PAGELATCH_UP
Occurs when a task is waiting on a latch for a buffer that is not in an I/O request. The latch request is in Update mode.
Detailed Description​
Latches are lightweight, fast methods of managing concurrency on a specific resource.
The PAGELATCH_* group of latches are seen in management of data pages that have already been read into memory.
PAGELATCH_UP is waiting for a latch to be allocated in update (UP) mode so that a page can be modified.
How to reduce this wait​
Waits on the PAGELATCH_* series of latches can be caused by hot pages in tables or indexes where the update or concurrency rate is very high, or due to pressure on TempDB.
Tempdb issues can be investigated using this article Breaking Down TempDB Contention
Using the the Microsoft white paper on Diagnosing and Resolving Latch Contention will help you find out what is going on and point your in the right direction to resolve your issue.
Ezhil Arasu has written a blog article here on LinkedIn about diagnosing PAGELATCH_UP waits using DBmarlin.
Additional Links​
Search online​
If this article doesn't have the information you need you can try searching online. Remember, you can contribute suggestions to this page.