Re: TCP_KEEPIDLE vs TCPTV_KEEP_IDLE

2013-05-06 Thread Richard Sharpe
On Mon, May 6, 2013 at 6:35 AM, Gleb Smirnoff wrote: > On Mon, May 06, 2013 at 06:32:37AM -0700, Richard Sharpe wrote: > R> On Mon, May 6, 2013 at 6:28 AM, Gleb Smirnoff wrote: > R> > On Mon, May 06, 2013 at 06:26:14AM -0700, Richard Sharpe wrote: > R> > R> Than

Re: TCP_KEEPIDLE vs TCPTV_KEEP_IDLE

2013-05-06 Thread Richard Sharpe
On Mon, May 6, 2013 at 6:28 AM, Gleb Smirnoff wrote: > On Mon, May 06, 2013 at 06:26:14AM -0700, Richard Sharpe wrote: > R> Thank you for that answer. I don't have the option to install FreeBSD > R> 9.1. Maybe we will move to 9.1 in the future. > R> > R> Howe

Re: TCP_KEEPIDLE vs TCPTV_KEEP_IDLE

2013-05-06 Thread Richard Sharpe
On Mon, May 6, 2013 at 6:23 AM, Gleb Smirnoff wrote: > On Mon, May 06, 2013 at 06:15:11AM -0700, Richard Sharpe wrote: > R> On Mon, May 6, 2013 at 1:22 AM, Gleb Smirnoff wrote: > R> > On Sun, May 05, 2013 at 09:40:42AM -0700, Richard Sharpe wrote: > R> > R> Sa

Re: TCP_KEEPIDLE vs TCPTV_KEEP_IDLE

2013-05-06 Thread Richard Sharpe
On Mon, May 6, 2013 at 1:22 AM, Gleb Smirnoff wrote: > On Sun, May 05, 2013 at 09:40:42AM -0700, Richard Sharpe wrote: > R> Samba currently has a way to set socket parameters from the smb.conf. > R> > R> This works fine for things like SO_SNDBUF etc, but not so well for t

TCP_KEEPIDLE vs TCPTV_KEEP_IDLE

2013-05-05 Thread Richard Sharpe
happening because the names you would use in the smb.conf file would be Linux-specific, and documentation is often woefully incomplete. Is there a better method? -- Regards, Richard Sharpe (何以解憂?唯有杜康。--曹操) ___ freebsd-net@freebsd.org mailing list http

Re: Is there any way to limit the amount of data in an mbuf chain submitted to a driver?

2013-05-04 Thread Richard Sharpe
On Sat, May 4, 2013 at 4:59 PM, Eric van Gyzen wrote: > On 05/04/2013 04:19 PM, Richard Sharpe wrote: >> On Sat, May 4, 2013 at 2:18 PM, Jack Vogel wrote: >>> Ahh, Twinville, new hardware :) The version at the tip is 2.5.8 and I am >>> working on version 2.5.12 inter

Re: Is there any way to limit the amount of data in an mbuf chain submitted to a driver?

2013-05-04 Thread Richard Sharpe
e. I would love to. Where is the repo. > Jack > > > > On Sat, May 4, 2013 at 1:54 PM, Richard Sharpe > wrote: >> >> On Sat, May 4, 2013 at 1:41 PM, Jack Vogel wrote: >> > If you don't use TSO you will hurt your TX performance significantly >> > fro

Re: Is there any way to limit the amount of data in an mbuf chain submitted to a driver?

2013-05-04 Thread Richard Sharpe
ss=0x02 at slot=0 function=1 The version calls itself ixgbe-2.4.4 ... Hmmm, copyright is 2001-2010 ... so perhaps a bit old. > Jack > > > > On Sat, May 4, 2013 at 1:30 PM, Richard Sharpe > wrote: >> >> On Sat, May 4, 2013 at 10:39 AM, Adrian Chadd wrote: &

Re: Is there any way to limit the amount of data in an mbuf chain submitted to a driver?

