All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stephen Hemminger <shemminger@vyatta.com>
To: Dmitry Popov <dp@highloadlab.com>
Cc: "David S. Miller" <davem@davemloft.net>,
	William.Allen.Simpson@gmail.com,
	"Eric Dumazet" <eric.dumazet@gmail.com>,
	"Andreas Petlund" <apetlund@simula.no>,
	"Ilpo Järvinen" <ilpo.jarvinen@helsinki.fi>,
	"Alexey Kuznetsov" <kuznet@ms2.inr.ac.ru>,
	"Pekka Savola (ipv6)" <pekkas@netcore.fi>,
	"James Morris" <jmorris@namei.org>,
	"Hideaki YOSHIFUJI" <yoshfuji@linux-ipv6.org>,
	"Patrick McHardy" <kaber@trash.net>,
	"Herbert Xu" <herbert@gondor.hengli.com.au>,
	"Gilad Ben-Yossef" <gilad@codefidence.com>,
	"Yony Amit" <yony@comsleep.com>, "Zhu Yi" <yi.zhu@intel.com>,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Subject: Re: [PATCH] tcp: md5 signature check scaling
Date: Wed, 27 Oct 2010 08:56:03 -0700	[thread overview]
Message-ID: <20101027085603.490e326b@nehalam> (raw)
In-Reply-To: <AANLkTi=U1smX6XXDMyBTicyqbUU5V-t56jmH7qtX2XW5@mail.gmail.com>

On Wed, 27 Oct 2010 16:52:30 +0400
Dmitry Popov <dp@highloadlab.com> wrote:

> From: Dmitry Popov <dp@highloadlab.com>
> 
> TCP MD5 signature checking without socket lock.
> 
> Each tcp_sock has 2 RCU-protected arrays (tcp[46]_md5sig_info) of
> tcp[46]_md5sig_key address-key pairs.
> Each key (tcp_md5sig_key) has kref struct so that there is no need to
> lock the whole array to work with one key.
> 
> MD5 functions were rewritten according to above statement and hash
> check (tcp_v4_inbound_md5_hash) was moved before socket lock.
> 
> Signed-off-by: Dmitry Popov <dp@highloadlab.com>

You traded locking for ref counting which may not be as big
a win as your think.

Also, the overhead of RCU here might impact tests that involve
lots of socket creation and destruction.

-- 

WARNING: multiple messages have this Message-ID (diff)
From: Stephen Hemminger <shemminger@vyatta.com>
To: Dmitry Popov <dp@highloadlab.com>
Cc: "David S. Miller" <davem@davemloft.net>,
	William.Allen.Simpson@gmail.com,
	"Eric Dumazet" <eric.dumazet@gmail.com>,
	"Andreas Petlund" <apetlund@simula.no>,
	"Ilpo Järvinen" <ilpo.jarvinen@helsinki.fi>,
	"Alexey Kuznetsov" <kuznet@ms2.inr.ac.ru>,
	"Pekka Savola (ipv6)" <pekkas@netcore.fi>,
	"James Morris" <jmorris@namei.org>,
	"Hideaki YOSHIFUJI" <yoshfuji@linux-ipv6.org>,
	"Patrick McHardy" <kaber@trash.net>,
	"Herbert Xu" <herbert@gondor.apana.org.au>,
	"Gilad Ben-Yossef" <gilad@codefidence.com>,
	"Yony Amit" <yony@comsleep.com>, "Zhu Yi" <yi.zhu@intel.com>,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Subject: Re: [PATCH] tcp: md5 signature check scaling
Date: Wed, 27 Oct 2010 08:56:03 -0700	[thread overview]
Message-ID: <20101027085603.490e326b@nehalam> (raw)
In-Reply-To: <AANLkTi=U1smX6XXDMyBTicyqbUU5V-t56jmH7qtX2XW5@mail.gmail.com>

On Wed, 27 Oct 2010 16:52:30 +0400
Dmitry Popov <dp@highloadlab.com> wrote:

> From: Dmitry Popov <dp@highloadlab.com>
> 
> TCP MD5 signature checking without socket lock.
> 
> Each tcp_sock has 2 RCU-protected arrays (tcp[46]_md5sig_info) of
> tcp[46]_md5sig_key address-key pairs.
> Each key (tcp_md5sig_key) has kref struct so that there is no need to
> lock the whole array to work with one key.
> 
> MD5 functions were rewritten according to above statement and hash
> check (tcp_v4_inbound_md5_hash) was moved before socket lock.
> 
> Signed-off-by: Dmitry Popov <dp@highloadlab.com>

You traded locking for ref counting which may not be as big
a win as your think.

Also, the overhead of RCU here might impact tests that involve
lots of socket creation and destruction.

-- 

  parent reply	other threads:[~2010-10-27 15:56 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-10-27 12:52 [PATCH] tcp: md5 signature check scaling Dmitry Popov
2010-10-27 13:00 ` Eric Dumazet
2010-10-27 13:00   ` Eric Dumazet
2010-10-27 13:18   ` Dmitry Popov
2010-10-27 13:18     ` Dmitry Popov
2010-10-27 15:56 ` Stephen Hemminger [this message]
2010-10-27 15:56   ` Stephen Hemminger
  -- strict thread matches above, loose matches on Subject: below --
2010-10-27 12:52 Dmitry Popov

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=20101027085603.490e326b@nehalam \
    --to=shemminger@vyatta.com \
    --cc=William.Allen.Simpson@gmail.com \
    --cc=apetlund@simula.no \
    --cc=davem@davemloft.net \
    --cc=dp@highloadlab.com \
    --cc=eric.dumazet@gmail.com \
    --cc=gilad@codefidence.com \
    --cc=herbert@gondor.hengli.com.au \
    --cc=ilpo.jarvinen@helsinki.fi \
    --cc=jmorris@namei.org \
    --cc=kaber@trash.net \
    --cc=kuznet@ms2.inr.ac.ru \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pekkas@netcore.fi \
    --cc=yi.zhu@intel.com \
    --cc=yony@comsleep.com \
    --cc=yoshfuji@linux-ipv6.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.