This is before adding the "asc" index and after adding the "last_activity_at" index. The major difference is the lack of spikes and consistent RPM. This test was run for 3 minutes with a small course vs large course on a 20:1 ratio. The large course used is BerkeleyX/ColWri2.2x/1T2014 (~25,000 threads, 30,000 comments) , while the small course is SMES/ASLCx/1T2015 (1700 Threads, 3047 comments).  Image Added
| Name | reqs | # | fails | Avg | Min | Max | Median | req/s | 95% |
|---|
| Large | GET_comment_list | 46 | 0(0.00%) | 443 | 207 | 1155 | 370 | 0 | 840 | | | GET_thread | 2404 | 0(0.00%) | 225 | 168 | 1275 | 210 | 0.7 | 290 | | | GET_thread_list | 1296 | 0(0.00%) | 489 | 181 | 1104 | 480 | 0.6 | 830 | | | PATCH_comment | 45 | 0(0.00%) | 490 | 221 | 2060 | 450 | 0 | 780 | | | PATCH_thread | 53 | 0(0.00%) | 489 | 174 | 1912 | 410 | 0.1 | 1100 | | Small | GET_comment_list | 877 | 0(0.00%) | 211 | 154 | 1072 | 200 | 0.3 | 300 | | | GET_thread | 55710 | 2(0.00%) | 198 | 141 | 1562 | 190 | 28.2 | 260 | | | GET_thread_list | 29694 | 0(0.00%) | 449 | 147 | 3919 | 430 | 13.2 | 810 | | | PATCH_comment | 875 | 4(0.46%) | 340 | 184 | 1584 | 320 | 0.2 | 560 | | | PATCH_thread | 1038 | 9(0.86%) | 259 | 150 | 1055 | 240 | 0.5 | 420 |
|