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.

Reply via email to