netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Eric Dumazet <dada1@cosmosbay.com>
To: Chris Friesen <cfriesen@nortel.com>
Cc: Ray Lee <ray-lk@madrabbit.org>,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: questions on NAPI processing latency and dropped network packets
Date: Mon, 14 Jan 2008 17:56:28 +0100	[thread overview]
Message-ID: <478B943C.7080009@cosmosbay.com> (raw)
In-Reply-To: <478B8473.6080506@nortel.com>

Chris Friesen a écrit :
> Ray Lee wrote:
>> On Jan 10, 2008 9:24 AM, Chris Friesen <cfriesen@nortel.com> wrote:
>
>>> After a recent userspace app change, we've started seeing packets being
>>> dropped by the ethernet hardware (e1000, NAPI is enabled).  The
>>> error/dropped/fifo counts are going up in ethtool:
>
>> Can you reproduce it with a simple userspace cpu hog? (Two, really,
>> one per cpu.)
>> Can you reproduce it with the newer e1000?
>
> Hmm...good questions and I haven't checked either.  The first one is 
> relatively straightforward.  The second is a bit trickier...last time 
> I tried the latest e1000 driver the card wouldn't boot (we use netboot).
>
>> Can you reproduce it with git head?
>
> Unfortunately, I don't think I'll be able to try this.  We require 
> kernel mods for our userspace to run, and I doubt I'd be able to get 
> the time to port all the changes forward to git head.
>
>> If the answer to the first one is yes, the last no, then bisect until
>> you get a kernel that doesn't show the problem. Backport the fix,
>> unless the fix happens to be CFS. However, I suspect that your
>> userpace app is just starving the system from time to time.
>
> It's conceivable that userspace is starving the kernel, but we have do 
> about 45% idle on one cpu, and 7-10% idle on the other.
>
> We also have an odd situation where on an initial test run after 
> bootup we have 18-24% idle on cpu1, but resetting the test tool drops 
> that to the 7-10% I mentioned above.
>
> Based on profiling and instrumentation it seems like the cost of 
> sctp_endpoint_lookup_assoc() more than triples, which means that the 
> amount of time that bottom halves are disabled in that function also 
> triples.
Any idea of the size of sctp hash size you have ?
(your dmesg probably includes a message starting with SCTP: Hash tables 
configured... 

How many concurrent sctp sockets are handled ?

Maybe sctp_assoc_hashfn() is too weak for your use, and some chains are 
*really* long.





  reply	other threads:[~2008-01-14 16:56 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-01-10 17:24 questions on NAPI processing latency and dropped network packets Chris Friesen
2008-01-10 17:37 ` Kok, Auke
2008-01-10 18:12   ` Chris Friesen
2008-01-10 18:26     ` Kok, Auke
2008-01-10 18:25 ` James Chapman
2008-01-10 21:29   ` Chris Friesen
2008-01-10 18:41 ` Rick Jones
2008-01-10 19:01   ` Kok, Auke
2008-01-11  1:20 ` David Miller
2008-01-11 14:59   ` Chris Friesen
2008-01-11 22:29     ` Herbert Xu
2008-01-12  1:53     ` David Miller
2008-01-14 15:58       ` Chris Friesen
2008-01-15  7:19         ` Jarek Poplawski
2008-01-15 14:47           ` Chris Friesen
2008-01-15 15:17             ` Radoslaw Szkodzinski
2008-01-15 17:14               ` Chris Friesen
2008-01-15 17:23                 ` Eric Dumazet
2008-01-15 20:29             ` Jarek Poplawski
2008-01-16  0:17               ` Herbert Xu
2008-01-16  6:58                 ` Jarek Poplawski
2008-01-16 20:04                   ` Willy Tarreau
2008-01-16 22:42                     ` Jarek Poplawski
2008-01-12  5:37 ` Ray Lee
2008-01-14 15:49   ` Chris Friesen
2008-01-14 16:56     ` Eric Dumazet [this message]
2008-01-14 19:25       ` Chris Friesen
2008-01-14 19:33         ` Eric Dumazet
2008-01-14 20:02           ` Chris Friesen
2008-01-15 15:09             ` Vlad Yasevich
2008-01-21 19:53 ` Chris Friesen
2008-01-21 21:11   ` Ben Greear
2008-01-21 23:15     ` Chris Friesen
2008-01-21 23:32       ` Ben Greear
2008-01-21 21:31   ` Eric Dumazet
2008-01-21 23:25     ` Chris Friesen
2008-01-22  5:46       ` Eric Dumazet

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=478B943C.7080009@cosmosbay.com \
    --to=dada1@cosmosbay.com \
    --cc=cfriesen@nortel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=ray-lk@madrabbit.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).