[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <f58e2ee8-9228-0c94-1954-c2ef7b6b46d1@linux.intel.com>
Date: Wed, 20 Dec 2017 17:05:29 -0500
From: "Liang, Kan" <kan.liang@...ux.intel.com>
To: Andi Kleen <ak@...ux.intel.com>
Cc: peterz@...radead.org, mingo@...hat.com, acme@...nel.org,
linux-kernel@...r.kernel.org, tglx@...utronix.de, jolsa@...hat.com,
eranian@...gle.com
Subject: Re: [PATCH V2 4/4] perf/x86: fix: disable userspace RDPMC usage for
large PEBS
On 12/20/2017 4:41 PM, Andi Kleen wrote:
> On Wed, Dec 20, 2017 at 11:42:51AM -0800, kan.liang@...ux.intel.com wrote:
>> From: Kan Liang <kan.liang@...ux.intel.com>
>>
>> The userspace RDPMC usage never works for large PEBS since the large
>> PEBS is introduced by
>> commit b8241d20699e ("perf/x86/intel: Implement batched PEBS interrupt
>> handling (large PEBS interrupt threshold)")
>>
>> When the PEBS interrupt threshold is larger than one, there is no way to
>> get exact auto-reload times and value for userspace RDPMC.
>>
>> Disable the userspace RDPMC usage when large PEBS is enabled.
>
> The only drawback is that the event wraps quickly.
It's broken. The value read from RDPMC command will always between
-reload_val and 0. Without reload times, I think it's impossible to
calculate the total count number.
> I suspect in many
> cases it's still usable for measuring short regions.
>
Unless the short region is less than reload_val.
Otherwise, reload times is needed.
Thanks,
Kan
> I wouldn't force disable it, just let the users deal with it.
>
> -Andi
>
Powered by blists - more mailing lists