On 9.5.2023. 9:56, Alexander Bluhm wrote:
> On Sun, May 07, 2023 at 09:00:31PM +0200, Alexander Bluhm wrote:
>> Not sure if I addressed all corner cases already. I think IPsec
>> is missing.
> Updated diff:
> - parts have been commited
> - works with IPsec now
> - some bugs fixed
> - sysctl net.in
On Tue, May 09, 2023 at 09:56:36AM +0200, Alexander Bluhm wrote:
> On Sun, May 07, 2023 at 09:00:31PM +0200, Alexander Bluhm wrote:
> > Not sure if I addressed all corner cases already. I think IPsec
> > is missing.
>
> Updated diff:
> - parts have been commited
> - works with IPsec now
Thanks f
On Sun, May 07, 2023 at 09:00:31PM +0200, Alexander Bluhm wrote:
> Not sure if I addressed all corner cases already. I think IPsec
> is missing.
Updated diff:
- parts have been commited
- works with IPsec now
- some bugs fixed
- sysctl net.inet.tcp.tso
- netstat TSO counter
If you test this, rec
On Fri, May 05, 2023 at 05:54:49PM +0200, Alexander Bluhm wrote:
> Claudio suggested to implement TCP send offloading in software as
> a fallback if hardware cannot do it.
Updated diff below:
- some cleanup has been commited
- pf route-to should work now
- disable TSO if IP options are set
Not su
Hi,
Claudio suggested to implement TCP send offloading in software as
a fallback if hardware cannot do it. So I took Jan's diff, ripped
that part out and polished it.
Result is that software TSO can be a bit faster than regular TCP.
http://bluhm.genua.de/perform/results/2023-05-04T07%3A05%3A11Z
