[perfmon2] Fwd: [patch] Performance Counters for Linux, v3

[stephane e. <er...@go...>]

---------- Forwarded message ----------
From: stephane eranian <er...@go...>
Date: Mon, Dec 15, 2008 at 1:58 PM
Subject: Re: [patch] Performance Counters for Linux, v3
To: Paul Mackerras <pa...@sa...>
Cc: Ingo Molnar <mi...@el...>, Peter Zijlstra
<a.p...@ch...>, Vince Weaver <vi...@de...>,
lin...@vg..., Thomas Gleixner <tg...@li...>,
Andrew Morton <ak...@li...>, Eric Dumazet
<da...@co...>, Robert Richter <rob...@am...>, Arjan
van de Veen <ar...@in...>, Peter Anvin <hp...@zy...>, "David
S. Miller" <da...@da...>


Hi,

On Mon, Dec 15, 2008 at 1:37 AM, Paul Mackerras <pa...@sa...> wrote:
> Ingo Molnar writes:
>
>> * stephane eranian <er...@go...> wrote:
>>
>> > Hi,
>> >
>> > Given the level of abstractions you are using for the API, and given
>> > your argument that the kernel can do the HW resource scheduling better
>> > than anybody else.
>> >
>> > What happens in the following test case:
>> >
>> >    - 2-way system (cpu0, cpu1)
>> >
>> >    - on cpu0, two processes P1, P2, each self-monitoring and counting event E1.
>> >      Event E1 can only be measured on counter C1.
>> >
>> >    - on cpu1, there is a cpu-wide session, monitoring event E1, thus using C1
>> >
>> >    - the scheduler decides to migrate P1 onto CPU1. You now have a
>> >      conflict on C1.
>> >
>> > How is this managed?
>>
>> If there's a single unit of sharable resource [such as an event counter,
>> or a physical CPU], then there's just three main possibilities: either
>> user 1 gets it all, or user 2 gets it all, or they share it.
>>
>> We've implemented the essence of these variants, with sharing the resource
>> being the sane default, and with the sysadmin also having a configuration
>> vector to reserve the resource to himself permanently. (There could be
>> more variations of this.)
>>
>> What is your point?
>>
Could you explain what you mean by sharing here?

Are you talking about time multiplexing the counter?