[Spread-users] Wackamole IP takeover time

[Theo Schlossnagle]

Min Lu wrote:

>We seem to have all things running alright. But I have
>a question here. Has anyone done benchmarking on the
>IP takeover time on two-node Wackamole to see exactly
>how much time is needed to the virtual IP to be
>switched over(excluding applications). It seems to be
>reasonably fast, and I know it depends on the network
>conditions and physical network connections. I just
>need the numbers.
>  
>
The decision is instantaneous (few milliseconds), Actually bringing the 
IP online and arp spoofing is extremely fast as well (milliseconds 
again).  The only process that operates in the seconds range is the user 
configurable options  (hard coded in the last release and in 
wackamole.conf in the CVS tree)  If you environment is extremely stable 
you can achieve subsecond IP takeover times without much issue.

In my production environments, I range this from 2 to 5 seconds to be on 
the safe side -- machines and networks don't alwas act as expected and 
it is better to give them the benefit of the doubt in my experience.

-- 
Theo Schlossnagle
Principal Consultant
OmniTI Computer Consulting, Inc. -- http://www.omniti.com/
Phone:  +1 301 776 6376       Fax:  +1 410 880 4879
1024D/82844984/95FD 30F1 489E 4613 F22E  491A 7E88 364C 8284 4984
2047R/33131B65/71 F7 95 64 49 76 5D BA  3D 90 B9 9F BE 27 24 E7