
Hardware: x86_64
OS: Linux
medium
medium
Target Milestone: rc
: 6.2
Assignee: George Beshers
QA Contact: Petr Beňas
URL:
Whiteboard:
Depends On:
Blocks: 652290 652291
TreeView+ depends on / blocked
 
Reported: 2011-04-14 03:20 UTC by George Beshers
Modified: 2015-01-04 23:00 UTC (History)
7 users (show)

Fixed In Version: kernel-2.6.32-169.el6
Doc Type: Enhancement
Doc Text:
Clone Of:
Environment:
Last Closed: 2011-12-06 13:06:53 UTC
Target Upstream Version:


Attachments (Terms of Use)


Links
System ID Private Priority Status Summary Last Updated
Red Hat Product Errata RHSA-2011:1530 0 normal SHIPPED_LIVE Moderate: Red Hat Enterprise Linux 6 kernel security, bug fix and enhancement update 2011-12-06 01:45:35 UTC

Description George Beshers 2011-04-14 03:20:11 UTC
Description of problem:

1. Feature Overview:
   a) Name of feature:
      UV: add smp_affinity_list 

   b) Feature Description:
      Attempting to set irq affinity where there is a large amount of
      cpus present on a system is difficult when you have to hand create
      the cpu bit masks.  Add a _list variant of the command.



2. Feature Details:
   a) Architectures:
      64-bit Intel EM64T

   b) Bugzilla Dependencies:
      none

   c) Drivers or hardware dependencies:


   d) Upstream acceptance information:
      Accepted into the -mm tree.

   e) External links:
      to be supplied

   f) Severity (H,M,L):
      high: we are relying on it for large UV1 and UV2 systems.

   g) Feature Needed by:


3. Business Justification:
   a) Why is this feature needed?
      It facilitates management of devices in large UV systems.

   b) What hardware does this enable?
      UV1 and UV2 SGI unique capability to move IRQs around

   c) Business impact?

   d) Other business drivers:

4. Primary contact at Red Hat, email, phone (chat)
   First_Name Last_Name
   xxx_xxxx
   Phone Number

5. Primary contact at Partner, email, phone (chat)
      Lori Gilbertson, loriann, 651-683-3433, N/A  
                                               
   Partner technical contact, email, phone, chat
      George Beshers, gbeshers/gbeshers, 508-212-6362, gbeshers



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


How reproducible:


Steps to Reproduce:
1.
2.
3.
  
Actual results:


Expected results:


Additional info:

Comment 2 RHEL Program Management 2011-04-14 06:02:34 UTC
Since RHEL 6.1 External Beta has begun, and this bug remains
unresolved, it has been rejected as it is not proposed as
exception or blocker.

Red Hat invites you to ask your support representative to
propose this request, if appropriate and relevant, in the
next release of Red Hat Enterprise Linux.

Comment 3 George Beshers 2011-06-16 14:18:02 UTC
The patch for this has been accepted upstream.

As I read comment #2 the NACK was for rhel6.1 not rhel6.2.
Given the information provided would you please assign
the BZ to me?

Thanks,
George

commit 4b060420a596095869a6d7849caa798d23839cd1
Author: Mike Travis <travis>
Date:   Tue May 24 17:13:12 2011 -0700

    bitmap, irq: add smp_affinity_list interface to /proc/irq

    Manually adjusting the smp_affinity for IRQ's becomes unwieldy when the
    cpu count is large.

    Setting smp affinity to cpus 256 to 263 would be:

        echo 000000ff,00000000,00000000,00000000,00000000,00000000,00000000,00000000 > smp_affinity

    instead of:

        echo 256-263 > smp_affinity_list

    Think about what it looks like for cpus around say, 4088 to 4095.

    We already have many alternate "list" interfaces:

    /sys/devices/system/cpu/cpuX/indexY/shared_cpu_list
    /sys/devices/system/cpu/cpuX/topology/thread_siblings_list
    /sys/devices/system/cpu/cpuX/topology/core_siblings_list
    /sys/devices/system/node/nodeX/cpulist
    /sys/devices/pci***/***/local_cpulist

    Add a companion interface, smp_affinity_list to use cpu lists instead of
    cpu maps.  This conforms to other companion interfaces where both a map
    and a list interface exists.

    This required adding a bitmap_parselist_user() function in a manner
    similar to the bitmap_parse_user() function.

    [akpm: make __bitmap_parselist() static]
    Signed-off-by: Mike Travis <travis>
    Cc: Thomas Gleixner <tglx>
    Cc: Jack Steiner <steiner>
    Cc: Lee Schermerhorn <lee.schermerhorn>
    Cc: Andy Shevchenko <andy.shevchenko>
    Signed-off-by: Andrew Morton <akpm>
    Signed-off-by: Linus Torvalds <torvalds>

Comment 4 Marizol Martinez 2011-06-27 20:43:02 UTC
George -- Per the flags, this BZ was reviewed by PM for RHEL 6.2 and was declined. It's currently being proposed for RHEL 6.3. Since the patch is upstream and you are willing to work on this item, can you please discuss with Peter for RHEL 6.2 inclusion? Thanks!

Comment 5 George Beshers 2011-07-11 12:47:11 UTC
Exception approved by PeterM.
Posted.

Comment 6 Aristeu Rozanski 2011-07-18 15:28:09 UTC
Patch(es) available on kernel-2.6.32-169.el6

Comment 10 Petr Beňas 2011-07-27 08:26:22 UTC
Reproduced in 2.6.32-168.el6.x86_64 and verified in 2.6.32-169.el6.x86_64.

Comment 11 errata-xmlrpc 2011-12-06 13:06:53 UTC
Since the problem described in this bug report should be
resolved in a recent advisory, it has been closed with a
resolution of ERRATA.

For information on the advisory, and where to find the updated
files, follow the link below.

If the solution does not work for you, open a new bug report.

http://rhn.redhat.com/errata/RHSA-2011-1530.html


Note You need to log in before you can comment on or make changes to this bug.