X-bit labs

SSD, i-RAM and Traditional Hard Disk Drives (page 3)

Category: Storage

by Aleksey Meyev

[ 04/23/2008 | 08:05 PM ]

Testbed and Methods

The following testing utilities were used:

• IOMeter 2003.02.15
• WinBench 99 2.0
• FC-Test 1.0
• PCMark 2004
• PCMark 2005
• PCMark Vantage

Testbed configuration looked as follows:

• Albatron PX865PE Pro II mainboard
• Intel Pentium 4 2.4GHz CPU
• IBM DTLA-307015 system disk, 15GB
• Radeon 7000 32MB graphics card
• 256MB DDR2-533 SDRAM
• Microsoft Windows XP Professional SP2

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. The SAS interface was provided by an LSI SAS3041E-R controller.

Performance in Intel IOMeter

Sequential Read & Write Patterns

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 numeric data can be viewed in tables. We’ll discuss diagrams.

• IOMeter: Sequential Read results (table)
• IOMeter: Sequential Write results (table)

As might have been expected, the SSDs cannot compete with the HDDs at sequential operations. There is some competition on small data chunks, but the HDDs go ahead on large chunks, even the 2.5” Hitachi 7K200 having a higher maximum speed than the SSDs. The gap isn’t large, though. The SSDs are roughly similar to 5400rpm 2.5” HDDs in terms of sequential reading.

Note that the 32GB SSD with the slower UATA66 interface is faster than the 64GB model with the SATA interface. Perhaps the higher capacity is achieved by means of slower chips? Or is it just the way the SSDs behave in this particular test? We’ll find the answer in the other tests.

As for the i-RAM, it is only inferior to the 15,000rpm drive from Toshiba. And it must be due to the i-RAM using a 150MB/s SATA interface (the interface’s practical bandwidth is even lower as you can see). Its performance might be better with SATA II.

We see the same overall picture at sequential writing as in the previous test. There are certain differences, though. The 64GB SSD is not so far behind the 32GB model while the latter is ahead of the Hitachi 7K200 on small data blocks and even ahead of the Samsung F1 on 512-byte blocks.