DPDK patches and discussions
 help / color / mirror / Atom feed
* [dpdk-dev] [PATCH] app/eventdev: remove unnecessary barrier for order test
@ 2021-05-10  6:11 Feifei Wang
       [not found] ` <AM5PR0802MB2465F23DEA897DA3CFB06B029E2C9@AM5PR0802MB2465.eurprd08.prod.outlook.com>
  2021-06-30  6:49 ` [dpdk-dev] " Jerin Jacob
  0 siblings, 2 replies; 5+ messages in thread
From: Feifei Wang @ 2021-05-10  6:11 UTC (permalink / raw)
  To: Jerin Jacob; +Cc: dev, nd, Feifei Wang, Ruifeng Wang, Honnappa Nagarahalli

For "order_launch_lcores" function, wmb after that the main lcore
updates the variable "t->err", which represents the end of the test
signal, is unnecessary. Because after the main lcore updates this
siginal variable, it will jump out of the launch function loop, and wait
other lcores stop or return error in the main function(evt_main.c).
During this time, there is no storing operation and thus no need for
wmb.

Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
---
 app/test-eventdev/test_order_common.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/app/test-eventdev/test_order_common.c b/app/test-eventdev/test_order_common.c
index 04456d56db..d7760061ba 100644
--- a/app/test-eventdev/test_order_common.c
+++ b/app/test-eventdev/test_order_common.c
@@ -308,7 +308,6 @@ order_launch_lcores(struct evt_test *test, struct evt_options *opt,
 				rte_event_dev_dump(opt->dev_id, stdout);
 				evt_err("No schedules for seconds, deadlock");
 				t->err = true;
-				rte_smp_wmb();
 				break;
 			}
 			old_remaining = remaining;
-- 
2.25.1


^ permalink raw reply	[flat|nested] 5+ messages in thread

* [dpdk-dev] 回复: [PATCH] app/eventdev: remove unnecessary barrier for order test
       [not found] ` <AM5PR0802MB2465F23DEA897DA3CFB06B029E2C9@AM5PR0802MB2465.eurprd08.prod.outlook.com>
@ 2021-05-18  9:27   ` Feifei Wang
  2021-05-18 14:05     ` Jerin Jacob
  0 siblings, 1 reply; 5+ messages in thread
From: Feifei Wang @ 2021-05-18  9:27 UTC (permalink / raw)
  To: jerinj; +Cc: Ruifeng Wang, Honnappa Nagarahalli, dev, nd, nd

Hi, Jerin

Sorry to disturb you. Would you please help me review this patch, thanks very much.


Best Regards
Feifei

> -----Original Message-----
> From: Feifei Wang <feifei.wang2@arm.com>
> Sent: Monday, May 10, 2021 2:12 PM
> To: jerinj@marvell.com
> Cc: dev@dpdk.org; nd <nd@arm.com>; Feifei Wang
> <Feifei.Wang2@arm.com>; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> Subject: [PATCH] app/eventdev: remove unnecessary barrier for order test
> 
> For "order_launch_lcores" function, wmb after that the main lcore updates
> the variable "t->err", which represents the end of the test signal, is
> unnecessary. Because after the main lcore updates this siginal variable, it will
> jump out of the launch function loop, and wait other lcores stop or return
> error in the main function(evt_main.c).
> During this time, there is no storing operation and thus no need for wmb.
> 
> Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> ---
>  app/test-eventdev/test_order_common.c | 1 -
>  1 file changed, 1 deletion(-)
> 
> diff --git a/app/test-eventdev/test_order_common.c b/app/test-
> eventdev/test_order_common.c
> index 04456d56db..d7760061ba 100644
> --- a/app/test-eventdev/test_order_common.c
> +++ b/app/test-eventdev/test_order_common.c
> @@ -308,7 +308,6 @@ order_launch_lcores(struct evt_test *test, struct
> evt_options *opt,
>  				rte_event_dev_dump(opt->dev_id, stdout);
>  				evt_err("No schedules for seconds,
> deadlock");
>  				t->err = true;
> -				rte_smp_wmb();
>  				break;
>  			}
>  			old_remaining = remaining;
> --
> 2.25.1
> 


^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: [dpdk-dev] 回复: [PATCH] app/eventdev: remove unnecessary barrier for order test
  2021-05-18  9:27   ` [dpdk-dev] 回复: " Feifei Wang
@ 2021-05-18 14:05     ` Jerin Jacob
  2021-05-19  2:00       ` [dpdk-dev] 回复: " Feifei Wang
  0 siblings, 1 reply; 5+ messages in thread
From: Jerin Jacob @ 2021-05-18 14:05 UTC (permalink / raw)
  To: Feifei Wang; +Cc: jerinj, Ruifeng Wang, Honnappa Nagarahalli, dev, nd

On Tue, May 18, 2021 at 2:57 PM Feifei Wang <Feifei.Wang2@arm.com> wrote:
>
> Hi, Jerin
>
> Sorry to disturb you. Would you please help me review this patch, thanks very much.

