[XML-DEV Mailing List Archive Home] [By Thread] [By Date] [Recent Entries] [Reply To This Message]

Re: Exploiting multi-core CPUs during XML parsing

• To: Elliotte Harold <elharo@m...>
• Subject: Re: Exploiting multi-core CPUs during XML parsing
• From: "Andrew S. Townley" <andrew.townley@b...>
• Date: Sat, 01 Apr 2006 11:00:24 +0100
• Cc: Sean McGrath <sean.mcgrath@p...>, xml-dev@l...
• In-reply-to: <442E47C2.9070302@m...>
• References: <442E2A2A.1070003@p...> <1143878208.3107.46.camel@macross> <442E47C2.9070302@m...>

I thought about that (specifically the use of the facilities in the nio
package), but I figured that the original request was targeted at
environments other than Java.  Right now, Java's direct support for
multi-core CPUs is a little lacking (ref the parser thread from last
week or so).  If it was Java, I agree, you could use the approach you
suggest.

Is the JVM really smart enough to take appropriate advantage of a
filesystem that provided the capability Sean wanted?  In the perfect
world, you would have the kernel taking care of buffering/caching the
data for you so that it would be available to multiple user-process
threads, but as far as most OS's are concerned, they just see it as
another CPU.  On a somewhat tangential note, there was an article in the
May IEEE Computer magazine about the issues facing OS's around these new
chips [1].  Based on what I remember reading, I don't think you'd really
notice the difference in Java on today's OS platforms.

ast

[1] http://csdl2.computer.org/persagen/DLAbsToc.jsp?resourcePath=/dl/mags/co/&toc=comp/mags/co/2005/05/r5toc.xml&DOI=10.1109/MC.2005.160

On Sat, 2006-04-01 at 10:28, Elliotte Harold wrote:
> What about memory mapped files? If you can treat the file as an array, 
> it's just as easy to move backwards through the array as forwards.
> 
> For network applications you might have to have three threads: one to 
> fill a buffer without parsing, one to parse from the start of the 
> buffer, one to parse from the back once the buffer is fully loaded. 
> Presumably the fill thread could outrun the other two.
-- 
Join me in Dubrovnik, Croatia on May 8-10th when I will be speaking at
InfoSeCon 2006.  For more information, see www.infosecon.org.

***************************************************************************************************
The information in this email is confidential and may be legally privileged.  Access to this email by anyone other than the intended addressee is unauthorized.  If you are not the intended recipient of this message, any review, disclosure, copying, distribution, retention, or any action taken or omitted to be taken in reliance on it is prohibited and may be unlawful.  If you are not the intended recipient, please reply to or forward a copy of this message to the sender and delete the message, any attachments, and any copies thereof from your system.
***************************************************************************************************

• Follow-Ups:
  • Re: Exploiting multi-core CPUs during XML parsing
    • From: Liam Quin <liam@w...>

• References:
  • Exploiting multi-core CPUs during XML parsing
    • From: Sean McGrath <sean.mcgrath@p...>
  • Re: Exploiting multi-core CPUs during XML parsing
    • From: "Andrew S. Townley" <andrew.townley@b...>
  • Re: Exploiting multi-core CPUs during XML parsing
    • From: Elliotte Harold <elharo@m...>

• Prev by Date: RE: Re: Exploiting multi-core CPUs during XML parsing
• Next by Date: Unrequested unsubscription notifications?
• Previous by thread: Re: Exploiting multi-core CPUs during XML parsing
• Next by thread: Re: Exploiting multi-core CPUs during XML parsing
• Index(es):
  • Date
  • Thread