|
Julian Anastasov wrote:
>
> Hello,
>
> On Mon, 14 May 2001, Joseph Mack wrote:
>
> > according to the ipvsadm man page, for "lc" scheduling, the
> > new connections are assigned according to the number of
> > "active connections". Is this the same as "ActConn" in the
> > output of ipvsadm?
>
> The formula is: ActConn * K + InActConn
>
> where K can be 32 ot 50, I don't remember the last used value.
>
> So, it is not only the active conns, this will break UDP.
thanks
> The implicit persistence of TCP connection reuse can cause
> such side effects even for RR. Is this TCP SYN test?
no, it's a tcp connect, fetch about 15kb data, and disconnect.
> When the setup includes small number of hosts and the used rate is
> big enough to reuse the client's port, the LVS detects existing
> connections and new connections are not created. This is the reason
> you can see some of the rs not to be used at all, even for such method
> as RR.
> > (I will have to look further to see if these real-servers
> > are in fact identical)
ahem, I didn't have ip_tables compiled into the two slower real-servers
(and I didn't look at my own error messages). They seem to be running
more identically now. (Will watch it for a few hours before I'm sure.)
the client is using ports from 1025-4999 (has about 2000 open
at one time) and it's not going above the 4999 barrier. ipvsadm
shows a constant InActConn of 990-995 for all realservers,
but the number of connections on each of the real-servers (netstat -an)
ranges from 400-900.
So if the client is reusing ports (I thought you always incremented
the port by 1 till you got to 64k and then it rolled over again),
LVS won't create a new entry in the hash table if the old one
hasn't expired?
Joe
--
Joseph Mack PhD, Senior Systems Engineer, Lockheed Martin
contractor to the National Environmental Supercomputer Center,
mailto:mack.joseph@xxxxxxx ph# 919-541-0007, RTP, NC, USA
|
