DPDK CI discussions
 help / color / mirror / Atom feed
* Re: [dpdk-ci] [dpdk-dev] [PATCH v1 0/1] distributor test fix
       [not found] ` <20210119035910.8324-1-l.wojciechow@partner.samsung.com>
@ 2021-01-19  8:44   ` David Marchand
  2021-01-19 13:06     ` Lukasz Wojciechowski
       [not found]   ` <20210119035910.8324-2-l.wojciechow@partner.samsung.com>
  1 sibling, 1 reply; 5+ messages in thread
From: David Marchand @ 2021-01-19  8:44 UTC (permalink / raw)
  To: Lukasz Wojciechowski; +Cc: dev, Aaron Conole, ci, Lincoln Lavoie

On Tue, Jan 19, 2021 at 4:59 AM Lukasz Wojciechowski
<l.wojciechow@partner.samsung.com> wrote:
>
> According to the discussion in this thread:
> https://protect2.fireeye.com/v1/url?k=24ecce33-7b77f77c-24ed457c-0cc47a30
> d446-e317a6beb8cfa273&q=1&e=f8bb12df-3698-4bce-a7b7-d72e22b91431&u=https%
> 3A%2F%2Finbox.dpdk.org%2Fdev%2FCAOE1vsOehF4ZMOWffpEv%3DQF6YOc5wXtg23PV83B
> 9CLiTMn8wQA%40mail.gmail.com%2F%23r
>
> I was able to reproduce the distributor test failure in the exactly same
> way as described, but on x86_64 machine with 32 cores.
> So it does not seem to be the problem related to the ARM architecture.
> IMO issue occurs when there are many worker threads returning at the same
> time packets.
>
> I was not able to observe the issue on ARM devices, but I used only
> machines with 4 cores. So that is max 3 worker cores,
> so maximum of 32*3 = 96 packets processed at the same time
> which is less than 127 , so the issue cannot occur.
>
> Can anyone verify this patch on a machine similar to one used in CI lab,
> on which the issue occurred?

Thanks for looking at it, Lukasz.
Unfortunately, I can't reproduce it on my x86 system (26 workers in
the test) and I don't have a ARM machine.

-- 
David Marchand


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

* Re: [dpdk-ci] [dpdk-dev] [PATCH v1 0/1] distributor test fix
  2021-01-19  8:44   ` [dpdk-ci] [dpdk-dev] [PATCH v1 0/1] distributor test fix David Marchand
@ 2021-01-19 13:06     ` Lukasz Wojciechowski
  2021-01-28 13:34       ` David Marchand
  0 siblings, 1 reply; 5+ messages in thread
From: Lukasz Wojciechowski @ 2021-01-19 13:06 UTC (permalink / raw)
  To: David Marchand; +Cc: dev, Aaron Conole, ci, Lincoln Lavoie

Thank you David,
If you have the possibility you can try on some emulated virtual 
machine, where cores are much slower, so the workers don't return 
packages immediately.
It reproduces in 100% cases in such environment.

Best regards

Lukasz

W dniu 19.01.2021 o 09:44, David Marchand pisze:
> On Tue, Jan 19, 2021 at 4:59 AM Lukasz Wojciechowski
> <l.wojciechow@partner.samsung.com> wrote:
>> According to the discussion in this thread:
>> https://protect2.fireeye.com/v1/url?k=24ecce33-7b77f77c-24ed457c-0cc47a30
>> d446-e317a6beb8cfa273&q=1&e=f8bb12df-3698-4bce-a7b7-d72e22b91431&u=https%
>> 3A%2F%2Finbox.dpdk.org%2Fdev%2FCAOE1vsOehF4ZMOWffpEv%3DQF6YOc5wXtg23PV83B
>> 9CLiTMn8wQA%40mail.gmail.com%2F%23r
>>
>> I was able to reproduce the distributor test failure in the exactly same
>> way as described, but on x86_64 machine with 32 cores.
>> So it does not seem to be the problem related to the ARM architecture.
>> IMO issue occurs when there are many worker threads returning at the same
>> time packets.
>>
>> I was not able to observe the issue on ARM devices, but I used only
>> machines with 4 cores. So that is max 3 worker cores,
>> so maximum of 32*3 = 96 packets processed at the same time
>> which is less than 127 , so the issue cannot occur.
>>
>> Can anyone verify this patch on a machine similar to one used in CI lab,
>> on which the issue occurred?
> Thanks for looking at it, Lukasz.
> Unfortunately, I can't reproduce it on my x86 system (26 workers in
> the test) and I don't have a ARM machine.
>
-- 
Lukasz Wojciechowski
Principal Software Engineer

