by Aleksey Meyev
05/02/2008 | 05:14 PM
2.5-inch hard disk drives used to be considered an attribute of notebooks while their low storage capacity was put up with as an annoying, yet inevitable, drawback. This attitude seems to call for a revision now thanks to the rapid growth of recording density. The capacity of 200-250 gigabytes (and even 320GB in newer models) is quite enough not only for an office/workstation PC but also for a home multimedia/gaming system. What is good about 2.5” HDDs, they feature low power consumption and, accordingly, low heat dissipation. They are also small and produce little noise. No wonder then that we now often hear about non-mobile applications of such HDDs. They are installed into compact computers such as the Mac Mini or AOpen miniPC. People who build silent PCs install such HDDs into full-size system cases instead of noisy 3.5” models. And if you are planning to assemble a compact Network Attached Storage or even an inexpensive 1U server with a good disk subsystem, you may want to consider using 2.5” HDDs as well.
What about performance? How do 2.5” drives compare with their larger counterparts in terms of sheer speed? This question has become even more interesting after 2.5” HDDs with a spindle rotation speed of 7200rpm were introduced. It’s the same speed as 3.5” drives have. In this review, we will try to compare 2.5” HDDs not only with each other but also with two 3.5” HDD models.
We’ll also check out the influence of such parameters as recording density and spindle rotation speed on HDD performance. To carry such a test out we will benchmark not only new HDDs but also previous-generation models. Thus, we will compare, for example, a 7200rpm drive with low recording density and a 5400rpm drive with high recording density.
A total of ten devices will take part in this test session:
We tried to pick up HDDs with a storage capacity of 200GB but the Fujitsu MHW2 BJ is 160GB (Fujitsu hasn’t yet achieved a recording density of 100GB per platter in its 2.5” 7200rpm drives, and 160 gigabytes is the highest capacity in the series). The Hitachi 7K100 and Seagate 7200.1 belong to the previous generation when the maximum recording density was 50GB per platter and have a capacity of 100GB only. It would have been better to take a Seagate drive from the newer 7200.1 series, but we couldn’t get one.
Of course, the newer 7K200 series has inherited most of its technologies from the 7K100 series: iridium-magnesium-chromium heads, thermal fly-height control, parking on a ramp for protection during reboots, and the power-saving features HiVERT and ABLE. What is really new in the new series, the recording density per platter has doubled. The amount of cache memory has doubled as well, reaching 16 megabytes. The other HDDs in this review have only 8 megabytes of cache memory. We’ll see if the 7K200 can put these innovations to good use and deliver the 22% performance boost promised by the manufacturer (relative to the 7K100 series).
Fujitsu is traditionally taciturn about its products. We don’t know anything about them besides the basic specs. You should note that the MHW2160BJ has a lower capacity than the competing Hitachi 7K200 due to lower recording density. The MHY2200BH with a spindle rotation speed of 5400rpm is based on the highest-capacity platters and is not the senior model in its series (the 250GB model was tested by us earlier). The 4200rpm MHV2200BT has the lowest recording density among the Fujitsu drives in this review, so it has three rather than two platters to deliver the required capacity. As a consequence, its case is 3mm thicker than standard, which may provoke some troubles with installation.
The Momentus 7200.1 is obviously no match to the Hitachi 7K200. We include it only for the sake of comparison because it is a contemporary of the Hitachi 7K100 series and has appropriate recording density. We are still looking forward to testing the next 2.5” series with a spindle rotation speed of 7200rpm – Momentus 7200.2.
We also took two 3.5” models already tested on our site, ST3200820A (Seagate 7200.10) and ST3200822A (Seagate 7200.7).
The following testing utilities were used:
Testbed configuration:
We installed the generic OS drivers for the drives and formatted them in FAT32 and NTFS as one partition with the default cluster size. For some tests 32GB partitions were created on the drives and formatted in FAT32 and NTFS with the default cluster size, too. The SATA interface was provided by a Promise SATA300 TX4302 controller.
IOMeter is sending a stream of read and write requests with a request queue depth of 4. The size of the requested data block is changed each minute, so that we could see the dependence of the drive’s sequential read/write speed on the size of the data block. This test is indicative of the highest speed the drive can achieve.
