[GitHub] [openwhisk] yl3469 commented on issue #2846: surface more of the inner data around system overhead and init time

[GitBox <gi...@apache.org>]

yl3469 commented on issue #2846:
URL: https://github.com/apache/openwhisk/issues/2846#issuecomment-872239033


   Hello,
   
   Thank you so much for this commit. I was wondering if you could elaborate more on how the interpretation should be changed for the topmost component in a sequence? 
   For example, currently, I have two very short actions in a sequence (i.e., I checked that the execution time should be 0 for each action), and the results read from CouchDB are as follows:
   
   ```
   start = 10008,
   end = 10159,
   duration = 15
   waitTime = 0 
   initTime = 0
   latency = 15
   (commTime = 13) 
   
   ```
   
   Another example:
   
   ```
   start = 0,
   end = 197,
   duration = 27,
   waitTime = 1,
   initTime = 0,
   latency = 28,
   commTime = 24
   
   ```
   Note that I computed commTime = start Time of the second action - end time of the first action, which is using an internal timer inside the function. 
   
   I noticed that duration = end-start; duration + wait + init = latency for an action. However this does not hold true for a sequence record.
   I was wondering could you please shed more light on what is the gap? How would you interprete the time for the sequence?
   
   Thank you!
   
   Regards


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: issues-unsubscribe@openwhisk.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org