From mboxrd@z Thu Jan 1 00:00:00 1970 From: Kay Sievers Date: Mon, 01 Jun 2009 13:30:04 +0000 Subject: Re: [GIT] Experimental threaded udev Message-Id: <1243863004.28812.8.camel@yio.site> List-Id: References: <4A1EA138.10400@tuffmail.co.uk> In-Reply-To: <4A1EA138.10400@tuffmail.co.uk> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: linux-hotplug@vger.kernel.org On Mon, 2009-06-01 at 14:33 +0200, Kay Sievers wrote: > Here is version 2 of the patch, with a few things corrected. Pretty weird test, but it seems to survive on my Dual Core 1.5 GHz laptop: Create lots of devices: $ time (modprobe scsi_debug add_host max_luns2 num_tgts num_parts=2; udevadm settle) real 11m28.193s 23.000 block devices: $ find /sys/class/block/ | wc -l 23824 72.000 sysfs devices: $ find /sys/ -name uevent | wc -l 72224 We created 262 workers: $ ps afx | grep udevd | wc -l 262 And 10 seconds later, all workers are gone: $ ps afx | grep udevd | wc -l 2 Kay