The 3.5” Seagate 7200.10 has the highest maximum of read speed. It also delivers the highest speed when processing small data chunks. The Hitachi 7K200 and Fujitsu MHW2 BJ, new 2.5” HDDs with a spindle rotation speed of 7200rpm, are about as fast as the Seagate 7200.7. The 2.5” HDDs cannot overtake the 3.5” models, even the Seagate 7200.7 with low recording density, on small data chunks, though.
Comparing the two generations of Hitachi drives, the doubled recording density has provided a serious performance boost for the new 7K200 in terms of maximum read speed. The speed of processing small data chunks has improved, too. The 7K100 is slower than every other drive, including the 4200rpm Fujitsu MHV2 BT, but the 7K200 is as fast as modern 2.5” HDDs. Take note how good the Seagate 7200.1 is at processing small data chunks while being inferior to every other “small” 7200rpm HDD in terms of maximum read speed.
Comparing Fujitsu’s HDDs between each other, you can see their maximum speed increase in strict proportion to their spindle rotation speed. They have similar read speeds on small data chunks.
The two 3.5” HDDs from Seagate win the sequential writing test, too. Interestingly, the Fujitsu MHW2 BJ is close to the Seagate 7200.7 in terms of maximum speed whereas the Hitachi 7K200 has a very low speed of writing, losing to the previous-generation 7K100 as well as to the 5400rpm Fujitsu MHY2 BH. We’ll see shortly if it’s just a specific reaction of the 7K200 to synthetic load or it really has such a low speed of writing.
Fujitsu’s HDDs behave predictably, performing proportionally to the spindle rotation speed except that the MHY2 BH is surprisingly poor at writing small data chunks.
In this test IOMeter is sending a stream of requests to read and write 512-byte data blocks with a request queue of 1 for 10 minutes. The total number of requests processed by the HDD is over 60 thousand, so we get a sustained response time that doesn’t depend on the HDD’s buffer size. The results are sorted by read response time.
It’s clear that the read response depends on the spindle rotation speed: Fujitsu’s HDDs are ranked according to this parameter (7200, 5400 and 4200rpm). The 7200rpm models are all very close irrespective of the form-factor. The Hitachi 7K200 is the best one in this test.
To remind you, the ratio of write to read response is indicative of the efficiency of the deferred write algorithms. Seagate’s HDDs are all inferior to the other manufacturers’ products in this respect because their algorithms are traditionally weak. Well, the Seagate 7200.1 has a somewhat lower response time at writing than Seagate’s 3.5” drives, but this only makes it fast enough to outperform the 4200rpm Fujitsu MHV2 BT.
In the Database pattern the drive is processing a stream of requests to read and write 8KB random-address data blocks. The ratio of read to write requests is changing from 0% to 100% throughout the test while the request queue size varies from 1 to 256.
We’ll discuss the results of each drive individually.
Hitachi has made some progress in the new drive’s firmware, correcting the defects of the 7K100. Take note that the 7K200 copes betters with the hardest types of load when there is about the same share of writes and reads. The overall performance at long request queues has improved greatly.
First of all, the radically different behavior of the MHV2 BT must be noted: this hard disk has too low results at loads with a low percentage of writes even for its low spindle rotation speed. The other two models are similar, the MHW2 BJ being faster at every load proportionally to the difference in their spindle rotation speeds.
Among Seagate’s drives, the 7200.10 model copes best with the middle part of the diagram, but loses to the older 7200.7 at long queue depths when there are only reads or writes to be done. Interestingly, it is the 2.5” 7200.1 that is the best HDD at 100% writes. The same HDD is considerably slower than its Seagate mates at medium queue depths (4 and 16) when there are more reads than writes.
Comparing all the participating HDDs, Hitachi’s are better than the others when reading at a short queue depth, and the Seagate team are better when reading at long queue depths. Hitachi’s HDDs are also superior at random writing but are closely followed by the 7200rpm Fujitsu MHW2 BJ. When the amount of writes and reads is about the same, the Hitachi 7K200 wins at short queues, and the Seagate 7200.10 is the best at long queues.
The multithreaded tests simulate a situation when there are one to four clients accessing the hard disk at the same time. The depth of the outgoing request queue is varied from 1 to 8.
We’ll discuss diagrams for a request queue of 1 as the most illustrative ones. When the queue is longer, the speed depends but little on the number of applications.
This test has always been a hard trail. Seagate’s 3.5” HDDs are in the lead when processing one thread (and the 7200.10 enjoys a lead of 10MB/s over the others), but find themselves the slowest at two threads, having very low speeds. The Hitachi 7K200 is the best drive to read multiple threads, being two times as fast as the previous-generation 7K100 and six times as fast as Seagate’s HDDs.
The gaps between Fujitsu’s HDDs are smaller when there are more threads to be processed, yet they are still ranked up according to their spindle rotation speed.
Take note that the Fujitsu MHY2 BH and the Seagate 7200.1 deliver similar performance when reading one thread: the higher recording density of the former makes up for the latter’s higher spindle speed. This shows the influence of recording density on a HDD’s performance. Performance being the same, a HDD with a lower spindle speed is going to be preferable for notebook owners due to its low power consumption.
Seagate’s HDDs are not as utterly hopeless at multithreaded writing as they were at reading. When writing one thread, the HDDs are ranked up exactly as they were at sequential writing. The three HDDs from Fujitsu perform proportionally to their spindle rotation speeds. The Hitachi 7K200 is surprisingly slower than the 7K100, while the Fujitsu MHW2 BJ proves to be the best among the 2.5” models.
When writing two threads, the low-recording-density Seagate 7200.7 takes first place – somewhat surprisingly. It is followed by Seagate’s other two HDDs and by the Fujitsu MHW2 BJ. The Hitachi 7K200 doesn’t slow down much and now outperforms the 7K100 as well as the 5400rpm Fujitsu MHY2 BH.
The leader remains the same at three threads but the Fujitsu MHW2 BJ is getting farther away from Seagate’s duo, in which the 7200.10 loses more speed than the 7200.1. Hitachi’s HDDs slow down considerably, the 7K200 being overtaken by the Fujitsu MHY2 BH.
Increasing the number of threads further makes the Seagate 7200.7 slow down. The Fujitsu MHW2 BJ becomes the leader.
Do you often have to write data in multiple threads? Now you know what company’s disks are the best for this job.
This group of tests simulates disk loads typical of servers and workstations. Such applications are not typical for mobile devices, so I won’t analyze the results deeply. The names of the patterns are self-explanatory. The Workstation pattern is used with the full capacity of the drive as well as with a 32GB partition. The request queue is limited to 32 requests in the Workstation pattern.
The results are presented as performance ratings which are calculated by the following formulas:
Rating (File-Server) = Total I/O (queue=1)/1 + Total I/O (queue=4)/2 + Total I/O (queue=16)/4 + Total I/O (queue=64)/6 + Total I/O (queue=256)/8
Rating (Web-Server) = Total I/O (queue=1)/1 + Total I/O (queue=4)/1 + Total I/O (queue=16)/2 + Total I/O (queue=64)/4 + Total I/O (queue=256)/6
Rating (Workstation) = Total I/O (queue=1)/1 + Total I/O (queue=2)/1 + Total I/O (queue=4)/2 + Total I/O (queue=8)/3 + Total I/O (queue=16)/4.
It’s the Seagate 7200.10 that wins this test, but you may note that the 2.5” drives with a spindle speed of 7200rpm are not much slower. The Seagate 7200.1 and Hitachi 7K100 are only slower at high loads while the Hitachi 7K200 is even faster at a request queue of 1. It’s also interesting that the 5400rpm Fujitsu MHY2 BH overtakes the old Seagate 7200.7: the high recording density and effective firmware algorithms beat the higher spindle speed.
The results produced by the Web-Server pattern as similar to the previous test, but the firmware algorithms play a bigger role here. This is the reason why the Hitachi 7K100 and Seagate 7200.1 outperform the Fujitsu MHW2 BJ which is based on higher-density platters. Note that the Seagate 7200.7 is the slowest of all, including the Fujitsu MHV2 BT that has a spindle rotation speed of only 4200rpm and the lowest recording density among the 2.5” models included into this review.
The Seagate 7200.10 wins the Workstation pattern when the entire disk capacity is used for the test. The 2.5” drives with a spindle speed of 7200rpm are not far behind, though. The old Seagate 7200.7 is outperformed by the Seagate 7200.1 and Hitachi 7K200. The HDDs with lower spindle rotation speeds cannot match their faster mates in this test.
There are certain changes in the results when we limit the test zone to a 32GB partition. First of all, the 3.5” HDDs improve their positions. Second, the 5400rpm Fujitsu MHY2 BH performs better, overtaking the Hitachi 7K100.
We’ll use WinBench to record data-transfer graphs:
No surprises here: the 7200rpm HDDs take top places, the 3.5” models being in the lead among them. Interestingly, the 5400rpm Fujitsu MHY2 BH is comparable to the Seagate 7200.1 at the beginning of the disk due to its higher recording density, but slows down at the end of the disk.
Next, we’ll compare the performance of the HDDs in WinBench 99 tests for a 32GB partition. FAT32 results come first.
Check out detailed FAT32 results here.
3.5” HDDs are beyond competition in this test. The fastest of the 2.5” models are no match to them. The effect of high recording density is clear: the Fujitsu MHW2 BJ and Hitachi 7K200 enjoy a big lead over the other compact drives. The advantage of the latter over the Hitachi 7K100 is especially convincing. Having a higher recording density but a lower spindle speed, the Fujitsu MHY2 BH beats the Seagate 7200.1.
Check out detailed NTFS results here.
It’s the same as in FAT32 except that the Hitachi 7K100 loses more speed than the other HDDs and rolls back to last place.
Now we will check performance of the hard disk drives with FC-Test. Two 32GB partitions are created on the drives and formatted in NTFS and then in FAT32. A file-set is created of the hard disk. This file-set is then read from the disk, copied within the same partition and then copied into another partition. The time taken to perform these operations is measured and the speed of the drive is calculated. To remind you, the Windows and Programs file-sets consist of a large number of small files whereas the other three patterns (ISO, MP3, and Install) include a few large files each.
FAT32 results come first.
We see a dramatically different picture when we switch from block requests of the synthetic benchmarks to real-life files. It is the Fujitsu MHW2 BJ that wins this test, being only inferior to the Seagate 7200.7 on large files. The latter has a very low speed on small files, however. It even manages to lose to the 4200rpm Fujitsu MHV2 BT in the Programs pattern. The higher-density 3.5” Seagate 7200.10 is always in the middle of the table, being about as fast as the other 7200rpm drives. Its form-factor doesn’t give it any advantage.
The Hitachi 7K200 has modest results. It is unable to put its advantage in recording density to good use here.
When copying, the results depend less on the specific file-set. The Seagate 7200.10 is victorious although its advantage is shrinking as the average file size gets smaller. The leader is followed by two 2.5” HDDs with high recording density and by the Seagate 7200.7. The latter is ahead of its rival on large files but behind of it on small files.
The Seagate 7200.1 has very modest performance and is overtaken by the Fujitsu MHY2 BH which has a lower spindle rotation speed but a higher recording density.
Copying within the same partition depends on what exactly file-set the drive is dealing with. The Seagate 7200.10 is ahead on very large files but is overtaken by the Hitachi 7K200, and occasionally by the Fujitsu MHW2 BJ, on smaller files. Well, all of the Seagate drives are rather slow when copying small files: the 7200.7 model is inferior to the Fujitsu MHY2 BH, 2.5” HDD with a lower spindle rotation speed, and the 7200.1 model is the slowest of all, including the 4200rpm Fujitsu MHV 2BT.
The Hitachi 7K200 is still good when copying from one partition into another, being slightly inferior to the Seagate 7200.10 on larger files and beating it on small files. The other two drives from Seagate have modest results again.
Now let’s check out NTFS results.
It’s the same as in FAT32: the Fujitsu MHW2 BJ shows superb speed, the old Seagate 7200.7 copes best with copying large files but fails the copying of small files. The Seagate 7200.10 again has no advantage over the 2.5” HDDs with the same spindle rotation speed.
