netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jamal Hadi Salim <jhs@mojatatu.com>
To: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	Linux Kernel Network Developers <netdev@vger.kernel.org>,
	bpf <bpf@vger.kernel.org>,
	Xiongchun Duan <duanxiongchun@bytedance.com>,
	Dongdong Wang <wangdongdong.6@bytedance.com>,
	Muchun Song <songmuchun@bytedance.com>,
	Cong Wang <cong.wang@bytedance.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Andrii Nakryiko <andrii@kernel.org>,
	Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
	Yonghong Song <yhs@fb.com>,
	Pedro Tammela <pctammela@mojatatu.com>,
	Joe Stringer <joe@cilium.io>
Subject: Re: [RFC Patch bpf-next] bpf: introduce bpf timer
Date: Wed, 12 May 2021 18:56:04 -0400	[thread overview]
Message-ID: <59378178-57e2-c278-02cd-d58f9973b638@mojatatu.com> (raw)
In-Reply-To: <CAM_iQpXLcpga=DF+ateBk1jiiCx2mPJW=WHT+j3JrS8kuPS4Zw@mail.gmail.com>

On 2021-05-11 5:29 p.m., Cong Wang wrote:
> On Mon, May 10, 2021 at 1:55 PM Jamal Hadi Salim <jhs@mojatatu.com> wrote:

>>
>> That cilium PR was a good read of the general issues.
>> Our use case involves anywhere between 4-16M cached entries.
>>
>> Like i mentioned earlier:
>> we want to periodically, if some condition is met in the
>> kernel on a map entry, to cleanup, update or send unsolicited
>> housekeeping events to user space.
>> Polling in order to achieve this for that many entries is expensive.
> 
> Thanks for sharing your use case. As we discussed privately, please
> also share the performance numbers you have.
> 

The earlier tests i mentioned to you were in regards to LRU.
I can share those as well - but seems for what we are discussing
here testing cost of batch vs nobatch is more important.
Our LRU tests indicate that it is better to use global as opposed
to per-CPU LRU. We didnt dig deeper but it seemed gc/alloc - which was
happening under some lock gets very expensive regardless if you
are sending sufficient number of flows/sec (1M flows/sec in our
case).
We cannot use LRU (for reasons stated earlier). It has to be hash
table with aging under our jurisdiction. I will post numbers for
sending the entries to user space for gc.

cheers,
jamal


  reply	other threads:[~2021-05-12 23:21 UTC|newest]

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-01  4:26 [RFC Patch bpf-next] bpf: introduce bpf timer Cong Wang
2021-04-01  6:38 ` Song Liu
2021-04-01 17:28   ` Cong Wang
2021-04-01 20:17     ` Song Liu
2021-04-02 17:34       ` Cong Wang
2021-04-02 17:57         ` Song Liu
2021-04-02 19:08           ` Cong Wang
2021-04-02 19:43             ` Song Liu
2021-04-02 20:57               ` Cong Wang
2021-04-02 23:31                 ` Song Liu
2021-04-05 23:49                   ` Cong Wang
2021-04-06  1:07                     ` Song Liu
2021-04-06  1:24                       ` Cong Wang
2021-04-06  6:17                         ` Song Liu
2021-04-06 16:48                           ` Cong Wang
2021-04-06 23:36                             ` Song Liu
2021-04-08 22:45                               ` Cong Wang
2021-04-02 19:28 ` Alexei Starovoitov
2021-04-02 21:24   ` Cong Wang
2021-04-02 23:45     ` Alexei Starovoitov
2021-04-06  0:36       ` Cong Wang
2021-04-12 23:01         ` Alexei Starovoitov
2021-04-15  4:02           ` Cong Wang
2021-04-15  4:25             ` Alexei Starovoitov
2021-04-15 15:51               ` Cong Wang
2021-04-26 23:00               ` Cong Wang
2021-04-26 23:05                 ` Alexei Starovoitov
2021-04-26 23:37                   ` Cong Wang
2021-04-27  2:01                     ` Alexei Starovoitov
2021-04-27 11:52                       ` Jamal Hadi Salim
2021-04-27 16:36                       ` Cong Wang
2021-04-27 18:33                         ` Alexei Starovoitov
2021-05-09  5:37                           ` Cong Wang
2021-05-10 20:55                             ` Jamal Hadi Salim
2021-05-11 21:29                               ` Cong Wang
2021-05-12 22:56                                 ` Jamal Hadi Salim [this message]
2021-05-11  5:05                             ` Joe Stringer
2021-05-11 21:08                               ` Cong Wang
2021-05-12 22:43                               ` Jamal Hadi Salim
2021-05-13 18:45                                 ` Jamal Hadi Salim
2021-05-14  2:53                                   ` Cong Wang
2021-08-11 21:03                                     ` Joe Stringer
2021-05-20 18:55 [RFC PATCH bpf-next] bpf: Introduce bpf_timer Alexei Starovoitov
2021-05-21 14:38 ` Alexei Starovoitov
2021-05-21 21:37 ` Cong Wang
2021-05-23 16:01   ` Alexei Starovoitov
2021-05-24  8:45     ` Lorenz Bauer
2021-05-25  3:16     ` Cong Wang
2021-05-25  4:59       ` Cong Wang
2021-05-25 18:21         ` Alexei Starovoitov
2021-05-25 19:35           ` Jamal Hadi Salim
2021-05-25 19:57             ` Alexei Starovoitov
2021-05-25 21:09               ` Jamal Hadi Salim
2021-05-25 22:08                 ` Alexei Starovoitov
2021-05-26 15:34                   ` Jamal Hadi Salim
2021-05-26 16:58                     ` Alexei Starovoitov
2021-05-26 18:25                       ` Jamal Hadi Salim
2021-05-30  6:36           ` Cong Wang
2021-06-02  2:00             ` Alexei Starovoitov
2021-06-02  8:48               ` Toke Høiland-Jørgensen
2021-06-02 17:54                 ` Martin KaFai Lau
2021-06-02 18:13                   ` Kumar Kartikeya Dwivedi
2021-06-02 18:26                     ` Alexei Starovoitov
2021-06-02 18:30                       ` Kumar Kartikeya Dwivedi
2021-06-02 18:46                     ` John Fastabend
2021-05-23 11:48 ` Toke Høiland-Jørgensen
2021-05-23 15:58   ` Alexei Starovoitov
2021-05-24  8:42     ` Lorenz Bauer
2021-05-24 14:48       ` Alexei Starovoitov
2021-05-24 17:33     ` Alexei Starovoitov
2021-05-24 18:39       ` Toke Høiland-Jørgensen
2021-05-24 18:38     ` Toke Høiland-Jørgensen
2021-05-24 11:49 ` Lorenz Bauer
2021-05-24 14:56   ` Alexei Starovoitov
2021-05-24 19:13     ` Andrii Nakryiko
2021-05-25  5:22       ` Cong Wang
2021-05-25 19:47         ` Andrii Nakryiko

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=59378178-57e2-c278-02cd-d58f9973b638@mojatatu.com \
    --to=jhs@mojatatu.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=cong.wang@bytedance.com \
    --cc=daniel@iogearbox.net \
    --cc=duanxiongchun@bytedance.com \
    --cc=joe@cilium.io \
    --cc=kafai@fb.com \
    --cc=netdev@vger.kernel.org \
    --cc=pctammela@mojatatu.com \
    --cc=songliubraving@fb.com \
    --cc=songmuchun@bytedance.com \
    --cc=wangdongdong.6@bytedance.com \
    --cc=xiyou.wangcong@gmail.com \
    --cc=yhs@fb.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).