Forum Post: RE: The latches and the disk IO

  • Thread starter Thread starter Rob Fitzpatrick
  • Start date Start date
Status
Not open for further replies.
R

Rob Fitzpatrick

Guest
OK. My point was that I think the buffer pool scan portion of the checkpoint should be very fast, so some other portion of checkpoint processing is likely the culprit for your durations. Given the client's other apparent I/O problems, isn't it possible that even if there is one BI or AI buffer to flush during a checkpoint that it could be taking longer than it should?

Continue reading...
 
Status
Not open for further replies.
Back
Top