netdev - Re: [PATCH net-next-2.6] net: sock_def_readable() and friends RCU conversion

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 linux-hardening linux-cve-announce 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]

Message-ID: <1272701011.2230.134.camel@edumazet-laptop>
Date:	Sat, 01 May 2010 10:03:31 +0200
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	David Miller <davem@...emloft.net>
Cc:	hadi@...erus.ca, xiaosuo@...il.com, therbert@...gle.com,
	shemminger@...tta.com, netdev@...r.kernel.org, eilong@...adcom.com,
	bmb@...enacr.com
Subject: Re: [PATCH net-next-2.6] net: sock_def_readable() and friends RCU
 conversion

Le samedi 01 mai 2010 à 09:02 +0200, Eric Dumazet a écrit :
> Le vendredi 30 avril 2010 à 16:35 -0700, David Miller a écrit :
> > From: Eric Dumazet <eric.dumazet@...il.com>
> > Date: Thu, 29 Apr 2010 23:01:49 +0200
> > 
> > > [PATCH net-next-2.6] net: sock_def_readable() and friends RCU conversion
> > 
> > So what's the difference between call_rcu() freeing this little waitqueue
> > struct and doing it for the entire socket?
> > 
> > We'll still be doing an RCU call every socket destroy, and now we also have
> > a new memory allocation/free per connection.
> > 
> > This has to show up in things like 'lat_connect' and friends, does it not?
> 
> Before patch :
> 
> lat_connect -N 10 127.0.0.1
> TCP/IP connection cost to 127.0.0.1: 27.8872 microseconds
> 
> After :
> 
> lat_connect -N 10 127.0.0.1
> TCP/IP connection cost to 127.0.0.1: 20.7681 microseconds
> 
> Strange isnt it ?
> 
> (special care should be taken with this bench, as it leave many sockets
> in TIME_WAIT state, so to get consistent numbers we have to wait a while
> before restarting it)


Oops, this was with the other patch (about dst no_refcounting in input
path), sorry.

With the "sock_def_readable() and friends RCU conversion" patch I got :

lat_connect -N 10 127.0.0.1
TCP/IP connection cost to 127.0.0.1: 27.6244 microseconds


Anyway, this lat_connect seems very unreliable (lot of variance)

with linux-2.6.31, ~33 us
with linux-2.6.33, ~30 us

David, I also need this RCU thing in order to be able to group all
wakeups at the end of net_rx_action().

Plan was to use RCU, so that I dont need to increase sk_refcnt when
queueing a "wakeup" (and decrease sk_refcnt a long time after)

Previous attempt was a bit hacky,
http://patchwork.ozlabs.org/patch/24179/

I expect 2010 one will be cleaner :)


--
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