netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Maciej Żenczykowski" <zenczykowski@gmail.com>
To: David Miller <davem@davemloft.net>
Cc: eilong@broadcom.com, eric.dumazet@gmail.com, dmitry@broadcom.com,
	netdev@vger.kernel.org, yuvalmin@broadcom.com
Subject: Re: [PATCH] bnx2x: fix occasional statistics off-by-4GB error
Date: Mon, 18 Mar 2013 13:06:16 -0700	[thread overview]
Message-ID: <CAHo-OowoWD_BT2W8ok32pcSmcshXttpErna-X92Ojz_A8es8iw@mail.gmail.com> (raw)
In-Reply-To: <CAHo-OoxaaLLXtAZcx99m7p5=Hez3gpUWxvoQAgksyG3PRZH-Ng@mail.gmail.com>

Current best guess is UPDATE_ESTAT_QSTAT_64 which uses SUB_64
implemented via DIFF_64 which is crazy.

On Mon, Mar 18, 2013 at 12:54 PM, Maciej Żenczykowski
<zenczykowski@gmail.com> wrote:
> I've reproduced this in the lab.
>
> I can confirm this patch fixes per-queue statistics (ie. ethtool -S
> "[0]: tx_bytes") - which previously were not monotonically increasing.
> However there is still a bug wrt. global device stats (ie. ethtool -S
> "tx_bytes" and /proc/net/dev transmit bytes).
> I'm guessing there's another similar bug later on during aggregation.
>
> I expect to find the offending code and send out a patch soon.
>
> On Mon, Mar 18, 2013 at 10:13 AM, David Miller <davem@davemloft.net> wrote:
>> From: "Eilon Greenstein" <eilong@broadcom.com>
>> Date: Mon, 18 Mar 2013 12:06:22 +0200
>>
>>> Maciej - thanks for the detailed information. You are right - it has
>>> nothing to do with the HW/FW and it is simply a bug that needs to be
>>> fixed. I withdraw my objections and add my ACK.
>>>
>>> Acked-by: Eilon Greenstein <eilong@broadcom.com>
>>
>> Applied and queued up for -stable.
>> --
>> To unsubscribe from this list: send the line "unsubscribe netdev" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html

  parent reply	other threads:[~2013-03-18 20:06 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-15 21:03 bnx2x statistics occasionally wrong by near multiples of 4GB Maciej Żenczykowski
2013-03-15 21:56 ` [PATCH] bnx2x: fix occasional statistics off-by-4GB error Maciej Żenczykowski
2013-03-17 13:10   ` Dmitry Kravkov
2013-03-17 18:24     ` David Miller
2013-03-17 19:37       ` Eilon Greenstein
2013-03-17 20:25         ` Eric Dumazet
2013-03-17 20:53           ` Eilon Greenstein
2013-03-17 23:17             ` Eric Dumazet
2013-03-18  7:27               ` Eilon Greenstein
2013-03-18  6:18             ` Maciej Żenczykowski
2013-03-18 10:06               ` Eilon Greenstein
2013-03-18 17:13                 ` David Miller
2013-03-18 19:54                   ` Maciej Żenczykowski
2013-03-18 20:05                     ` David Miller
2013-03-18 20:06                     ` Maciej Żenczykowski [this message]
2013-03-18 20:35                       ` Eric Dumazet
2013-03-18 20:36                       ` Maciej Żenczykowski
2013-03-21 21:23                         ` Maciej Żenczykowski
2013-03-21 21:25                           ` David Miller

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=CAHo-OowoWD_BT2W8ok32pcSmcshXttpErna-X92Ojz_A8es8iw@mail.gmail.com \
    --to=zenczykowski@gmail.com \
    --cc=davem@davemloft.net \
    --cc=dmitry@broadcom.com \
    --cc=eilong@broadcom.com \
    --cc=eric.dumazet@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=yuvalmin@broadcom.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).