From: Eric Dumazet <eric.dumazet@gmail.com>
To: Julian Anastasov <ja@ssi.bg>
Cc: Willy Tarreau <w@1wt.eu>, David Miller <davem@davemloft.net>,
netdev@vger.kernel.org
Subject: Re: TCP_DEFER_ACCEPT is missing counter update
Date: Fri, 16 Oct 2009 05:51:16 +0200 [thread overview]
Message-ID: <4AD7EDB4.7060907@gmail.com> (raw)
In-Reply-To: <Pine.LNX.4.58.0910152257410.3047@u.domain.uli>
Julian Anastasov a écrit :
> Sorry for the long mail ...
>
> I was not clear enough in previous email. Your goal
> is to decrease period per client while the actually decreased
> threshold is on the listener's socket. 256 conns will be enough
> to completely disable TCP_DEFER_ACCEPT on the listener (u8). I'm not
> sure that you tested what happens after Nth client (where
> N matches your TCP_DEFER_ACCEPT value as retransmissions), do you
> still see accept deferring for next clients? Now if your patch
> is applied the deferring will be disabled soon after server start.
So, it appears defer_accept value is not an inherited attribute,
but shared by all embryons. Therefore we should not touch it.
No need to type so much text Julian.
Of course it should be done, or add a new connection field to count number
of pure ACKS received on each SYN_RECV embryon.
Do you volunter for this patch ?
next prev parent reply other threads:[~2009-10-16 3:52 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-10-13 5:07 TCP_DEFER_ACCEPT is missing counter update Willy Tarreau
2009-10-13 7:11 ` David Miller
2009-10-13 7:19 ` Willy Tarreau
2009-10-13 7:27 ` David Miller
2009-10-13 21:27 ` Julian Anastasov
2009-10-14 4:52 ` Willy Tarreau
2009-10-14 7:27 ` Julian Anastasov
2009-10-14 20:17 ` Willy Tarreau
2009-10-14 21:12 ` Olaf van der Spek
2009-10-14 22:43 ` David Miller
2009-10-15 6:08 ` Willy Tarreau
2009-10-15 8:47 ` Julian Anastasov
2009-10-15 12:41 ` Willy Tarreau
2009-10-15 22:44 ` Julian Anastasov
2009-10-16 3:51 ` Eric Dumazet [this message]
2009-10-16 5:00 ` Eric Dumazet
2009-10-16 5:29 ` Willy Tarreau
2009-10-16 6:05 ` Eric Dumazet
2009-10-16 6:18 ` Willy Tarreau
2009-10-16 7:08 ` Eric Dumazet
2009-10-16 7:19 ` Willy Tarreau
2009-10-16 5:03 ` Willy Tarreau
2009-10-16 8:49 ` Julian Anastasov
2009-10-16 10:40 ` Eric Dumazet
2009-10-16 19:27 ` Willy Tarreau
2009-10-17 11:48 ` Julian Anastasov
2009-10-17 12:07 ` Eric Dumazet
2009-10-17 14:20 ` Julian Anastasov
2009-10-19 20:01 ` Eric Dumazet
2009-10-19 20:11 ` Willy Tarreau
2009-10-19 20:17 ` Eric Dumazet
2009-10-20 2:23 ` David Miller
2009-10-15 7:59 ` Julian Anastasov
2009-10-16 10:08 ` Ilpo Järvinen
2009-10-13 7:23 ` Eric Dumazet
2009-10-13 7:34 ` Willy Tarreau
2009-10-13 8:08 ` Olaf van der Spek
2009-10-13 8:29 ` Eric Dumazet
2009-10-13 8:35 ` David Miller
2009-10-13 7:35 ` David Miller
2009-10-13 8:12 ` Willy Tarreau
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=4AD7EDB4.7060907@gmail.com \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=ja@ssi.bg \
--cc=netdev@vger.kernel.org \
--cc=w@1wt.eu \
/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).