linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Steven Sistare <steven.sistare@oracle.com>
To: Valentin Schneider <valentin.schneider@arm.com>,
	mingo@redhat.com, peterz@infradead.org
Cc: subhra.mazumdar@oracle.com, dhaval.giani@oracle.com,
	daniel.m.jordan@oracle.com, pavel.tatashin@microsoft.com,
	matt@codeblueprint.co.uk, umgwanakikbuti@gmail.com,
	riel@redhat.com, jbacik@fb.com, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, quentin.perret@arm.com,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 03/10] sched/topology: Provide cfs_overload_cpus bitmap
Date: Mon, 26 Nov 2018 14:06:15 -0500	[thread overview]
Message-ID: <bccc5096-1353-5103-8c45-3dc5193db4e1@oracle.com> (raw)
In-Reply-To: <7d9b6789-af17-bcab-e52d-7e05483e10ea@arm.com>

On 11/20/2018 7:42 AM, Valentin Schneider wrote:
> On 19/11/2018 17:33, Steven Sistare wrote:
> [...]
>>>
>>> Thinking about misfit stealing, we can't use the sd_llc_shared's because
>>> on big.LITTLE misfit migrations happen across LLC domains.
>>>
>>> I was thinking of adding a misfit sparsemask to the root_domain, but
>>> then I thought we could do the same thing for cfs_overload_cpus.
>>>
>>> By doing so we'd have a single source of information for overloaded CPUs,
>>> and we could filter that down during idle balance - you mentioned earlier
>>> wanting to try stealing at each SD level. This would also let you get
>>> rid of [PATCH 02].
>>>
>>> The main part of try_steal() could then be written down as something like
>>> this:
>>>
>>> ----->8-----
>>>
>>> for_each_domain(this_cpu, sd) {
>>> 	span = sched_domain_span(sd)
>>> 		
>>> 	for_each_sparse_wrap(src_cpu, overload_cpus) {
>>> 		if (cpumask_test_cpu(src_cpu, span) &&
>>> 		    steal_from(dts_rq, dst_rf, &locked, src_cpu)) {
>>> 			stolen = 1;
>>> 			goto out;
>>> 		}
>>> 	}
>>> }
>>>
>>> ------8<-----
>>>
>>> We could limit the stealing to stop at the highest SD_SHARE_PKG_RESOURCES
>>> domain for now so there would be no behavioural change - but we'd
>>> factorize the #ifdef SCHED_SMT bit. Furthermore, the door would be open
>>> to further stealing.
>>>
>>> What do you think?
>>
>> That is not efficient for a multi-level search because at each domain level we 
>> would (re) iterate over overloaded candidates that do not belong in that level.
> 
> 
> Mmm I was thinking we could abuse the wrap() and start at
> (fls(prev_span) + 1), but we're not guaranteed to have contiguous spans -
> the Arm Juno for instance has [0, 3, 4], [1, 2] as MC-level domains, so
> that goes down the drain.
> 
> Another thing that has been trotting in my head would be some helper to
> create a cpumask from a sparsemask (some sort of sparsemask_span()),
> which would let us use the standard mask operators:
> 
> ----->8-----
> struct cpumask *overload_span = sparsemask_span(overload_cpus)
> 
> for_each_domain(this_cpu, sd)
> 	for_each_cpu_and(src_cpu, overload_span, sched_domain_span(sd))
> 		<steal_from here>
> -----8>-----
> 
> The cpumask could be part of the sparsemask struct to save us the
> allocation, and only updated when calling sparsemask_span().

I thought of providing something like this along with other sparsemask
utility functions, but I decided to be minimalist, and let others add
more functions if/when they become needed.  this_cpu_cpumask_var_ptr(select_idle_mask) 
is a temporary that could be used as the destination of the conversion.

