Hello,
I am looking for some help with an issue with ipvsadm and keepalived. i
have this configuration:
vrrp_instance VI_LB1 {
state MASTER
interface eth1
virtual_router_id 145
priority 200
debug 5
virtual_ipaddress {
10.0.2.170 dev eth3
}
virtual_server 10.0.2.170 80 {
delay_loop 10
lb_algo rr
lb_kind NAT
nat_mask 255.255.255.240
#persistence_timeout 300
#persistence_granularity 255.255.255.255
protocol TCP
real_server 10.0.2.162 8000 {
weight 1
HTTP_GET {
url {
path /alteon.html
digest a7b8YT-3f1c10e9065bea9e94c9645a53
}
connect_timeout 3
nb_get_retry 3
delay_before_retry 3
}
}
real_server 10.0.2.168 8000 {
weight 1
HTTP_GET {
url {
path /alteon.html
digest 2552f777ytRf14237efd294kjy944cac3
}
connect_timeout 3
nb_get_retry 3
delay_before_retry 3
}
}
}
my issue is that when i do a bench test with jmeter my loadbalancer start
dropping requests when i reach more than 270 req/sec, i have tested with
apache loadbalancer the same scenario and i can reach 700 req/sec, i don't
understand why ipvsadm and keepalived drop requests when we have more than
275 req/sec, but the main issue for LVS and keepalived that there is any
log file except /var/log/messages and on ths file we didn't find any
information about why ipvsadm drop these requests. I hope someone can help
me.
Thanks a lot
Bassem
_______________________________________________
Please read the documentation before posting - it's available at:
http://www.linuxvirtualserver.org/
LinuxVirtualServer.org mailing list - lvs-users@xxxxxxxxxxxxxxxxxxxxxx
Send requests to lvs-users-request@xxxxxxxxxxxxxxxxxxxxxx
or go to http://lists.graemef.net/mailman/listinfo/lvs-users
|