Problem solve Get help with specific problems with your technologies, process and projects.

Oracle disk I/O tuning: Disk capacity --The two-edged sword

This is the fourth tip in a series on the different aspects of disk I/O performance and optimization for Oracle databases.

The following is the fourth tip in a series on the different aspects of disk I/O performance and optimization for Oracle databases. Each tip is excerpted from the not-yet-released Rampant TechPress book, "Oracle disk I/O tuning," by Mike Ault. Check back to the main series page for upcoming installments.

Mike Ault

Mike Ault is one of SearchOracle.com's Oracle Internals experts. Mike is senior Oracle consultant with Burleson Consulting, and one of the leading names in Oracle technology.

To view Mike's expert responses or to ask him a question, click here.


Disk capacity -- The two-edged sword

While data transfer rates from disks have grown in direct proportion to disk speed, disk data capacity has been growing exponentially. This results in a two-edged sword that cuts us if we only plan for volume by reducing our IO capacity, or cuts us budget wise if we really plan based on IO needs. What this means is that while the amount of data we can store has been increasing on a per-disk basis, the speed at which we can access that data has decreased. For example, look at table 1-1.

Max Capacity Drives/terabyte Average Access Time (msec) MB/s/Drive Transfer Rate (total)
9 gig 112 9.9 8.5 952
18 gig 56 7.7 14 728
36 gig 28 5.4 23 544
73 gig 14 5.6 33 462
180 gig 6 4.16 58 348
Table 1-1: Comparison of IO Capacity Verses Drive Size

So to achieve the same IO capacity as we had with our 112-9 gigabyte disks we would need to buy 2.7 (952/348) times the needed capacity of 180 gigabyte drives even with their superior access times and MB/s transfer rates. The values in table 1-1 reflect the performance values when that drive capacity was the maximum available. Of course as we saw in Figure 1.7, if we replace the old 9 gig drives with the new 40 gig (36 gig formatted) drives with the sustained transfer rate of 58 MB/s we get 28*58 or a total transfer rate of 1624 MB/s which would require 28 of either the new 73 or 180 gig drives in order to match the IO rate from the 28-40 gig drives.

So if we used the new 40 gig drives, we could expect better IO transfer rates of up to 70 percent based on IO rate, while if we bought the 180 gig drives based on storage capacity alone we would see a decrease in IO capacity of over 270%. This is why IO capacity should be the driving factor in disk drive purchase, not storage volume per disk.

Recent research shows that the more loaded a disk drive is (volume wise) the poorer it performs, generally speaking you should shoot for only filling drives to at most 50-60 percent of their total capacity.

I guess it all boils down to you must know the expected IO rate from your database and plan the number of disk drives based on the required IO rate, not only on the amount of space required, or you could find yourself volume rich but IO capacity poor. In addition, don't plan to get exactly the volume of disks you need, to get maximum performance, double that number allowing for only a 50-60 percent by volume usage.

Click to buy the book, "Oracle disk I/O tuning," by Mike Ault.


About the author

Mike Ault is a SearchOracle.com expert and a senior Oracle consultant with Burleson Consulting, and one of the leading names in Oracle technology. The author of more than 20 Oracle books and hundreds of articles in national publications, Mike Ault has five Oracle Masters Certificates and was the first popular Oracle author with his landmark book "Oracle7 administration and management." Mike also wrote several of the "Exam Cram" books, and enjoys a reputation as a leading author and Oracle consultant. Ask Mike a question today!


This was last published in July 2004

Dig Deeper on Oracle database performance problems and tuning

Start the conversation

Send me notifications when other members comment.

Please create a username to comment.

-ADS BY GOOGLE

SearchDataManagement

SearchBusinessAnalytics

SearchSAP

SearchSQLServer

TheServerSide.com

SearchDataCenter

SearchContentManagement

SearchHRSoftware

Close