Hitachi Deskstar 7K1000: Two Terabyte RAID Redux
by Gary Key on April 23, 2007 12:00 PM EST- Posted in
- Storage
Final Thoughts
Equipped with a new test bed that should remove the vast majority of CPU and GPU bound situations we noticed further improvements in our quasi-synthetic PCMark05 tests. We measured an improvement of 43% in the final PCMark05 score with RAID 0 compared to a 25% improvement in our previous test bed. While we expected the File Write and Anti-Virus tests to improve significantly, we were slightly surprised with the General Usage scores that were up to 28% better. However, the Application loading score was still in the 5% range with the Raptors but the Hitachi 7K1000 showed almost zero differences. The most surprising result was the fact that the Deskstar 7K1000 scored 3%~5% better than the Raptors on the Intel platform.
In our last article the only meaningful application performance improvement with RAID 0 came in the Nero Recode tests where the improved write performance reduced our encoding process by about 5%. Now that we have basically removed the CPU from being a factor in these tests, we see a 30% difference with RAID 0 during encoding, a 21% difference in file extraction, and a 45% difference when doing file copy or move operations on the RAID volume.
All of those results sound very impressive but in the balance of our application and game tests we only noticed a 2%~3% performance difference between RAID 0 and single drive configurations. Unless you extract files, copy or move them on the same drive, and encode all day long then the benefits of RAID 0 on the typical consumer desktop is not worth the price of admission. What is the price? In this case, $399 for a second 7K1000, a halving of the mean time between failure rates on each drive, a data backup nightmare, and increases in noise, thermals, and power consumption.
We really wanted to provide additional benchmarks for this article as we had developed and tested benchmarks for Photoshop CS3, AutoCAD 2008, Oblivion, S.T.A.L.K.E.R., and multi-tasking scenarios with BiTorrent clients but there was an issue during testing. We had a Western Digital WD1500 meet its maker during testing. The drive literally smoked its platters. Of course we lost the entire test image and a significant amount of test time. However, those are the perils of pushing hardware on a continuous basis. The fact that it happened during RAID 0 testing made it difficult to accept but it just as easily could have happened in single drive testing resulting in the same loss of data. A data loss that would not have occurred if we had been using RAID 1, 5, or 10.
RAID 0 can provide some impressive performance results in synthetic benchmarks and certain applications that are write speed starved as we have shown. In fact, with the new test bed the test results where RAID 0 shines are even more impressive now. However, we still do not think RAID 0 is worth the trouble or cost for the average desktop user or gamer, especially with the software RAID capabilities included on most motherboards. If you must run RAID on the desktop, then we highly recommend the use of RAID 1, 5, or 10 (0+1) in order to protect your data and probably a hardware controller if you can afford one. We are going to delve into the world of RAID in the coming weeks with additional tests, system configurations, and hardware controllers. At this time we still do not recommend RAID 0 for most desktop users due to the lack of widespread performance improvements and potential data integrity concerns with it.
Equipped with a new test bed that should remove the vast majority of CPU and GPU bound situations we noticed further improvements in our quasi-synthetic PCMark05 tests. We measured an improvement of 43% in the final PCMark05 score with RAID 0 compared to a 25% improvement in our previous test bed. While we expected the File Write and Anti-Virus tests to improve significantly, we were slightly surprised with the General Usage scores that were up to 28% better. However, the Application loading score was still in the 5% range with the Raptors but the Hitachi 7K1000 showed almost zero differences. The most surprising result was the fact that the Deskstar 7K1000 scored 3%~5% better than the Raptors on the Intel platform.
In our last article the only meaningful application performance improvement with RAID 0 came in the Nero Recode tests where the improved write performance reduced our encoding process by about 5%. Now that we have basically removed the CPU from being a factor in these tests, we see a 30% difference with RAID 0 during encoding, a 21% difference in file extraction, and a 45% difference when doing file copy or move operations on the RAID volume.
All of those results sound very impressive but in the balance of our application and game tests we only noticed a 2%~3% performance difference between RAID 0 and single drive configurations. Unless you extract files, copy or move them on the same drive, and encode all day long then the benefits of RAID 0 on the typical consumer desktop is not worth the price of admission. What is the price? In this case, $399 for a second 7K1000, a halving of the mean time between failure rates on each drive, a data backup nightmare, and increases in noise, thermals, and power consumption.
We really wanted to provide additional benchmarks for this article as we had developed and tested benchmarks for Photoshop CS3, AutoCAD 2008, Oblivion, S.T.A.L.K.E.R., and multi-tasking scenarios with BiTorrent clients but there was an issue during testing. We had a Western Digital WD1500 meet its maker during testing. The drive literally smoked its platters. Of course we lost the entire test image and a significant amount of test time. However, those are the perils of pushing hardware on a continuous basis. The fact that it happened during RAID 0 testing made it difficult to accept but it just as easily could have happened in single drive testing resulting in the same loss of data. A data loss that would not have occurred if we had been using RAID 1, 5, or 10.
