Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 23 May 2016 15:38:32 +0000
From:      KrishnamRaju ErapaRaju <Krishna2@chelsio.com>
To:        Hans Petter Selasky <hps@selasky.org>, "freebsd-infiniband@freebsd.org" <freebsd-infiniband@freebsd.org>
Subject:   RE: write() system call(via rdma_get_cm_event) is not honoring a signal with flag SA_RESTART.
Message-ID:  <4EAB2619577FCA4EBCE11F17B7373447C4313CE5@nice.asicdesigners.com>
In-Reply-To: <6085b7db-aab4-0496-1789-0992bc1f1c5d@selasky.org>
References:  <4EAB2619577FCA4EBCE11F17B7373447C4313548@nice.asicdesigners.com> <3500e324-7d7c-ed94-5913-911fd9877bef@selasky.org> <4EAB2619577FCA4EBCE11F17B7373447C431372B@nice.asicdesigners.com> <6085b7db-aab4-0496-1789-0992bc1f1c5d@selasky.org>

next in thread | previous in thread | raw e-mail | index | archive | help
Hi Hans,

Did you get a chance to have a closer look into this issue?
Looping in application for errno: 512 would be workaround, but the fix(I th=
ink) should be in RDMA core, as there are many rdma applications, which alr=
eady written assuming system calls gets restarted when interrupted by a sig=
nal.


Thanks,
Krishna.

-----Original Message-----
From: Hans Petter Selasky [mailto:hps@selasky.org]=20
Sent: Thursday, May 19, 2016 6:04 PM
To: KrishnamRaju ErapaRaju <Krishna2@chelsio.com>; freebsd-infiniband@freeb=
sd.org
Subject: Re: write() system call(via rdma_get_cm_event) is not honoring a s=
ignal with flag SA_RESTART.

On 05/19/16 14:22, KrishnamRaju ErapaRaju wrote:
> Hans,
>
> I think it's not a regression.
>
> To verify it I have fetched the latest sources(both FreeBSD & OFED 3.2) a=
nd started building...
>  Between, may I know when will OFED 3.2 patches be pushed to upstream?
>
> Also, before started building,  I'd quickly replaced -ERESTARTSYS with -5=
12 in ucma_get_event, I still don't see the write() system call getting res=
tarted.
>
> Here are the return codes:
> ucma_get_event, returns -512
> rdma_get_cm_event, returns -1, errorno: 512
>
> So can FreeBSD understand the interrupted system call return value(-512) =
like Linux?

Hi,

I need to check this a bit closer. Possibly you'll need to loop in the appl=
ication or library when you see errno 512.

--HPS



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4EAB2619577FCA4EBCE11F17B7373447C4313CE5>