On Thu, Feb 22, 2001 at 01:36:11PM -0500, Nimesh Vakharia wrote:
> On Tue, 20 Feb 2001, Alex Samonte wrote:
> Agreed that LB is not looking at the payload BUT it caputures it,
> it copies it into memory, rewrites the packet header. Copies it out to the
> outbound buffer and then sends the packet back to the client. DSR u'r not
> doing this for outbound packets. Typically in any HTTP serving environment
> your inbound traffic is usually 1/10th or 1/15th of your outbound
> traffic. ie your pushing 3M inbound, server responses will be around
> 30-40M outbound. You are eliminating 30-40M of traffic going through your
My point is the size of the packet is not a big impact on the LB. The number
of pps is.
> > > Overall I've nothing against any setup, but DSR seems to be a
> > > good option and not something u should be afraid off. Think I convinced
> > > you try using DSR in your next setup? :P
> > DSR was a patch when there was a performance bottleneck in the LB. It allowed
> > me to scale further when there were no other options. Now there are options.
> Well, I'll be happy as long as you don't rule it out of your book
> and be optimistic about it :).
I don't rule it out, but I consider DSR a corner case.
This archive was generated by hypermail 2b30 : Thu Feb 22 2001 - 21:45:22 EST