netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: David Ahern <dsahern@gmail.com>
Cc: netdev@vger.kernel.org, borkmann@iogearbox.net, ast@kernel.org,
	davem@davemloft.net, shm@cumulusnetworks.com,
	roopa@cumulusnetworks.com, toke@toke.dk,
	john.fastabend@gmail.com, brouer@redhat.com,
	Vincent Bernat <bernat@luffy.cx>
Subject: Re: [RFC v2 bpf-next 8/9] bpf: Provide helper to do lookups in kernel FIB table
Date: Wed, 2 May 2018 13:27:36 +0200	[thread overview]
Message-ID: <20180502132736.3560fcac@redhat.com> (raw)
In-Reply-To: <20180429180752.15428-9-dsahern@gmail.com>

On Sun, 29 Apr 2018 11:07:51 -0700
David Ahern <dsahern@gmail.com> wrote:

> Initial performance numbers collected by Jesper, forwarded packets/sec:
> 
>        Full stack    XDP FIB lookup    XDP Direct lookup
> IPv4   1,947,969       7,074,156          7,415,333
> IPv6   1,728,000       6,165,504          7,262,720

Do notice these number is single CPU core forwarding performance!
On a Broadwell E5-1650 v4 @ 3.60GHz.

Another interesting data point is that xdp_redirect_map performance is
13,365,161 pps, which allow us to calculate/isolate the overhead/cost
of the FIB lookup.

(1/13365161-1/7074156)*10^9 = -66.5 ns
(1/13365161-1/7415333)*10^9 = -60.0 ns

Which is very close to the measured 50 ns cost of the FIB lookup, done
by Vincent Bernat.
  See: https://vincent.bernat.im/en/blog/2017-ipv4-route-lookup-linux



Another way I calculate this is by (ran a new benchmark):

Performance: 7641593 (7,641,593) <= tx_unicast /sec
 * Packet-gap: (1/7641593*10^9)  = 130.86 ns

Find all FIB related lookup functions in perf-report::

 Samples: 93K of event 'cycles:ppp', Event count (approx.): 88553104553
   Overhead   Cost      CPU  Command      Symbol
     20.63 %  26.99 ns  002  ksoftirqd/2  [k] fib_table_lookup
     12.92 %  16.90 ns  002  ksoftirqd/2  [k] bpf_fib_lookup
      2.40 %   3.14 ns  002  ksoftirqd/2  [k] fib_select_path
      0.83 %   1.09 ns  002  ksoftirqd/2  [k] fib_get_table
      0.40 %   0.52 ns  002  ksoftirqd/2  [k] l3mdev_fib_table_rcu
 -----------
 Tot:37.18 % (20.63+12.92+2.40+0.83+0.40)
 ===========

Cost of FIB lookup:
 - 130.86/100*37.18 = 48.65 ns overhead by FIB lookup.

Again very close to Vincent's IPv4 measurements of ~50 ns.



Notice that the IPv6 measurements does not match up:
 https://vincent.bernat.im/en/blog/2017-ipv6-route-lookup-linux
This is because, we/I'm just testing the IPv6 route cache here...

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer

  parent reply	other threads:[~2018-05-02 11:27 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-29 18:07 [RFC v2 bpf-next 0/9] bpf: Add helper to do FIB lookups David Ahern
2018-04-29 18:07 ` [RFC v2 bpf-next 1/9] net/ipv6: Rename fib6_lookup to fib6_node_lookup David Ahern
2018-04-29 18:07 ` [RFC v2 bpf-next 2/9] net/ipv6: Rename rt6_multipath_select David Ahern
2018-04-29 18:07 ` [RFC v2 bpf-next 3/9] net/ipv6: Extract table lookup from ip6_pol_route David Ahern
2018-04-29 18:07 ` [RFC v2 bpf-next 4/9] net/ipv6: Refactor fib6_rule_action David Ahern
2018-04-29 18:07 ` [RFC v2 bpf-next 5/9] net/ipv6: Add fib6_lookup David Ahern
2018-05-01 18:15   ` Vincent Bernat
2018-05-01 18:25     ` David Ahern
2018-04-29 18:07 ` [RFC v2 bpf-next 6/9] net/ipv6: Update fib6 tracepoint to take fib6_info David Ahern
2018-04-29 18:07 ` [RFC v2 bpf-next 7/9] net/ipv6: Add fib lookup stubs for use in bpf helper David Ahern
2018-04-29 18:07 ` [RFC v2 bpf-next 8/9] bpf: Provide helper to do lookups in kernel FIB table David Ahern
2018-04-29 23:36   ` Alexei Starovoitov
2018-04-30  1:13     ` David Ahern
2018-05-15  3:46       ` David Ahern
2018-05-02 11:27   ` Jesper Dangaard Brouer [this message]
2018-05-02 15:37     ` David Ahern
2018-05-02 17:00       ` David Miller
2018-04-29 18:07 ` [RFC v2 bpf-next 9/9] samples/bpf: Add examples of ipv4 and ipv6 forwarding in XDP David Ahern
2018-05-02 11:13   ` Jesper Dangaard Brouer
2018-05-02 15:40     ` David Ahern
2018-05-01 14:20 ` [RFC v2 bpf-next 0/9] bpf: Add helper to do FIB lookups David Miller

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=20180502132736.3560fcac@redhat.com \
    --to=brouer@redhat.com \
    --cc=ast@kernel.org \
    --cc=bernat@luffy.cx \
    --cc=borkmann@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@gmail.com \
    --cc=john.fastabend@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=roopa@cumulusnetworks.com \
    --cc=shm@cumulusnetworks.com \
    --cc=toke@toke.dk \
    /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).