netdev - Re: [PATCH v2 0/2] Tracepoint for tcp retransmission

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Fri, 3 Feb 2012 23:40:09 -0500
From:	Yuchung Cheng <ycheng@...gle.com>
To:	Satoru Moriya <satoru.moriya@....com>
Cc:	David Miller <davem@...emloft.net>,
	"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
	"nhorman@...driver.com" <nhorman@...driver.com>,
	"tgraf@...radead.org" <tgraf@...radead.org>,
	"stephen.hemminger@...tta.com" <stephen.hemminger@...tta.com>,
	"hagen@...u.net" <hagen@...u.net>,
	"eric.dumazet@...il.com" <eric.dumazet@...il.com>,
	Seiji Aguchi <seiji.aguchi@....com>
Subject: Re: [PATCH v2 0/2] Tracepoint for tcp retransmission

Hi Satoru,

I totally understand that you need deeper instrumentation for *your*
business. At Google, we instrument a lot more in TCP as well. But we
have yet to upstream these changes because it's not universally useful
for default Linux kernel. I failed to see how different failures of a
TCP retransmission must be recorded and exported. Could you elaborate
your last point?

On Fri, Feb 3, 2012 at 4:47 PM, Satoru Moriya <satoru.moriya@....com> wrote:
>
> On 01/20/2012 01:50 PM, David Miller wrote:
> > You were given an alternative way to trace these kinds of events, and
> > you have yet to give us a solid reason why that cannot work for you.
>
> OK. I'll try to explain it.
>
> First of all, we'd like to use this tracepoint with our
> flight recorder.
>
> tcpdump:
>  tcpdump captures all the packets and so its overhead is not
>  acceptable. Also we can't keep the data on memory but must
>  write the data to file for each time. It introduce other
>  overhead which we can't accept.
>
> commit 63e03724b51, dropwatch, skb:kfree_skb:
>  With this tracepoint, we can detect packet drop.
>  But it may be too late because with tcp kernel retransmits
>  packets repeatedly if it can't get ack and after that it
>  may drops packets in a no-win situation.
>  Also sometimes customer finds delays which is caused by
>  temporal packet drop and retransmission. With this tracepoint
>  we can explain it based on the real data.
>
> netstat:
>  This is a good tool for the first step to analyze what
>  happened. But it shows only statistics and it's not enough
>  for us to analyze incidents and explain it to our customers.
>  We need each packet drop data(when it happen, whether it
>  succeeded or not etc.)
>
> systemtap:
>  Actually, we've already used systemtap in our flight recorder.
>  But we believe that tcp retransmission is one of the fundamental
>  function in tcp stack and so kernel itself should provide the
>  instruments from which we can get enough information.
>
> Regards,
> Satoru
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html