Date: Wed, 02 Mar 2016 10:43:37 +0100 From: Miroslav Lachman <000.fbsd@quip.cz> To: Bob Friesenhahn <bfriesen@simple.dallas.tx.us> Cc: Steven Hartland <killing@multiplay.co.uk>, freebsd-fs@freebsd.org Subject: Re: abnormally high CPU load after zfs destroy Message-ID: <56D6B5C9.7090409@quip.cz> In-Reply-To: <alpine.GSO.2.01.1603012050080.20809@freddy.simplesystems.org> References: <56D4964D.3010604@quip.cz> <56D4B66D.4070007@multiplay.co.uk> <56D5CEC1.2070000@quip.cz> <alpine.GSO.2.01.1603012050080.20809@freddy.simplesystems.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Bob Friesenhahn wrote on 03/02/2016 03:50: > On Tue, 1 Mar 2016, Miroslav Lachman wrote: > >> Steven Hartland wrote on 02/29/2016 22:21: >>> Its likely churning through the actual delete, show system processes in >>> top and you'll see it. >> >> Yes, there are about 300 kernel thread doing ZFS work, but should it >> really bomb the system that way? The system is heavilly lagging for >> about 10 minutes. Are there any sysctl to control this behavior? > > Is it possible that you enabled the dedup feature? No, dedup is disabled and I never tried it on this machine. Miroslav Lachman
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?56D6B5C9.7090409>