netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Martin KaFai Lau <kafai@fb.com>
To: Jakub Sitnicki <jakub@cloudflare.com>
Cc: <netdev@vger.kernel.org>, <bpf@vger.kernel.org>,
	<dccp@vger.kernel.org>, <kernel-team@cloudflare.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Gerrit Renker <gerrit@erg.abdn.ac.uk>,
	Jakub Kicinski <kuba@kernel.org>,
	Andrii Nakryiko <andrii.nakryiko@gmail.com>
Subject: Re: [PATCH bpf-next v2 00/17] Run a BPF program on socket lookup
Date: Mon, 11 May 2020 12:45:20 -0700	[thread overview]
Message-ID: <20200511194520.pr5d74ao34jigvof@kafai-mbp.dhcp.thefacebook.com> (raw)
In-Reply-To: <20200511185218.1422406-1-jakub@cloudflare.com>

On Mon, May 11, 2020 at 08:52:01PM +0200, Jakub Sitnicki wrote:

[ ... ]

> Performance considerations
> ==========================
> 
> Patch set adds new code on receive hot path. This comes with a cost,
> especially in a scenario of a SYN flood or small UDP packet flood.
> 
> Measuring the performance penalty turned out to be harder than expected
> because socket lookup is fast. For CPUs to spend >= 1% of time in socket
> lookup we had to modify our setup by unloading iptables and reducing the
> number of routes.
> 
> The receiver machine is a Cloudflare Gen 9 server covered in detail at [0].
> In short:
> 
>  - 24 core Intel custom off-roadmap 1.9Ghz 150W (Skylake) CPU
>  - dual-port 25G Mellanox ConnectX-4 NIC
>  - 256G DDR4 2666Mhz RAM
> 
> Flood traffic pattern:
> 
>  - source: 1 IP, 10k ports
>  - destination: 1 IP, 1 port
>  - TCP - SYN packet
>  - UDP - Len=0 packet
> 
> Receiver setup:
> 
>  - ingress traffic spread over 4 RX queues,
>  - RX/TX pause and autoneg disabled,
>  - Intel Turbo Boost disabled,
>  - TCP SYN cookies always on.
> 
> For TCP test there is a receiver process with single listening socket
> open. Receiver is not accept()'ing connections.
> 
> For UDP the receiver process has a single UDP socket with a filter
> installed, dropping the packets.
> 
> With such setup in place, we record RX pps and cpu-cycles events under
> flood for 60 seconds in 3 configurations:
> 
>  1. 5.6.3 kernel w/o this patch series (baseline),
>  2. 5.6.3 kernel with patches applied, but no SK_LOOKUP program attached,
>  3. 5.6.3 kernel with patches applied, and SK_LOOKUP program attached;
>     BPF program [1] is doing a lookup LPM_TRIE map with 200 entries.
Is the link in [1] up-to-date?  I don't see it calling bpf_sk_assign().

> 
> RX pps measured with `ifpps -d <dev> -t 1000 --csv --loop` for 60 seconds.
> 
> | tcp4 SYN flood               | rx pps (mean ± sstdev) | Δ rx pps |
> |------------------------------+------------------------+----------|
> | 5.6.3 vanilla (baseline)     | 939,616 ± 0.5%         |        - |
> | no SK_LOOKUP prog attached   | 929,275 ± 1.2%         |    -1.1% |
> | with SK_LOOKUP prog attached | 918,582 ± 0.4%         |    -2.2% |
> 
> | tcp6 SYN flood               | rx pps (mean ± sstdev) | Δ rx pps |
> |------------------------------+------------------------+----------|
> | 5.6.3 vanilla (baseline)     | 875,838 ± 0.5%         |        - |
> | no SK_LOOKUP prog attached   | 872,005 ± 0.3%         |    -0.4% |
> | with SK_LOOKUP prog attached | 856,250 ± 0.5%         |    -2.2% |
> 
> | udp4 0-len flood             | rx pps (mean ± sstdev) | Δ rx pps |
> |------------------------------+------------------------+----------|
> | 5.6.3 vanilla (baseline)     | 2,738,662 ± 1.5%       |        - |
> | no SK_LOOKUP prog attached   | 2,576,893 ± 1.0%       |    -5.9% |
> | with SK_LOOKUP prog attached | 2,530,698 ± 1.0%       |    -7.6% |
> 
> | udp6 0-len flood             | rx pps (mean ± sstdev) | Δ rx pps |
> |------------------------------+------------------------+----------|
> | 5.6.3 vanilla (baseline)     | 2,867,885 ± 1.4%       |        - |
> | no SK_LOOKUP prog attached   | 2,646,875 ± 1.0%       |    -7.7% |
What is causing this regression?

