Hitachi Deskstar 7K1000 in RAID 0: Is Two Terabytes really better than One?
by Gary Key on April 19, 2007 12:15 AM EST- Posted in
- Storage
iPeak Video/Audio Tests
The iPeak based Video/Audio benchmarks are designed around simulating media encoding and HTPC activities. These are basic benchmarks at this time but this section will be expanded once we start testing under Vista. Our change to a better performing dual core processor will assist us in maintaining a balance between the CPU and Storage systems during the trace file creation and benchmarking processes. These benchmarks are CPU intensive in nature but also require a balanced storage system with the ability at times to handle read and write requests simultaneously in a very efficient manner.
The AnyDVD benchmark is heavily weighted to write requests. The results show a common pattern in write intensive situations with the RAID 0 setups improving about 66% over their single drive counterparts. The 7K1000 scores particularly well in these write intensive benchmarks due to its areal density and large cache design.
The Nero Recode 2 benchmark is weighted to streaming read requests at the start of the test but is balanced by continuous write operations during the encoding process. This benchmark is one of the most demanding ones in our test suite with the disk being active the entire trace file with several 100% utilization peaks. The results show an almost 93% improvement in hard disk performance with RAID 0. We believe this is one of the few tests where RAID 0 on the desktop will make an actual difference in real-world performance.
The individual drive results surprised us as we expected the Hitachi with its 32 MB cache and high sustained transfer rates to score near the Raptors. However, it turns out after reviewing the trace file results it was obvious that the 7K1000 was hampered by its inability to process large data blocks in sequential order efficiently as it had a number of buffer overruns during the read portion of the tests. This indicates to us the drive firmware is probably tuned for non-sequential read/writes as the rest of our tests indicate. The 32 MB cache should have easily compensated for any potential large block issues in this test.
iPeak Game Installation Tests
Our iPeak based Game Installation benchmarks simply show the ability of the hard drive to write data as quickly as possible to the disc based upon the installation software instructions. As detailed in our iPeak setup description we installed the games from our source drive in order to eliminate the optical drive bottleneck. In separate application timing we witnessed basically the same percentage spread when installing the games via our DVD drive so these results are representative of actual installation performance.
The Raptors once again finish at or near the top in our gaming tests due to their rotational and random access speeds. Our 7K1000 drive finishes ahead of the other 7200rpm drives with a great deal of benefit going to the 32 MB cache and high sustained transfer rates. In the RAID 0 results we see the Raptor scores improving 38% in The Sims2 and 55% in BF2. The 7K1000 benefits greatly from RAID 0 in these tests with improvements of 50% in The Sims2 and 90% in BF2 with the Raptors once again showing their strength in gaming.
We need to remember these tests reflect pure hard drive performance and will be mitigated by the overall system platform as we will see in our application tests. These tests are basically designed around continual read/write requests that favor large cache sizes, properly tuned firmware, and high sustained transfer rates.
iPeak Game Play Tests
The iPeak based Game Play tests are centered on the benefits of having a hard disk that can load non-linear or sequential data files quickly without interrupting the flow of the game.
In game play the RAID 0 setups hold a 7% to 12% advantage in these benchmarks. We noticed in the trace files that performance improved only when the game levels changed. The best overall gaming performance with a SATA drive is still provided by the Raptors. However, considering the space, noise levels, and cost per GB advantages of the Hitachi drive, we are willing to change our recommendation for most users (though plenty will feel 1TB is too big and would rather go with a 500GB model).
The iPeak based Video/Audio benchmarks are designed around simulating media encoding and HTPC activities. These are basic benchmarks at this time but this section will be expanded once we start testing under Vista. Our change to a better performing dual core processor will assist us in maintaining a balance between the CPU and Storage systems during the trace file creation and benchmarking processes. These benchmarks are CPU intensive in nature but also require a balanced storage system with the ability at times to handle read and write requests simultaneously in a very efficient manner.
The AnyDVD benchmark is heavily weighted to write requests. The results show a common pattern in write intensive situations with the RAID 0 setups improving about 66% over their single drive counterparts. The 7K1000 scores particularly well in these write intensive benchmarks due to its areal density and large cache design.
The Nero Recode 2 benchmark is weighted to streaming read requests at the start of the test but is balanced by continuous write operations during the encoding process. This benchmark is one of the most demanding ones in our test suite with the disk being active the entire trace file with several 100% utilization peaks. The results show an almost 93% improvement in hard disk performance with RAID 0. We believe this is one of the few tests where RAID 0 on the desktop will make an actual difference in real-world performance.
The individual drive results surprised us as we expected the Hitachi with its 32 MB cache and high sustained transfer rates to score near the Raptors. However, it turns out after reviewing the trace file results it was obvious that the 7K1000 was hampered by its inability to process large data blocks in sequential order efficiently as it had a number of buffer overruns during the read portion of the tests. This indicates to us the drive firmware is probably tuned for non-sequential read/writes as the rest of our tests indicate. The 32 MB cache should have easily compensated for any potential large block issues in this test.
iPeak Game Installation Tests
Our iPeak based Game Installation benchmarks simply show the ability of the hard drive to write data as quickly as possible to the disc based upon the installation software instructions. As detailed in our iPeak setup description we installed the games from our source drive in order to eliminate the optical drive bottleneck. In separate application timing we witnessed basically the same percentage spread when installing the games via our DVD drive so these results are representative of actual installation performance.