RAID 0 can provide some impressive performance results in synthetic benchmarks and certain applications that are write speed starved as we have shown. In fact, with the new test bed the test results where RAID 0 shines are even more impressive now. However, we still do not think RAID 0 is worth the trouble or cost for the average desktop user or gamer, especially with the software RAID capabilities included on most motherboards. If you must run RAID on the desktop, then we highly recommend the use of RAID 1, 5, or 10 (0+1) in order to protect your data and probably a hardware controller if you can afford one. We are going to delve into the world of RAID in the coming weeks with additional tests, system configurations, and hardware controllers. At this time we still do not recommend RAID 0 for most desktop users due to the lack of widespread performance improvements and potential data integrity concerns with it.
Facebook
Twitter
RSS
26 Comments
View All Comments
Abki - Friday, May 22, 2009 - link
RAID 0 only give faster transafer rate of data from/to disk.It dosent give anything else faster even if you want it. If time for get or put data to disk dosent matter you have to buy a cheaper disk instead. Why weaste money on raptor or Deskstar.
About raid 1, it isnt so good and safe. Accidents has happen with 2 disk system, 1 get failure and raid system transfer same fault to the other disk. In the end its no data on any disk that is usuable. The only tru safe is to have a backup of all data. Sould be taken at least every day. That is what the second disc should be used for and not RAD 1.
Axbattler - Tuesday, April 24, 2007 - link
I do believe that the main cost of stripping is the risk of failure. For everything though, you get what you pay for: the second drive, and the space associated with having a second drive. It is no harder to backup 2TB in RAID-0 than 2TB of individual drives, if you are going to have that much data, then it is an issue you are going to face anyway. So to me, it comes down to trading off risk of failure, and selected performance gains. I happen to think it is not worth it but I do think it is a matter of opinion (more of a 'to each their own' type of thing).michal1980 - Monday, April 23, 2007 - link
any one? I know its an extra drive. but you get some data protection, and some performance benefit, and you do not loss 50% of the drive space.but I heard bad things about on-board raid 5.
strikeback03 - Tuesday, April 24, 2007 - link
I don't believe you lose any drive space in RAID 0, as there is no data redundancy.yyrkoon - Tuesday, April 24, 2007 - link
The bad things you've heard concerning onboard RAID5 was probably performance related, which would most likely be true, since most onboard RAID would not have a good XOR 'engine', unless perhaps some of the server classed boards have them.As for Matrix RAID, I personally am a bit sceptical, from my limited understanding of it, it basically gives you the ability to do a RAID 0+1 array on two drives. Someone correct me if I am wrong.
tshen83 - Monday, April 23, 2007 - link
I thought last time I already criticized that reviewing the 1TB drive with RAID 0 performance is missing the point, yet you come up with a redux part on the same drive. First of all, I don't care how much Hitachi is paying YOU or AT to pimp this drive(obviously they paid the wrong guy). If you don't understand that comparing a 1TB drive against the raptors are STUPID, you should get your head checked. One is targetted at the MASS STORAGE people(you know, I should spell it out for you, the guys who want 4TB +) and the raptor is targetted at the people as a PERFORMANCE OS boot drive. COMPARING THOSE TWO DRIVES ARE STUPID!now, if you really need a triple redux on this stupid drive, you should cover power usage, noise, heat, and basically constantly read/write to the 1TB drive to see how long the deathstar will last.
sdsdv10 - Tuesday, April 24, 2007 - link
The title says it all...Sunrise089 - Monday, April 23, 2007 - link
Personal Attack: CheckTotally unsupported claim of bias: Check
Misunderstanding of market segments: Check
Use of ALL CAPS: Check
Improper understanding of "are/is": Check
Comment that makes you look like an ass: Check
tshen83 - Wednesday, April 25, 2007 - link
I will be honest:you are right about those: Personal Attach: Check and Use of ALL CAPS: Check
you are wrong about the following:
totally unsupported claim of bias? about what? about Hitachi drives being deathstars? Did you read that Hitachi bought the IBM deathstar hard drive business?
Improper understanding of "are/is"...ok...typo..so what? Try typing the whole message in 20 seconds.....you is stupid :)
comment that makes me look like an ass? So do you consider all criticisms make people look like ass?
Misunderstanding of Market Segment: Really? Is it me who misunderstood? The whole point I made is that Anandtech shouldn't review the 1TB drive against the raptors because the difference in market segment. 1TB isn't about performance. It's about mass storage. Mass storage drives needs different measurements: reliability(MTBF), RAID 1/5/6 performance, heat, noise, power consumption. OS performance drives(raptors) need those benchmarks: IO, Seek, Sustained write/read, etc. you get the point. Firmwares are tweaked differently for those two opposing sides.
I agree with the poster below you, Don't read the review: Check! To be honest, Anandtech hasn't come out with anything good for a while.(except that AppleTV review)
yyrkoon - Tuesday, April 24, 2007 - link
LMAOYou forget one thing on your check list.
Dont read the article ? CHECK !!!