[Pacemaker] High context switches
Andreas Zafiris
orion at realize.gr
Tue Nov 3 08:17:04 UTC 2009
Hello,
Please forgive me if this has already been discussed...
I have a pacemaker+openais setup of 2 Debian amd64 machines (IBM x3550, 2 Xeon 2.5GHz, 6GB Ram) with the following openais.conf:
Kernel: 2.6.26-2-amd64
Pacemaker-openais version: 1.0.5+hg20091012-1~bpo50+1
--- BEGIN openais.conf
otem {
version: 2
token: 3000
token_retransmits_before_loss_const: 10
join: 60
consensus: 1500
vsftype: none
max_messages: 20
clear_node_high_bit: yes
secauth: off
threads: 0
rrp_mode: none
interface {
# The following values need to be set based on your environment
ringnumber: 0
bindnetaddr: 10.10.1.0
mcastaddr: 226.94.1.1
mcastport: 5405
}
}
logging {
to_stderr: yes
debug: off
timestamp: on
to_file: no
to_syslog: yes
syslog_facility: daemon
}
amf {
mode: disabled
}
service {
ver: 0
name: pacemaker
use_mgmtd: yes
}
aisexec {
user: root
group: root
}
--- END openais.conf
Has anyone had high context switches (as seen in vmstat)
procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu----
r b swpd free buff cache si so bi bo in cs us sy id wa
1 0 0 3193472 2570928 156592 0 0 1 0 6 11 0 1 99 0
0 0 0 3193692 2570928 156592 0 0 0 20 62 18953 0 1 99 0
0 0 0 3193628 2570928 156592 0 0 0 0 35 19088 0 1 99 0
0 0 0 3193184 2570928 156592 0 0 0 0 48 19049 0 1 99 0
0 0 0 3193792 2570928 156592 0 0 0 0 41 18947 0 1 99 0
0 0 0 3193828 2570928 156592 0 0 0 0 46 19105 0 1 99 0
1 0 0 3192480 2570928 156592 0 0 0 0 45 19087 0 1 99 0
0 0 0 3193196 2570928 156592 0 0 0 0 27 18930 0 1 99 0
This is the behaviour I see while the system is idle. Please note that the system with openais-legacy stopped, stays around 500 cs
Is this normal?
Thanks,
Andreas
More information about the Pacemaker
mailing list