hc-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Ortwin Gl├╝ck <...@odi.ch>
Subject Re: [HttpCommon] The trouble with NIO is not about performance
Date Mon, 22 Aug 2005 07:36:58 GMT
I think what we are currently finding out about NIO and old IO should be 
documented on a Wiki page somewhere. It may be a good reference for 
anyone who wants to really optimize the use of HttpClient for their use 
pattern.

Odi

Sam Berlin wrote:
> Hi Oleg,
> 
> Sorry I cannot read/reply more frequently -- I'm in the middle of a
> trip across the states.
> 
> It may be a pit premature to say that NIO will always be inferior to
> classic I/O under a thousand connections.  The result entirely depends
> on type of machine the program is running on.  On beefed-up servers
> that aren't doing much else, classic I/O will always be easier.  On
> normal consumer boxes, non-blocking I/O becomes a better choice almost
> immediately.
> 
> I don't have the capability to run your sample code right now, but I
> never noticed such a drastic performance decrease when converting
> classic I/O to non-blocking code before.  In fact, the conversion
> significantly increased performance because less threads were waiting
> on locks and there was much less context-switches.
> 
> Tomcat is pretty much designed to always be acting on a
> server-machine, but HttpClient has the potential to work within any
> application, some of which may be designed for casual users.  It would
> be worthwhile, for those applications, to be able to use HttpClient
> with a non-blocking engine.
> 
> Thanks,
>  Sam


-- 
[web]  http://www.odi.ch/
[blog] http://www.odi.ch/weblog/
[pgp]  key 0x81CF3416
        finger print F2B1 B21F F056 D53E 5D79  A5AF 02BE 70F5 81CF 3416

---------------------------------------------------------------------
To unsubscribe, e-mail: httpclient-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: httpclient-dev-help@jakarta.apache.org


Mime
View raw message