| 1 |
On Thu, Apr 10, 2003 at 09:44:50AM +0200, Eske Christiansen wrote: |
| 2 |
> On Thu, Apr 10, 2003 at 07:06:28AM +0800, William Kenworthy wrote: |
| 3 |
> > But is it a "real" problem or just the way you have configured the |
| 4 |
> > kernel? One respondent suggested low latency: have you configured the |
| 5 |
> > kernel the same as the redhat one? Is large memory selected in gentoo |
| 6 |
> > and not redhat etc? |
| 7 |
> |
| 8 |
> Don't you think that a syscall to tcp select that is 5 times slower is a |
| 9 |
> problem. I do. |
| 10 |
|
| 11 |
P4's are slow at syscalls aren't they? I'm pretty sure that Linus has commented |
| 12 |
on lkml and dri-dev about this issue. Maybe they've addressed this in redhat's kernel? |
| 13 |
Maybe the increased time is for a good reason? |
| 14 |
|
| 15 |
28 microseconds is what %age of a typical web server connection processing time? |
| 16 |
|
| 17 |
> If the gentoo kernel is not best performance kernel that is offered in gentoo |
| 18 |
> don't you think that an update to the installation text is in order. |
| 19 |
|
| 20 |
Yes, but one benchmark measured by one person with one comment of "what I want |
| 21 |
gentoo for is a web server" is hardly a basis for deciding "best performance |
| 22 |
kernel" is it? It's not even a basis for deciding what's best for a server. |
| 23 |
|
| 24 |
-- |
| 25 |
Michael. |
| 26 |
|
| 27 |
-- |
| 28 |
gentoo-dev@g.o mailing list |
Archives