On Sat, Mar 18, 2017 at 7:07 PM, Subash Abhinov Kasiviswanathan
wrote:
>> Less than 1% performance improvement in a benchmark doesn't justify
>> the complexity of the patch. Eric's hypothesis was that an unconnected
>> UDP socket may show issues because of cache misses in look-ups due to
>> so man
On Sat, 2017-03-18 at 20:07 -0600, Subash Abhinov Kasiviswanathan wrote:
> > Less than 1% performance improvement in a benchmark doesn't justify
> > the complexity of the patch. Eric's hypothesis was that an unconnected
> > UDP socket may show issues because of cache misses in look-ups due to
> > s
Less than 1% performance improvement in a benchmark doesn't justify
the complexity of the patch. Eric's hypothesis was that an unconnected
UDP socket may show issues because of cache misses in look-ups due to
so many different sources. This should be fairly easy to benchmark by
randomly setting so
On Sat, Mar 18, 2017 at 10:32 AM, Subash Abhinov Kasiviswanathan
wrote:
>> All these hypotheses are quite testable, and it should be obvious that
>> if a patch is supposed to improve performance there should be some
>> effort to quantify the impact.
>
>
> Hi Tom
>
> I ran a single stream unconnect
All these hypotheses are quite testable, and it should be obvious that
if a patch is supposed to improve performance there should be some
effort to quantify the impact.
Hi Tom
I ran a single stream unconnected UDPv4 test on an ARM64 system and I
see
a slight increase in performance (782 -> 788
On Fri, Mar 10, 2017 at 4:22 PM, Eric Dumazet wrote:
> On Fri, 2017-03-10 at 08:33 -0800, Tom Herbert wrote:
>
>> Okay, now I'm confused. You're saying that when early demux was added
>> for IPv6 performance improved, but this patch is allowing early demux
>> to be disabled on the basis that it hu
On Fri, 2017-03-10 at 08:33 -0800, Tom Herbert wrote:
> Okay, now I'm confused. You're saying that when early demux was added
> for IPv6 performance improved, but this patch is allowing early demux
> to be disabled on the basis that it hurts performance for unconnected
> UDP workloads. While it's
On Thu, Mar 9, 2017 at 9:26 PM, Subash Abhinov Kasiviswanathan
wrote:
> On 2017-03-09 20:42, Tom Herbert wrote:
>>
>> On Thu, Mar 9, 2017 at 7:31 PM, Subash Abhinov Kasiviswanathan
>> wrote:
>>>
>>> Certain system process significant unconnected UDP workload.
>>> It would be preferrable to disabl
Hi Subash,
[auto build test ERROR on v4.9-rc8]
[cannot apply to net-next/master net/master next-20170309]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/commits/Subash-Abhinov-Kasiviswanathan/net-Add-sy
Hi Subash,
[auto build test ERROR on v4.9-rc8]
[cannot apply to net-next/master net/master next-20170309]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/commits/Subash-Abhinov-Kasiviswanathan/net-Add-sy
Well, then you need to make sure ipprot->early_demux is read once in
the
callers, like ip_rcv_finish(), otherwise compiler could read it twice
and we could deref a NULL pointer.
ipprot = rcu_dereference(inet_protos[protocol]);
if (ipprot && ipprot->early_demux) {
ipprot->early_demux(skb);
On 2017-03-09 20:42, Tom Herbert wrote:
On Thu, Mar 9, 2017 at 7:31 PM, Subash Abhinov Kasiviswanathan
wrote:
Certain system process significant unconnected UDP workload.
It would be preferrable to disable UDP early demux for those systems
and enable it for TCP only.
Presumably you want this
On Thu, 2017-03-09 at 20:31 -0700, Subash Abhinov Kasiviswanathan wrote:
> Certain system process significant unconnected UDP workload.
> It would be preferrable to disable UDP early demux for those systems
> and enable it for TCP only.
> +void tcp_v4_early_demux_configure(int enable)
> +{
> +
On Thu, Mar 9, 2017 at 7:31 PM, Subash Abhinov Kasiviswanathan
wrote:
> Certain system process significant unconnected UDP workload.
> It would be preferrable to disable UDP early demux for those systems
> and enable it for TCP only.
>
Presumably you want this for performance reasons. Can you prov
Certain system process significant unconnected UDP workload.
It would be preferrable to disable UDP early demux for those systems
and enable it for TCP only.
v1->v2: Change function pointer instead of adding conditional as
suggested by Stephen.
Signed-off-by: Subash Abhinov Kasiviswanathan
Sugge
15 matches
Mail list logo
