Data Storage Capacity Mostly Wasted In Data Center 165
Posted
by
CmdrTaco
from the and-they-never-turn-the-lights-off dept.
from the and-they-never-turn-the-lights-off dept.
Lucas123 writes "Even after the introduction of technologies such as thin provisioning, capacity reclamation and storage monitoring and reporting software, 60% to 70% of data capacity remains unused in data centers due to over provisioning for applications and misconfiguring data storage systems. While the price of storage resource management software can be high, the cost of wasted storage is even higher with 100TB equalling $1 million when human resources, floor space, and electricity is figured in. 'It's a bit of a paradox. Users don't seem to be willing to spend the money to see what they have,' said Andrew Reichman, an analyst at Forrester Research."
Intentional? (Score:5, Insightful)
I don't know about your data center, but ours keeps drives well below full capacity intentionally.
The more disk arms you spread the operations over, the faster the operations get, and smaller drives are often more expensive than larger ones.
Plus, drives that are running close to full can't manage fragmentation nearly as well.
100TB = $1 million (Score:2, Insightful)
I didn't know that I've got $25000 dollars worth of storage at home :-)
Let's play the odds: (Score:5, Insightful)
Likelihood that I get fired because I buy a few hundred gigs too much, that sit in a dusty corner somewhere, barely even noticed except in passing because there is nobody with a clear handle on the overall picture(and, if there his, he is looking at things from the sort of bird's eye view where a few hundred gigs looks like a speck on the map): Relatively insignificant...
Slashvertisement (Score:5, Insightful)
for a storage monitoring system.
Re:Overprovisioning (Score:5, Insightful)
Re:Let's play the odds: (Score:4, Insightful)
Exactly, and that's the way it should be. Your CTO wants you to suggest spending a few extra hundreds of dollars on storage to avoid downtime.
Re:Intentional? (Score:5, Insightful)
You also have to think of the obvious spare capacity. In 2005, my company invested in a huge (at the time) 10TB array. The boss rightfully freaked out when we were hitting more than 30% usage in 2007. After having a slow, quasi-linear growth of files for the previous couple of years, the usage jumped to 50% in a matter of months. It ended up that our CAD users switched to a newer version of the software without our knowledge (CAD group managed their own software) and didn't tell us. The unexpected *DOES* happen, and it would have been incredibly stupid to have been running closer to capacity.
Accounting would have probably had half of us fired if they hadn't been able to do their document imaging which tends to take up a lot of space on the SAN.
Yet another sad FUD or FUD-esque article based on Forrester's findings.
Re:Overprovisioning (Score:3, Insightful)
Dad here. Had that fight (or similar). I asked a simple question to the kid who wanted it all. I asked him "all or nothing?" and again he said "all", to which I said "nothing".
Of course he rightly cried "Not Fair!!!", and I said, you set the rules, you wanted it all, setting the rule up that you didn't want to be fair, I'm just playing by your rules.
Never had that problem again. EVER.
Re:Mod parent up (Score:2, Insightful)
Interesting. Was the culprit all cad files out of the new rev?
Yes, for the most part. Because of a bad config, they were going from drawings around 1-10MB to drawings over 100MB. That's what happens when you get management to take the IT department out of the software management and configuration equation. We were, of course, still left to sweep up the pieces.
Re:Intentional? (Score:5, Insightful)
ISPs & hosting services (Score:3, Insightful)
This isn't like an ISP overbooking a line and hoping that everyone doesn't decide to download a movie at the same time. If a hosting service says your account can have 10GB of storage, contractually they need to make sure 10GB of storage exists.
Even though most accounts don't need it.
One client of mine dramatically over-provisioned his database server. But then again, he expects at some point to break past his current customer plateau and hit the big time. Will he do so? Who can say?
It may be a bit wasteful to over-provision a server, but I can guarantee you that continually ripping out "just big enough" servers and installing larger ones is even more wasteful.
Your pick.
Re:Intentional? (Score:5, Insightful)
FTA:
Rick Clark, CEO of Aptare Inc., said most companies can reclaim large chunks of data center storage capacity because it was never used by applications in the first place. . . . Aptare's latest version of reporting software, StorageConsole 8, costs about $30,000 to $40,000 for small companies, $75,000 to $80,000 for midsize firms, and just over $250,000 for large enterprises.
