Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH v4 1/2] x86/fpu: track AVX-512 usage of tasks
To:     "Li, Aubrey" <aubrey.li@linux.intel.com>,
        Dave Hansen <dave.hansen@intel.com>,
        Aubrey Li <aubrey.li@intel.com>, tglx@linutronix.de,
        mingo@redhat.com, peterz@infradead.org, hpa@zytor.com
Cc:     ak@linux.intel.com, tim.c.chen@linux.intel.com,
        linux-kernel@vger.kernel.org
References: <20181211002448.3520-1-aubrey.li@intel.com>
 <df1a1b5b-3e8b-5d96-12df-25be30c391af@intel.com>
 <143a5451-c7cf-16a5-a7ef-8c4b0633b689@linux.intel.com>
From:   Arjan van de Ven <arjan@linux.intel.com>
Message-ID: <6a549986-f01a-a3c6-10c8-c116667bf7e4@linux.intel.com>
Date:   Tue, 11 Dec 2018 16:14:19 -0800
User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101
 Thunderbird/52.9.1
MIME-Version: 1.0
In-Reply-To: <143a5451-c7cf-16a5-a7ef-8c4b0633b689@linux.intel.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 12/11/2018 3:46 PM, Li, Aubrey wrote:
> On 2018/12/12 1:18, Dave Hansen wrote:
>> On 12/10/18 4:24 PM, Aubrey Li wrote:
>>> The tracking turns on the usage flag at the next context switch of
>>> the task, but requires 3 consecutive context switches with no usage
>>> to clear it. This decay is required because well-written AVX-512
>>> applications are expected to clear this state when not actively using
>>> AVX-512 registers.
>>
>> One concern about this:  Given a HZ=1000 system, this means that the
>> flag needs to get scanned every ~3ms.  That's a pretty good amount of
>> scanning on a system with hundreds or thousands of tasks running around.
>>
>> How many tasks does this scale to until you're eating up an entire CPU
>> or two just scanning /proc?
>>
> 
> Do we have a real requirement to do this in practical environment?
> AFAIK, 1s or even 5s is good enough in some customers environment.

maybe instead of a 1/0 bit, it's useful to store the timestamp of the last
time we found the task to use avx? (need to find a good time unit)