Also, conversion adds cost, particularly on larger systems.  When comparing a
cpumask and a sparsemask, it is more efficient to iterate over the smaller
set, and test for membership in the larger, such as in try_steal:

    for_each_cpu(src_cpu, cpu_smt_mask(dst_cpu)) {
            if (sparsemask_test_elem(src_cpu, overload_cpus)
 
>> To extend stealing across LLC, I would like to keep the per-LLC sparsemask, 
>> but add to each SD a list of sparsemask pointers.  The list nodes would be
>> private, but the sparsemask structs would be shared.  Each list would include
>> the masks that overlap the SD's members.  The list would be a singleton at the
>> core and LLC levels (same as the socket level for most processors), and would 
>> have multiple elements at the NUMA level.
> 
> I see. As for misfit, creating asym_cpucapacity siblings of the sd_llc_*()
> functions seems a bit much - there'd be a lot of redundancy for basically
> just a single shared sparsemask, which is why I was rambling about moving
> things to root_domain.
> 
> Having different locations where sparsemasks are stored is a bit of a
> pain which I'd like to avoid, but if it can't be unified I suppose we'll
> have to live with it.

I don't follow.  A per-LLC sparsemask representing misfits can be allocated with
one more line in sd_llc_alloc, and you can steal across LLC using the list I
briefly described above.

- Steve

  reply	other threads:[~2018-11-26 19:07 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-09 12:50 [PATCH v3 00/10] steal tasks to improve CPU utilization Steve Sistare
2018-11-09 12:50 ` [PATCH v3 01/10] sched: Provide sparsemask, a reduced contention bitmap Steve Sistare
2018-11-27 15:16   ` Steven Sistare
2018-11-28  1:19     ` Omar Sandoval
2018-12-06 16:07       ` Steven Sistare
2018-12-06 18:19         ` Omar Sandoval
2018-11-09 12:50 ` [PATCH v3 02/10] sched/topology: Provide hooks to allocate data shared per LLC Steve Sistare
2018-11-09 12:50 ` [PATCH v3 03/10] sched/topology: Provide cfs_overload_cpus bitmap Steve Sistare
2018-11-09 17:38   ` Valentin Schneider
2018-11-19 17:32     ` Steven Sistare
2018-11-20 12:52       ` Valentin Schneider
2018-11-12 16:42   ` Valentin Schneider
2018-11-19 17:33     ` Steven Sistare
2018-11-20 12:42       ` Valentin Schneider
2018-11-26 19:06         ` Steven Sistare [this message]
2018-12-03 16:56           ` Valentin Schneider
2018-12-06 16:40             ` Steven Sistare
2018-12-06 17:28               ` Valentin Schneider
2018-11-09 12:50 ` [PATCH v3 04/10] sched/fair: Dynamically update cfs_overload_cpus Steve Sistare
2018-11-09 12:50 ` [PATCH v3 05/10] sched/fair: Hoist idle_stamp up from idle_balance Steve Sistare
2018-11-09 19:07   ` Valentin Schneider
2018-11-19 17:31     ` Steven Sistare
2018-11-20 10:24       ` Valentin Schneider
2018-11-09 12:50 ` [PATCH v3 06/10] sched/fair: Generalize the detach_task interface Steve Sistare
2018-11-09 12:50 ` [PATCH v3 07/10] sched/fair: Provide can_migrate_task_llc Steve Sistare
2018-11-09 12:50 ` [PATCH v3 08/10] sched/fair: Steal work from an overloaded CPU when CPU goes idle Steve Sistare
2018-11-09 12:50 ` [PATCH v3 09/10] sched/fair: disable stealing if too many NUMA nodes Steve Sistare
2018-11-09 12:50 ` [PATCH v3 10/10] sched/fair: Provide idle search schedstats Steve Sistare
2018-11-10 17:08   ` kbuild test robot
2018-11-09 15:02 ` hackbench run scripts Steven Sistare

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=bccc5096-1353-5103-8c45-3dc5193db4e1@oracle.com \
    --to=steven.sistare@oracle.com \
    --cc=daniel.m.jordan@oracle.com \
    --cc=dhaval.giani@oracle.com \
    --cc=jbacik@fb.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=matt@codeblueprint.co.uk \
    --cc=mingo@redhat.com \
    --cc=pavel.tatashin@microsoft.com \
    --cc=peterz@infradead.org \
    --cc=quentin.perret@arm.com \
    --cc=riel@redhat.com \
    --cc=subhra.mazumdar@oracle.com \
    --cc=umgwanakikbuti@gmail.com \
    --cc=valentin.schneider@arm.com \
    --cc=vincent.guittot@linaro.org \
    --subject='Re: [PATCH v3 03/10] sched/topology: Provide cfs_overload_cpus bitmap' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).