netdev - Re: [PATCH 00/10 net-next] Introduce per interface ipv4 statistics

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: <1324054244.25554.56.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC>
Date:	Fri, 16 Dec 2011 17:50:44 +0100
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Christoph Lameter <cl@...ux.com>
Cc:	igorm@....rs, netdev@...r.kernel.org, davem@...emloft.net
Subject: Re: [PATCH 00/10 net-next] Introduce per interface ipv4 statistics

Le vendredi 16 décembre 2011 à 10:44 -0600, Christoph Lameter a écrit :
> On Fri, 16 Dec 2011, Eric Dumazet wrote:
> 
> > > Also I did it because ipv6 has per interface stats.
> >
> > I was considering _removing_ them, or make it optional.
> >
> > Memory costs are huge for percpu data.
> >
> 
> And these costs are going to increase as we add more processors. Intel is
> talking about hundred in the future.
> 
> So maybe we need to change the per cpu subsystem to be able to allocate
> these only for subsets of cpus and then only allow the operation of
> the network subsystems on the same subset? That would also increase cache
> hotness. Pretty radical but I think at some point we will have to consider
> that given that the number of cpus keep growing.
> 

Or we could use a hierarchical split : Say 16 (or 32 or 64) cpus share
same counters (must be atomic if NR_CPUS > 16/32/64)

percpu_alloc() -> percpugroup_alloc()



--
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