I/O Read-Ahead In SQL Server

Kendra Little shows how read-ahead works, using the example of index seeks:

Looking at an actual execution plan, I dig into the index seek operator and it shows me information about the physical IO. Almost all of the requests were read-ahead reads.

Read-ahead is a mechanism that SQL Server can use when it’s pulling a lot of information from disk. Instead of pulling 8K pages onesy-twosy-threesy, SQL Server can suck up big chunks of pages from disk with a vacuum cleaner.

If you’re running developer or enterprise edition, you may get a larger vacuum cleaner.

Read-ahead is a good piece of functionality, but those reads still have a cost associated, and the cheapest read is the read you don’t do.

Related Posts

Running SQL Server On Cluster Shared Volumes

Sreekanth Bandarla continues a series on clustered shared volumes: In the previous part of this series, we have seen what a cluster shared volume is and what are the advantages and other considerations to keep in mind when deploying CSVs for SQL Server workloads. In this article, I will walk though actual installation of a failover cluster Instance […]

Read More

Switching To Managed Disks In Azure

Chris Seferlis walks us through an easy method to convert unmanaged disks to managed disks in Azure: First off, why would you want a managed disk over an unmanaged one? Greater scalability due to much higher IOPs and storage limits. There’s no longer the need to add additional storage accounts when you’re adding disk space, […]

Read More

Categories

October 2017
MTWTFSS
« Sep Nov »
 1
2345678
9101112131415
16171819202122
23242526272829
3031