Reading is the test where the 3.5” HDDs are better than their smaller counterparts. Seagate’s 7200.10 and 7200.7 models take top places with every file-set. The Seagate 7200.1 is very slow among the 2.5” HDDs, being inferior even to the 5400rpm Fujitsu MHY2 BH.
It’s the same at copying. The two 3.5” HDDs from Seagate and the high-density Hitachi 7K200 and Fujitsu MHW2 BJ are in the lead. Seagate’s 3.5” HDDs are good at copying large files but the Hitachi 7K200 goes ahead on small files, utilizing the advantage of a larger buffer and more effective firmware algorithms. The Seagate 7200.1 has low performance, again.
PCMark04 benchmarks drives in four different modes: Windows XP Startup is the typical disk subsystem load at system startup; Application Loading is the disk activity at sequential starting-up and closing of six popular applications; File Copying measures the HDD performance when copying a set of files; the Hard Disk Drive Usage parameter reflects the disk activity in a number of popular applications. These four parameters are used to calculate the overall performance rating using the following formula:
HDD Score= (XP Startup Trace x 120) + (Application Load Trace x 180) + (File Copy Trace x 28) + (General Usage x 265)
Curiously enough, it is the Hitachi 7K200 that takes less time than the others to boot the OS up. It even outperforms the Seagate 7200.10! As for the Seagate 7200.7, it is slower than almost every 2.5” 7200rpm drive, being barely ahead of the Seagate 7200.1. The HDDs with lower spindle rotation speeds take two last places.
The Hitachi 7K200 is in the lead again when loading applications. It is quite far ahead of both 3.5” HDDs from Seagate. The Fujitsu MHW2 BJ is surprisingly slow, probably due to some flaws in the firmware algorithms. Next go the 7200rpm drives with low recording density. The HDDs with low spindle rotation speeds are the slowest.
The Hitachi 7K200 triumphs again. The results could have been predicted basing on the previous tests, but we’d like to note the good performance of the Fujitsu MHY2 BH – it outperformed both 2.5” 7200rpm HDDs with low recording density.
The leader doesn’t change. The other 7200rpm drives have similar results irrespective of the form-factor. The Seagate 7200.1 is the only exception, yet it is also faster than the HDDs with lower spindle rotation speeds.
Of course, it is the Hitachi 7K200 that has the highest overall score. It is followed by the Seagate 7200.10 and Fujitsu MHW2 BJ. The HDDs with low spindle rotation speeds cannot leave last places in this test.
The Hitachi 7K200 is a superb hard disk drive with good performance. It is currently the leader among 2.5” HDDs with a spindle rotation speed of 7200rpm. The only downside we can note about it is its low speed of sequential writing, which affects its speed of writing large files. This explains why the 7K200 was occasionally outperformed by the Fujitsu MHW2 BJ which has a smaller buffer and lower-density platters. The average performance level of the new series is indeed higher just as promised by Hitachi.
Comparing HDDs of different form-factors, the 3.5” models were only better in a limited number of tests, mostly involving the reading of large files. When firmware algorithms were more important than sequential speeds (in such tests as copying small files, multithreaded reading/writing), the 2.5” HDDs competed with their larger counterparts quite successfully. They competed mostly with the Seagate 7200.10, which is still a widespread product although the 7200.11 series has already hit the shops. If you take an old 3.5” HDD for comparison, for example the Seagate 7200.7, its speed is going to be lower in general than the speed of modern 2.5” models. So, you shouldn’t think that a 2.5” HDD will lead to a performance hit for your system. It is likely that the only difference you’ll notice is the lower level of noise.
As for the HDDs with lower spindle rotation speeds, the new 5400rpm models with high recording density are quite competitive against older 7200rpm drives as the Fujitsu MHY2 BH showed during this test session. Such HDDs consume less power but provide a larger storage capacity (up to 320GB), so you should think twice if you really need a high spindle rotation speed when you are upgrading your notebook’s disk. On the other hand, 4200rpm HDDs are really slow. You should only use them when their price or low power consumption makes a difference.
On our wish list is the release of Seagate’s new HDD series, the increase of sequential speed in Hitachi’s HDDs to a high enough level, and the introduction of high-density platters in Fujitsu’s products. Hopefully, we’ll not have to wait long to see all of this happen.