From: "Samudrala, Sridhar" <sridhar.samudrala@intel.com>
To: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: magnus.karlsson@intel.com, bjorn.topel@intel.com,
netdev@vger.kernel.org, bpf@vger.kernel.org,
intel-wired-lan@lists.osuosl.org, maciej.fijalkowski@intel.com,
tom.herbert@intel.com
Subject: Re: [PATCH bpf-next 0/5] Add support for SKIP_BPF flag for AF_XDP sockets
Date: Thu, 15 Aug 2019 23:25:55 -0700 [thread overview]
Message-ID: <f9df4d0e-c5f2-036d-994c-3162274820ea@intel.com> (raw)
In-Reply-To: <20190815122844.52eeda08@cakuba.netronome.com>
On 8/15/2019 12:28 PM, Jakub Kicinski wrote:
> On Wed, 14 Aug 2019 20:46:18 -0700, Sridhar Samudrala wrote:
>> This patch series introduces XDP_SKIP_BPF flag that can be specified
>> during the bind() call of an AF_XDP socket to skip calling the BPF
>> program in the receive path and pass the buffer directly to the socket.
>>
>> When a single AF_XDP socket is associated with a queue and a HW
>> filter is used to redirect the packets and the app is interested in
>> receiving all the packets on that queue, we don't need an additional
>> BPF program to do further filtering or lookup/redirect to a socket.
>>
>> Here are some performance numbers collected on
>> - 2 socket 28 core Intel(R) Xeon(R) Platinum 8180 CPU @ 2.50GHz
>> - Intel 40Gb Ethernet NIC (i40e)
>>
>> All tests use 2 cores and the results are in Mpps.
>>
>> turbo on (default)
>> ---------------------------------------------
>> no-skip-bpf skip-bpf
>> ---------------------------------------------
>> rxdrop zerocopy 21.9 38.5
>> l2fwd zerocopy 17.0 20.5
>> rxdrop copy 11.1 13.3
>> l2fwd copy 1.9 2.0
>>
>> no turbo : echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo
>> ---------------------------------------------
>> no-skip-bpf skip-bpf
>> ---------------------------------------------
>> rxdrop zerocopy 15.4 29.0
>> l2fwd zerocopy 11.8 18.2
>> rxdrop copy 8.2 10.5
>> l2fwd copy 1.7 1.7
>> ---------------------------------------------
>
> Could you include a third column here - namely the in-XDP performance?
> AFAIU the way to achieve better performance with AF_XDP is to move the
> fast path into the kernel's XDP program..
The in-xdp drop that can be measured with xdp1 is lower than rxdrop
zerocopy with skip-bpf although in-xdp drop uses only 1 core. af-xdp
1-core performance would improve with need-wakeup or busypoll patches
and based on early experiments so far af-xdp with need-wakeup/busypoll +
skip-bpf perf is higher than in-xdp drop.
Will include in-xdp drop data too in the next revision.
>
> Maciej's work on batching XDP program's execution should lower the
> retpoline overhead, without leaning close to the bypass model.
>
prev parent reply other threads:[~2019-08-16 6:25 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-15 3:46 [PATCH bpf-next 0/5] Add support for SKIP_BPF flag for AF_XDP sockets Sridhar Samudrala
2019-08-15 3:46 ` [PATCH bpf-next 1/5] xsk: Convert bool 'zc' field in struct xdp_umem to a u32 bitmap Sridhar Samudrala
2019-08-15 3:46 ` [PATCH bpf-next 2/5] xsk: Introduce XDP_SKIP_BPF bind option Sridhar Samudrala
2019-08-15 3:46 ` [PATCH bpf-next 3/5] i40e: Enable XDP_SKIP_BPF option for AF_XDP sockets Sridhar Samudrala
2019-08-16 9:21 ` kbuild test robot
2019-08-15 3:46 ` [PATCH bpf-next 4/5] ixgbe: " Sridhar Samudrala
2019-08-15 3:46 ` [PATCH bpf-next 5/5] xdpsock_user: Add skip_bpf option Sridhar Samudrala
2019-08-15 11:12 ` [PATCH bpf-next 0/5] Add support for SKIP_BPF flag for AF_XDP sockets Toke Høiland-Jørgensen
2019-08-15 16:25 ` Samudrala, Sridhar
2019-08-15 17:11 ` Toke Høiland-Jørgensen
2019-08-16 6:12 ` Samudrala, Sridhar
2019-08-15 12:51 ` Björn Töpel
2019-08-15 16:46 ` Samudrala, Sridhar
2019-08-16 13:32 ` [Intel-wired-lan] " Björn Töpel
2019-08-16 22:08 ` Jonathan Lemon
2019-08-19 7:39 ` Björn Töpel
2019-08-15 19:28 ` Jakub Kicinski
2019-08-16 6:25 ` Samudrala, Sridhar [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=f9df4d0e-c5f2-036d-994c-3162274820ea@intel.com \
--to=sridhar.samudrala@intel.com \
--cc=bjorn.topel@intel.com \
--cc=bpf@vger.kernel.org \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=jakub.kicinski@netronome.com \
--cc=maciej.fijalkowski@intel.com \
--cc=magnus.karlsson@intel.com \
--cc=netdev@vger.kernel.org \
--cc=tom.herbert@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).