| Timestamp WaitEventID Descr | Waits | WaitTime |
| 10:36:40 | 29 waiting for regular buffer read to complete | 111 | 500 |
| 10:36:40 | 52 waiting for i/o on MASS initated by another task | 12 | 200 |
| 10:36:40 | 150 waiting for a lock | 3 | 100 |
| 10:36:40 | 171 waiting for CTLIB event to complete | 125 | 100 |
| Timestamp WaitEventID Descr | Waits | WaitTime |
| 10:41:45 | 215 waiting on run queue after sleep | 1 | 315600 |
| 10:41:45 | 29 waiting for regular buffer read to complete | 106 | 700 |
| 10:41:45 | 51 waiting for last i/o on MASS to complete | 48 | 500 |
| 10:41:45 | 55 wait for i/o to finish after writing last log page | 64 | 400 |
| 10:41:45 | 214 waiting on run queue after yield | 67 | 400 |
| 10:41:45 | 52 waiting for i/o on MASS initated by another task | 26 | 200 |
| 10:41:45 | 124 wait for mass read to finish when getting page | 7 | 100 |
| Timestamp WaitEventID Descr | Waits | WaitTime |
| 10:47:53 | 215 waiting on run queue after sleep | 0 | 171500 |
| 10:47:53 | 29 waiting for regular buffer read to complete | 874 | 158500 |
| 10:47:53 | 171 waiting for CTLIB event to complete | 25 | 2500 |
Above is the MDA output (deltas between observations) for a spid that I'm troubleshooting. These are the wait events that have WaitTime > 0 for my spid.
My concern is waitevent 215 (waiting for run queue after sleep). I understand that there is physical io going on here (events 29,51,52,55), but why the 315 seconds of waiting on single event of 215 (run queue), followed by 171 seconds (with waits=0, weird)? This is a single SQL statement updating a TEXT field, and taking around 5 minutes (holding locks) to complete. Are the physical io's of event 29 simply amplifying event 215 numbers? Hoping to get an MDA mad scientist's input here 