Date: Tue, 19 May 2020 23:47:10 +0200 From: "Kristof Provost" <kp@FreeBSD.org> To: "Andrew Gallatin" <gallatin@cs.duke.edu> Cc: "Eric Joyner" <erj@FreeBSD.org>, "Jacob Keller" <jacob.e.keller@intel.com>, shurd@FreeBSD.org, src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: Re: svn commit: r347418 - head/sys/net Message-ID: <CE8E8A09-00DA-4496-B3A8-E7BFA83ECFBC@FreeBSD.org> In-Reply-To: <c954afea-b96d-a2c3-7037-4a419d23be86@cs.duke.edu> References: <201905100041.x4A0fhNT083122@repo.freebsd.org> <3BBFB371-EA44-4EE9-8A55-542CDE273CC4@FreeBSD.org> <c954afea-b96d-a2c3-7037-4a419d23be86@cs.duke.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
On 19 May 2020, at 17:02, Andrew Gallatin wrote:
> On 2020-05-19 04:21, Kristof Provost wrote:
>
>> The if_bnxt driver initialises |.isc_nrxd_max = {INT32_MAX,
>> INT32_MAX, INT32_MAX},|, so presumably that’s the cause.
>> I don’t know what a sane value would be though. I’ve defaulted to
>> 4096 (because that’s what some other iflib users seems to do) for
>> now, and that seems to work. It doesn’t panic and I can get traffic
>> through it at least:
>
> You seem to be setting the max, not the default, and 4K max
> descriptors on a 100g device is going to basically cripple it.
>
Yeah, I just grabbed whatever number other iflib users used. My
immediate concern was to get it to stop panicking.
> How about setting to the next power of 2 below max int so as to keep
> with the authors intent?
>
Makes sense, yes.
> If we don't already have a macro, something like (INT32_MAX >> 1) + 1
>
https://reviews.freebsd.org/D24922
Best regards,
Kristof
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CE8E8A09-00DA-4496-B3A8-E7BFA83ECFBC>