New system, higher active connections?

Joseph Mack NA3T jmack at wm7d.net
Fri Oct 13 17:49:53 BST 2006


On Fri, 13 Oct 2006, H. Wade Minter wrote:

>> someone else reported the same problem a little while 
>> ago. The only thing I can think is that RH has done 
>> something with the code that we don't know about. If your 
>> system is otherwise behaving OK, you could ignore 
>> it/recalibrate your ideas of what it does.

do the numbers differ from the expected numbers by about 
2^32? (in which case the code was compiled against some 
weird header).

> Would the code changes (if they're there) be in the 
> kernel/networking level, or the packaged LVS?

there's the kernel code and then there's the userspace code 
(ipvsadm) which flips bits in the kernel code.

> To put it another way, would it gain us anything to build 
> ipvsadm-1.24-6.src.rpm from linuxvirtualserver.org and use 
> that instead of the ipvsadm-1.24-7.2.1 package from 
> Fedora?

who knows. worth a try.

Joe

-- 
Joseph Mack NA3T EME(B,D), FM05lw North Carolina
jmack (at) wm7d (dot) net - azimuthal equidistant map
generator at http://www.wm7d.net/azproj.shtml
Homepage http://www.austintek.com/ It's GNU/Linux!


More information about the lvs-users mailing list