From: Patrick McHardy <kaber@trash.net>
To: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: netfilter-devel@vger.kernel.org
Subject: Re: [PATCH 7/8] [PATCH] dynamic calculation of event message size for ctnetlink
Date: Tue, 18 Nov 2008 12:03:00 +0100 [thread overview]
Message-ID: <4922A0E4.5010806@trash.net> (raw)
In-Reply-To: <4922973A.7000001@netfilter.org>
Pablo Neira Ayuso wrote:
> Pablo Neira Ayuso wrote:
>> Patrick McHardy wrote:
>>> These calculations look somewhat expensive to perform for every message.
>>> Do you have any numbers for this new patch that shows the difference
>>> in CPU usage compared to the resizing done by af_netlink.c?
>> Fabian Hugelshofer reported some reduction (~5%) on an embedded
>> environment but he was using top to measure the difference. I'll collect
>> some more trustable data and get back to you.
>
> Some oprofile results:
>
> wo/patch
> 2189 0.0305 nf_conntrack_netlink.ko nf_conntrack_netlink
> ctnetlink_conntrack_event
>
> w/patch
> 2302 0.0440 nf_conntrack_netlink.ko nf_conntrack_netlink
> ctnetlink_conntrack_event
>
> While __alloc_skb and netlink_broadcast report similar values for w/ and
> wo/ the patch.
So its actually getting worse? :) Any other differences, like less
cycles for memcpy in netlink_trim()?
next prev parent reply other threads:[~2008-11-18 11:03 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-11-17 8:39 [PATCH 1/8] [PATCH] use nf_conntrack_get instead of atomic_inc Pablo Neira Ayuso
2008-11-17 8:39 ` [PATCH 2/8] [PATCH] use EOPNOTSUPP instead of EINVAL if the conntrack has no helper Pablo Neira Ayuso
2008-11-17 14:56 ` Patrick McHardy
2008-11-17 8:40 ` [PATCH 3/8] [PATCH] get rid of module refcounting in ctnetlink Pablo Neira Ayuso
2008-11-17 15:01 ` Patrick McHardy
2008-11-17 8:40 ` [PATCH 4/8] [PATCH] connection tracking helper name persistent aliases Pablo Neira Ayuso
2008-11-17 15:02 ` Patrick McHardy
2008-11-17 8:40 ` [PATCH 5/8] [PATCH] Helper modules load-on-demand support for ctnetlink Pablo Neira Ayuso
2008-11-17 8:55 ` Alexey Dobriyan
2008-11-17 15:24 ` Patrick McHardy
2008-11-17 8:41 ` [PATCH 6/8] [PATCH] deliver events for conntracks created via ctnetlink Pablo Neira Ayuso
2008-11-17 8:41 ` [PATCH 7/8] [PATCH] dynamic calculation of event message size for ctnetlink Pablo Neira Ayuso
2008-11-17 8:44 ` David Miller
2008-11-17 15:32 ` Patrick McHardy
2008-11-18 3:33 ` Pablo Neira Ayuso
2008-11-18 10:21 ` Pablo Neira Ayuso
2008-11-18 11:03 ` Patrick McHardy [this message]
2008-11-19 0:03 ` Pablo Neira Ayuso
2008-11-19 12:05 ` Patrick McHardy
2008-11-18 11:01 ` Patrick McHardy
2008-11-17 8:42 ` [PATCH 8/8] [PATCH] bump the expectation helper name Pablo Neira Ayuso
2008-11-17 14:55 ` [PATCH 1/8] [PATCH] use nf_conntrack_get instead of atomic_inc Patrick McHardy
-- strict thread matches above, loose matches on Subject: below --
2008-10-09 8:33 [PATCH 1/8] [PATCH] get rid of module refcounting in ctnetlink Pablo Neira Ayuso
2008-10-09 8:35 ` [PATCH 7/8] [PATCH] dynamic calculation of event message size for ctnetlink Pablo Neira Ayuso
2008-10-09 16:45 ` Pablo Neira Ayuso
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=4922A0E4.5010806@trash.net \
--to=kaber@trash.net \
--cc=netfilter-devel@vger.kernel.org \
--cc=pablo@netfilter.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.