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  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:	Sat, 20 Oct 2012 09:47:22 +0200
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Vimalkumar <j.vimal@...il.com>
Cc:	davem@...emloft.net, Jamal Hadi Salim <jhs@...atatu.com>,
	netdev@...r.kernel.org
Subject: Re: [PATCH] htb: improved accuracy at high rates

On Fri, 2012-10-19 at 15:26 -0700, Vimalkumar wrote:
> Current HTB (and TBF) uses rate table computed by
> the "tc" userspace program, which has the following
> issue:
> 
> The rate table has 256 entries to map packet lengths
> to token (time units).  With TSO sized packets, the
> 256 entry granularity leads to loss/gain of rate,
> making the token bucket inaccurate.
> 
> Thus, instead of relying on rate table, this patch
> explicitly computes the time and accounts for packet
> transmission times with nanosec granularity.
> 
> This greatly improves accuracy of HTB with a wide
> range of packet sizes.
> 
> Example:
> 
> tc qdisc add dev $dev root handle 1: \
> 	htb default 1
> 
> tc class add dev $dev classid 1:1 parent 1: \
> 	rate 1Gbit mtu 64k
> 
> Ideally it should work with all intermediate sized
> packets as well, but...
> 
> Test:
> for i in {1..20}; do
> 	(netperf -H $host -t UDP_STREAM -l 30 -- -m $size &);
> done
> 
> With size=400 bytes: achieved rate ~600Mb/s
> With size=1000 bytes: achieved rate ~835Mb/s
> With size=8000 bytes: achieved rate ~1012Mb/s
> 
> With new HTB, in all cases, we achieve ~1000Mb/s.
> Many thanks to Eric Dumazet for review and feedback.
> 
> Signed-off-by: Vimalkumar <j.vimal@...il.com>
> ---

Thanks Vimal for this promising work.

I am going to test it, but my preliminary remarks are :


1)  This is a net-next work, so its better to add the net-next tag in
the title, as in : 

"[PATCH net-next] htb: improved accuracy at high rates"

So next submission will also include a version tag as in :

"[PATCH net-next V2] htb: improved accuracy at high rates"


2) I dont know how you generated your diff, but its not applicable
   without knowing where file is located.

So instead of

diff --git a/sch_htb.c b/sch_htb.c
index 29b942c..a808ba1 100644
--- a/sch_htb.c
+++ b/sch_htb.c

we need the proper :

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 9d75b77..13e02b3 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c

3) Always use an up2date net-next tree before submitting an official
patch.

Here is what I have applying your patch (once I fixed the path)

patching file net/sched/sch_htb.c
Hunk #9 succeeded at 612 (offset -3 lines).
Hunk #10 succeeded at 654 (offset -3 lines).
Hunk #11 succeeded at 704 (offset -3 lines).
Hunk #12 succeeded at 715 (offset -3 lines).
Hunk #13 succeeded at 902 (offset -2 lines).
Hunk #14 succeeded at 915 (offset -2 lines).
Hunk #15 succeeded at 934 (offset -2 lines).
Hunk #16 succeeded at 1121 (offset -1 lines).

It means you worked on an old version, so its always suspicious


--
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