Re: *Measuring sql performance (elapsed time and scalability) by number of logical reads

  • From: "Radoulov, Dimitre" <cichomitiko@xxxxxxxxx>
  • To: "Andrey Kriushin" <Andrey.Kriushin@xxxxxxxx>
  • Date: Tue, 2 May 2006 23:15:17 +0200

[...]

The second is IFFS with 610 LIO in 72513 us.
Total is 1523 LIO..... AND 223005 us. Not 83118 us, right? Looks like we've found ~140 msec. And those 140 msec are not just hash value calculation, but also memory management (chunk allocation) in PGA, probably growing PGA itself etc.


Also, as somebody already mentioned, LIO time can vary significantly. 10605/913 ~= 11.6 us and 72513/610 ~= 119 us. The length of hash chains may count, for example. Well, on quiet instance that might be row processing time inside the block as well and not only the time to pin the buffer.
[...]

Thank you for your time and valuable feedback.
Anyway, correct me if I'm wrong, but I would expect those to be considered wait events, not service time.



Regards, Dimitre


-- //www.freelists.org/webpage/oracle-l


Other related posts: