Date: Fri, 2 Dec 2011 14:15:05 -0600 (CST) From: Bob Friesenhahn <bfriesen@simple.dallas.tx.us> To: Jason Hellenthal <jhell@DataIX.net> Cc: freebsd-fs@freebsd.org Subject: Re: Monitoring ZFS IO Message-ID: <alpine.GSO.2.01.1112021413240.2282@freddy.simplesystems.org> In-Reply-To: <20111202200241.GA38979@DataIX.net> References: <4ED8D7A5.7090700@icritical.com> <op.v5u91pls8527sy@212-182-167-131.ip.telfort.nl> <4ED8EC9A.2080706@icritical.com> <alpine.GSO.2.01.1112021135550.2282@freddy.simplesystems.org> <20111202200241.GA38979@DataIX.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 2 Dec 2011, Jason Hellenthal wrote: >>> >>> I want to see how many bytes or KB have been read and written to a given >>> zpool since creation (as in the newer of uptime or zpool creation) on the >>> system. >> >> This implies that these statistics would need to be stored in the pool >> itself, which implies that the statistics need to be periodically >> written (e.g. in each transaction group) as a form of metadata. >> > > I thought this was ( df -[h,b,m,g]) output... ;) Apparently the term "creation" was meant to mean "since boot" rather than since filesystem creation. Regardless, it is possible to write thousands of times more data to a filesystem than it contains. This means that 'df' won't do the job. It would be nice if the zfs pool could store its own performance data since the dawn of time. Bob -- Bob Friesenhahn bfriesen@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer, http://www.GraphicsMagick.org/
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?alpine.GSO.2.01.1112021413240.2282>