Date: Thu, 24 Feb 2011 19:23:54 +0100 From: Christer Solskogen <christer.solskogen@gmail.com> To: Jeremy Chadwick <freebsd@jdc.parodius.com> Cc: "freebsd-stable@freebsd.org" <freebsd-stable@freebsd.org> Subject: Re: ZFS - abysmal performance with samba since upgrade to 8.2-RELEASE Message-ID: <AANLkTi=qM8Jym1SpVSoYKC%2B1mqjmuYudVhT5m%2BhXQgJ7@mail.gmail.com> In-Reply-To: <20110224075517.GA18146@icarus.home.lan> References: <4D660909.6090202@my.gd> <20110224075517.GA18146@icarus.home.lan>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Feb 24, 2011 at 8:55 AM, Jeremy Chadwick <freebsd@jdc.parodius.com> wrote: > > =A0# Set TXG write limit to a lower threshold. =A0This helps "level out" > =A0# the throughput rate (see "zpool iostat"). =A0A value of 256MB works = well > =A0# for systems with 4GB of RAM, while 1GB works well for us w/ 8GB on > =A0# disks which have 64MB cache. > =A0vfs.zfs.txg.write_limit_override=3D1073741824 > > Sorry if you have said this before, but could you elaborate a bit about this number? For instance, how much does the cache on the disk has to say. In my case: 3x1.5TB raidz with WD15EADS-00R6B0 which has 32MB cache and 12GB memory. What would you recommend and why. --=20 chs,
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTi=qM8Jym1SpVSoYKC%2B1mqjmuYudVhT5m%2BhXQgJ7>