[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAA93jw49WSxU1tATiB1nQJRLvwHXJOaHq2t_1+Kp-Eb9FzS=rA@mail.gmail.com>
Date: Mon, 2 Jan 2012 22:56:27 +0100
From: Dave Taht <dave.taht@...il.com>
To: Eric Dumazet <eric.dumazet@...il.com>
Cc: David Miller <davem@...emloft.net>,
netdev <netdev@...r.kernel.org>,
Stephen Hemminger <shemminger@...tta.com>
Subject: Re: [PATCH] sch_qfq: fix overflow in qfq_update_start()
On Mon, Jan 2, 2012 at 10:45 PM, Eric Dumazet <eric.dumazet@...il.com> wrote:
> Le lundi 02 janvier 2012 à 16:47 +0100, Eric Dumazet a écrit :
>> grp->slot_shift is between 22 and 41, so using 32bit wide variables is
>> probably a typo.
>>
>> This could explain QFQ hangs Dave reported to me, after 2^23 packets ?
>>
>> (23 = 64 - 41)
>>
>> Reported-by: Dave Taht <dave.taht@...il.com>
>> CC: Stephen Hemminger <shemminger@...tta.com>
>> CC: Dave Taht <dave.taht@...il.com>
>
> Oh well, I forgot my SOB :(
>
> Signed-off-by: Eric Dumazet <eric.dumazet@...il.com>
>
> David please just tell me if you prefer me to resend it
>
>
I figure I'm the wrong david, but I'll be testing the QFQ patch overnight.
I have tested it for about an hour thus far.
Your SFQ patch, posted earlier today, does bring SFQ and QFQ back
into equivalence at 10 iperfs.
http://www.teklibre.com/~d/bloat/sfqnewvsqfq10iperfs.png
Well done.
--
Dave Täht
SKYPE: davetaht
US Tel: 1-239-829-5608
FR Tel: 0638645374
http://www.bufferbloat.net
--
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
Powered by blists - more mailing lists