linux-kernel - Re: Possible netns creation and execution performance/scalability regression since v3.8 due to rcu callbacks being offloaded to multiple cpus

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <5398C6C3.90405@canonical.com>
Date:	Wed, 11 Jun 2014 16:14:43 -0500
From:	Dave Chiluk <chiluk@...onical.com>
To:	"Eric W. Biederman" <ebiederm@...ssion.com>
CC:	paulmck@...ux.vnet.ibm.com,
	Rafael Tinoco <rafael.tinoco@...onical.com>,
	linux-kernel@...r.kernel.org, davem@...emloft.net,
	Christopher Arges <chris.j.arges@...onical.com>,
	Jay Vosburgh <jay.vosburgh@...onical.com>
Subject: Re: Possible netns creation and execution performance/scalability
 regression since v3.8 due to rcu callbacks being offloaded to multiple cpus

On 06/11/2014 03:46 PM, Eric W. Biederman wrote:
> ip netns add also performs a bind mount so we get into all of the vfs
> level locking as well.

It's actually quite a bit worse than that as ip netns exec creates a new
mount namespace as well.  That being said, the vfs issues have been
healthily mitigated by a number of recent patches by Al Viro to
fs/namespace.c.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/