[ClusterLabs] Antw: Antw: notice: throttle_handle_load: High CPU load detected

Vladislav Bogdanov bubble at hoster-ok.com
Tue May 9 14:42:28 CEST 2017


09.05.2017 00:56, Ken Gaillot wrote:

[...]

> Those messages indicate there is a real issue with the CPU load. When
> the cluster notices high load, it reduces the number of actions it will
> execute at the same time. This is generally a good idea, to avoid making
> the load worse.
>

[...]

> message, and 2.0 to get the "High CPU load" message. These are measured
> against the 1-minute system load average (the same number you would get
> with top, uptime, etc.).

Well, linux loadavg actually has nothing to *CPU* load.

https://en.wikipedia.org/wiki/Load_(computing)

The most common example to prove that is a storage system (I see that 
with in-kernel iSCSI target) with dedicated data disks/arrays, where 
loadavg can be very high (100-200 is not uncommon), but actual CPU usage 
(user+system) is not more that 20%. For such systems load threshold 
plays bad role, unnecessarily slowing down cluster reactions.

Best,
Vladislav




More information about the Users mailing list