From: "Gavin Hu (Arm Technology China)" <Gavin.Hu@arm.com>
To: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>,
Stephen Hemminger <stephen@networkplumber.org>
Cc: "dev@dpdk.org" <dev@dpdk.org>, nd <nd@arm.com>,
"thomas@monjalon.net" <thomas@monjalon.net>,
"jerinj@marvell.com" <jerinj@marvell.com>,
"pbhagavatula@marvell.com" <pbhagavatula@marvell.com>,
nd <nd@arm.com>
Subject: Re: [dpdk-dev] [PATCH v3 5/5] config: add WFE config entry for aarch64
Date: Wed, 24 Jul 2019 17:59:59 +0000 [thread overview]
Message-ID: <VI1PR08MB53763B4AF0B0CAC1856E890B8FC60@VI1PR08MB5376.eurprd08.prod.outlook.com> (raw)
In-Reply-To: <VE1PR08MB51493CCA0D72856EB58C730298C70@VE1PR08MB5149.eurprd08.prod.outlook.com>
Hi Stephen,
> -----Original Message-----
> From: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> Sent: Wednesday, July 24, 2019 3:10 AM
> To: Stephen Hemminger <stephen@networkplumber.org>; Gavin Hu (Arm
> Technology China) <Gavin.Hu@arm.com>
> Cc: dev@dpdk.org; nd <nd@arm.com>; thomas@monjalon.net;
> jerinj@marvell.com; pbhagavatula@marvell.com; Honnappa Nagarahalli
> <Honnappa.Nagarahalli@arm.com>; nd <nd@arm.com>
> Subject: RE: [PATCH v3 5/5] config: add WFE config entry for aarch64
>
> >
> > On Tue, 23 Jul 2019 23:43:46 +0800
> > Gavin Hu <gavin.hu@arm.com> wrote:
> >
> > > Add the RTE_USE_WFE configuration entry for aarch64, disabled by
> default.
> > > It can be enabled selectively based on the performance benchmarking.
> > >
> > > Signed-off-by: Gavin Hu <gavin.hu@arm.com>
> > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > Reviewed-by: Steve Capper <steve.capper@arm.com>
> > > Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> > > Acked-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
> > > ---
> > > config/arm/meson.build | 1 +
> > > config/common_armv8a_linux | 6 ++++++
> > > 2 files changed, 7 insertions(+)
> > >
> > > diff --git a/config/arm/meson.build b/config/arm/meson.build index
> > > 979018e..496813a 100644
> > > --- a/config/arm/meson.build
> > > +++ b/config/arm/meson.build
> > > @@ -116,6 +116,7 @@ impl_dpaa = ['NXP DPAA', flags_dpaa,
> > > machine_args_generic]
> > > impl_dpaa2 = ['NXP DPAA2', flags_dpaa2, machine_args_generic]
> > >
> > > dpdk_conf.set('RTE_FORCE_INTRINSICS', 1)
> > > +dpdk_conf.set('RTE_USE_WFE', 0)
> > >
> > > if not dpdk_conf.get('RTE_ARCH_64')
> > > dpdk_conf.set('RTE_CACHE_LINE_SIZE', 64) diff --git
> > > a/config/common_armv8a_linux b/config/common_armv8a_linux index
> > > 481712e..48c7ab5 100644
> > > --- a/config/common_armv8a_linux
> > > +++ b/config/common_armv8a_linux
> > > @@ -12,6 +12,12 @@ CONFIG_RTE_ARCH_64=y
> > >
> > > CONFIG_RTE_FORCE_INTRINSICS=y
> > >
> > > +# Use WFE instructions to implement the rte_wait_for_equal_xxx APIs,
> > > +# calling these APIs put the cores enter low power state while
> > > +waiting # for the memory address to be become equal to the expected
> value.
> > > +# This is supported only by aarch64.
> > > +CONFIG_RTE_USE_WFE=n
> > > +
> > > # Maximum available cache line size in arm64 implementations.
> > > # Setting to maximum available cache line size in generic config #
> > > to address minimum DMA alignment across all arm64 implementations.
> >
> > Introducing config options is a maintenance nightmare.
> > How are distributions supposed to ship a package?
> > Does full regression test get done on both options?
> >
> > The user should not be able to change this.
> Agree with these concerns here. In our tests, we are finding that this patch
> does not result in performance improvements on all micro-architectures.
> May be these micro-architectures will evolve in the future knowing that
> WFE is being used in DPDK. But at this point, it does not make sense to
> enable this by default. This means additional testing/regression with the flag
> enabled. We could add this to Travis build (Travis yml file).
>
> Currently, this patch will address use cases where the target
> hardware/environment is known during compilation.
In our testing, like running testpmd and packet_ordering(for WFE ring benchmarking), it showed no improvements nor degradation in performance.
For some micro-benchmarking, it showed slight improvements sometimes, no degradation were seen.
The added benefit of the patch set is power saving, but it is not a primary concern in DPDK and we are short of measurement ways to benchmark that.
next prev parent reply other threads:[~2019-07-24 18:00 UTC|newest]
Thread overview: 168+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-30 16:21 [dpdk-dev] [RFC 0/5] use WFE for locks and ring on aarch64 Gavin Hu
2019-06-30 16:21 ` [dpdk-dev] [RFC 1/5] eal: add the APIs to wait until equal Gavin Hu
2019-06-30 20:27 ` Stephen Hemminger
2019-07-01 7:16 ` Gavin Hu (Arm Technology China)
2019-07-01 7:43 ` Thomas Monjalon
2019-07-02 14:07 ` Gavin Hu (Arm Technology China)
2019-07-01 9:58 ` Pavan Nikhilesh Bhagavatula
2019-07-02 14:08 ` Gavin Hu (Arm Technology China)
2019-06-30 16:21 ` [dpdk-dev] [RFC 2/5] ticketlock: use new API to reduce contention on aarch64 Gavin Hu
2019-06-30 16:21 ` [dpdk-dev] [RFC 3/5] ring: use wfe to wait for ring tail update " Gavin Hu
2019-06-30 16:21 ` [dpdk-dev] [RFC 4/5] spinlock: use wfe to reduce contention " Gavin Hu
2019-06-30 16:21 ` [dpdk-dev] [RFC 5/5] config: add WFE config entry for aarch64 Gavin Hu
2019-06-30 20:29 ` [dpdk-dev] [RFC 0/5] use WFE for locks and ring on aarch64 Stephen Hemminger
2019-07-01 9:12 ` Gavin Hu (Arm Technology China)
2019-07-03 8:58 ` [dpdk-dev] [RFC v2 " Gavin Hu
2019-07-03 8:58 ` [dpdk-dev] [RFC v2 1/5] eal: add the APIs to wait until equal Gavin Hu
2019-07-20 6:46 ` [dpdk-dev] [EXT] " Pavan Nikhilesh Bhagavatula
2019-07-03 8:58 ` [dpdk-dev] [RFC v2 2/5] ticketlock: use new API to reduce contention on aarch64 Gavin Hu
2019-07-20 6:57 ` Pavan Nikhilesh Bhagavatula
2019-07-03 8:58 ` [dpdk-dev] [RFC v2 3/5] ring: use wfe to wait for ring tail update " Gavin Hu
2019-07-03 8:58 ` [dpdk-dev] [RFC v2 4/5] spinlock: use wfe to reduce contention " Gavin Hu
2019-07-20 6:59 ` Pavan Nikhilesh Bhagavatula
2019-07-03 8:58 ` [dpdk-dev] [RFC v2 5/5] config: add WFE config entry for aarch64 Gavin Hu
2019-07-20 7:03 ` Pavan Nikhilesh Bhagavatula
2019-07-23 15:47 ` Gavin Hu (Arm Technology China)
2019-07-23 15:43 ` [dpdk-dev] [PATCH v3 0/5] use WFE for locks and ring on aarch64 Gavin Hu
2019-07-23 19:15 ` Honnappa Nagarahalli
2019-07-23 21:27 ` Thomas Monjalon
2019-07-24 2:44 ` Honnappa Nagarahalli
2019-07-24 7:43 ` Thomas Monjalon
2019-07-23 15:43 ` [dpdk-dev] [PATCH v3 1/5] eal: add the APIs to wait until equal Gavin Hu
2019-07-24 11:52 ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2019-07-24 18:10 ` Gavin Hu (Arm Technology China)
2019-07-23 15:43 ` [dpdk-dev] [PATCH v3 2/5] ticketlock: use new API to reduce contention on aarch64 Gavin Hu
2019-07-23 15:43 ` [dpdk-dev] [PATCH v3 3/5] ring: use wfe to wait for ring tail update " Gavin Hu
2019-07-23 15:43 ` [dpdk-dev] [PATCH v3 4/5] spinlock: use wfe to reduce contention " Gavin Hu