In slowpath, I thought of having this barrier. But I agree that it can
be removed.
Since this is not bug. We will merge this patch in next release.



>
>
> Best Regards
> Feifei
>
> > -----Original Message-----
> > From: Feifei Wang <feifei.wang2@arm.com>
> > Sent: Monday, May 10, 2021 2:12 PM
> > To: jerinj@marvell.com
> > Cc: dev@dpdk.org; nd <nd@arm.com>; Feifei Wang
> > <Feifei.Wang2@arm.com>; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> > Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > Subject: [PATCH] app/eventdev: remove unnecessary barrier for order test
> >
> > For "order_launch_lcores" function, wmb after that the main lcore updates
> > the variable "t->err", which represents the end of the test signal, is
> > unnecessary. Because after the main lcore updates this siginal variable, it will
> > jump out of the launch function loop, and wait other lcores stop or return
> > error in the main function(evt_main.c).
> > During this time, there is no storing operation and thus no need for wmb.
> >
> > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > ---
> >  app/test-eventdev/test_order_common.c | 1 -
> >  1 file changed, 1 deletion(-)
> >
> > diff --git a/app/test-eventdev/test_order_common.c b/app/test-
> > eventdev/test_order_common.c
> > index 04456d56db..d7760061ba 100644
> > --- a/app/test-eventdev/test_order_common.c
> > +++ b/app/test-eventdev/test_order_common.c
> > @@ -308,7 +308,6 @@ order_launch_lcores(struct evt_test *test, struct
> > evt_options *opt,
> >                               rte_event_dev_dump(opt->dev_id, stdout);
> >                               evt_err("No schedules for seconds,
> > deadlock");
> >                               t->err = true;
> > -                             rte_smp_wmb();
> >                               break;
> >                       }
> >                       old_remaining = remaining;
> > --
> > 2.25.1
> >
>

^ permalink raw reply	[flat|nested] 5+ messages in thread

* [dpdk-dev] 回复:  回复: [PATCH] app/eventdev: remove unnecessary barrier for order test
  2021-05-18 14:05     ` Jerin Jacob
@ 2021-05-19  2:00       ` Feifei Wang
  0 siblings, 0 replies; 5+ messages in thread
From: Feifei Wang @ 2021-05-19  2:00 UTC (permalink / raw)
  To: Jerin Jacob; +Cc: jerinj, Ruifeng Wang, Honnappa Nagarahalli, dev, nd, nd



> -----邮件原件-----
> 发件人: Jerin Jacob <jerinjacobk@gmail.com>
> 发送时间: 2021年5月18日 22:05
> 收件人: Feifei Wang <Feifei.Wang2@arm.com>
> 抄送: jerinj@marvell.com; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>; dev@dpdk.org;
> nd <nd@arm.com>
> 主题: Re: [dpdk-dev] 回复: [PATCH] app/eventdev: remove unnecessary
> barrier for order test
> 
> On Tue, May 18, 2021 at 2:57 PM Feifei Wang <Feifei.Wang2@arm.com>
> wrote:
> >
> > Hi, Jerin
> >
> > Sorry to disturb you. Would you please help me review this patch, thanks
> very much.
> 
> In slowpath, I thought of having this barrier. But I agree that it can be
> removed.
> Since this is not bug. We will merge this patch in next release.

That's Ok. Thanks very much for your reviewing.