> | with SK_LOOKUP prog attached | 2,520,474 ± 0.7%       |   -12.1% |
This also looks very different from udp4.

> 
> Also visualized on bpf-sk-lookup-v1-rx-pps.png chart [2].
> 
> cpu-cycles measured with `perf record -F 999 --cpu 1-4 -g -- sleep 60`.
> 
> |                              |      cpu-cycles events |          |
> | tcp4 SYN flood               | __inet_lookup_listener | Δ events |
> |------------------------------+------------------------+----------|
> | 5.6.3 vanilla (baseline)     |                  1.12% |        - |
> | no SK_LOOKUP prog attached   |                  1.31% |    0.19% |
> | with SK_LOOKUP prog attached |                  3.05% |    1.93% |
> 
> |                              |      cpu-cycles events |          |
> | tcp6 SYN flood               |  inet6_lookup_listener | Δ events |
> |------------------------------+------------------------+----------|
> | 5.6.3 vanilla (baseline)     |                  1.05% |        - |
> | no SK_LOOKUP prog attached   |                  1.68% |    0.63% |
> | with SK_LOOKUP prog attached |                  3.15% |    2.10% |
> 
> |                              |      cpu-cycles events |          |
> | udp4 0-len flood             |      __udp4_lib_lookup | Δ events |
> |------------------------------+------------------------+----------|
> | 5.6.3 vanilla (baseline)     |                  3.81% |        - |
> | no SK_LOOKUP prog attached   |                  5.22% |    1.41% |
> | with SK_LOOKUP prog attached |                  8.20% |    4.39% |
> 
> |                              |      cpu-cycles events |          |
> | udp6 0-len flood             |      __udp6_lib_lookup | Δ events |
> |------------------------------+------------------------+----------|
> | 5.6.3 vanilla (baseline)     |                  5.51% |        - |
> | no SK_LOOKUP prog attached   |                  6.51% |    1.00% |
> | with SK_LOOKUP prog attached |                 10.14% |    4.63% |
> 
> Also visualized on bpf-sk-lookup-v1-cpu-cycles.png chart [3].
> 

[ ... ]

> 
> [0] https://urldefense.proofpoint.com/v2/url?u=https-3A__blog.cloudflare.com_a-2Dtour-2Dinside-2Dcloudflares-2Dg9-2Dservers_&d=DwIDaQ&c=5VD0RTtNlTh3ycd41b3MUw&r=VQnoQ7LvghIj0gVEaiQSUw&m=v4r30a5NaPFxNXVRakV9SeJkshbI4G4c5D83yZtGm-g&s=PhkIqKdmL12ZMD_6jY_rALjmO2ahv_KNF3F7TikyfTo&e= 
> [1] https://github.com/majek/inet-tool/blob/master/ebpf/inet-kern.c
> [2] https://urldefense.proofpoint.com/v2/url?u=https-3A__drive.google.com_file_d_1HrrjWhQoVlqiqT73-5FeLtWMPhuGPKhGFX_&d=DwIDaQ&c=5VD0RTtNlTh3ycd41b3MUw&r=VQnoQ7LvghIj0gVEaiQSUw&m=v4r30a5NaPFxNXVRakV9SeJkshbI4G4c5D83yZtGm-g&s=9tums5TZ16ttY69vEHkzyiEkblxT3iwvm0mFjZySJXo&e= 
> [3] https://urldefense.proofpoint.com/v2/url?u=https-3A__drive.google.com_file_d_1cYPPOlGg7M-2DbkzI4RW1SOm49goI4LYbb_&d=DwIDaQ&c=5VD0RTtNlTh3ycd41b3MUw&r=VQnoQ7LvghIj0gVEaiQSUw&m=v4r30a5NaPFxNXVRakV9SeJkshbI4G4c5D83yZtGm-g&s=VWolTQx3GVmSh2J7TQixTlGvRTb6S9qDNx4N8id5lf8&e= 
> [RFCv1] https://lore.kernel.org/bpf/20190618130050.8344-1-jakub@cloudflare.com/
> [RFCv2] https://lore.kernel.org/bpf/20190828072250.29828-1-jakub@cloudflare.com/

