Pure Hard Disk Performance - IPEAK

We begin our usual hard disk drive test session with Intel's IPEAK benchmarking utility. We first run a trace capture on Winstone 2004's Business and Multimedia Content Creation benchmark runs to catch all of the IO operations that take place during each test. We then play each capture back using RankDisk, which reports back to us a mean service time, or average time that the drive takes to complete an IO operation.

IPEAK Business Winstone 2004 - Pure Hard Disk Performance

The 160GB 7200.9 performs, on average, 561 operations per second, which tops all of the other 160GB units on the chart including the 80GB/platter Samsung Spinpoint drives and even the 5 x 133GB/platter 500GB 7200.9. However, the drive is far behind Hitachi's 160GB 3.0Gb/sec T7K250 with 2 x 125GB platters and barely visible in Western Digital's rearview mirror as the WD1600JS comes second only to its 74GB Raptor cousin.

With two of these 160GB 7200.9 units in a RAID-0 setup, we see that the operations per second increase about 55%. We performed this test as a brief look at how RAID affects performance...and to prove to the skeptics that setting up two or more drives in RAID-0 at least will increase the performance. Here, we see that happening. Let's see if this trend continues.

Let's take a look at Content Creation performance.

IPEAK Content Creation Winstone 2004 - Pure Hard Disk Performance

The results for the 160GB 7200.9 are consistent here as well, as the single drive performs 378 operations per second just behind Seagate's last generation 400GB 7200.8 unit. Here, Hitachi's T7K250 drops behind, but only by an average of 6 operations per second, which makes very little difference, if any. The drives in a RAID-0 setup again increases performance about 58% from a single drive setup.

IPEAK Average Read Service Time

The read service times are also lower most likely due to the higher density, single platter design in the 160GB 7200.9. There is very little difference here between the single drive and RAID-0 (2x160GB) drive setups.

IPEAK Write Service Times

We have taken the liberty to also include the average Write Service Times for the 160GB 7200.9. The single 160GB 7200.9 drive has an average write service time of 8.67ms while our RAID-0 setup resulted in about half that at 4.67ms.

The Test WinBench 99 - Transfer Rate Test
POST A COMMENT

23 Comments

View All Comments

  • yacoub - Thursday, February 2, 2006 - link

    If you're going to do an acoustics test, you should make a useful graph instead of that tiny one that makes them all look relatively equivalent in noise output. You should also note any particular sound properties the drive emits. Whine, pitch, vibration, etc. It would be subjective but it's also very important.

    If anything, harddrive speed and performance are relatively similar among most drives. The noise output however, is often greatly different, and is especially important if the drive emits noise at a certain frequency that annoys the user. I'd rather wait an extra millisecond for a seek than have to put up with a constant ringing noise or whine from the drive.

    You could also at least include a modern Samsung SpinPoint like the P120 SP2004C 200GB drive in your test list instead of the dated Samsungs you use currently. Aside from it having better performance than most of the older Samsungs you list, it also is one of the quietest 7200rpm 3.5" HDs out there - enough that it would certainly stand out in your acoustics test instead of the current lot you test with that leaves a graph that gives a false impression of "oh, looks like all HDs are about the same in noise so I won't bother using that as a purchase consideration."

    http://www.storagereview.com/articles/200511/SP250...">http://www.storagereview.com/articles/200511/SP250... shows a more useful acoustics test graph and the strongest point of the Samsung SpinPoint SP2004C - its SPL. Anyone building a quiet PC should certainly consider it. I love mine.

    SilentPCReview also has a SpinPoint P120 SP2004C review but their site seems to be down at the moment.
    Reply
  • RallyMaster - Wednesday, February 1, 2006 - link

    Is this the ST3160812AS? If so...I have one! Never thought my 95 dollar hard drive was capable of doing so well. Wow. Reply
  • wharris1 - Wednesday, February 1, 2006 - link

    yes, this article was initially posted last week. Reply
  • Olaf van der Spek - Wednesday, February 1, 2006 - link

    > We also benchmarked a couple of these drives in a RAID-0 array as a brief look at RAID performance with results that were pleasing to our eyes.

    Really?
    No improvements in either application or game level load times.
    Little improvements in the zip/unzip tests.

    What exactly is so pleasing?
    Results in vague iPeak tests?
    Reply
  • JWalk - Tuesday, February 7, 2006 - link

    Ding! We have a winner.

    Nothing appears to have changed when it comes to real-world applications and RAID-0 performance. Anand himself and Eugene at storagereview.com have settled this numerous times.

    If you want to see big synthetic benchmark numbers, run RAID-0. If you want actual real-world results, use a fast single drive. RAID has its place, but not in a RAID-0 array for normal desktop/gaming use.
    Reply
  • Ecmaster76 - Tuesday, January 31, 2006 - link

    Did this one get pulled and put back up or something? Reply
  • neogodless - Tuesday, January 31, 2006 - link

    I think the focus on RAID makes the omission of temperature and noise data a strange thing. How does that second drive affect the temperature inside the case, especially if the drives are side by side? How does it affect noise? Reply
  • patentman - Friday, January 27, 2006 - link

    "With the announcement and release of Seagate's new 160GB 5400.3 2.5" notebook drive, which utilizes the new perpendicular magnetic recording method"

    I think I've said this before, but perpendicular magnetic recording is not new by any stetch of the imagination. There are patents on this technology that were filed in the late 80's. Mainstream products using this technology might be new, but the actual method of recording is, in the computer world, very very old.
    Reply
  • PuravSanghani - Wednesday, February 1, 2006 - link

    Patentman,

    Though the patent may have been around since the late 80's, only recently has a hard drive manufacturer been able to implement the technology in their products.

    Toshiba was the first to do this with their smaller drives and Seagate is the first do implement this technology in notebook drives. The race is on to see who will introduce desktop drives based on this technology!

    Purav
    Reply
  • Mr Perfect - Friday, January 27, 2006 - link

    The 160GB 7200.9 is not in either of the two temperature charts or the noise chart. The 500GB 7200.9 is there, but no it's little brother. Reply

Log in

Don't have an account? Sign up now