RE: 306GB drives!
From: Tom Linden (tom_at_kednos.com)
Date: 08/17/03
- Next message: Main, Kerry: "RE: 306GB drives!"
- Previous message: Larry Kilgallen: "Re: Priviliged Library Vector flags - PLV$M_WAIT_CALLERS_MODE"
- Maybe in reply to: Mike Naime: "306GB drives!"
- Next in thread: Rob Young: "RE: 306GB drives!"
- Reply: Rob Young: "RE: 306GB drives!"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Date: Sun, 17 Aug 2003 06:51:42 -0700
>-----Original Message-----
>From: Mike Naime [mailto:mnaime@kc.rr.com]
>Sent: Saturday, August 16, 2003 9:49 PM
>To: Info-VAX@Mvb.Saic.Com
>Subject: Re: 306GB drives!
>
>
>
>Rob Young <young_r@encompasserve.org> wrote in message
>news:zYVV3vv$GJP9@eisner.encompasserve.org...
>> In article <_Nu%a.93731$o27.2153066@twister.rdc-kc.rr.com>, "Mike Naime"
><mnaime@kc.rr.com> writes:
>> >
>> > Rob Young <young_r@encompasserve.org> wrote in message
>> > news:Xrz7BErQmnjo@eisner.encompasserve.org...
>> >> In article <%lj%a.93485$o27.2125405@twister.rdc-kc.rr.com>, "Mike
>Naime"
>> > <mnaime@kc.rr.com> writes:
>> >
>> >> But you certainly could do a cheaper solution for backups
>> >> (if new) since you have existing infrastructure it makes
>> >> a lot of sense for you to pop in bigger drives.
>> >>
>> >
>> > Cheaper, yes. No argument there. But cheaper usually is inversely
>> > proportional to faster! After a test restore from tape. (The cheaper
>> > solution) Upper management let my director buy more storage
>for online
>> > backups. Restoring from tape is a 3rd or 4th option.
>> >
>>
>> I wasn't talking about tape. A cheaper disk based way would
>> be to use ATA. For instance, Nexsan ATA is about 1.7 cents/MByte.
>> You can get adventurous and get cheaper than that. But at 1.7
>> cents that is $2 or so a GByte, you won't be buying HSG drives
>> that cheap any time soon.
>>
>> http://www.fusiondm.net/pages/ataboy.htm
72GB scsi sca drives are avaialble for about $235 which works out to about
0.3 cents/Mbyte and to this you must add the cost of the cabinetry and
cabling, so say a total of 0.4 cents
The doubling time for capacity by my reckoning is less than two years
I bought the first 8" 80MByte drives from Fujitsu in 1982 which means
12 generations in 21 years. A full length movie is about 1.5 to 2.5 GBytes
so I think you are right about the future usages.
>>
>
>How does it play with VMS??? Do you have one to comment on?
>
>>
>>
>>
>> I'm pretty sure this is something that won't extend out. We will
>> see a flattening in drive sizes in a bit. After that, surely
>> we cutover to some of this Oak Ridge technology:
>
>>
>> http://www.acq.osd.mil/bmdo/bmdolink/pdf/roo.pdf
>>
>> Oak Ridge National Laboratory (Oak Ridge, TN)
>>
>> A new technique developed at Oak Ridge National Laboratory offers an
>answer to
>> the demand for increased storage density. Surface-enhanced Raman optical
>data
>> storage is based on a technology that detects the optical signature of
>> laser-excited molecules. This data storage method involves the alteration
>of
>> molecules that are embedded in a polymeric or silver- colored disk. A
>laser
>> is used to "write" information on a disk, on which the optically altered
>> molecules and unaltered molecules serve as "bits." The normally
>weak Raman
>> signature of each molecule is amplified or enhanced by the substrate of
>the
>> storage disk, such that the signature can be read by a signal detector.
>>
>> Or something simalarly whizbangy.
>>
>> You see a flattening today - even if only in home PC markets.
>> In the future it may make little or no sense to get super large
>> sizes as even with partitioning you end up with catastrophic
>> effects if you blow out a RAIDset and other issues that I'm sure
>> folks have in mind.
>
>I remember when I got my first 40MEG drive, one of the guys at work told me
>"You will never fill that up!" :-)
>
>I'm not real sure about a leveling off. As the drives get bigger, and tech
>gets faster, we put more and more on disk. Save that high quality home
>video directly on disk? Or other online storage. I'm sure that we will
>start seeing the raid technology more prevalent in the home market fairly
>soon. I have a couple of friends that already have it in their home
>systems, but they are not your average "Home" user.
>
>I see this as opening the market for online movie ordering...Etc. As the
>broadband pipes get bigger...and storage gets larger, faster, and
>cheaper... people use it up. Look at the new "VCR's" that use a
>hard drive
>to record that TV show that you want to watch later.... Look at the amount
>of people that now take broadband for granted. Who want's dial
>up anymore?
