Here is an interesting bit of chartness for people struggling with issues since the Sept 13th Maintenance period.
http://amistrongeryet.com/op_detail.jsp?op=gae_db_readNonTransactional The Median datastore (no transaction) read is great.. 32.9 ms (twice as fast as the median SimpleDB inconsistent read) http://amistrongeryet.com/op_detail.jsp?op=simpledb_readInconsistent But, the outliers (for the app this guy uses for stat collection) have gone "wild" since Sept 13th.. before the 13th he was recording sub-500 ms outliers on reads.. After the 13th (granted I'm guessing the big spike on the 13th is related to the actual datastore downtime), you see the 99th percentile latency growing steadily above 500 ms.. up to 1000 ms and beyond. Personally, I don't mind the wild westiness of Appengine since it seems to be leading towards faster and faster reads even with a growing userbase. (but, I can see how someone with a customer facing app would get a little angsty) The datastore histogram (from the link above) may have a fatter tail on the right side.. but its pushing further to the left than Simple DB.. 10th percentile reads are sub-10 ms.. Here is the main area that collects all the data: http://amistrongeryet.com/dashboard.jsp -- You received this message because you are subscribed to the Google Groups "Google App Engine" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/google-appengine?hl=en.
