On Fri, Dec 02, 2005 at 09:23:33PM +0100, JaniD++ wrote:
> I have 4 HW-equal disk nodes, what i use with NBD.
> When i try to get the top performance, i seriously found the network as the
> bottleneck.
What motherboard are you using? On my test box I am able to get 100MB/s
reads over the network with nbd (granted that is with the file cached on
the server).
> 169: 18907824 0 IO-APIC-level libata, eth0
Shared interrupts? Bad...
> 177: 1144300306 0 IO-APIC-level eth1
Is eth1 the e1000? Try binding it to the second CPU by doing an
echo >/proc/irq/177 2
The e1000 driver also has several tunable options for its various
features. See drivers/net/e1000/e1000_param.c. Disabling interrupt
rate throttling might help.
-ben
--
"You know, I've seen some crystals do some pretty trippy shit, man."
Don't Email: <[EMAIL PROTECTED]>.
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
