netdev - Re: [RFC PATCH] openvswitch: use percpu flow stats

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: <1471636616.29842.110.camel@edumazet-glaptop3.roam.corp.google.com>
Date:   Fri, 19 Aug 2016 12:56:56 -0700
From:   Eric Dumazet <eric.dumazet@...il.com>
To:     Thadeu Lima de Souza Cascardo <cascardo@...hat.com>
Cc:     dev@...nvswitch.org, netdev@...r.kernel.org
Subject: Re: [RFC PATCH] openvswitch: use percpu flow stats

On Fri, 2016-08-19 at 16:47 -0300, Thadeu Lima de Souza Cascardo wrote:
> Instead of using flow stats per NUMA node, use it per CPU. When using
> megaflows, the stats lock can be a bottleneck in scalability.

...

>  
>  	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
> -				       + (nr_node_ids
> +				       + (num_possible_cpus()
>  					  * sizeof(struct flow_stats *)),
>  				       0, 0, NULL);
>  	if (flow_cache == NULL)

This is bogus.

Please use nr_cpu_ids instead of num_possible_cpus().