Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Expand
title BerkeleyX/ColWri2.2x/1T2014 (~25,000 threads, 30,000 comments)

Namereqs#failsAvgMinMaxMedianreq/s95%
GETGET_comment_list2290(0.00%)34615624302900.2 
GETGET_thread149330(0.00%)221151184721014.8610 
GETGET_thread_list80050(0.00%)49316819064906.4290 
PATCHPATCH_comment2260(0.00%)47721745684000.2820 
PATCHPATCH_thread2592(0.77%)39318823123300.2790 
Expand
titleTsinghuaX/00690242_2x/3T2014 (29 threads, 155 comments)

 

Namereqs#failsAvgMinMaxMedianreq/s95%
GETGET_comment_list5140(0.00%)1761335141700.2240
GETGET_thread297340(0.00%)164126216216019.2220
GETGET_thread_list157380(0.00%)195123142715010.1340
PATCHPATCH_comment5120(0.00%)31016723772900.4520
PATCHPATCH_thread5068(1.56%)23913632932200.3380

...

    In a new test, it was found that SMES/ASLCx/1T2015 (1700 Threads, 3047 comments) was slowing down over time. To identify what was happening, a new course was seeded which we will call DAPI (1000 Threads, 500 comments). In the analysis of the forums, we saw that the median body size was 250 characters. Our PATCH operations can be 4, 250, 1000, 5000, or 10000 characters. This test was run over 10 hours. The decrease in response time needed to be addressed.

Expand

 

 

Over time DAPI (1000 threads, 500 comments) slowed down over time.

Namereqs#failsAvgMinMaxMedianreq/s95%
GETGET_comment_list157930(0.00%)22016231162000.2340
GETGET_thread9550971(0.00%)214-8450920023.8290
GETGET_thread_list5109210(0.00%)44515559542011.6810
PATCHPATCH_comment157920(0.00%)33718738513200.2490
PATCHPATCH_thread17333164(0.94%)27316130192500.5400

When running a similar test with a more verbose output, we clearly saw that the page size

 


 

    

     

NEXT STEPS:

Run with new index.

...