From mboxrd@z Thu Jan 1 00:00:00 1970 From: Robert Love Subject: Initial nice value for FCoE receive threads Date: Wed, 25 Feb 2009 14:13:42 -0800 Message-ID: <1235600022.7691.272.camel@fritz> Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Return-path: Received: from mga14.intel.com ([143.182.124.37]:17252 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752376AbZBYWNp (ORCPT ); Wed, 25 Feb 2009 17:13:45 -0500 Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: linux-scsi@vger.kernel.org Cc: robert.w.love@intel.com fcoe.ko uses per-CPU kernel threads to process the incoming frames. We used to nice to -19, but a typo during our re-architecture phase fliped that value to 19. I think a performance review will help to determine a good value, but for now I'm trying to figure out a decent starting value. Both lpfc and qla2xxx use -20 for their threads, but I don't think that they're per-CPU. Is -20 a good initial nice value for fcoe.ko?