netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Dominique Martinet <asmadeus@codewreck.org>,
	Eric Dumazet <eric.dumazet@gmail.com>
Cc: Michal Kubecek <mkubecek@suse.cz>, netdev@vger.kernel.org
Subject: Re: tcp hang when socket fills up ?
Date: Sun, 15 Apr 2018 19:26:09 -0700	[thread overview]
Message-ID: <38b6a690-e01d-471f-ce85-e6e6a8acd26d@gmail.com> (raw)
In-Reply-To: <20180416014740.GA12245@nautica>



On 04/15/2018 06:47 PM, Dominique Martinet wrote:

> Also, here are the per-socket stats I could find (ss -i after having
> reproduced hang):
> 	 reno wscale:7,7 rto:7456 backoff:5 rtt:32.924/1.41 ato:40 mss:1374
> 	 pmtu:1500 rcvmss:1248 advmss:1448 cwnd:1 ssthresh:16
> 	 bytes_acked:32004 bytes_received:4189 segs_out:85 segs_in:54
> 	 data_segs_out:78 data_segs_in:18 send 333.9Kbps lastsnd:3912
> 	 lastrcv:11464 lastack:11387 pacing_rate 21.4Mbps delivery_rate
> 	 3.5Mbps busy:12188ms unacked:33 retrans:1/5 lost:33 rcv_rtt:37
> 	 rcv_space:29200 rcv_ssthresh:39184 notsent:28796 minrtt:24.986
> 

ss -temoi might give us more info

Really it looks like at some point, all incoming packets are shown by tcpdump but do not reach the TCP socket anymore.

(segs_in: might be steady, look at the d0 counter shown by ss -temoi  (dX : drop counters, sk->sk_drops)


Are you sure you do not have some iptables/netfilter stuff ?

While running your experiment, try on the server.

perf record -a -g -e skb:kfree_skb  sleep 30
perf report

  reply	other threads:[~2018-04-16  2:26 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-06  9:07 tcp hang when socket fills up ? Dominique Martinet
2018-04-13  9:42 ` Dominique Martinet
2018-04-13 15:01 ` Eric Dumazet
2018-04-13 16:32 ` Michal Kubecek
2018-04-14  1:09   ` Dominique Martinet
2018-04-14  1:39     ` Eric Dumazet
2018-04-14  1:55       ` Dominique Martinet
2018-04-16  1:47         ` Dominique Martinet
2018-04-16  2:26           ` Eric Dumazet [this message]
2018-04-16  3:55             ` Dominique Martinet
2018-04-16  4:03               ` Dominique Martinet
2018-04-16 11:01               ` Florian Westphal
2018-04-17  3:52                 ` Dominique Martinet
2018-04-17  5:28                   ` Eric Dumazet
2018-04-17  6:52                     ` Michal Kubecek
2018-04-17  9:20                     ` Michal Kubecek
2018-04-17 12:34                       ` Dominique Martinet
2018-04-17 13:00                         ` Michal Kubecek
2018-04-17 13:29                         ` Florian Westphal
2018-04-18  8:13                           ` Jozsef Kadlecsik
2018-04-18  8:30                             ` Dominique Martinet
2018-04-18  9:36                               ` Dominique Martinet
2018-04-18 10:27                                 ` Jozsef Kadlecsik
2018-04-18 11:30                                   ` Dominique Martinet
2018-04-18 11:37                                     ` Jozsef Kadlecsik
2018-04-16 20:43         ` Marcelo Ricardo Leitner

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=38b6a690-e01d-471f-ce85-e6e6a8acd26d@gmail.com \
    --to=eric.dumazet@gmail.com \
    --cc=asmadeus@codewreck.org \
    --cc=mkubecek@suse.cz \
    --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).