In other words, the whole thing is an attempt to get companies to spend tens of thousands of dollars for something that could be done by well-written shell script.
Do the math (Score:1, Insightful)
70% used space with the 100TB mentioned in the article, leaving us with 70TB.
Think of how much porn 70TB is!
Re:Overprovisioning (Score:2, Insightful)
There's a reason his mom killed herself. Would you want to be known as the one who gave birth to that festering, pustule of fat?
Re:Overprovisioning (Score:2, Insightful)
Nope, he wasn't screwed, because it wasn't the only option; it was a false dichotomy. I gave him a chance to offer another choice, it was just veiled. Kobioshi Maru. He could have thought about it and said "half" even though that wasn't an obvious choice.
I often give my kids tests to break them out of self imposed boxes (false dichotomy). Pick a number between 1 and 10 .... 1 - no, 2 - no, 3 - no, 4 - no .... 9 - no, 10 no ... THAT IMPOSSIBLE DAD!!.
No it isn't. The number I had in mind was Pi.
Raising kids to think for themselves, and outside the "boxes" society tends to put on things makes them able to deal better with things that don't appear to make sense.
You can dumb down your kids by not challenging them, or you can challenge them every step of the way, in ways that force them to learn more than they know.
Re:Let's play the odds: (Score:3, Insightful)
Of course this is the case. This study is as exciting as news that George Michael is gay. There have been plenty of studies to this effect. My company makes tons of money consulting on better storage utilization. [Some Fortune 500 companies I've visited run below 40% utilization.] EMC, IBM, HDS, NetApp and the rest have no real interest in selling you less drives. They all make vague, glossy statements about saving storage money but in reality you need to be wasteful if you want to protect your ass. Think of the things we spend $ on just to get another 9 on the uptime digits: UPS, generators, clustering, DR systems/networks that sit idle, dark fibre between datacenters, RAID 1(+0), RAID 6, tapes, VTLs, Storage Arrays, redundant Fibre Channel SANs, . . .
From a human perspective, fuzzyfungus is right. Over-engineering is less likely to cost your job than failure. Plus, over-engineering is easy to justify.
Some things are just known to cost money if you MUST ensure that business is not subject to fallibility in hw and sw. The fact that there are 50 TBs unused out of your 200 TB of usable storage really might not mean too much. [Some of the numbers quoted could point to the mirrored side of RAID 1 stripes as wasted. It's a cheap gimmick to make the numbers look worse but still true to a certain extent if the performance difference between R5 and R1 is not needed.] Of course, there are usually low hanging fruit that can be attacked to save real money and prevent cascading costs on the other cost centers mentioned above but there will always be waste. It's the cost of five 9's.
Re:Intentional? (Score:3, Insightful)
When I see services advertised at those kinds of rates I can't help but remember P.T. Barnum's slogan: "There's a sucker born every minute."
Re:Intentional? (Score:5, Insightful)
Not to mention the fact that over the last few years drive capacities have skyrocketed while drive performance has remained the same. That is, your average drive / spindle has grown from 36 GB to 72 GB to 146 GB to 300 GB to 400 GB to 600 GB, etc. while delivering a non-growing 150 IOPS per spindle.
If you have an application that has particular data accessibility requirements, you end up buying IOPS and not capacity. A recent deployment was for a database that needed 5000 IOPS with services times to remain less than 10 ms. The database is two terabytes. A simple capacity analysis would call for a handful of drives, perhaps sixteen 300 GB drives mirrored for a usable capacity of 2.4 TB. Unfortunately those sixteen drives will only be able to deliver around 800 IOPS at 10 ms per. Instead we had to configure one hundred and thirty 300 GB drives, ending up with over 21 TB of storage capacity that is about ten percent utilized.
These days anytime an analyst or storage vendor starts talking to me about thin provisioning, zero page reclaim, etc. I have to take a minute and explain to them my actual needs and that they have very little to do with gigabytes or terabytes. Usually I have to do this multiple times.
In the near future we will be moving to SSD based storage once more enterprise vendors have worked through the quirks and gained some experience.
