On 2018-09-04 17:32, Ralf Ramsauer wrote:
Hi,
On 04/09/2018 13:45, Jan Kiszka wrote:
This can provide hints why latencies are not as low as expected, even
without any hypervisor exits.
Signed-off-by: Jan Kiszka <[email protected]>
---
Changes in v3
- tuned CPU list according to Ralf's feedback
I just found out that rt-test's cyclictest also supports SMI counting
since v1.2. In v1.3, they extended their list. They use the same
MSR-based method.
https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git/tree/src/cyclictest/cyclictest.c?h=v1.3#n908
Is it worth to align our model list with cyclictest?
I'd like to know their authoritative source. cyclictest only points to
another project called turbostat. Didn't dig deeper yet.
Jan
--
You received this message because you are subscribed to the Google Groups
"Jailhouse" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
