Date: Sat, 28 Aug 2010 12:48:21 -0400 From: Dan Langille <dan@langille.org> To: Attilio Rao <attilio@freebsd.org> Cc: freebsd-scsi@freebsd.org Subject: Re: camcontrol rescan all - locks system Message-ID: <4C793DD5.6020300@langille.org> In-Reply-To: <4C7935FE.2040608@langille.org> References: <4C78FF01.5020500@langille.org> <4C792465.9060201@feral.com> <4C793045.2010300@langille.org> <AANLkTikFi1iE9%2BM5h-dsVuAbH9F3do-kFTi2Ex_x_7O6@mail.gmail.com> <4C7935FE.2040608@langille.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 8/28/2010 12:14 PM, Dan Langille wrote: > On 8/28/2010 12:07 PM, Attilio Rao wrote: >> Can you use procstat on the camcontrol? > > The system is completely unresponsive. > >> Is this problem easilly reproducible for you? > > I believe so. I have seen this behavior before, on another system. > > FYI, I went to the console to reboot. CTL-ALT-DEL had no [immediate] > effect. Then I hit the power button. Then these messages started > appearing every 20 seconds on the console: > > swap_pager: indefinite wait buffer: bufobj: 0, blkno: 928, size 4096 > > Screen shot here: > > http://www.flickr.com/photos/20922021@N04/4934586561/ > > I will probably power cycle the system to get it back. Given that the > system goes unresponsive if I do an camcontrol, what debugging can I > provide? Since my last post, I'm seeing new console message: Approaching the limit on PV entries, consider increasing either the vm.pmap.shpgperproc or the vm.pmap.pv_entry_max sysctl. Screenshot: http://www.flickr.com/photos/20922021@N04/4934683561/ -- Dan Langille - http://langille.org/
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4C793DD5.6020300>