Date: Fri, 1 Jul 2005 15:27:40 -0400 From: "Mark Bucciarelli" <mark@gaiahost.coop> To: freebsd-questions@freebsd.org, "questions@freebsd.org" <questions@freebsd.org> Subject: Re: RAID Cards Message-ID: <20050701192740.GC2593@pooh.hubcapconsulting.com> In-Reply-To: <20050630213413.GJ2392@dan.emsphone.com> References: <42C45161.1070402@toldme.com> <20050630204448.8E0F543D4C@mx1.FreeBSD.org> <20050630211028.GP1280@rabbit> <20050630213413.GJ2392@dan.emsphone.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Jun 30, 2005 at 04:34:13PM -0500, Dan Nelson wrote: > In the last episode (Jun 30), Mark Bucciarelli said: > > > > I don't see the big win in hardware raid. > > The three big plusses for hardware raid are: if you get one with > battery-backed cache (strongly recommended), then the array can cache raid-5 > writes until it gets full stripes, and can hold off doing mirror writes if > there are pending read requests. Ah ... this is certainly a win for an io-bound system. > Also, if your power goes out or the system spontaneously reboots, you won't > have to rebuild parity or resync the mirrors (assuming battery-backed > cache). We pay a lot of money to ensure the lights stay on and sacrifice small animals to avoid spontaneous reboots. > And finally, hardware raid cards will automatically rebuild onto a hot spare I know I could do this with Linux software raid, not sure about gmirror. > if available and you can swap out the dead drive and swap a new spare in > without having to run a single command. Another win. Thanks, your brought up some issues I hadn't thought of. I expect hardware raid cards will go the way of modems and printers and offload their processing to the main CPU. And I guess the choice partly depends on whose software you trust more--free software from FreeBSD or proprietary code written in a cathedral. You can probabaly guess my bias. ;) m
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050701192740.GC2593>