Date: Thu, 17 Nov 2011 10:58:32 -0800 From: Freddie Cash <fjwcash@gmail.com> To: "list, mailing" <list@sprymed.com> Cc: freebsd-performance@freebsd.org Subject: Re: ZFS Few Questions Message-ID: <CAOjFWZ7oSE%2BMnFnTqi8tfb%2By3WN49cvqSWdMATS8770hzq9krg@mail.gmail.com> In-Reply-To: <CAKy=mtCcHavRFh16yaVH86Oh6DgePmxOhbQmmAySxWA5Zn8-yA@mail.gmail.com> References: <CAKy=mtCcHavRFh16yaVH86Oh6DgePmxOhbQmmAySxWA5Zn8-yA@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Nov 17, 2011 at 10:26 AM, list, mailing <list@sprymed.com> wrote: > Hello everyone I just had a few questions about ZFS. > I normally use Hardware RAID 5. > > Question 1: > > With the ZFS snapshots what is the lost in drive space? > > If no data changes after you create the snapshots, then no disk space is used by the snapshots. If data changes after you create the snapshot, then the snapshot holds the original data. For example, if you have 100 GB in the filesystem, create a snapshot, then modify 10 GB of data, the snapshot will hold 10 GB of data (the original, unchanged data), and the total disk usage (filesystem + snapshot) is 110 GB. > Hard drives I have: > 4 x 500 GB = 1.5T on RAID 5 > > I have see lots of videos like: http://www.youtube.com/watch?v=CN6iDzesEs0 With ZFS, you decide how much disk space you want to use for redundancy. With 4 harddrives, you have the following options: 2x mirror vdev = 1.0 TB of usable space; best performance, can lose 2 drives before losing data 1x raidz1 vdev = 1.5 TB of usable space; decent performance, can lose 1 drive before losing data 1x raidz2 vdev = 1.0 TB of usable space; ok performance,, can lose 2 drives before losing data raidz1 is similar to RAID5. raidz2 is similar to RAID6. > > Question 2: > > FreeBSD 9.0 installable on ZFS root? > Yes. > Question 3: > > Anyone Recommend for MySQL server? (Performance) > Read through the ZFS Admin Guide for recommendations for running databases on top of ZFS. > Question 4: > > fsck used with when Server just turns off? (Fast or slower filesystem check > when compared to UFS on HW RAID 5 ) > Taking note of: "FreeBSD 9.0 adds support for lightweight journaling on top > of softupdates(SU+J), which greatly reduces and need for background fsck, > and uses NFS-style ACLs by default." > > ZFS does not have a separate "fsck" tool. It does not need it. If the box crashes, ZFS will just come back online, possibly losing 5-10 seconds worth of uncommitted data. If ZFS is unable to come back online automatically, you can manually roll it back a transaction group or two. You'll lose a bit of data, but the filesystems will be coherent and intact and operational. -- Freddie Cash fjwcash@gmail.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAOjFWZ7oSE%2BMnFnTqi8tfb%2By3WN49cvqSWdMATS8770hzq9krg>