2019-07-24 12:17 ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2019-07-23 15:43 ` [dpdk-dev] [PATCH v3 5/5] config: add WFE config entry for aarch64 Gavin Hu
2019-07-23 18:05 ` Stephen Hemminger
2019-07-23 19:10 ` Honnappa Nagarahalli
2019-07-24 17:59 ` Gavin Hu (Arm Technology China) [this message]
2019-07-24 12:25 ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2019-08-22 6:12 ` [dpdk-dev] [PATCH v4 0/6] use WFE for locks and ring on aarch64 Gavin Hu
2019-10-16 8:08 ` David Marchand
2019-10-24 20:26 ` David Christensen
2019-08-22 6:12 ` [dpdk-dev] [PATCH v4 1/6] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-08-22 6:12 ` [dpdk-dev] [PATCH v4 2/6] eal: add the APIs to wait until equal Gavin Hu
2019-09-11 12:26 ` Jerin Jacob
2019-09-12 8:25 ` Gavin Hu (Arm Technology China)
2019-08-22 6:12 ` [dpdk-dev] [PATCH v4 3/6] ticketlock: use new API to reduce contention on aarch64 Gavin Hu
2019-08-22 6:12 ` [dpdk-dev] [PATCH v4 4/6] ring: use wfe to wait for ring tail update " Gavin Hu
2019-08-22 6:12 ` [dpdk-dev] [PATCH v4 5/6] spinlock: use wfe to reduce contention " Gavin Hu
[not found] ` <CY4PR1801MB1863AF9695BB10930E817D78DEB00@CY4PR1801MB1863.namprd18.prod.outlook.com>
[not found] ` <VI1PR08MB5376BEBCC1FD1E03F0B8A8848FB00@VI1PR08MB5376.eurprd08.prod.outlook.com>
2019-09-14 15:21 ` [dpdk-dev] [EXT] " Gavin Hu (Arm Technology China)
2019-08-22 6:12 ` [dpdk-dev] [PATCH v4 6/6] config: add WFE config entry for aarch64 Gavin Hu
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 0/8] use WFE " Gavin Hu
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 1/8] config: add WFE config entry " Gavin Hu
2019-09-12 15:48 ` Jerin Jacob
2019-09-13 16:01 ` Gavin Hu (Arm Technology China)
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 2/8] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 3/8] eal: add the APIs to wait until equal Gavin Hu
2019-09-12 16:11 ` Jerin Jacob
2019-09-13 17:05 ` Gavin Hu (Arm Technology China)
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 4/8] spinlock: use wfe to reduce contention on aarch64 Gavin Hu
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 5/8] ticketlock: use new API " Gavin Hu
2019-09-12 16:14 ` Jerin Jacob
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 6/8] ring: use wfe to wait for ring tail update " Gavin Hu
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 7/8] net/thunderx: use new API to save cycles " Gavin Hu
2019-09-12 16:15 ` Jerin Jacob
2019-09-12 11:24 ` [dpdk-dev] [PATCH v5 8/8] event/opdl: " Gavin Hu
2019-09-12 16:16 ` Jerin Jacob
2019-09-14 14:59 ` [dpdk-dev] [PATCH v6 0/7] use WFE for aarch64 Gavin Hu
2019-09-26 13:41 ` Jerin Jacob
2019-09-27 5:45 ` Gavin Hu (Arm Technology China)
2019-09-14 14:59 ` [dpdk-dev] [PATCH v6 1/7] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-09-14 14:59 ` [dpdk-dev] [PATCH v6 2/7] eal: add the APIs to wait until equal Gavin Hu
2019-09-14 14:59 ` [dpdk-dev] [PATCH v6 3/7] spinlock: use wfe to reduce contention on aarch64 Gavin Hu
2019-09-14 14:59 ` [dpdk-dev] [PATCH v6 4/7] ticketlock: use new API " Gavin Hu
2019-09-14 14:59 ` [dpdk-dev] [PATCH v6 5/7] ring: use wfe to wait for ring tail update " Gavin Hu
