Message-ID: <878tvvtir5.fsf@e105922-lin.cambridge.arm.com>
Date:	Wed, 17 Aug 2016 18:20:14 +0100
From:	Punit Agrawal <punit.agrawal@....com>
To:	Paolo Bonzini <pbonzini@...hat.com>
Cc:	kvm@...r.kernel.org, Marc Zyngier <marc.zyngier@....com>,
	Will Deacon <will.deacon@....com>,
	linux-kernel@...r.kernel.org, Steven Rostedt <rostedt@...dmis.org>,
	Ingo Molnar <mingo@...hat.com>, kvmarm@...ts.cs.columbia.edu,
	linux-arm-kernel@...ts.infradead.org
Subject: Re: [RFC PATCH 0/7] Add support for monitoring guest TLB operations

Paolo Bonzini <pbonzini@...hat.com> writes:

> On 17/08/2016 19:01, Punit Agrawal wrote:
>>> Can you explain what this is used for?  In other words, why would this
>>> be used instead of just running perf in the guest?
>> 
>> As TLB maintenance operations are synchronised in hardware, they can
>> impact performance beyond the guest. The operations generate traffic on
>> the interconnect and depending on the implementation, they can also
>> affect the remote TLB's translation bandwidth.
>> 
>> These patches are useful on systems where the host and guest are
>> controlled by different users - the guest could be running arbitrary
>> software. 
>> 
>> Having the ability to monitor the usage of guest TLB invalidations in
>> the host can be useful to diagnose performance issues on such systems.
>
> Are there hardware performance counters for these operations?

That would have been ideal! There are PMU events defined for TLB
accesses and refills but unhelpfully none of them track maintenance
operations.

>
> Paolo
> _______________________________________________
> kvmarm mailing list
> kvmarm@...ts.cs.columbia.edu
> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

Powered by blists - more mailing lists