Samsung R&D Institute Poland
Samsung Electronics
Office +48 22 377 88 25
l.wojciechow@partner.samsung.com


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

* Re: [dpdk-ci] [dpdk-dev] [PATCH v1 0/1] distributor test fix
  2021-01-19 13:06     ` Lukasz Wojciechowski
@ 2021-01-28 13:34       ` David Marchand
  0 siblings, 0 replies; 5+ messages in thread
From: David Marchand @ 2021-01-28 13:34 UTC (permalink / raw)
  To: Lukasz Wojciechowski; +Cc: dev, Aaron Conole, ci, Lincoln Lavoie

On Tue, Jan 19, 2021 at 2:07 PM Lukasz Wojciechowski
<l.wojciechow@partner.samsung.com> wrote:
>
> Thank you David,
> If you have the possibility you can try on some emulated virtual
> machine, where cores are much slower, so the workers don't return
> packages immediately.
> It reproduces in 100% cases in such environment.

I reproduced the issue with starting a testpmd on the same cores in this system.
I usually reproduce it after 1-2 minutes of continuously running the
distributor_autotest unit test.

I've applied your fix in my tree and I will let this loop run for a while.


-- 
David Marchand


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

* Re: [dpdk-ci] [dpdk-stable] [PATCH v1 1/1] test/distributor: prevent return buffer overload
       [not found]     ` <CAJFAV8ws=mCTFF6hQQ8kUFRxuR8QYGzB7ubMFRBDCiU=JmEnZQ@mail.gmail.com>
@ 2021-01-29  8:03       ` David Marchand
  2021-01-29 12:36         ` Lukasz Wojciechowski
  0 siblings, 1 reply; 5+ messages in thread
From: David Marchand @ 2021-01-29  8:03 UTC (permalink / raw)
  To: Lukasz Wojciechowski, David Hunt, Bruce Richardson
  Cc: dev, dpdk stable, Ruifeng Wang (Arm Technology China), ci

On Thu, Jan 28, 2021 at 3:10 PM David Marchand
<david.marchand@redhat.com> wrote:
>
> On Tue, Jan 19, 2021 at 4:59 AM Lukasz Wojciechowski
> <l.wojciechow@partner.samsung.com> wrote:
> >
> > The distributor library implementation uses a cyclic queue to store
> > packets returned from workers. These packets can be later collected
> > with rte_distributor_returned_pkts() call.
> > However the queue has limited capacity. It is able to contain only
> > 127 packets (RTE_DISTRIB_RETURNS_MASK).
> >
> > Big burst tests sent 1024 packets in 32 packets bursts without waiting
> > until they are processed by the distributor. In case when tests were
> > run with big number of worker threads, it happened that more than
> > 127 packets were returned from workers and put into cyclic queue.
> > This caused packets to be dropped by the queue, making them impossible
> > to be collected later with rte_distributor_returned_pkts() calls.
> > However the test waited for all packets to be returned infinitely.
> >
> > This patch fixes the big burst test by not allowing more than
> > queue capacity packets to be processed at the same time, making
> > impossible to drop any packets.
> > It also cleans up duplicated code in the same test.
> >
> > Bugzilla ID: 612
> > Fixes: c0de0eb82e40 ("distributor: switch over to new API")
> > Cc: stable@dpdk.org
> >
> > Signed-off-by: Lukasz Wojciechowski <l.wojciechow@partner.samsung.com>
> Tested-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: David Hunt <david.hunt@intel.com>

Applied, thanks Lukasz.

