All the mail mirrored from lore.kernel.org
 help / color / mirror / Atom feed
* Limit of 160 for number of VCPUsin the guest
@ 2016-02-19 23:16 Hardik H Bagdi
  0 siblings, 0 replies; only message in thread
From: Hardik H Bagdi @ 2016-02-19 23:16 UTC (permalink / raw
  To: kvm

Hello,

For research, I am experimenting with increasing the number of VCPUs
in the guest OS.

I always get the following warning whenever I increased the number of
VCPUs beyond 160.

"Warning: Number of SMP cpus requested (250) exceeds the recommended
cpus supported by KVM (160)
 Warning: Number of hot-pluggable cpus requested (250) exceeds the
recommended cpus supported by KVM (160)"

I also observed that the performance of sysbench CPU benchmark
degrades exponentially exactly beyond 160 VCPUs.

Can anyone explain what is so special about this 160 VCPUs limit that
causes this performance degradation?

Obviously someone else must also have experimented and hence
recommended that 160VCPUs limit in the warning.

Thank you,
Hardik Bagdi

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2016-02-19 23:17 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-02-19 23:16 Limit of 160 for number of VCPUsin the guest Hardik H Bagdi

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.