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
| ||
|
Date: Thu, 5 May 2011 06:47:52 +0000 From: Yevgeny Petrilin <yevgenyp@...lanox.co.il> To: Eric Dumazet <eric.dumazet@...il.com>, Ben Hutchings <bhutchings@...arflare.com> CC: "davem@...emloft.net" <davem@...emloft.net>, "netdev@...r.kernel.org" <netdev@...r.kernel.org> Subject: RE: [PATCH] mlx4_en: Setting RSS hash result to skb->rxhash field > > > > An 8-bit hash is almost useless. It's entirely useless if you then > > shift it into the top bits of rxhash. > > > > Agreed. This is very bad. > > Yevgeny probably did this shift because get_rps_cpu() does : > > tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; > > (If rxhash is not a pure random u32 distribution, then high order bits are more important than low order bits) > > Eric, you are correct. We do plan to enable full 32 bit hash for our devices. Once it is done, we will naturally use the whole 32 bits. In the meanwhile, even with this change we see improved performance when enabling RPS. Thanks, Yevgeny
Powered by blists - more mailing lists