The Raptors once again finish at or near the top in our gaming tests due to their rotational and random access speeds. Our 7K1000 drive finishes ahead of the other 7200rpm drives with a great deal of benefit going to the 32 MB cache and high sustained transfer rates. In the RAID 0 results we see the Raptor scores improving 38% in The Sims2 and 55% in BF2. The 7K1000 benefits greatly from RAID 0 in these tests with improvements of 50% in The Sims2 and 90% in BF2 with the Raptors once again showing their strength in gaming.
We need to remember these tests reflect pure hard drive performance and will be mitigated by the overall system platform as we will see in our application tests. These tests are basically designed around continual read/write requests that favor large cache sizes, properly tuned firmware, and high sustained transfer rates.
iPeak Game Play Tests
The iPeak based Game Play tests are centered on the benefits of having a hard disk that can load non-linear or sequential data files quickly without interrupting the flow of the game.
In game play the RAID 0 setups hold a 7% to 12% advantage in these benchmarks. We noticed in the trace files that performance improved only when the game levels changed. The best overall gaming performance with a SATA drive is still provided by the Raptors. However, considering the space, noise levels, and cost per GB advantages of the Hitachi drive, we are willing to change our recommendation for most users (though plenty will feel 1TB is too big and would rather go with a 500GB model).
Facebook
Twitter
RSS
48 Comments
View All Comments
Pirks - Thursday, April 19, 2007 - link
call it a waste after you lose a terabyte of data because you hdd died on ya, until then - move alongyyrkoon - Thursday, April 19, 2007 - link
BTW, those of us who are truely serious about their data, do not keep the data stored on HDD alone. Tape, offsite, optical, choose your poison.Pirks - Friday, April 20, 2007 - link
for me number one reason for data loss was ALWAYS hdd failure, those caviars that click to death. I've never experienced data loss for any other reason. hence my natural impulse is to put two hdds in mirror raid - this eliminates most potent threat. and striping only doubles it, plus striping only slows things down when you copy big files (video mux/demux and stuff like that) so for me its mirror only (plus extra drive to speed up file copies a LOT)yyrkoon - Thursday, April 19, 2007 - link
If you are smart about how you use your HDDs, you will have no need, BUT if it makes you feel all warm and fuzzy inside, more power to you. The rest of us, who live in reality, and have HDDs much older than 10 years old, still functional, know better.Pirks - Friday, April 20, 2007 - link
yeah, I have 80 gig wd that I bought I forgot when, 5 years ago? maybe more... it's hot and noisy but looks like it's immortal. however, I wish ALL hdds were like this one. which they are not, unfortunately. those who experienced dead hdds (without doing anything special, just hdd that suddenly dies on you after a couple of years of excellent service) know better than youmlambert890 - Thursday, April 19, 2007 - link
it's not hundreds of dollars, its not insane, and you are wrong. its really kind of amusing that people are "debating" the basic premise of if a stripe set yields better read performance as if this were some new invention newly discovered and untested!Boushh - Thursday, April 19, 2007 - link
Well, maybe not hunderds of dollars (I agree that putting two of these 1 TB drive in RAID 0 is not very usefull) but if you go down the price list you can buy 2 320 Gb drives and put them in RAID 0. They are not expensive, and I know from my own experience that it realy makes a difference. All disk based activity is a lot faster than it would be on a single drive.I've may OS and my games on the RAID 0, and it realy helps speeding things up. So when the price is right RAID 0 is the way to speed up disk activity.
DigitalFreak - Thursday, April 19, 2007 - link
*sigh*mlambert890 - Thursday, April 19, 2007 - link
sigh all you want, but this is not up for debate. Many of us spend all day every day building and operating RAID systems. maybe for you, one article from anand that confirms some weird bias you have is sufficient. for those of us with 20+ years of doing this, the benefits of multiple spindles really dont need to be retested, and reproven, to make yet another generation feel cozy.synthetic benchmarks arent operating in some alternate reality. if whatever you are doing on your pc involves moving large, linear, blocks of data then you will benefit from a throughput boost clearly. in this case, a stripe set will yield quantitative benefit.
for many, loading something (even a game) seconds faster has value. esp since raid 0 has become a complete commodity. pointless article really, and pointless comments from the clueless. raid 0 has been written about and analyzed by smarter poeople with better measurement tools for decades. maybe people should try using common sense and broadening their google searches (that is if collecting their own real world experience is too much trouble)
OrSin - Thursday, April 19, 2007 - link
I got 20 years plus experience working in server farms and Raid is great from 0 to 5.With that said desktop raid dont do crap. I have over 10 systems in my house most on the extra same hardware. I tested Raid 0 and raid 5 and the difference in transfer speed even from GB switchs in less then 8%. Sorry but unless the maps or levels are just sitting in cache it don't do anything. Most of the delay is in seek time and Raid dont improve that at all. In fact I beleive it slows it (no proof). Please with all your experience the desktop and Server space is very different. Also remember SCSI raids improve seek time alot. I think if SATA hardware raids improve then raiding desktop might help.
PS
What are people doing they they even need a 50% improvement in hardrive speed on a desktop? Load levels and map? Sorry but saving even 5 secs out of 10, 5 times a day is not work the extra money to me. CPU, Ram, and Video cards scale so much better. You want the speed make a ram disk. :)