From: Stefano Brivio <sbrivio@redhat.com>
To: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: netfilter-devel@vger.kernel.org,
"Florian Westphal" <fw@strlen.de>,
"Kadlecsik József" <kadlec@blackhole.kfki.hu>,
"Eric Garver" <eric@garver.life>, "Phil Sutter" <phil@nwl.cc>
Subject: Re: [PATCH nf-next v2 0/8] nftables: Set implementation for arbitrary concatenation of ranges
Date: Mon, 25 Nov 2019 14:36:18 +0100 [thread overview]
Message-ID: <20191125143618.4b28ca62@elisabeth> (raw)
In-Reply-To: <20191125100214.ke2inuq7cequbdgx@salvia>
On Mon, 25 Nov 2019 11:02:14 +0100
Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> BTW, do you have numbers comparing the AVX2 version with the C code? I
> quickly had a look at your numbers, but not clear to me if this is
> compared there.
No, sorry, I didn't report that anywhere, I probably should have in
the commit messages for 4/8 and 5/8. This was from v1 at 4/8, single
thread on AMD Epyc 7351, C implementation without unrolled loops:
TEST: performance
net,port [ OK ]
baseline (drop from netdev hook): 9971887pps
baseline hash (non-ranged entries): 5991032pps
baseline rbtree (match on first field only): 2666255pps
set with 1000 full, ranged entries: 2220404pps
port,net [ OK ]
baseline (drop from netdev hook): 10004499pps
baseline hash (non-ranged entries): 6011221pps
baseline rbtree (match on first field only): 4035566pps
set with 100 full, ranged entries: 4018240pps
net6,port [ OK ]
baseline (drop from netdev hook): 9497500pps
baseline hash (non-ranged entries): 4685436pps
baseline rbtree (match on first field only): 1354978pps
set with 1000 full, ranged entries: 1052188pps
port,proto [ OK ]
baseline (drop from netdev hook): 10749256pps
baseline hash (non-ranged entries): 6774103pps
baseline rbtree (match on first field only): 2819211pps
set with 30000 full, ranged entries: 283492pps
net6,port,mac [ OK ]
baseline (drop from netdev hook): 9463935pps
baseline hash (non-ranged entries): 3777039pps
baseline rbtree (match on first field only): 2943527pps
set with 10 full, ranged entries: 1927899pps
net6,port,mac,proto [ OK ]
baseline (drop from netdev hook): 9502200pps
baseline hash (non-ranged entries): 3637739pps
baseline rbtree (match on first field only): 1342323pps
set with 1000 full, ranged entries: 753960pps
net,mac [ OK ]
baseline (drop from netdev hook): 10065715pps
baseline hash (non-ranged entries): 5082895pps
baseline rbtree (match on first field only): 2677391pps
set with 1000 full, ranged entries: 1215104pps
I would re-run tests on v3 patches and include the comparisons in
commit messages.
By the way, as you can see, even though the comparison with rbtree is
unfair (comparing > 1 fields adds substantial complexity), without AVX2
it doesn't scale as nicely. I plan to propose some optimisations that
should substantially improve the non-vectorised case, but what I have
in mind right now is a bit convoluted and I would skip it in this
initial submission.
--
Stefano
prev parent reply other threads:[~2019-11-25 13:36 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-22 13:39 [PATCH nf-next v2 0/8] nftables: Set implementation for arbitrary concatenation of ranges Stefano Brivio
2019-11-22 13:40 ` [PATCH nf-next v2 1/8] netfilter: nf_tables: Support for subkeys, set with multiple ranged fields Stefano Brivio
2019-11-23 20:01 ` Pablo Neira Ayuso
2019-11-25 9:30 ` Stefano Brivio
2019-11-25 9:58 ` Pablo Neira Ayuso
2019-11-25 13:26 ` Stefano Brivio
2019-11-25 14:30 ` Pablo Neira Ayuso
2019-11-25 14:54 ` Stefano Brivio
2019-11-25 20:38 ` Pablo Neira Ayuso
2019-11-22 13:40 ` [PATCH nf-next v2 2/8] bitmap: Introduce bitmap_cut(): cut bits and shift remaining Stefano Brivio
2019-11-22 13:40 ` [PATCH nf-next v2 3/8] nf_tables: Add set type for arbitrary concatenation of ranges Stefano Brivio
2019-11-27 9:29 ` Pablo Neira Ayuso
2019-11-27 11:02 ` Stefano Brivio
2019-11-27 18:29 ` Pablo Neira Ayuso
2019-11-22 13:40 ` [PATCH nf-next v2 4/8] selftests: netfilter: Introduce tests for sets with range concatenation Stefano Brivio
2019-11-22 13:40 ` [PATCH nf-next v2 5/8] nft_set_pipapo: Provide unrolled lookup loops for common field sizes Stefano Brivio
2019-11-22 13:40 ` [PATCH nf-next v2 6/8] nft_set_pipapo: Prepare for vectorised implementation: alignment Stefano Brivio
2019-11-22 13:40 ` [PATCH nf-next v2 7/8] nft_set_pipapo: Prepare for vectorised implementation: helpers Stefano Brivio
2019-11-22 13:40 ` [PATCH nf-next v2 8/8] nft_set_pipapo: Introduce AVX2-based lookup implementation Stefano Brivio
2019-11-26 6:36 ` kbuild test robot
2019-11-23 20:05 ` [PATCH nf-next v2 0/8] nftables: Set implementation for arbitrary concatenation of ranges Pablo Neira Ayuso
2019-11-25 9:31 ` Stefano Brivio
2019-11-25 10:02 ` Pablo Neira Ayuso
2019-11-25 13:36 ` Stefano Brivio [this message]
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=20191125143618.4b28ca62@elisabeth \
--to=sbrivio@redhat.com \
--cc=eric@garver.life \
--cc=fw@strlen.de \
--cc=kadlec@blackhole.kfki.hu \
--cc=netfilter-devel@vger.kernel.org \
--cc=pablo@netfilter.org \
--cc=phil@nwl.cc \
/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).