Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 25 Mar 2014 12:33:30 -0700
From:      Sean Fagan <sef@ixsystems.com>
To:        Ryan Stone <rysto32@gmail.com>
Cc:        freebsd-net <freebsd-net@freebsd.org>
Subject:   Re: Non-interrupt packet sending and receiving
Message-ID:  <B749E41A-4B5F-436D-9033-66526EB4B872@ixsystems.com>
In-Reply-To: <CAFMmRNxKAX9d0A=qCtX7f-NSKEM_4KcEZFMFvrzRVNzR=oWcKg@mail.gmail.com>
References:  <27D25BFC-7BB3-400F-8405-43B8D08135D2@ixsystems.com> <CAFMmRNxKAX9d0A=qCtX7f-NSKEM_4KcEZFMFvrzRVNzR=oWcKg@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Mar 25, 2014, at 12:15 PM, Ryan Stone <rysto32@gmail.com> wrote:

> You might want to take a look at the projects/sv branch, which
> implement kernel core dumps over the network.  We had to solve a
> similar problem there (in lem, em, igb and ixgbe) and ended up
> piggybacking on most of the DEVICE_POLLING code to do it.  The work
> ended up stalling over objections over calling into the mbuf allocator
> (which I guess may be a stumbling block for your work).  Unfortunately
> we weren't able to come up with a clean way to share the existing
> rx/tx paths in the drivers while separating the mbuf allocations out.

I checked the XNU drivers I could find online, and it turns out that they
did mbuf allocations.  Since I was using that as my model, I went
with it for now.

I was aware of the network core dump work, but not until I'd started to make
some progress with this.  (The kdp protocol theoretically has support for
dumping a core over the network, but I haven't implemented that at all.)
Looking at if_lem.c, it appears similar to a large degree.  Perhaps I should
start from scratch...

Sean.




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?B749E41A-4B5F-436D-9033-66526EB4B872>