Best Regards
Feifei
> 
> 
> 
> >
> >
> > Best Regards
> > Feifei
> >
> > > -----Original Message-----
> > > From: Feifei Wang <feifei.wang2@arm.com>
> > > Sent: Monday, May 10, 2021 2:12 PM
> > > To: jerinj@marvell.com
> > > Cc: dev@dpdk.org; nd <nd@arm.com>; Feifei Wang
> > > <Feifei.Wang2@arm.com>; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> > > Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > > Subject: [PATCH] app/eventdev: remove unnecessary barrier for order
> > > test
> > >
> > > For "order_launch_lcores" function, wmb after that the main lcore
> > > updates the variable "t->err", which represents the end of the test
> > > signal, is unnecessary. Because after the main lcore updates this
> > > siginal variable, it will jump out of the launch function loop, and
> > > wait other lcores stop or return error in the main function(evt_main.c).
> > > During this time, there is no storing operation and thus no need for wmb.
> > >
> > > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > > ---
> > >  app/test-eventdev/test_order_common.c | 1 -
> > >  1 file changed, 1 deletion(-)
> > >
> > > diff --git a/app/test-eventdev/test_order_common.c b/app/test-
> > > eventdev/test_order_common.c index 04456d56db..d7760061ba 100644
> > > --- a/app/test-eventdev/test_order_common.c
> > > +++ b/app/test-eventdev/test_order_common.c
> > > @@ -308,7 +308,6 @@ order_launch_lcores(struct evt_test *test,
> > > struct evt_options *opt,
> > >                               rte_event_dev_dump(opt->dev_id, stdout);
> > >                               evt_err("No schedules for seconds,
> > > deadlock");
> > >                               t->err = true;
> > > -                             rte_smp_wmb();
> > >                               break;
> > >                       }
> > >                       old_remaining = remaining;
> > > --
> > > 2.25.1
> > >
> >

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: [dpdk-dev] [PATCH] app/eventdev: remove unnecessary barrier for order test
  2021-05-10  6:11 [dpdk-dev] [PATCH] app/eventdev: remove unnecessary barrier for order test Feifei Wang
       [not found] ` <AM5PR0802MB2465F23DEA897DA3CFB06B029E2C9@AM5PR0802MB2465.eurprd08.prod.outlook.com>
@ 2021-06-30  6:49 ` Jerin Jacob
  1 sibling, 0 replies; 5+ messages in thread
From: Jerin Jacob @ 2021-06-30  6:49 UTC (permalink / raw)
  To: Feifei Wang; +Cc: Jerin Jacob, dpdk-dev, nd, Ruifeng Wang, Honnappa Nagarahalli

On Mon, May 10, 2021 at 11:42 AM Feifei Wang <feifei.wang2@arm.com> wrote:
>
> For "order_launch_lcores" function, wmb after that the main lcore
> updates the variable "t->err", which represents the end of the test
> signal, is unnecessary. Because after the main lcore updates this
> siginal variable, it will jump out of the launch function loop, and wait
> other lcores stop or return error in the main function(evt_main.c).
> During this time, there is no storing operation and thus no need for
> wmb.
>
> Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>

Acked-by: Jerin Jacob <jerinj@marvell.com>
Applied to dpdk-next-net-eventdev/for-main. Thanks

> ---
>  app/test-eventdev/test_order_common.c | 1 -
>  1 file changed, 1 deletion(-)
>
> diff --git a/app/test-eventdev/test_order_common.c b/app/test-eventdev/test_order_common.c
> index 04456d56db..d7760061ba 100644
> --- a/app/test-eventdev/test_order_common.c
> +++ b/app/test-eventdev/test_order_common.c
> @@ -308,7 +308,6 @@ order_launch_lcores(struct evt_test *test, struct evt_options *opt,
>                                 rte_event_dev_dump(opt->dev_id, stdout);
>                                 evt_err("No schedules for seconds, deadlock");
>                                 t->err = true;
> -                               rte_smp_wmb();
>                                 break;
>                         }
>                         old_remaining = remaining;
> --
> 2.25.1
>

^ permalink raw reply	[flat|nested] 5+ messages in thread

end of thread, other threads:[~2021-06-30  6:49 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-05-10  6:11 [dpdk-dev] [PATCH] app/eventdev: remove unnecessary barrier for order test Feifei Wang
     [not found] ` <AM5PR0802MB2465F23DEA897DA3CFB06B029E2C9@AM5PR0802MB2465.eurprd08.prod.outlook.com>
2021-05-18  9:27   ` [dpdk-dev] 回复: " Feifei Wang
2021-05-18 14:05     ` Jerin Jacob
2021-05-19  2:00       ` [dpdk-dev] 回复: " Feifei Wang
2021-06-30  6:49 ` [dpdk-dev] " Jerin Jacob

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git