Bug 105349 - With an SMP kernel NUMA should be enabled for increased memory performance
Summary: With an SMP kernel NUMA should be enabled for increased memory performance
Status: CLOSED NOTABUG
Alias: None
Product: Red Hat Enterprise Linux 3
Classification: Red Hat
Component: kernel
Version: 3.0
Hardware: All
OS: Linux
medium
medium
Target Milestone: ---
Assignee: Arjan van de Ven
QA Contact: David Lawrence
URL:
Whiteboard:
Keywords:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2003-09-25 09:40 UTC by Albert Fluegel
Modified: 2007-11-30 22:06 UTC (History)
0 users

(edit)
Clone Of:
(edit)
Last Closed: 2003-09-26 08:09:40 UTC


Attachments (Terms of Use)

Description Albert Fluegel 2003-09-25 09:40:03 UTC
Description of problem:
Not a problem, but a feature request.
Some guy from IBM stated, that with NUMA enabled on
an Opteron SMP system memory performance is sped up
by up to 30%. Please set
CONFIG_K8_NUMA=y
CONFIG_ACPI_NUMA=y
in /usr/src/redhat/SOURCES/kernel-2.4.21-x86_64-smp.config

Version-Release number of selected component (if applicable):
2.4.21-1.1931.2.393

How reproducible:
N/A

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


Expected results:


Additional info:

Comment 1 Albert Fluegel 2003-09-25 15:17:41 UTC
the kernel cannot be built with NUMA support turned on.
Reason is a loop in #includes. First, the asm/mmzone.h
needs a definition from linux/mmzone.h . Including
linuz/mmzone.h before asm/mmzone.h leads to an error
because some wait_q_type is not defined. Reason is, that
mmzone.h and wait.h include each other.

Comment 2 Arjan van de Ven 2003-09-26 07:03:06 UTC
I wonder what the IBM person bases this on, especially since
1) Opteron systems hardly are NUMA
2) The kernel by default (including ours) does not have a lot of NUMA support
   (some other linux distros patch in a lot of this, which slows down the normal
case. gaining 30% relative to that is easier of course :)

Comment 3 Albert Fluegel 2003-09-26 07:41:57 UTC
AFAIK Opteron SMP systems are NUMA by design. Each part of the memory is
assigned to a CPU. When a CPU wants to access memory, that is assigned
to the other CPU, the access passes the memory controller of the other
CPU, what makes the access slower than a local one.
I really would like to benchmark this, but as explained i don't get
the kernel built due to type definition problems :-(


Comment 4 Arjan van de Ven 2003-09-26 07:45:21 UTC
They are NUMA, however the NUMA factor is very very close to 1 (unlike some
other boxes where the NUMA speed is in the order of 15); academic research has
shown that a numa factor of 2 is about the turnover point for the OS doing
special NUMA hacks. A performance improvement of 30% is certainly believable for
systems with a large NUMA factor (like the IBM x440) but I have a hard time
believing it for real world use on AMD Opteron machines.


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