ame straight back into the tun instead.)
--
Colin Percival
Security Officer Emeritus, FreeBSD | The power to serve
Founder, Tarsnap | www.tarsnap.com | Online backups for the truly paranoid
___
freebsd-net@freebsd.org mailing list
https://lists.freebsd.or
ision=327013 . Can you
> please file a bug on this? This looks like an iflib issue.
I can confirm that this happens with the 12.0-CURRENT r327524 snasphot (on a
c4.8xlarge EC2 instance, in case it matters).
Colin Percival
> On 1/12/18, 2:43 AM, "owner-freebsd-...@freebsd.org
makes me wonder if this is a similar issue. (If
it is, there's a locking problem somewhere...)
Colin Percival
On 01/12/18 01:23, Bradley T. Hughes wrote:
> (Cross-posting to -net, but I'm not subscribed there... yet)
>
> I was wondering if anyone else has experienced this panic
On 01/18/17 02:36, Konstantin Belousov wrote:
> On Wed, Jan 18, 2017 at 04:37:40AM +0000, Colin Percival wrote:
>> Thanks, looks like that was exactly it -- if the TCP send buffer was full
>> we would call sbwait, and if a signal arrived it would return ERESTART.
>> It l
On 01/17/17 02:06, Konstantin Belousov wrote:
> On Tue, Jan 17, 2017 at 04:57:23AM +0000, Colin Percival wrote:
>> I think I've tracked an NFS problem down to sosend returning ERESTART; it
>> looks like it's easy to work around this, but I'm not sure *why* sosend is
&
ng something obvious? In case it matters, this is NFS making use
of RPC code, sosending over a TCP connection which goes out over an ixv
interface.
--
Colin Percival
Security Officer Emeritus, FreeBSD | The power to serve
Founder, Tarsnap | www.tarsnap.com | Online backups fo
On 06/03/12 20:14, Lawrence Stewart wrote:
> On 06/04/12 02:51, Colin Percival wrote:
>> I've attached a new patch which:
>> 1. adds a IFCAP_TSO_MSS "capability" and a if_tx_tso_mss field to struct
>> ifnet,
>
> A minor thing, but I don't like t
On 06/03/12 15:56, Bjoern A. Zeeb wrote:
> On 3. Jun 2012, at 16:51 , Colin Percival wrote:
>> I've attached a new patch which:
>> 1. adds a IFCAP_TSO_MSS "capability" and a if_tx_tso_mss field to struct
>> ifnet,
>> 2. sets these in netfront when
On 06/03/12 12:05, Andrew Gallatin wrote:
> On 06/03/12 12:51, Colin Percival wrote:
>> I've attached a new patch which:
>> 1. adds a IFCAP_TSO_MSS "capability" and a if_tx_tso_mss field to struct
>> ifnet,
>> 2. sets these in netfront when the IFCAP_TSO
On 05/30/12 08:30, Andrew Gallatin wrote:
> On 05/30/12 10:59, Colin Percival wrote:
>> The Xen virtual network interface has an issue (ok, really the issue is with
>> the linux back-end, but that's what most people are using) where it can't
>> handle scatter-gather
On 05/30/12 08:30, Andrew Gallatin wrote:
> On 05/30/12 10:59, Colin Percival wrote:
>> The Xen virtual network interface has an issue (ok, really the issue is with
>> the linux back-end, but that's what most people are using) where it can't
>> handle scatter-gather
esting on EC2 with 10 GbE and TSO turned
on, I get ~250-300 Mbps without this patch and 3-4 Gbps with this patch;
this replaces a patch I was using in my EC2 builds which did (6)&(7) above
with a hard-coded maximum mbuf chain length.
Please tell me all the things I did wrong. :-)
--
Colin
e what the right way is to feed a value from the interface up into
tcp_output; can someone advise?
--
Colin Percival
Security Officer, FreeBSD | freebsd.org | The power to serve
Founder / author, Tarsnap | tarsnap.com | Online backups for the truly
I've attached a patch which fixes this and improves Linux->FreeBSD network
performance on EC2 cluster compute nodes from 13 Mbps to 4100 Mbps... any
objections to me committing this?
--
Colin Percival
Security Officer, FreeBSD | freebsd.org | The power to serve
Founder / author,
m->m_data -= hdrlen;
> #else
> [snip packet data copying code]
> #endif /* notyet */
These have been around since CVS revision 1.1; going further back, I find this
in "@(#)tcp_output.c7.22 (Berkeley) 8/31/90" from 4.3BSD Net/2.
Can we agree that this part
Hi,
Just in case it isn't obvious already, the sendfile data corruption bug
discussed on the freebsd-net list last week is FreeBSD-SA-10:07.mbuf:
http://security.FreeBSD.org/advisories/FreeBSD-SA-10:07.mbuf.asc
--
Colin Percival
Security Officer, FreeBSD | freebsd.org | The power to
At 14:35 04/05/2004, Luigi Rizzo wrote:
>On Tue, May 04, 2004 at 01:42:20PM +0100, Colin Percival wrote:
>> if we're going to check that
>> 0 < ifp->if_index <= if_index, it seems that we should also be
>> checking that ifp->if_index corresponds to an interfac
than a gap left behind when an interface was
removed).
Colin Percival
Index: src/sys/netinet/ip_input.c
===
RCS file: /home/ncvs/src/sys/netinet/ip_input.c,v
retrieving revision 1.270
diff -u -p -r1.270 ip_input.c
--- src/sys/netinet/
ty fix.
Could someone on -net look at this?
Colin Percival
___
[EMAIL PROTECTED] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
[CC: secteam, since this relates to a recent advisory]
In http://www.freebsd.org/cgi/query-pr.cgi?pr=kern/64053 a
problem is reported as having been introduced by the recent
TCP reassembly patch.
Could someone look into this please?
Colin Percival
our, and uses the same 6
packets as it would if TTCP were disabled.
Colin Percival
___
[EMAIL PROTECTED] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
21 matches
Mail list logo
