Re: [PATCH 4.9 50/71] inet: frags: use rhashtables for reassembly units

From: Stefan Schmidt <stefan@datenfreihafen.org>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Cc: stable@vger.kernel.org, Eric Dumazet <edumazet@google.com>,
	Kirill Tkhai <ktkhai@virtuozzo.com>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	Florian Westphal <fw@strlen.de>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	Alexander Aring <alex.aring@gmail.com>,
	Stefan Schmidt <stefan@osg.samsung.com>,
	"David S. Miller" <davem@davemloft.net>
Subject: Re: [PATCH 4.9 50/71] inet: frags: use rhashtables for reassembly units
Date: Fri, 26 Oct 2018 15:39:47 +0200	[thread overview]
Message-ID: <62bd748b-20a8-d021-7b3b-32146df8beb8@datenfreihafen.org> (raw)
In-Reply-To: <20181016170541.874459615@linuxfoundation.org>

Hello Greg.

[Hope I am not to late for this]

On 16/10/2018 19:09, Greg Kroah-Hartman wrote:
> 4.9-stable review patch.  If anyone has any objections, please let me know.
> 
> ------------------
> 
> From: Eric Dumazet <edumazet@google.com>
> 
> Some applications still rely on IP fragmentation, and to be fair linux
> reassembly unit is not working under any serious load.
> 
> It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!)
> 
> A work queue is supposed to garbage collect items when host is under memory
> pressure, and doing a hash rebuild, changing seed used in hash computations.
> 
> This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
> occurring every 5 seconds if host is under fire.
> 
> Then there is the problem of sharing this hash table for all netns.
> 
> It is time to switch to rhashtables, and allocate one of them per netns
> to speedup netns dismantle, since this is a critical metric these days.
> 
> Lookup is now using RCU. A followup patch will even remove
> the refcount hold/release left from prior implementation and save
> a couple of atomic operations.
> 
> Before this patch, 16 cpus (16 RX queue NIC) could not handle more
> than 1 Mpps frags DDOS.
> 
> After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB
> of storage for the fragments (exact number depends on frags being evicted
> after timeout)
> 
> $ grep FRAG /proc/net/sockstat
> FRAG: inuse 1966916 memory 2140004608
> 
> A followup patch will change the limits for 64bit arches.
> 
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
> Cc: Herbert Xu <herbert@gondor.apana.org.au>
> Cc: Florian Westphal <fw@strlen.de>
> Cc: Jesper Dangaard Brouer <brouer@redhat.com>
> Cc: Alexander Aring <alex.aring@gmail.com>
> Cc: Stefan Schmidt <stefan@osg.samsung.com>
> Signed-off-by: David S. Miller <davem@davemloft.net>
> (cherry picked from commit 648700f76b03b7e8149d13cc2bdb3355035258a9)
> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> ---
>  Documentation/networking/ip-sysctl.txt  |    7 
>  include/net/inet_frag.h                 |   81 +++----
>  include/net/ipv6.h                      |   16 -
>  net/ieee802154/6lowpan/6lowpan_i.h      |   26 --
>  net/ieee802154/6lowpan/reassembly.c     |   91 +++-----
>  net/ipv4/inet_fragment.c                |  349 ++++++--------------------------
>  net/ipv4/ip_fragment.c                  |  112 ++++------
>  net/ipv6/netfilter/nf_conntrack_reasm.c |   51 +---
>  net/ipv6/reassembly.c                   |  110 ++++------
>  9 files changed, 267 insertions(+), 576 deletions(-)
> 

When this patch hit master a while back we had to address a regression
in the ieee802514 6lowpan layer. It seems this fix is missing in the
backport series (only looking at your patchset here, no the full tree).

https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git/commit/?id=f18fa5de5ba7f1d6650951502bb96a6e4715a948

I would appreciate if you could pull this into this series as well.

regards
Stefan Schmidt