IOMeter v2004.07.30

IOMeter v2004.07.30 


Iometer is an I/O subsystem measurement and characterization tool for single and clustered systems. It was originally developed by the Intel Corporation and announced at the Intel Developers Forum (IDF) on February 17, 1998 – since then it got wide spread within the industry.

Meanwhile Intel has discontinued to work on Iometer and it was given to the Open Source Development Lab (OSDL). In November 2001, a project was registered at SourceForge.net and an initial drop was provided. Since the relaunch in February 2003, the project is driven by an international group of individuals who are continuesly improving, porting and extend the product.

Gigabyte iRAM Solid State SATA Storage Review - Storage  1

Gigabyte iRAM Solid State SATA Storage Review - Storage  2

Gigabyte iRAM Solid State SATA Storage Review - Storage  3

Gigabyte iRAM Solid State SATA Storage Review - Storage  4

In our four test situations here, we look at the performance of the same drives on a typical file server, web server, database and workstation work load.  This series of tests looks at the number of I/Os that each device can handle per second.  In each case, the iRAM is so far ahead of the competition that it scales our data graphs enough to merge the other competitors into almost a single line. 

Gigabyte iRAM Solid State SATA Storage Review - Storage  5

Gigabyte iRAM Solid State SATA Storage Review - Storage  6

Gigabyte iRAM Solid State SATA Storage Review - Storage  7

Gigabyte iRAM Solid State SATA Storage Review - Storage  8

This second series of tests looks at how long each transaction takes to complete based on varying queue depths (instructions pending).  Even at its worst, the Gigabyte iRAM is barely getting off the bottom of the graph (which is good!) as the time required for transactions stays very fast even on the larger queue depths.  The standard hard drives can’t make that claim as even the Raptor 74 GB drive hits 1200 ms of delay at the 256 queue size. 

These tests results are incredibly fast, though the one caveat of course is that drive environments that use drive patterns like this obviously need more than 4 GB of storage.

« PreviousNext »