2019-09-14 14:59 ` [dpdk-dev] [PATCH v6 6/7] net/thunderx: use new API to save cycles " Gavin Hu
2019-09-14 14:59 ` [dpdk-dev] [PATCH v6 7/7] event/opdl: " Gavin Hu
2019-09-27 5:41 ` [dpdk-dev] [PATCH v7 0/7] use WFE for aarch64 Gavin Hu
2019-10-17 18:37 ` David Marchand
2019-09-27 5:41 ` [dpdk-dev] [PATCH v7 1/7] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-09-27 8:24 ` Hemant Agrawal
2019-10-17 15:06 ` David Marchand
2019-09-27 5:41 ` [dpdk-dev] [PATCH v7 2/7] eal: add the APIs to wait until equal Gavin Hu
2019-09-27 11:03 ` Jerin Jacob
2019-10-17 13:14 ` Ananyev, Konstantin
2019-10-21 7:21 ` Gavin Hu (Arm Technology China)
2019-10-17 15:45 ` David Marchand
2019-10-21 7:38 ` Gavin Hu (Arm Technology China)
2019-10-21 19:17 ` David Marchand
2019-10-17 16:44 ` Ananyev, Konstantin
2019-10-23 16:20 ` Gavin Hu (Arm Technology China)
2019-10-23 16:29 ` Gavin Hu (Arm Technology China)
2019-10-24 10:21 ` Ananyev, Konstantin
2019-10-24 10:52 ` Gavin Hu (Arm Technology China)
2019-09-27 5:41 ` [dpdk-dev] [PATCH v7 3/7] spinlock: use wfe to reduce contention on aarch64 Gavin Hu
2019-10-17 18:27 ` David Marchand
2019-10-18 5:45 ` Gavin Hu (Arm Technology China)
2019-10-21 7:27 ` Gavin Hu (Arm Technology China)
2019-09-27 5:41 ` [dpdk-dev] [PATCH v7 4/7] ticketlock: use new API " Gavin Hu
2019-09-27 5:41 ` [dpdk-dev] [PATCH v7 5/7] ring: use wfe to wait for ring tail update " Gavin Hu
2019-09-27 5:41 ` [dpdk-dev] [PATCH v7 6/7] net/thunderx: use new API to save cycles " Gavin Hu
2019-09-27 5:41 ` [dpdk-dev] [PATCH v7 7/7] event/opdl: " Gavin Hu
2019-10-21 9:47 ` [dpdk-dev] [PATCH v8 0/6] use WFE for aarch64 Gavin Hu
2019-10-21 9:47 ` [dpdk-dev] [PATCH v8 1/6] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-10-21 19:00 ` David Marchand
2019-10-21 9:47 ` [dpdk-dev] [PATCH v8 2/6] eal: add the APIs to wait until equal Gavin Hu
2019-10-21 19:19 ` David Marchand
2019-10-22 9:36 ` Ananyev, Konstantin
2019-10-22 10:17 ` David Marchand
2019-10-22 16:05 ` Gavin Hu (Arm Technology China)
2019-10-22 16:03 ` Gavin Hu (Arm Technology China)
2019-10-21 9:47 ` [dpdk-dev] [PATCH v8 3/6] spinlock: use wfe to reduce contention on aarch64 Gavin Hu
2019-10-21 9:47 ` [dpdk-dev] [PATCH v8 4/6] ticketlock: use new API " Gavin Hu
2019-10-21 9:47 ` [dpdk-dev] [PATCH v8 5/6] net/thunderx: use new API to save cycles " Gavin Hu
2019-10-21 9:47 ` [dpdk-dev] [PATCH v8 6/6] event/opdl: " Gavin Hu
2019-10-24 10:42 ` [dpdk-dev] [PATCH v9 0/5] use WFE for aarch64 Gavin Hu
2019-10-24 10:42 ` [dpdk-dev] [PATCH v9 1/5] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-10-24 10:42 ` [dpdk-dev] [PATCH v9 2/5] eal: add the APIs to wait until equal Gavin Hu
2019-10-24 13:52 ` Ananyev, Konstantin
2019-10-24 13:57 ` Ananyev, Konstantin
2019-10-24 17:00 ` Gavin Hu (Arm Technology China)
2019-10-24 10:42 ` [dpdk-dev] [PATCH v9 3/5] ticketlock: use new API to reduce contention on aarch64 Gavin Hu
2019-10-24 10:42 ` [dpdk-dev] [PATCH v9 4/5] net/thunderx: use new API to save cycles " Gavin Hu
2019-10-24 10:42 ` [dpdk-dev] [PATCH v9 5/5] event/opdl: " Gavin Hu
2019-10-25 15:39 ` [dpdk-dev] [PATCH v10 0/5] use WFE for aarch64 Gavin Hu
