Dear Jailhouse community, dear Jan, 

I am considering using the performance monitor counters in Intel CPUs while 
using Jailhouse. 
Given that the counters are private to each logical core, this is a nice 
opportunity to get more insight in the performance of the application in the 
cell. 

The current implementation disables the perf counters when initializing a cell, 
and exits on any writes to MSR_IA32_PERF_GLOBAL_CTRL to ignore the msr write. 
Why are these counters disabled? Is it just to omit complexity, or am I 
overlooking a structural reason why the use of these counters is unviable?
I consulted the Intel SDM on perf counters, and could not find a reason not to 
whitelist the MSRs, so I wanted to check whether I am overlooking something. 

Thanks!

Kind regards,

Bram Hooimeijer 

-- 
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 jailhouse-dev+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/jailhouse-dev/AS8PR02MB666308E65BE540CAEE21862CB6809%40AS8PR02MB6663.eurprd02.prod.outlook.com.

Reply via email to