Re: [PATCH v2 4/9] perf affinity: Add infrastructure to save/restore affinity

From: Alexey Budankov <alexey.budankov@linux.intel.com>
To: Andi Kleen <ak@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>, Jiri Olsa <jolsa@redhat.com>,
	acme@kernel.org, linux-kernel@vger.kernel.org, jolsa@kernel.org,
	eranian@google.com, kan.liang@linux.intel.com,
	peterz@infradead.org
Subject: Re: [PATCH v2 4/9] perf affinity: Add infrastructure to save/restore affinity
Date: Thu, 24 Oct 2019 11:46:10 +0300	[thread overview]
Message-ID: <6e90cef4-3eba-71aa-2a93-ea8182d47e58@linux.intel.com> (raw)
In-Reply-To: <20191023223704.GI4660@tassilo.jf.intel.com>

On 24.10.2019 1:37, Andi Kleen wrote:
> On Wed, Oct 23, 2019 at 09:08:47PM +0300, Alexey Budankov wrote:
>> On 23.10.2019 20:19, Andi Kleen wrote:
>>> On Wed, Oct 23, 2019 at 07:16:13PM +0300, Alexey Budankov wrote:
>>>>
>>>> On 23.10.2019 17:52, Andi Kleen wrote:
>>>>> On Wed, Oct 23, 2019 at 04:30:49PM +0200, Jiri Olsa wrote:
>>>>>> On Wed, Oct 23, 2019 at 06:02:35AM -0700, Andi Kleen wrote:
>>>>>>> On Wed, Oct 23, 2019 at 11:59:11AM +0200, Jiri Olsa wrote:
>>>>>>>> On Sun, Oct 20, 2019 at 10:51:57AM -0700, Andi Kleen wrote:
>>>>>>>>
>>>>>>>> SNIP
>>>>>>>>
>>>>>>>>> +}
>>>>>>>>> diff --git a/tools/perf/util/affinity.h b/tools/perf/util/affinity.h
>>>>>>>>> new file mode 100644
>>>>>>>>> index 000000000000..e56148607e33
>>>>>>>>> --- /dev/null
>>>>>>>>> +++ b/tools/perf/util/affinity.h
>>>>>>>>> @@ -0,0 +1,15 @@
>>>>>>>>> +// SPDX-License-Identifier: GPL-2.0
>>>>>>>>> +#ifndef AFFINITY_H
>>>>>>>>> +#define AFFINITY_H 1
>>>>>>>>> +
>>>>>>>>> +struct affinity {
>>>>>>>>> +	unsigned char *orig_cpus;
>>>>>>>>> +	unsigned char *sched_cpus;
>>>>>>>>
>>>>>>>> why not use cpu_set_t directly?
>>>>>>>
>>>>>>> Because it's too small in glibc (only 1024 CPUs) and perf already 
>>>>>>> supports more.
>>>>>>
>>>>>> nice, we're using it all over the place.. how about using bitmap_alloc?
>>>>>
>>>>> Okay.
>>>>>
>>>>> The other places is mainly perf record from Alexey's recent affinity changes.
>>>>> These probably need to be fixed.
>>>>>
>>>>> +Alexey
>>>>
>>>> Despite the issue indeed looks generic for stat and record modes,
>>>> have you already observed record startup overhead somewhere in your setups?
>>>> I would, first, prefer to reproduce the overhead, to have stable use case 
>>>> for evaluation and then, possibly, improvement.
>>>
>>> What I meant the cpu_set usages you added in 
>>>
>>> commit 9d2ed64587c045304efe8872b0258c30803d370c
>>> Author: Alexey Budankov <alexey.budankov@linux.intel.com>
>>> Date:   Tue Jan 22 20:47:43 2019 +0300
>>>
>>>     perf record: Allocate affinity masks
>>>
>>> need to be fixed to allocate dynamically, or at least use MAX_NR_CPUs to
>>> support systems with >1024CPUs. That's an independent functionality
>>> problem.
>>
>> Oh, it is clear now. Thanks for pointing this out. For that to move from 
>> cpu_mask_t to new custom struct affinity type its API requires extension 
>> to provide mask operations similar to the ones that cpu_mask_t provides: 
>> CPU_ZERO(), CPU_SET(), CPU_EQUAL(), CPU_OR().
>>
>> For example it could be like: affinity__mask_zero(), affinity__mask_set(), 
>> affinity__mask_equal(), affinity__mask_or() and then the collecting part 
>> of record could also be moved to struct affinity type and overcome >1024CPUs 
>> limitation.
> 
> Not sure you need to use my library, except perhaps the get_cpu_set_size()
> function. It is somewhat specialized.

Ok, I see.

> 
> Everything else you can use normal Linux bitmap functions,
> or call the sys call directly.

Thanks,
Alexey

> 
> -Andi
> 