I've been running an LVS -NAT [IP Virtual Server version 0.9.14
(size=4096)] for a couple of years. Originally, there were 3 realservers,
now there are 8. The director is a dual pentium III 400 mhz box running
Mandrake (2.2.17) and 500 megs of memory. The realservers vary from
single processor 500mhz Pentium III's to a dual Xeon 2.8 ghz with 1.5 megs
of memory. About 50% of the requests (all http) are routed to the dual
xeon box.
Lately the real servers are all running under heavier than normal loads
without any increase in http requests. Could the LVS be getting 'tired' ?
I've downloaded netparse and testlvs but the documentation is so scant
that I've not been able to use them. How can I test to see if the LVS is
becoming a bottleneck?
Does it matter that the LVS director here is slower than most of the real
servers it's directing?
Thanks!
-Neil
|