TCP stack throughput

Javier París Fernández paris@REDACTED
Wed Jul 27 13:33:32 CEST 2005


On Wed, Jul 27, 2005 at 01:20:11AM -0500, Scott Lystig Fritchie wrote:
> I'm sorry, I don't have Javier's original message in my mailbox.
> 
> >>>>> "uw" == Ulf Wiger <ulf@REDACTED> writes:
> 
> uw> Den 2005-07-19 19:39:12 skrev Javier París Fernández
> uw> <paris@REDACTED>:
> >> I observed several funny things. The time spent processing the
> >> connections seems to go up exponentially, but it is not limited by
> >> cpu, which was always under 50%. I don't know what is throttling
> >> it.
> 
> Are you using Linux, and if yes, which Linux distribution are you
> using?  I was very surprised to discover that the "top" program
> distributed with Red Hat Advanced Server 3.0, when running on an Intel
> CPU with Hyper-Threading enabled(*), will report that:
> 
> main()
> {
> 	int i;
> 
> 	for (;;) {
> 		i++;
> 	}
> }
> 
> ... will only consume 50% CPU time.

Well, in an HT CPU this is not true, but in a true SMP system
it could be seen as correct. After all, half the CPU capacity of
the system is not used.

By the way, the system is Debian Linux, and the cpu has HT, but a
loop similar to the one you put above shows 100% CPU usage in top.

Regards,
Javier.




More information about the erlang-questions mailing list