Re:Intentional? (Score:0, Insightful)
If your CxOs were hoodwinked by some con-slutant into buying super expensive storage "solutions" (and stuff like "blades"), then you'd probably also "need" expensive stuff like this to figure out how to allocate or reallocate the _overpriced_ space.
But if you got cheaper storage in the first place, it's better to just buy more storage if you run low on space than to spend lots of money on "solutions looking for problems".
Google, ebay, yahoo etc don't use such stuff. I doubt most companies should either.
Re:Let's play the odds: (Score:4, Insightful)
Re:Intentional? (Score:3, Insightful)
IO'/second count matters, too (Score:5, Insightful)
There are two numbers that matter for storage systems. One is the raw number of gigabytes that can be stored. The other is the number of IO's that can be performed in a second. The first limits the size of the collected data. The second limits how many new transactions can be processed per time period. That, in turn, determines how many pennies we can accept from our customers during a busy hour.
We size our systems to hit performance targets that are set in terms of transactions per second, not just gigabytes. Using round numbers, if a disk model can do 1000 IO/second, and we need 10,000 IO/second for a particular table, then we need at least 10 disks for that table (not counting mirrors). We often use the smallest disks we can buy, because we don't need the extra gigs. If the data volume doesn't ever fill up the gigabyte capacity of the disks, that's ok. Whenever the system uses all of the available IO's-per-second, we think about adding more disks.
Occasionally a new SA doesn't understand this, sees a bunch of "empty" space in a subsystem, and configures something to use that space. When that happens, we then have to scramble, as the problem is not usually discovered until the next busy day.
Re:100 TB for $1,000,000? No way! (Score:3, Insightful)
I'm not sure if you're trolling or not, but if you're serious did you happen to manage the storage for Microsoft's Sidekick servers?
A couple things wrong with your assumptions:
1) 1TB drives might be great for storing your goat porn collection, but on a server with actual load, how many of those drives do you need to get adequate IOPS? Also exactly 100 of them means no RAID, but that's OK because drives from Newegg never fail so your 100TB of data should be fine.
2) You seem to have left controllers out of your list. Anyone who's ever had a RAID controller start barfing garbage all over a LUN, or take out a second drive after a drive failure will tell you the controller is the really critical bit (and is usually a single point of failure in systems with DAS.)
3) Where's your backup hardware? Where's space for snapshots? Where's space for replication?
4) Ever time a RAID5 rebuild on say a 9 drive LUN with 1TB SATA disks?
Storage is expensive because the data on it has value and making sure that data is available and isn't lost or corrupted costs money. Cheap storage solutions don't end up that way when the drives have to go to OnTrack for recovery and the company's down for a week, or valuable data is lost.
Re:Overprovisioning (Score:3, Insightful)
At that point he was screwed. If he said "nothing", he could reasonably expect to get nothing. His only option was to say "all" if he wanted to get a chance at something.
If my son (nobly or stubbornly) said "nothing", I'd offer him half or nothing. Parents are allowed to alter the deals. Pray that they alter them further.
Re:Overprovisioning (Score:1, Insightful)
Oh my mom was much more devious.
She would let one of us cut the pie, and the other pick the first piece....
That's not devious - all moms with even a lick of sense do it that way.
Re:100 TB for $1,000,000? No way! (Score:4, Insightful)
Suddenly, that $1 million isn't so far fetched, eh?
Re:Overprovisioning (Score:2, Insightful)
Re:100 TB for $1,000,000? No way! (Score:3, Insightful)
Man hours more expensive than hardware. (Score:3, Insightful)
We do use thin provisioning, and virtualization in general, but I agree that there is benefit to keeping utilization low. We try to keep more space than we could possibly need both because it can sometimes surprise you by growing quickly and because the drives are faster if the data is spread across multiple drives. Also SSD drives sometimes live longer if not fully utilized, because they can distribute the wear and tear, so we usually leave 20% unformatted.
Downtime and slow systems are much more expensive than wasted drive space.
Re:Overprovisioning (Score:1, Insightful)
Not exactly. All parties can have "nothing", but only one party can have "all". Therefore, those who say "nothing" do so in the interest of fairness, and that fairness is rewarded. Assuming that the kid is old enough to understand this, it can be a great lesson.
Captcha: maturely