Re: [RFC PATCH 0/4] Scheduler time slice extension

[Prakash Sangappa <prakash.sangappa@oracle.com>]

> On Nov 14, 2024, at 11:41 AM, Prakash Sangappa <prakash.sangappa@oracle.com> wrote:
> 
> 
> 
>> On Nov 14, 2024, at 2:28 AM, Peter Zijlstra <peterz@infradead.org> wrote:
>> 
>> On Wed, Nov 13, 2024 at 08:10:52PM +0000, Prakash Sangappa wrote:
>>> 
>>> 
>>>> On Nov 13, 2024, at 11:36 AM, Mathieu Desnoyers <mathieu.desnoyers@efficios.com> wrote:
>>>> 
>>>> On 2024-11-13 13:50, Peter Zijlstra wrote:
>>>>> On Wed, Nov 13, 2024 at 12:01:22AM +0000, Prakash Sangappa wrote:
>>>>>> This patch set implements the above mentioned 50us extension time as posted
>>>>>> by Peter. But instead of using restartable sequences as API to set the flag
>>>>>> to request the extension, this patch proposes a new API with use of a per
>>>>>> thread shared structure implementation described below. This shared structure
>>>>>> is accessible in both users pace and kernel. The user thread will set the
>>>>>> flag in this shared structure to request execution time extension.
>>>>> But why -- we already have rseq, glibc uses it by default. Why add yet
>>>>> another thing?
>>>> 
>>>> Indeed, what I'm not seeing in this RFC patch series cover letter is an
>>>> explanation that justifies adding yet another per-thread memory area
>>>> shared between kernel and userspace when we have extensible rseq
>>>> already.
>>> 
>>> It mainly provides pinned memory, can be useful for  future use cases
>>> where updating user memory in kernel context can be fast or needs to
>>> avoid pagefaults.
>> 
>> 'might be useful' it not good enough a justification. Also, I don't
>> think you actually need this.
> 
> Will get back with database benchmark results using rseq API for scheduler time extension.

Sorry about the delay in response.

Here are the database swingbench numbers   - includes results with use of rseq API.

Test results:
=========
Test system 2 socket AMD Genoa

 	Swingbench - standard database benchmark 
		Cached(database files on tmpfs) run, with 1000 clients.

		Baseline(Without Sched time extension):  99K SQL exec/sec

		With Sched time extension: 
				Shared structure API use: 		153K SQL exec/sec  (Previously reported)
			55% improvement in throughput.

				Restartable sequences API use:	147K SQL exec/sec
 			48% improvement in throughput

While both show good performance benefit with scheduler time extension,
there is a 7% difference in throughput between Shared structure & Restartable sequences API. 
Use of shared structure is faster.



> 
>> 
>> See:
>> 
>> https://lkml.kernel.org/r/20220113233940.3608440-4-posk@google.com
>> 
>> for a more elaborate scheme.
>> 
>>>> Peter, was there anything fundamentally wrong with your approach based
>>>> on rseq ? https://lore.kernel.org/lkml/20231030132949.GA38123@noisy.programming.kicks-ass.net
>>>> 
>>>> The main thing I wonder is whether loading the rseq delay resched flag
>>>> on return to userspace is too late in your patch. Also, I'm not sure it is
>>>> realistic to require that no system calls should be done within time extension
>>>> slice. If we have this scenario:
>>> 
>>> I am also not sure if we need to prevent system calls in this scenario. 
>>> Was that restriction mainly because of restartable sequence API implements it?
>> 
>> No, the whole premise of delaying resched was because people think that
>> syscalls are too slow. If you do not think this, then you shouldn't be
>> using this.
> 
> Agree.
> 
> Thanks,
> -Prakash