2019-10-25 15:39 ` [dpdk-dev] [PATCH v10 1/5] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-10-25 15:39 ` [dpdk-dev] [PATCH v10 2/5] eal: add the APIs to wait until equal Gavin Hu
2019-10-25 17:27 ` Ananyev, Konstantin
2019-10-27 13:03 ` Gavin Hu (Arm Technology China)
2019-10-25 15:39 ` [dpdk-dev] [PATCH v10 3/5] ticketlock: use new API to reduce contention on aarch64 Gavin Hu
2019-10-25 15:39 ` [dpdk-dev] [PATCH v10 4/5] net/thunderx: use new API to save cycles " Gavin Hu
2019-10-25 15:39 ` [dpdk-dev] [PATCH v10 5/5] event/opdl: " Gavin Hu
2019-10-27 12:52 ` [dpdk-dev] [PATCH v11 0/5] use WFE for aarch64 Gavin Hu
2019-10-27 12:52 ` [dpdk-dev] [PATCH v11 1/5] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-10-27 12:52 ` [dpdk-dev] [PATCH v11 2/5] eal: add the APIs to wait until equal Gavin Hu
2019-10-27 20:49 ` David Marchand
2019-10-28 5:08 ` Gavin Hu (Arm Technology China)
2019-10-27 22:19 ` Ananyev, Konstantin
2019-10-28 5:04 ` Gavin Hu (Arm Technology China)
2019-10-27 12:52 ` [dpdk-dev] [PATCH v11 3/5] ticketlock: use new API to reduce contention on aarch64 Gavin Hu
2019-10-27 12:52 ` [dpdk-dev] [PATCH v11 4/5] net/thunderx: use new API to save cycles " Gavin Hu
2019-10-27 12:52 ` [dpdk-dev] [PATCH v11 5/5] event/opdl: " Gavin Hu
2019-11-04 15:32 ` [dpdk-dev] [PATCH v12 0/5] use WFE for aarch64 Gavin Hu
2019-11-04 15:32 ` [dpdk-dev] [PATCH v12 1/5] bus/fslmc: fix the conflicting dmb function Gavin Hu
2019-11-04 15:32 ` [dpdk-dev] [PATCH v12 2/5] eal: add the APIs to wait until equal Gavin Hu
2019-11-07 15:03 ` Ananyev, Konstantin
2019-11-04 15:32 ` [dpdk-dev] [PATCH v12 3/5] ticketlock: use new API to reduce contention on aarch64 Gavin Hu
2019-11-04 15:32 ` [dpdk-dev] [PATCH v12 4/5] net/thunderx: use new API to save cycles " Gavin Hu
2019-11-04 15:32 ` [dpdk-dev] [PATCH v12 5/5] event/opdl: " Gavin Hu
2019-11-07 21:35 ` [dpdk-dev] [PATCH v13 0/5] use WFE for aarch64 David Marchand
2019-11-07 21:35 ` [dpdk-dev] [PATCH v13 1/5] bus/fslmc: fix the conflicting dmb function David Marchand
2019-12-10 6:13 ` Honnappa Nagarahalli
2019-11-07 21:35 ` [dpdk-dev] [PATCH v13 2/5] eal: add the APIs to wait until equal David Marchand
2019-11-08 16:38 ` Ananyev, Konstantin
2019-11-08 17:00 ` Thomas Monjalon
2019-11-08 18:36 ` Ananyev, Konstantin
2019-11-11 5:11 ` Jerin Jacob
2019-11-11 5:51 ` Gavin Hu (Arm Technology China)
2019-12-10 7:51 ` Honnappa Nagarahalli
2020-01-16 21:38 ` David Marchand
2020-01-17 2:46 ` Gavin Hu
2019-11-07 21:35 ` [dpdk-dev] [PATCH v13 3/5] ticketlock: use new API to reduce contention on aarch64 David Marchand
2019-11-07 21:35 ` [dpdk-dev] [PATCH v13 4/5] net/thunderx: use new API to save cycles " David Marchand
2019-11-07 21:35 ` [dpdk-dev] [PATCH v13 5/5] event/opdl: " David Marchand
2020-01-17 11:15 ` [dpdk-dev] [PATCH v13 0/5] use WFE for aarch64 David Marchand
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=VI1PR08MB53763B4AF0B0CAC1856E890B8FC60@VI1PR08MB5376.eurprd08.prod.outlook.com \
--to=gavin.hu@arm.com \
--cc=Honnappa.Nagarahalli@arm.com \
--cc=dev@dpdk.org \
--cc=jerinj@marvell.com \
--cc=nd@arm.com \
--cc=pbhagavatula@marvell.com \
--cc=stephen@networkplumber.org \
--cc=thomas@monjalon.net \
/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).