Fastream Technologies wrote:
> What I tried to explain was that if your program is TCP/IP-dense,
> then in order to take advantage of multi-cores, you MUST code MT.
That's true, but does that neccessarily mean that you MUST run socket
communication in multiple threads? I can think of many other bo
What I tried to explain was that if your program is TCP/IP-dense, then in
order to take advantage of multi-cores, you MUST code MT.
Regards,
SZ
On 10/11/07, Arno Garrels <[EMAIL PROTECTED]> wrote:
>
> Fastream Technologies wrote:
> > I test my ICS-based MT proxy with 20k connections on our dual
Sure but I do not have a serious async server. You can download our MT
server from our web site anytime for a test.
Regards,
SZ
On 10/11/07, Arno Garrels <[EMAIL PROTECTED]> wrote:
>
> Fastream Technologies wrote:
> > I test my ICS-based MT proxy with 20k connections on our dual-core
> > system
Fastream Technologies wrote:
> I test my ICS-based MT proxy with 20k connections on our dual-core
> system. It performs 2GBps, local-to-local. So that's one CPU
> performance basically since the tester also uses CPU! I would not
> imagine such performance with single thread.
Those numbers don't te
>> --- Original Message ---
>>> From: Fastream
> Technologies[mailto:[EMAIL PROTECTED]
>> Sent: 10/11/2007 10:08:16 AM
>> To : twsocket@elists.org
>> Cc :
>> Subject : RE: Re: [twsocket] TWSocketThrdServer friendly notice
>> whend
Message ---
>From: Fastream
Technologies[mailto:[EMAIL PROTECTED]
>Sent: 10/11/2007 10:08:16 AM
>To : twsocket@elists.org
>Cc :
>Subject : RE: Re: [twsocket] TWSocketThrdServer
friendly notice whendisconnecting.
>
>I test my ICS-based MT proxy with 20k connec
I test my ICS-based MT proxy with 20k connections on our dual-core system.
It performs 2GBps, local-to-local. So that's one CPU performance basically
since the tester also uses CPU! I would not imagine such performance with
single thread.
Best Regards,
SZ
On 10/11/07, [EMAIL PROTECTED] <[EMAIL
--- QUOTE: SZ
If you do not want the ability to use multi-cores for
communication threads,
then async is the way to go. But IMO, it is an ill
design since chipmakers
are talking about 64-core CPUs and 10Gbps networks.
--- END.
Thanks, SZ. At this point I'm not so much concerned
about complexity (
On 10/11/07, [EMAIL PROTECTED] <[EMAIL PROTECTED]> wrote:
>
> --- QUOTE: Arno Garrels
> This is untested code. Also FThreadList has to be
> made public. Note that OnMessage would fire in
> different thread contexts but a single handler for
> all is fine. Hope this helps.
> --- END.
>
> I'll look in
--- QUOTE: Arno Garrels
This is untested code. Also FThreadList has to be
made public. Note that OnMessage would fire in
different thread contexts but a single handler for
all is fine. Hope this helps.
--- END.
I'll look into it.
--- QUOTE: Arno Garrels
I think it isn't very fast, I tested once
Btw: Should read:
TMessageEvent = procedure(Sender: TObject; var Msg: TMessage; var Handled:
Boolean) of object;
--
To unsubscribe or change your settings for TWSocket mailing list
please goto http://www.elists.org/mailman/listinfo/twsocket
Visit our website at http://www.overbyte.be
DZ-Jay wrote:
> On Oct 11, 2007, at 06:47, Arno Garrels wrote:
>
>> Iterating thru Srv.Clients is not the way to go!! It is not
>> thread-save and will most likely throw strange AVs. Instead
>> iterate thru the thread-list and post a custom message to each
>> thread, the inside the thread iterate
On Oct 11, 2007, at 06:47, Arno Garrels wrote:
> Iterating thru Srv.Clients is not the way to go!! It is not
> thread-save and will most likely throw strange AVs. Instead
> iterate thru the thread-list and post a custom message to each
> thread, the inside the thread iterate thru each thread's
>
DZ-Jay wrote:
> Thanks, Wilfried. That's what I'm doing now. However, I'm doing it
>> from the end of the Execute() method of the worker thread, right
>> before
> destroying the server, like this:
>
> Procedure WorkerThread.Execute;
> Begin
>_InitializeSrv(); // create
>Try
> Srv.
14 matches
Mail list logo
