hIOmon Use Cases

For starters: Perspective

When you think about storage I/O performance, what's the first (and maybe only) thing that comes to mind?  Most likely, it's the "speeds and feeds" of your disk drives – that is, how fast can they perform I/O operations (IOPS rate), how fast can they transfer data (MB/s), etc.

Not necessarily.  A "fast" engine (as based upon its maximum innate performance capabilities) can certainly provide the potential for a fast car.  But obviously there are a number of other factors that also need to be considered, including various technical details such as the transmission and gear ratios -- in other words, the "complete package".

Also of paramount importance is how the car is actually used.  A fast engine in bumper-to-bumper traffic doesn't help much!

Plus it's important to remember that performance usually demands a premium.  Simply stated, added performance in a product typically costs more, whether it be a "faster" engine or a "faster" storage device!

The hIOmon software packages enable you to both measure and monitor the performance of your disk storage I/O operations up at the application level and moreover upon an individual, specific device, file, and process basis.  The I/O operation metrics collected by hIOmon reflect exactly how the application itself experiences its interaction with the disk storage, as based upon the actual disk and file I/O operations that the application performs, giving you an "I/O profile" for the respective application.

With its "application focus", hIOmon lets you view storage I/O operation activity and performance from the application level regardless of the underlying storage (and associated I/O path) infrastructure.

In other words, hIOmon measures and monitors an application’s I/O activity regardless of the underlying file system type or file placement used, the storage I/O transport used (e.g., SCSI, iSCSI, Fibre Channel), the particular disk storage type/interface used (e.g., HDD, SSD, SATA, SAS, FC, SSD, RAID-level, etc.), storage volume configuration (or virtualization type) used, etc.

So rather than having to rely solely upon a limited set of I/O operation metrics collected down at the disk device, hIOmon allows you to take a "top-down” approach to easily and quickly determine exactly how your own specific applications are actually using your disk storage!

hIOmon can provide a robust set of device (and file I/O operation performance metrics so that you can discover how your particular, individual files are actually being accessed and used.

This comprehensive set of I/O operation performance metrics goes far beyond basic read and write I/O operation counts, response times, throughput, and data transfer sizes/amounts to uniquely include such metrics as queue lengths, idle times, associated "physical device" I/O operation metrics along with random/sequential access detection, plus much more – including the hIOmon "Performance Threshold Range Metrics" and the "DataTransferred/Time Index (DXTI)" metric, which provides a "high-level" means for a relative comparison of I/O operation performance that resembles the “fuel economy” index for an automotive vehicle (i.e., “miles-per-gallon” or “kilometres/litre”) as an overall measure of “performance efficiency”.

In addition, hIOmon provides I/O operation performance metrics aggregated upon an individual process/application basis so that you can view overall I/O operation performance for a specific process/application.  hIOmon also enables you to not only easily tell which specific files (along with their respective file I/O operation performance metrics) are associated with a particular process/application, but also the particular processes/applications associated with a specific file.

It is especially important to note that hIOmon can capture its robust set of I/O operation metrics while you use your very own actual applications, files, and devices as you normally do – and within your own particular computer system environment.  Moreover, hIOmon does not require any application, file, or file system modifications nor does it require operating system code changes!

One key hIOmon feature is its ability to collect, display, and export I/O operation performance metrics upon a summarized basis, i.e., where the I/O operation performance metrics are automatically aggregated by hIOmon at the time when the I/O operations are actually observed by hIOmon I/O Monitor software component. Furthermore, hIOmon is the only software tool currently available that collects summarized metrics such as random and sequential access I/O counts and data transfer amounts.

So rather than having to labor over reams and reams of data representing metrics for each and every individual I/O operation (i.e., "I/O trace" data), hIOmon allows you to efficiently collect aggregated I/O operation metrics for only your particular files of interest. These aggregated metrics can then be offloaded for display and/or export either periodically (user-specified), when the file is closed/inactive, or when a user-specified "Alert" threshold (e.g., a particular total write I/O operation count, a maximum read response time, total amount of write data transferred, etc.) is detected.

This hIOmon feature helps provide significantly reduced overhead both for your system and for you. The aggregated metrics collected by hIOmon enable you to easily and quickly focus upon your specific items of interest and concern, without struggling over mountains of I/O trace data and/or having to use various tools to generate "summarized" metrics from such trace data. But in the event that you do need to track down some particular I/O operation activity, hIOmon also provides an "I/O Trace Data" feature option as well.

hIOmon provides the flexibility and wide range of features required to tackle a variety of disk storage I/O-related issues and concerns. As examples, are you thinking about such fundamental tasks as:

• Leveraging lower-cost (but lower-performance) disk drives or disk arrays?
• Monitoring your higher-performance (but higher-cost) SANs to help ensure that the I/O performance requirements of your key files/applications are being satisfied?
• Determining the performance impact of placing/consolidating more (and perhaps some specific application) files all upon the same, higher-capacity disk device? Or of adding additional system memory and/or faster processors?
• Getting actual metrics upon a device or file basis to determine the performance impact associated with the various "storage virtualization" and/or network-attached file approaches?
• Capturing empirical metrics, which reflect actual file and/or device I/O activity from either the host and/or guest virtual machine perspective and moreover upon a quick and simple "summary" basis, that can help you determine whether storage I/O performance is a bottleneck within your virtual machine consolidation roll-out?

If so, then hIOmon can help you collect the pertinent file, device, and application-based I/O performance metrics that you need to make a more-informed assessment/decision, a better business case, and a more confident roll-out plan!

Bringing Transparency to Disk I/O Performance℠