  parent reply	other threads:[~2020-05-11 19:45 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-11 18:52 [PATCH bpf-next v2 00/17] Run a BPF program on socket lookup Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 01/17] flow_dissector: Extract attach/detach/query helpers Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 02/17] bpf: Introduce SK_LOOKUP program type with a dedicated attach point Jakub Sitnicki
2020-05-11 19:06   ` Jakub Sitnicki
2020-05-13  5:41   ` Martin KaFai Lau
2020-05-13 14:34     ` Jakub Sitnicki
2020-05-13 18:10       ` Martin KaFai Lau
2020-05-11 18:52 ` [PATCH bpf-next v2 03/17] inet: Store layer 4 protocol in inet_hashinfo Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 04/17] inet: Extract helper for selecting socket from reuseport group Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 05/17] inet: Run SK_LOOKUP BPF program on socket lookup Jakub Sitnicki
2020-05-11 20:44   ` Alexei Starovoitov
2020-05-12 13:52     ` Jakub Sitnicki
2020-05-12 23:58       ` Alexei Starovoitov
2020-05-13 13:55         ` Jakub Sitnicki
2020-05-13 14:21       ` Lorenz Bauer
2020-05-13 14:50         ` Jakub Sitnicki
2020-05-15 12:28     ` Jakub Sitnicki
2020-05-15 15:07       ` Alexei Starovoitov
2020-05-11 18:52 ` [PATCH bpf-next v2 06/17] inet6: Extract helper for selecting socket from reuseport group Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 07/17] inet6: Run SK_LOOKUP BPF program on socket lookup Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 08/17] udp: Store layer 4 protocol in udp_table Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 09/17] udp: Extract helper for selecting socket from reuseport group Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 10/17] udp: Run SK_LOOKUP BPF program on socket lookup Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 11/17] udp6: Extract helper for selecting socket from reuseport group Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 12/17] udp6: Run SK_LOOKUP BPF program on socket lookup Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 13/17] bpf: Sync linux/bpf.h to tools/ Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 14/17] libbpf: Add support for SK_LOOKUP program type Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 15/17] selftests/bpf: Add verifier tests for bpf_sk_lookup context access Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 16/17] selftests/bpf: Rename test_sk_lookup_kern.c to test_ref_track_kern.c Jakub Sitnicki
2020-05-11 18:52 ` [PATCH bpf-next v2 17/17] selftests/bpf: Tests for BPF_SK_LOOKUP attach point Jakub Sitnicki
2020-05-11 19:45 ` Martin KaFai Lau [this message]
2020-05-12 11:57   ` [PATCH bpf-next v2 00/17] Run a BPF program on socket lookup Jakub Sitnicki
2020-05-12 16:34     ` Martin KaFai Lau
2020-05-13 17:54       ` Jakub Sitnicki

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=20200511194520.pr5d74ao34jigvof@kafai-mbp.dhcp.thefacebook.com \
    --to=kafai@fb.com \
    --cc=andrii.nakryiko@gmail.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dccp@vger.kernel.org \
    --cc=edumazet@google.com \
    --cc=gerrit@erg.abdn.ac.uk \
    --cc=jakub@cloudflare.com \
    --cc=kernel-team@cloudflare.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    /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).