This should fix the issue seen at UNH on the ARM server.

-- 
David Marchand


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

* Re: [dpdk-ci] [dpdk-stable] [PATCH v1 1/1] test/distributor: prevent return buffer overload
  2021-01-29  8:03       ` [dpdk-ci] [dpdk-stable] [PATCH v1 1/1] test/distributor: prevent return buffer overload David Marchand
@ 2021-01-29 12:36         ` Lukasz Wojciechowski
  0 siblings, 0 replies; 5+ messages in thread
From: Lukasz Wojciechowski @ 2021-01-29 12:36 UTC (permalink / raw)
  To: David Marchand, David Hunt, Bruce Richardson
  Cc: dev, dpdk stable, Ruifeng Wang (Arm Technology China), ci

Thank you guys!

W dniu 29.01.2021 o 09:03, David Marchand pisze:
> On Thu, Jan 28, 2021 at 3:10 PM David Marchand
> <david.marchand@redhat.com> wrote:
>> On Tue, Jan 19, 2021 at 4:59 AM Lukasz Wojciechowski
>> <l.wojciechow@partner.samsung.com> wrote:
>>> The distributor library implementation uses a cyclic queue to store
>>> packets returned from workers. These packets can be later collected
>>> with rte_distributor_returned_pkts() call.
>>> However the queue has limited capacity. It is able to contain only
>>> 127 packets (RTE_DISTRIB_RETURNS_MASK).
>>>
>>> Big burst tests sent 1024 packets in 32 packets bursts without waiting
>>> until they are processed by the distributor. In case when tests were
>>> run with big number of worker threads, it happened that more than
>>> 127 packets were returned from workers and put into cyclic queue.
>>> This caused packets to be dropped by the queue, making them impossible
>>> to be collected later with rte_distributor_returned_pkts() calls.
>>> However the test waited for all packets to be returned infinitely.
>>>
>>> This patch fixes the big burst test by not allowing more than
>>> queue capacity packets to be processed at the same time, making
>>> impossible to drop any packets.
>>> It also cleans up duplicated code in the same test.
>>>
>>> Bugzilla ID: 612
>>> Fixes: c0de0eb82e40 ("distributor: switch over to new API")
>>> Cc: stable@dpdk.org
>>>
>>> Signed-off-by: Lukasz Wojciechowski <l.wojciechow@partner.samsung.com>
>> Tested-by: David Marchand <david.marchand@redhat.com>
> Reviewed-by: David Hunt <david.hunt@intel.com>
>
> Applied, thanks Lukasz.
>
> This should fix the issue seen at UNH on the ARM server.
>
-- 
Lukasz Wojciechowski
Principal Software Engineer

Samsung R&D Institute Poland
Samsung Electronics
Office +48 22 377 88 25
l.wojciechow@partner.samsung.com


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

end of thread, other threads:[~2021-01-29 12:37 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
     [not found] <CGME20210119035920eucas1p15da5a04b73d19e63287dc14905d765f2@eucas1p1.samsung.com>
     [not found] ` <20210119035910.8324-1-l.wojciechow@partner.samsung.com>
2021-01-19  8:44   ` [dpdk-ci] [dpdk-dev] [PATCH v1 0/1] distributor test fix David Marchand
2021-01-19 13:06     ` Lukasz Wojciechowski
2021-01-28 13:34       ` David Marchand
     [not found]   ` <20210119035910.8324-2-l.wojciechow@partner.samsung.com>
     [not found]     ` <CAJFAV8ws=mCTFF6hQQ8kUFRxuR8QYGzB7ubMFRBDCiU=JmEnZQ@mail.gmail.com>
2021-01-29  8:03       ` [dpdk-ci] [dpdk-stable] [PATCH v1 1/1] test/distributor: prevent return buffer overload David Marchand
2021-01-29 12:36         ` Lukasz Wojciechowski

DPDK CI discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror http://inbox.dpdk.org/ci/0 ci/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 ci ci/ http://inbox.dpdk.org/ci \
		ci@dpdk.org
	public-inbox-index ci

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


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