----------------------------------------------------------------
BEFORE YOU POST, search the faq at <http://java.apache.org/faq/>
WHEN YOU POST, include all relevant version numbers, log files,
and configuration files. Don't make us guess your problem!!!
----------------------------------------------------------------
I have a related question. I cannot get ibm118 version 1991013 to work with
Apache Jserv. 1.0fc. It just cannot start the jserv. Is there any way to get
around it?
Thanks
Also, anybody using it for production? Is it very stable? I use the 1990910
version and it just used up all my socket connection and kill the server.
Thanks
TK
-----Original Message-----
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED]]On Behalf Of Rupert Hülsey
Sent: Wednesday, November 03, 1999 7:06 PM
To: Java Apache Users
Subject: Re: ibm 118 vs. blackdown 117_v3
----------------------------------------------------------------
BEFORE YOU POST, search the faq at <http://java.apache.org/faq/>
WHEN YOU POST, include all relevant version numbers, log files,
and configuration files. Don't make us guess your problem!!!
----------------------------------------------------------------
Hi,
Michael asked which kind threads one should prefer;
we did a very simple experiment using the IBM JIT and the blackdown JDK in
two
absolutely indentical environments (the same computers and so on). What we
firgured out was the following:
it took the blackdown JDK 8000 milis to display the servlet (it did
something
like 100 million multiplications ...), the IBM JIT did the same in 500 milis
(no, I didnt mess up the zeros ;-) )
Well this means the IBM JIT is 16 times faster? At least it's faster.
Concerning
the native thread/green thread thing:
IBM uses native threads -this could be much faster because the whole
multithread-thing on linux isn't that perfect like multiprocessing? This
means,
Linux is great in handling lots of processes, only good in handling threads,
I
would think.
What is even more intresting is the fact that more and more multiprocessor
machines become available - this could mean, that the 'pseudo processes' IBM
JIT
produces are much more easyer to handle for the OS than the loadbalancing
using
green threads.
Well, thats what we found out with 'quick benchmarking' ;-)
Cheers,
Rupert
--
--------------------------------------------------------------
Please read the FAQ! <http://java.apache.org/faq/>
To subscribe: [EMAIL PROTECTED]
To unsubscribe: [EMAIL PROTECTED]
Archives and Other: <http://java.apache.org/main/mail.html>
Problems?: [EMAIL PROTECTED]
--
--------------------------------------------------------------
Please read the FAQ! <http://java.apache.org/faq/>
To subscribe: [EMAIL PROTECTED]
To unsubscribe: [EMAIL PROTECTED]
Archives and Other: <http://java.apache.org/main/mail.html>
Problems?: [EMAIL PROTECTED]
