[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <f7ta5spe1ix.fsf@redhat.com>
Date: Wed, 11 Oct 2023 09:23:18 -0400
From: Aaron Conole <aconole@...hat.com>
To: Nicholas Piggin <npiggin@...il.com>
Cc: netdev@...r.kernel.org, dev@...nvswitch.org, Pravin B Shelar
<pshelar@....org>, "Eelco Chaudron" <echaudro@...hat.com>, "Ilya
Maximets" <imaximet@...hat.com>, "Flavio Leitner" <fbl@...hat.com>, Paolo
Abeni <pabeni@...hat.com>, Jakub Kicinski <kuba@...nel.org>, "David S.
Miller" <davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>
Subject: Re: [PATCH 0/7] net: openvswitch: Reduce stack usage
Nicholas Piggin <npiggin@...il.com> writes:
> Hi,
>
> I'll post this out again to keep discussion going. Thanks all for the
> testing and comments so far.
Thanks for the update - did you mean for this to be tagged RFC as well?
I don't see any performance data with the deployments on x86_64 and
ppc64le that cause these stack overflows. Are you able to provide the
impact on ppc64le and x86_64?
I guess the change probably should be tagged as -next since it doesn't
really have a specific set of commits it is "fixing." It's really like
a major change and shouldn't really go through stable trees, but I'll
let the maintainers tell me off if I got it wrong.
> Changes since the RFC
> https://lore.kernel.org/netdev/20230927001308.749910-1-npiggin@gmail.com/
>
> - Replace slab allocations for flow keys with expanding the use
> of the per-CPU key allocator to ovs_vport_receive.
>
> - Drop patch 1 with Ilya's since they did the same thing (that is
> added at patch 3).
>
> - Change push_nsh stack reduction from slab allocation to per-cpu
> buffer.
>
> - Drop the ovs_fragment stack usage reduction for now sinc it used
> slab and was a bit more complicated.
>
> I posted an initial version of the per-cpu flow allocator patch in
> the RFC thread. Since then I cleaned up some debug code and increased
> the allocator size to accommodate the additional user of it.
>
> Thanks,
> Nick
>
> Ilya Maximets (1):
> openvswitch: reduce stack usage in do_execute_actions
>
> Nicholas Piggin (6):
> net: openvswitch: generalise the per-cpu flow key allocation stack
> net: openvswitch: Use flow key allocator in ovs_vport_receive
> net: openvswitch: Reduce push_nsh stack usage
> net: openvswitch: uninline action execution
> net: openvswitch: uninline ovs_fragment to control stack usage
> net: openvswitch: Reduce stack usage in ovs_dp_process_packet
>
> net/openvswitch/actions.c | 208 +++++++++++++++++++++++--------------
> net/openvswitch/datapath.c | 56 +++++-----
> net/openvswitch/flow.h | 3 +
> net/openvswitch/vport.c | 27 +++--
> 4 files changed, 185 insertions(+), 109 deletions(-)
Powered by blists - more mailing lists