BriForum 2013 Chicago: Why IOPS Suck and Everything You Know About Them is Probably Wrong!

Quoting IOPS numbers without providing a block size, R/W ratio or latency values is like buying a car without knowing what's under the hood or looking inside the car.  IOPS are still one of the hottest buzz words in the industry, but probably one of the most misunderstood topics out there.  Why is that?  In this session we'll talk about why seasoned IT consultants, storage admins and even storage vendors are getting it wrong with respect to IOPS.  We'll also talk about why IOPS are a terrible unit of measurement or metric - and why we should be talking about throughput instead.    We'll wrap up this technical session by looking at some real-world numbers from recent field engagements and dive into why they are drastically different from the best-case scenario numbers that a storage vendor might have quoted you.  Nick & Dan will also make a case for banning the word "IOPS" from the English dictionary (if it's even in there).  This session will be wildly entertaining and informative - a must attend for anyone who deals with storage!

Topics covered will also include:

  • Why throughput is a better unit of measurement or metric than IOPS
  • How block size affects IOPS and throughput
  • What real-world R/W ratios and disk latency looks like
  • How to properly size a storage solution
Presented by Nick Rintalan & Dan Allen
View All Videos

Start the conversation

Send me notifications when other members comment.

By submitting you agree to receive email from TechTarget and its partners. If you reside outside of the United States, you consent to having your personal data transferred to and processed in the United States. Privacy

Please create a username to comment.

-ADS BY GOOGLE

SearchVirtualDesktop

SearchEnterpriseDesktop

SearchServerVirtualization

SearchVMware

Close