Date: Thu, 18 Feb 2016 22:23:10 -0800 From: Ravi Pokala <rpokala@mac.com> To: "freebsd-fs@freebsd.org" <freebsd-fs@freebsd.org> Subject: Re: Hours of tiny transfers at the end of a ZFS resilver? Message-ID: <75A39599-A668-4A2E-9956-98479A28930A@panasas.com>
next in thread | raw e-mail | index | archive | help
>Date: Tue, 16 Feb 2016 09:09:17 +0000 >From: Steven Hartland <killing@multiplay.co.uk> >To: freebsd-fs@freebsd.org >Subject: Re: Hours of tiny transfers at the end of a ZFS resilver? >Message-ID: <56C2E73D.2010405@multiplay.co.uk> >Content-Type: text/plain; charset=windows-1252; format=flowed > >This is 4k underlying, SSD's are by far and away the worst culprits for this. On the one hand, you're right - SSDs actually *do* lie about their 512n/AF-512e/AF-4Kn designation. On the other hand, SSD erase blocks - and even program blocks - are larger than 4KB, so neither AF-* designation would be correct anyway. And to some extent, it doesn't matter for SSDs, since everything is so heavily indirected anyway. -Ravi (rpokala@)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?75A39599-A668-4A2E-9956-98479A28930A>