News
10/21/2009
03:43 PM
George Crump
George Crump
Commentary
50%
50%

Understanding Hard Drive Performance

In the last performance entries we discussed understanding storage bandwidth and understanding storage controllers. Next up is to understand the performance characteristics of the hard drive itself and how the mechanical hard drive can be the performance bottleneck.

In the last performance entries we discussed understanding storage bandwidth and understanding storage controllers. Next up is to understand the performance characteristics of the hard drive itself and how the mechanical hard drive can be the performance bottleneck.The big problem with hard drives is that they are stuck from a performance perspective. While everything else has increased in speed over the past few years, the fastest hard drives have been locked in at 15K RPM. What has kept mechanical drives viable in performance concerned data centers is the ability to group multiple drives together in an array group. Each drive in the array can respond to storage I/O requests. As long as you have enough requests, also known as queue depth, every time you add a drive to an array group performance improves.

The downside to large drive count array groups is that you often run into wasted capacity because so many drives are added to hit the performance requirement that the application can't use all the capacity that came along with the drive. Companies like 3PAR, Xiotech and Isilon get around this by performing fine grain virtualization, meaning they can stripe all the data from all the attached servers across all or most of the available drives in the storage system. This technique, known as wide striping, for many organizations strikes a balance between high performance and efficient capacity utilization.

At some point however you have a situation where you have added so many drives that it is not cost effective to do so or you run out of storage I/O requests and you have a response time or latency issue. The only step left is to speed up the drive itself.

Where are 20K RPM drives? While 20K RPM hard drives have been researched by various vendors, they have not been found to be viable for the market. There are problems with the heat, vibration and reliability issues with these faster drives. Cost is also an issue with 20K RPM hard drives. In fact they may be more expensive than an equivalent capacity Solid State Disk (SSD). For reasons we state in "SSD's are cost effective NOW", the downward price trend on SSDs seems to have eliminated the development of the 20K RPM drive market. With SSD you get better performance with none of the heat and vibration issues that were set to plague 20K drives. Finally SSDs, especially enterprise class SSD using SLC Flash, have proven to be as reliable as mechanical drives.

For many environments drive performance is not an issue and a simple array group of 10K or even 7.5K RPM drives provides all the performance their applications need. As performance becomes an issue, and storage controller and bandwidth issues are eliminated, then adding drive count is the next logical step, especially if you can leverage technologies like fine grain virtualization. Eventually the final stop is SSD.

Even in SSD their is likely to be tiers of service and you will want to use different SSD technologies for different SSD classes.

Track us on Twitter: http://twitter.com/storageswiss

Subscribe to our RSS feed.

George Crump is lead analyst of Storage Switzerland, an IT analyst firm focused on the storage and virtualization segments. Find Storage Switzerland's disclosure statement here.

Comment  | 
Print  | 
More Insights
Register for Dark Reading Newsletters
White Papers
Cartoon
Current Issue
Dark Reading December Tech Digest
Experts weigh in on the pros and cons of end-user security training.
Flash Poll
10 Recommendations for Outsourcing Security
10 Recommendations for Outsourcing Security
Enterprises today have a wide range of third-party options to help improve their defenses, including MSSPs, auditing and penetration testing, and DDoS protection. But are there situations in which a service provider might actually increase risk?
Video
Slideshows
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2014-5426
Published: 2014-11-27
MatrikonOPC OPC Server for DNP3 1.2.3 and earlier allows remote attackers to cause a denial of service (unhandled exception and DNP3 process crash) via a crafted message.

CVE-2014-2037
Published: 2014-11-26
Openswan 2.6.40 allows remote attackers to cause a denial of service (NULL pointer dereference and IKE daemon restart) via IKEv2 packets that lack expected payloads. NOTE: this vulnerability exists because of an incomplete fix for CVE 2013-6466.

CVE-2014-6609
Published: 2014-11-26
The res_pjsip_pubsub module in Asterisk Open Source 12.x before 12.5.1 allows remote authenticated users to cause a denial of service (crash) via crafted headers in a SIP SUBSCRIBE request for an event package.

CVE-2014-6610
Published: 2014-11-26
Asterisk Open Source 11.x before 11.12.1 and 12.x before 12.5.1 and Certified Asterisk 11.6 before 11.6-cert6, when using the res_fax_spandsp module, allows remote authenticated users to cause a denial of service (crash) via an out of call message, which is not properly handled in the ReceiveFax dia...

CVE-2014-7141
Published: 2014-11-26
The pinger in Squid 3.x before 3.4.8 allows remote attackers to obtain sensitive information or cause a denial of service (out-of-bounds read and crash) via a crafted type in an (1) ICMP or (2) ICMP6 packet.

Best of the Web
Dark Reading Radio
Archived Dark Reading Radio
Now that the holiday season is about to begin both online and in stores, will this be yet another season of nonstop gifting to cybercriminals?