public inbox for [email protected]
 help / color / mirror / Atom feed
From: Willem de Bruijn <[email protected]>
To: Pavel Begunkov <[email protected]>,
	 Willem de Bruijn <[email protected]>,
	 [email protected],  [email protected]
Cc: Jens Axboe <[email protected]>,
	 "David S . Miller" <[email protected]>,
	 Jakub Kicinski <[email protected]>,
	 David Ahern <[email protected]>,
	 Eric Dumazet <[email protected]>
Subject: Re: [RFC 6/6] io_uring/notif: implement notification stacking
Date: Mon, 15 Apr 2024 15:02:23 -0400	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

> > 
> > Slight aside: we know that MSG_ZEROCOPY is quite inefficient for
> > small sends. Very rough rule of thumb is you need around 16KB or
> > larger sends for it to outperform regular copy. Part of that is the
> > memory pinning. The other part is the notification handling.
> > MSG_ERRQUEUE is expensive. I hope that io_uring cannot just match, but
> > improve on MSG_ZEROCOPY, especially for smaller packets.
> 
> I has some numbers left from this patchset benchmarking. Not too
> well suited to answer your question, but still gives an idea.
> Just a benchmark, single buffer, 100g broadcom NIC IIRC. All is
> io_uring based, -z<bool> switches copy vs zerocopy. Zero copy
> uses registered buffers, so no page pinning and page table
> traversal at runtime. 10s per run is not ideal, but was matching
> longer runs.
> 
> # 1200 bytes
> ./send-zerocopy -4 tcp -D <ip> -t 10 -n 1 -l0 -b1 -d -s1200 -z0
> packets=15004160 (MB=17170), rps=1470996 (MB/s=1683)
> ./send-zerocopy -4 tcp -D <ip> -t 10 -n 1 -l0 -b1 -d -s1200 -z1
> packets=10440224 (MB=11947), rps=1023551 (MB/s=1171)
> 
> # 4000 bytes
> ./send-zerocopy -4 tcp -D <ip> -t 10 -n 1 -l0 -b1 -d -s4000 -z0
> packets=11742688 (MB=44794), rps=1151243 (MB/s=4391)
> ./send-zerocopy -4 tcp -D <ip> -t 10 -n 1 -l0 -b1 -d -s4000 -z1
> packets=14144048 (MB=53955), rps=1386671 (MB/s=5289)
> 
> # 8000 bytes
> ./send-zerocopy -4 tcp -D <ip> -t 10 -n 1 -l0 -b1 -d -s8000 -z0
> packets=6868976 (MB=52406), rps=673429 (MB/s=5137)
> ./send-zerocopy -4 tcp -D <ip> -t 10 -n 1 -l0 -b1 -d -s8000 -z1
> packets=10800784 (MB=82403), rps=1058900 (MB/s=8078)

Parity around 4K. That is very encouraging :)


  reply	other threads:[~2024-04-15 19:02 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-04-12 12:55 [RFC 0/6] implement io_uring notification (ubuf_info) stacking Pavel Begunkov
2024-04-12 12:55 ` [RFC 1/6] net: extend ubuf_info callback to ops structure Pavel Begunkov
2024-04-13 17:17   ` David Ahern
2024-04-14 17:07   ` Willem de Bruijn
2024-04-15  0:07     ` Pavel Begunkov
2024-04-15 15:06       ` Willem de Bruijn
2024-04-15 18:55         ` Pavel Begunkov
2024-04-15 19:01           ` Willem de Bruijn
2024-04-16 14:50       ` David Ahern
2024-04-16 15:31         ` Pavel Begunkov
2024-04-12 12:55 ` [RFC 2/6] net: add callback for setting a ubuf_info to skb Pavel Begunkov
2024-04-13 17:18   ` David Ahern
2024-04-12 12:55 ` [RFC 3/6] io_uring/notif: refactor io_tx_ubuf_complete() Pavel Begunkov
2024-04-12 12:55 ` [RFC 4/6] io_uring/notif: remove ctx var from io_notif_tw_complete Pavel Begunkov
2024-04-12 12:55 ` [RFC 5/6] io_uring/notif: simplify io_notif_flush() Pavel Begunkov
2024-04-12 12:55 ` [RFC 6/6] io_uring/notif: implement notification stacking Pavel Begunkov
2024-04-14 17:10   ` Willem de Bruijn
2024-04-14 23:55     ` Pavel Begunkov
2024-04-15 15:15       ` Willem de Bruijn
2024-04-15 18:51         ` Pavel Begunkov
2024-04-15 19:02           ` Willem de Bruijn [this message]
2024-04-12 13:44 ` [RFC 0/6] implement io_uring notification (ubuf_info) stacking Jens Axboe
2024-04-12 14:52 ` Jens Axboe
2024-04-13 17:17 ` David Ahern
2024-04-15  0:08   ` Pavel Begunkov

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=661d79bf3a774_2ce362948c@willemb.c.googlers.com.notmuch \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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