From: Michael Ellerman <mpe@ellerman.id.au>
To: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>,
Valentin Schneider <vschneid@redhat.com>,
Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
Peter Zijlstra <peterz@infradead.org>,
linux-kernel@vger.kernel.org,
Rohan McLure <rmclure@linux.ibm.com>,
Nicholas Piggin <npiggin@gmail.com>,
linuxppc-dev <linuxppc-dev@lists.ozlabs.org>,
Josh Poimboeuf <jpoimboe@kernel.org>
Subject: Re: [PATCH v2 2/6] powerpc/smp: Enable Asym packing for cores on shared processor
Date: Thu, 19 Oct 2023 15:38:40 +1100 [thread overview]
Message-ID: <87v8b35ir3.fsf@mail.lhotse> (raw)
In-Reply-To: <20231018163751.2423181-3-srikar@linux.vnet.ibm.com>
Srikar Dronamraju <srikar@linux.vnet.ibm.com> writes:
> If there are shared processor LPARs, underlying Hypervisor can have more
> virtual cores to handle than actual physical cores.
>
> Starting with Power 9, a core has 2 nearly independent thread groups.
You need to be clearer here that you're talking about "big cores", not
SMT4 cores as seen on bare metal systems.
> On a shared processors LPARs, it helps to pack threads to lesser number
> of cores so that the overall system performance and utilization
> improves. PowerVM schedules at a core level. Hence packing to fewer
> cores helps.
>
> For example: Lets says there are two 8-core Shared LPARs that are
> actually sharing a 8 Core shared physical pool, each running 8 threads
> each. Then Consolidating 8 threads to 4 cores on each LPAR would help
> them to perform better. This is because each of the LPAR will get
> 100% time to run applications and there will no switching required by
> the Hypervisor.
>
> To achieve this, enable SD_ASYM_PACKING flag at CACHE, MC and DIE level.
.. when the system is running in shared processor mode and has big cores.
cheers
> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
> index 37c41297c9ce..498c2d51fc20 100644
> --- a/arch/powerpc/kernel/smp.c
> +++ b/arch/powerpc/kernel/smp.c
> @@ -1009,9 +1009,20 @@ static int powerpc_smt_flags(void)
> */
> static int powerpc_shared_cache_flags(void)
> {
> + if (static_branch_unlikely(&powerpc_asym_packing))
> + return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING;
> +
> return SD_SHARE_PKG_RESOURCES;
> }
>
> +static int powerpc_shared_proc_flags(void)
> +{
> + if (static_branch_unlikely(&powerpc_asym_packing))
> + return SD_ASYM_PACKING;
> +
> + return 0;
> +}
> +
> /*
> * We can't just pass cpu_l2_cache_mask() directly because
> * returns a non-const pointer and the compiler barfs on that.
> @@ -1048,8 +1059,8 @@ static struct sched_domain_topology_level powerpc_topology[] = {
> { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
> #endif
> { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
> - { cpu_mc_mask, SD_INIT_NAME(MC) },
> - { cpu_cpu_mask, SD_INIT_NAME(DIE) },
> + { cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC) },
> + { cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(DIE) },
> { NULL, },
> };
>
> @@ -1687,6 +1698,8 @@ static void __init fixup_topology(void)
> if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
> pr_info_once("Enabling Asymmetric SMT scheduling\n");
> static_branch_enable(&powerpc_asym_packing);
> + } else if (is_shared_processor() && has_big_cores) {
> + static_branch_enable(&powerpc_asym_packing);
> }
>
> #ifdef CONFIG_SCHED_SMT
> --
> 2.31.1
next prev parent reply other threads:[~2023-10-19 4:39 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-18 16:37 [PATCH v2 0/6] powerpc/smp: Shared processor sched optimizations Srikar Dronamraju
2023-10-18 16:37 ` [PATCH v2 1/6] powerpc/smp: Cache CPU has Asymmetric SMP Srikar Dronamraju
2023-10-19 4:33 ` Michael Ellerman
2023-10-20 9:09 ` Srikar Dronamraju
2023-10-18 16:37 ` [PATCH v2 2/6] powerpc/smp: Enable Asym packing for cores on shared processor Srikar Dronamraju
2023-10-19 4:38 ` Michael Ellerman [this message]
2023-10-19 7:48 ` Peter Zijlstra
2023-10-19 11:50 ` Michael Ellerman
2023-10-19 12:54 ` Srikar Dronamraju
2023-10-19 15:56 ` Shrikanth Hegde
2023-10-20 5:44 ` Srikar Dronamraju
2023-10-18 16:37 ` [PATCH v2 3/6] powerpc/smp: Move shared_processor static key to smp.h Srikar Dronamraju
2023-10-19 4:41 ` Michael Ellerman
2023-10-19 13:08 ` Srikar Dronamraju
2023-10-20 10:44 ` Michael Ellerman
2023-10-19 10:30 ` Shrikanth Hegde
2023-10-18 16:37 ` [PATCH v2 4/6] powerpc/smp: Disable MC domain for shared processor Srikar Dronamraju
2023-10-19 4:48 ` Michael Ellerman
2023-10-19 7:50 ` Peter Zijlstra
2023-10-19 13:23 ` Srikar Dronamraju
2023-10-19 13:16 ` Srikar Dronamraju
2023-10-18 16:37 ` [PATCH v2 5/6] powerpc/smp: Add read_mostly attribute Srikar Dronamraju
2023-10-19 4:49 ` Michael Ellerman
2023-10-19 7:51 ` Peter Zijlstra
2023-10-19 12:56 ` Srikar Dronamraju
2023-10-18 16:37 ` [PATCH v2 6/6] powerpc/smp: Avoid asym packing within thread_group of a core Srikar Dronamraju
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=87v8b35ir3.fsf@mail.lhotse \
--to=mpe@ellerman.id.au \
--cc=jpoimboe@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mark.rutland@arm.com \
--cc=npiggin@gmail.com \
--cc=peterz@infradead.org \
--cc=rmclure@linux.ibm.com \
--cc=srikar@linux.vnet.ibm.com \
--cc=vschneid@redhat.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).