netdev - Re: [PATCH net-next] udp: prefetch rmem_alloc in udp_queue_rcv

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <1498061257.2799.15.camel@redhat.com>
Date:   Wed, 21 Jun 2017 18:07:37 +0200
From:   Paolo Abeni <pabeni@...hat.com>
To:     David Miller <davem@...emloft.net>
Cc:     netdev@...r.kernel.org
Subject: Re: [PATCH net-next] udp: prefetch rmem_alloc in udp_queue_rcv_skb()

On Wed, 2017-06-21 at 11:41 -0400, David Miller wrote:
> From: Paolo Abeni <pabeni@...hat.com>
> Date: Wed, 21 Jun 2017 10:24:40 +0200
> 
> > On UDP packets processing, if the BH is the bottle-neck, it
> > always sees a cache miss while updating rmem_alloc; try to
> > avoid it prefetching the value as soon as we have the socket
> > available.
> > 
> > Performances under flood with multiple NIC rx queues used are
> > unaffected, but when a single NIC rx queue is in use, this
> > gives ~10% performance improvement.
> > 
> > Signed-off-by: Paolo Abeni <pabeni@...hat.com>
> 
> Applied, but what about ipv6?

You are right, that was unintentionally left out. I'll do some tests
and send another patch for ipv6, too.

Thanks,

Paolo