>Tapes get faster, storage gets faster..... Who's to say that you cannot
>restore a 1TB "disk" in an hour 5-10 years from now. I see the conceptual
>idea behind the EVA expanding further. You have some sort of modular
>storage media that plugs into a storage controller that manages it for you.
>Individual storage media failures are minimized.
>
>> >
>> >>
>>
>> I think the PRIMARY purpose of a cluster is for availability. You lose
>> a member , you replace it. You can replace it in an hour or
>> so - great. I'm content to replace a member within a day. Going
>> forward I would like to add a member and go to next day on service.
>> If they had a "next week" service option, I'd take that too ;-).
>>
>
>It sounds like you are not being penalized for downtime, or that it really
>doesn't cost you anything when your systems are down. It also sounds like
>the APP and mailserver that you support is radically different from what I
>am doing. If you have the luxury of a day/week to replace something.
>Great!
>We use the cluster to distribute processing, and also for shared
>media. An
>AIX 2-node system needs twice the amount of storage spindles that the VMS
>system does because they CANNOT share the same storage space at the same
>time. Ditto for the W2K "Cluster"
>
>Do you have any uptime SLA's that you have to meet?
>
>> >> Nah. You have two or more EVAs and shadow across datacenters. That
>> >> way when your datacenter loses power you keep going.
>> >
>
>One thing that I missed here before. Why SHOULD my data center
>loose power?
>With PDU's, battery backup, and a generator that will lasts for a couple of
>days. No reason to take this as a given. IF everything works as
>advertised. (And so far it has) our power system reports/records power
>problems/outages, but does not go down. I lost power at home for 3 days,
>but our data center never lost power.
>
>> > Yes, but my point is that it would not be possible without the EVA.
>> > EVA's in 2 data centers does not necessarily need to be made redundant
>by
>> > host based shadowing.
>>
>> With VMS - sure. VMS doesn't support DRM 2 and/or DRM 2 isn't
>> here yet. To make it more generic - have 2 separate storage
>> "boxes" in 2 separate data centers. Now you use HBVS across
>> datacenters.
>>
>
>You lost me on that one. HBVS? Do you mean Host Based Volume Shadowing?
>
>Just out of curiousity, How much data are you talking about transfering
>between data centers?
>You probably could get away with just having a T-3 pipe between data
>centers.
>
>
>> > The solution is preferred if I can take the OS out of the picture.
>> > Otherwise, I will have 150+ systems trying to write to the far end.
>>
>> The far end doesn't have to be that far away. I'm not speaking
>> of DR but fault tolerant.
>>
>
>I have to consider both at the same time.
>
>> >>
>
>> Mail is the key. Mail proliferates like rabbits. Unfortunately,
>> it is mostly flat files on disk. Files that are old and make
>> little sense to back up over and over again. Unfortunately, scattered
>> on many tapes so restores are long. However, mail is very distributed
>> and a small subset are impacted if a server is down. This isn't
>> everybody in the world. Sure, consolidate your tapes OR go to
>> large ATA storage pool for D2D.
>>
>
>Fortunately I do not mess with mail. That would actually be a smaller
>problem. :-)
>
>> >>
>>
>> You mean [older] DLT is too slow? Surely you didn't have 2 or 3
>> LTO tape drives actively doing the restore? We typically get
>> 20 MByte/sec to/from LTO. With 40 MByte/sec on restore - that's
>> 140 GByte/hour. That isn't VMS - but VMS plays well with
>> 3rd party Enterprise Backup solutions and will natively work
>> with LTO 2 (faster yet) or so recent discussions have mentioned.
>
>Yes, (S)DLT is too slow. Also, you possibly need to re-configure storage
>(Drive normalization) and SAN zoning prior to starting the restore.
>
>>
>> What is your restore speed criteria? Surely met by LTO (assumption
>> you would have 2 streaming your restores).
>
>That, I am not really sure about. Or director and higher gets into those
>discussions. I'm too busy with my duties to really get into the nuts and
>bolts details of backups. We actually have a full time person that just
>works on backups. They are in the midst of re-defining the
>standard for the
>tape media that we use.
>
>Mike
>
>
>---
>Incoming mail is certified Virus Free.
>Checked by AVG anti-virus system (http://www.grisoft.com).
>Version: 6.0.506 / Virus Database: 303 - Release Date: 8/1/2003
>
--- Outgoing mail is certified Virus Free. Checked by AVG anti-virus system (http://www.grisoft.com). Version: 6.0.506 / Virus Database: 303 - Release Date: 8/1/2003
- Next message: Main, Kerry: "RE: 306GB drives!"
- Previous message: Larry Kilgallen: "Re: Priviliged Library Vector flags - PLV$M_WAIT_CALLERS_MODE"
- Maybe in reply to: Mike Naime: "306GB drives!"
- Next in thread: Rob Young: "RE: 306GB drives!"
- Reply: Rob Young: "RE: 306GB drives!"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Relevant Pages
|
