Complete.Org: Mailing Lists: Archives: discussion: October 2001:
[aclug-L] FW: Non-uniform memory access

[aclug-L] FW: Non-uniform memory access

[Top] [All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index] [Thread Index]
To: "Aclug Discussion" <discussion@xxxxxxxxx>
Subject: [aclug-L] FW: Non-uniform memory access
From: "Dale W Hodge" <dwh@xxxxxxxxxxxxxxxx>
Date: Fri, 19 Oct 2001 09:41:22 -0500
Reply-to: discussion@xxxxxxxxx

LINUX TIPS AND TRICKS --- October 19, 2001
Published by -- changing the way you view IT


* This week, Danny presents one of the key features of the imminent 2.5 
  kernel called non-uniform memory access (NUMA). 

By Danny Kalev

SMP in a Nutshell
In a previous newsletter (, 
I presented the principles of symmetric multiprocessing (SMP). An SMP 
system combines multiple processors that operate under a single 
operating system and access each other's memory over a common bus. 
However, SMP's scalability is rather limited; once the system includes 
more than 16 processors, performance usually deteriorates. The problem 
lies with the throughput of the shared bus that connects the processors 
to memory devices. As the number of processors increases, the bus 
becomes saturated and turns into a performance bottleneck. 

Enter NUMA
NUMA is a relatively new method of configuring a cluster of processors 
in a multiprocessor system so that they share memory locally thereby 
improving performance and users' ability to expand the system beyond 
the inherent limits of SMP. NUMA adds an intermediate level of memory 
shared among a few processors so that most data accesses don't have to 
travel on the main bus. NUMA defines three cache layers, where a lower 
number indicates a faster cache: L1, L2 and L3. When a processor looks 
for data, it first looks in the L1 cache on the processor itself (MMX 
processes, for instance, have a private 32KB cache each), then on a 
larger L2 cache chip nearby, then on the L3 cache that NUMA provides. 
Only if all the previous lookups have failed does the processor seek 
the data in the external memory, which is significantly slower. Put 
differently, NUMA introduces an additional cache layer that reduces the 
number of accesses to the external memory.

NUMA-enabled SMP
A typical NUMA-based machine consists of multiple clusters, or units. 
Each unit consists of four processors interconnected by a local bus to 
a shared memory (the L3 cache) on a single motherboard. A common SMP 
bus interconnects several units thus forming an SMP system. Such a 
system may contain up to 256 processors. NUMA views each of these units 
as a node in the interconnection network. However, a user-level 
application views all the individual cluster's memories as a single 

For further information about NUMA see:

About the author(s)
Danny Kalev is a system analyst and software engineer with more than 10 
years of experience, specializing in C++ and object-oriented analysis 
and design on various platforms including VMS, DOS, Windows, Unix, and 
Linux. His technical interests involve code optimization, networking, 
and distributed computing. He is also a member of the ANSI C++ 
standardization committee and the author of ANSI/ISO C++ Professional 
Programmer's Handbook (Que, 1999). Danny can be reached at 


What is NUMA?

NUMA architectures and user level scheduling - a short introduction

Non Uniform Memory Access (NUMA)

The Linux 2.5 kernel summit



Index of Linux Tips and Tricks

Command Shell Options

Shell Configuration Files


- Go to:
- Click on "View my newsletters" to log in and manage your account
- To subscribe, check the box next to the newsletter
- To unsubscribe, uncheck the box next to the newsletter 
- When finished, click submit

Questions? Please e-mail customer service at: mailto:support@xxxxxxxxxxx


* Editorial: Andrew Santosusso, Newsletter Editor, 
* Advertising: Clare O'Brien, Vice President of Sales, 
* Recruitment advertising: Jamie Swartz, Eastern, Regional Sales 
  Manager, jamie_swartz@xxxxxxxxxxx or Paul Duthie, Western Regional 
  Sales Manager, paul_duthie@xxxxxxxxxxxxx
* Other inquiries: Jodie Naze, Senior Product Marketing Manager, 


Copyright 2001, Inc., All Rights Reserved.

-- This is the discussion@xxxxxxxxx list.  To unsubscribe,

[Prev in Thread] Current Thread [Next in Thread]
  • [aclug-L] FW: Non-uniform memory access, Dale W Hodge <=