Date: Mon, 13 Jul 2009 11:13:57 -0700 (PDT) From: Richard Mahlerwein <mahlerrd@yahoo.com> To: Free BSD Questions list <freebsd-questions@freebsd.org> Subject: Re: ZFS or UFS for 4TB hardware RAID6? Message-ID: <937260.17107.qm@web51002.mail.re2.yahoo.com>
next in thread | raw e-mail | index | archive | help
--- On Mon, 7/13/09, Maxim Khitrov <mkhitrov@gmail.com> wrote:=0A=0A> From:= Maxim Khitrov <mkhitrov@gmail.com>=0A> Subject: Re: ZFS or UFS for 4TB har= dware RAID6?=0A> To: mahlerrd@yahoo.com=0A> Cc: "Free BSD Questions list" <= freebsd-questions@freebsd.org>=0A> Date: Monday, July 13, 2009, 2:02 PM=0A>= On Mon, Jul 13, 2009 at 1:46 PM,=0A> Richard Mahlerwein<mahlerrd@yahoo.com= >=0A> wrote:=0A> >>=0A> >> Your mileage may vary, but...=0A> >>=0A> >> I wo= uld investigate either using more spindles if=0A> you want=0A> >> to stick = to RAID6, or perhaps using another RAID=0A> level if=0A> >> you will be wit= h 4 drives for a while.=A0 The=0A> reasoning=0A> >> is that there's an over= head with RAID 6 - parity=0A> blocks are=0A> >> written to 2 disks, so in a= 4 drive combination=0A> you have 2=0A> >> drives with data and 2 with pari= ty.=0A> >>=0A> >> With 4 drives, you could get much, much higher=0A> perfor= mance=0A> >> out of RAID10 (which is alternatively called=0A> RAID0+1 or=0A= > >> RAID1+0 depending on the manufacturer and on how=0A> accurate=0A> >> t= hey wish to be, and on how they actually=0A> implemented it,=0A> >> too). T= his would also mean 2 usable drives, as=0A> well, so=0A> >> you'd have the = same space available in RAID10 as=0A> your=0A> >> proposed RAID6.=0A> >>=0A= > >> I would confirm you can, on the fly, convert from=0A> RAID10 to=0A> >>= RAID6 after you add more drives.=A0 If you can not,=0A> then=0A> >> by all= means stick with RAID6 now!=0A> >>=0A> >> With 4 1 TB drives (for simpler = examples)=0A> >> RAID5 =3D 3 TB available, 1 TB worth used in=0A> "parity".= =0A> >> Fast reads, slow writes.=0A> >> RAID6 =3D 2 TB available, 2 TB wort= h used in=0A> "parity".=0A> >> Moderately fast reads, slow writes.=0A> >> R= AID10 =3D 2 TB available, 2TB in duplicate copies=0A> (easier=0A> >> work t= han parity calculations).=A0 Very fast=0A> reads,=0A> >> moderately fast wr= ites.=0A> >>=0A> >> When you switch to, say, 8 drives, the numbers=0A> star= t to=0A> >> change a bit.=0A> >> RAID5 =3D 7TB available, 1 lost.=0A> >> RA= ID6 =3D 6TB available, 2 lost.=0A> >> RAID10 =3D 4TB available, 4 lost.=0A>= >>=0A> >=0A> > Sorry, consider myself chastised for having missed the=0A> = "Security is more important than performance" bit. I tend=0A> toward soluti= ons that show the most value, and with 4=0A> drives, it seems that I'd stic= k with the same "data=0A> security" only pick up the free speed of RAID10. = =A0Change=0A> when you get to 6 or more drives, if necessary.=0A> >=0A> > F= or data security, I can't answer for the UFS2 vs.=0A> ZFS. =A0For hardware = setup, let me amend everything I said=0A> above with the following:=0A> >= =0A> > Since you are seriously focusing on data integrity,=0A> ignore every= thing I said but make sure you have good=0A> backups! =A0:)=0A> >=0A> > Sor= ry,=0A> > -Rich=0A> =0A> No problem :) I've been doing some reading since I= posted=0A> this=0A> question and it turns out that the controller will act= ually=0A> not allow=0A> me to create a RAID6 array using only 4 drives. 3wa= re=0A> followed the=0A> same reasoning as you; with 4 drives use RAID10.=0A= > =0A> I know that you can migrate from one to the other when a=0A> 5th dis= k is=0A> added, but RAID10 can only handle 2 failed drives if they=0A> are = from=0A> separate RAID1 groups. In this way, it is just slightly=0A> less r= esilient=0A> to failure than RAID6. With this new information, I think I=0A= > may as=0A> well get one more 2TB drive and start with 6TB of RAID6=0A> sp= ace. This=0A> will be less of a headache later on.=0A> =0A> - Max=0A=0AJust= as a question: how ARE you planning on backing this beast up? While I don= 't want to sound like a worry-wort, I have had odd things happen at the wor= st of times. RAID cards fail, power supplies let out the magic smoke, user= s delete items they really want back... *sigh*=0A=0AA bit of reading shows = that ZFS, if it's stable enough, has some really great features that would = be nice on such a large pile o' drives. =0A=0ASee http://wiki.freebsd.org/= ZFSQuickStartGuide=0A=0AI guess the last question I'll ask (as any more may= uncover my ignorance) is if you need to use hardware RAID at all? It seem= s both UFS2 and ZFS can do software RAID which seems to be quite reasonable= with respect to performance and in many ways seems to be more robust since= it is a bit more portable (no specialized hardware).=0A=0AThere are others= who may respond with better information on that front. I've been a strong= proponent of hardware RAID, but have recently begun to realize many of the= reasons for that are only of limited validity now.=0A=0A-Rich=0A=0A=0A =
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?937260.17107.qm>