2013-05-04 Thread Richard Sharpe
On Sat, May 4, 2013 at 10:39 AM, Adrian Chadd wrote: > On 4 May 2013 06:52, Richard Sharpe wrote: >> Hi folks, >> >> I understand better why I am seeing EINVAL intermittently when sending >> data from Samba via SMB2. >> >> The ixgbe driver, for TSO reas

Is there any way to limit the amount of data in an mbuf chain submitted to a driver?

2013-05-04 Thread Richard Sharpe
t hit. To confirm this I am going to set SO_SNDBUF back to the default of 65536 and test again. My repros are very reliable. However, I wondered if my only way around this if I want to continue to use SO_SNDBUF sizes larger than 65536 is to fragment large mbuf chains in the driver? -- Regards, Ri

Re: Seeing EINVAL from writev on 8.0 to a non-blocking socket even though the data seems to hit the wire

2013-05-03 Thread Richard Sharpe
On Fri, May 3, 2013 at 10:18 AM, Richard Sharpe wrote: > On Fri, May 3, 2013 at 7:39 AM, Eric van Gyzen wrote: >> On 05/02/2013 19:00, Richard Sharpe wrote: >>> On Thu, May 2, 2013 at 7:52 AM, Eric van Gyzen wrote: >>>> On 05/02/2013 08:48, Richard Sharpe wrote:

Re: Seeing EINVAL from writev on 8.0 to a non-blocking socket even though the data seems to hit the wire

2013-05-03 Thread Richard Sharpe
On Fri, May 3, 2013 at 7:39 AM, Eric van Gyzen wrote: > On 05/02/2013 19:00, Richard Sharpe wrote: >> On Thu, May 2, 2013 at 7:52 AM, Eric van Gyzen wrote: >>> On 05/02/2013 08:48, Richard Sharpe wrote: >>>> On Wed, May 1, 2013 at 9:34 PM, Alfred Perlstein

Re: Seeing EINVAL from writev on 8.0 to a non-blocking socket even though the data seems to hit the wire

2013-05-02 Thread Richard Sharpe
On Thu, May 2, 2013 at 7:52 AM, Eric van Gyzen wrote: > On 05/02/2013 08:48, Richard Sharpe wrote: >> On Wed, May 1, 2013 at 9:34 PM, Alfred Perlstein wrote: >>> On 5/1/13 8:03 PM, Richard Sharpe wrote: >>>> Hi folks, >>>> >>>> I am check

Re: Seeing EINVAL from writev on 8.0 to a non-blocking socket even though the data seems to hit the wire

2013-05-02 Thread Richard Sharpe
On Thu, May 2, 2013 at 7:52 AM, Eric van Gyzen wrote: > On 05/02/2013 08:48, Richard Sharpe wrote: >> On Wed, May 1, 2013 at 9:34 PM, Alfred Perlstein wrote: >>> On 5/1/13 8:03 PM, Richard Sharpe wrote: >>>> Hi folks, >>>> >>>> I am check

Re: Seeing EINVAL from writev on 8.0 to a non-blocking socket even though the data seems to hit the wire

2013-05-02 Thread Richard Sharpe
On Wed, May 1, 2013 at 9:34 PM, Alfred Perlstein wrote: > On 5/1/13 8:03 PM, Richard Sharpe wrote: >> Hi folks, >> >> I am checking to see if there are any known bugs with respect to this >> in FreeBSD 8.0. >> >> Situation is that Samba 3.6.6 uses writev

Re: Seeing EINVAL from writev on 8.0 to a non-blocking socket even though the data seems to hit the wire

2013-05-01 Thread Richard Sharpe
On Wed, May 1, 2013 at 9:34 PM, Alfred Perlstein wrote: > On 5/1/13 8:03 PM, Richard Sharpe wrote: >> Hi folks, >> >> I am checking to see if there are any known bugs with respect to this >> in FreeBSD 8.0. >> >> Situation is that Samba 3.6.6 uses writev

Seeing EINVAL from writev on 8.0 to a non-blocking socket even though the data seems to hit the wire

2013-05-01 Thread Richard Sharpe
on a smaller IOVEC. Where should I look to check if there is some path where this might be happening? Is this even the correct mailing list? -- Regards, Richard Sharpe (何以解憂?唯有杜康。--曹操) ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org