THE SQL Server Blog Spot on the Web

Welcome to - The SQL Server blog spot on the web Sign in | |
in Search

Tibor Karaszi

Is there and overhead to RPC events?

This blog has moved! You can find this content at the following new location:

Published Monday, January 11, 2010 12:31 PM by TiborKaraszi
Filed under: ,

Comment Notification

If you would like to receive an email when updates are made to this post, please register here

Subscribe to this post's comments using RSS



djo said:

Great post and examples.   It taught me a ton.

February 5, 2011 9:51 AM

jack kangas said:

There is something else happening in the RPC:Completed step - some sort of cleanup that I can't find documentation for.

(pls don't comment on users code - I don't have control and my head already hurts)

I have a load progrram that is doing 30M select and then insert and every 1/2 second or so - either the insert or select will have a duration of about 1.5 seconds - while the pageiolatch_sh and writelog waits go up.

But the other 99% of the time the select takes .55ms and insert takes .8ms (800 microseconds).

There is no Un_prepare step being sent in - is that the cause/reason for the sudden uptick.

I don't see any memory grants pending and the disk queue lengths don't show anything - disk queue legnth jumps up and then back down to zero.

Any clues jack"dot"kangas"attsign"cbc"dash"companies"dot"com

February 11, 2011 9:44 AM

Anon said:

Awesome expirement.  Very helpful.

August 4, 2013 11:37 AM

db said:

I'm not sure you're tests reflect real world usage (especially for the 2nd experiment). You're creating a single command object and executing it in a loop without changing the input values.

I ran an experiment with changing inputs and the additional COM overhead to bind all the procedure arguments caused the 'parameterized as stored procedure' variant to run slower.

October 12, 2015 6:37 PM

Leave a Comment

Privacy Statement