I suppose I shall add some data to this thread. I have a regular task than runs at 5 minute intervals for a given range of hours every day.
The task fetches some data from a remote url (actually from GData so it is from Google), processes it, and puts 8 entities to the datastore. I believe the 1.3.1 update was on February 10th. Here are some datapoints since that date (this is a range (max,min) of the total time taken for process during the day): 2-10-2010: 4-10 seconds 2-18-2010: 3-9 seconds 2-22-2010: 2-9 seconds 2-23-2010: 2-7 seconds 2-25-2010: 2-3 seconds 2-26-2010: 2-3 seconds So.. a combination of things could have happened.. the GData service is returning data consistently faster.. puts are slightly faster (this seemed to start this week with the minimum run time dipping below 3 seconds), and/or the cold start time for the process stabilized. Either way, the past two days, the max runtime for the process has dropped significantly. AND, as of this Monday put() times seem to have dropped a lot (percentage wise). Who knows if this performance change will hold.. or if it is just an anomaly. On Fri, Feb 26, 2010 at 7:29 PM, Thomas Johansson <[email protected]>wrote: > Can't speak for others, but our load times have gone from on average > 3-4 seconds from cold to 1-2 seconds, since the outage. The instances > seem to live longer as well, but most importantly the cold start has > been *much* better since then. > > On Feb 26, 7:11 pm, "Ikai L (Google)" <[email protected]> wrote: > > No, the outage wasn't related to a performance upgrade. There are any > number > > of reasons why your application isn't being cycled out. I'm curious as to > > whether other users see this or if they see the opposite effect. > > > > > > > > On Fri, Feb 26, 2010 at 9:13 AM, Blake <[email protected]> wrote: > > > I was seeing 7 second load times for my first request back into the > > > system after the JVM (must have) went to sleep. Now it's super fast, > > > as if the JVM wasn't sleeping. This is really great. > > > > > Is anyone else seeing this too? I wonder if the outage was a side > > > effect of a big performance push. > > > > > -- > > > 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]<google-appengine%[email protected]> > <google-appengine%[email protected]<google-appengine%[email protected]> > > > > > . > > > For more options, visit this group at > > >http://groups.google.com/group/google-appengine?hl=en. > > > > -- > > Ikai Lan > > Developer Programs Engineer, Google App Enginehttp:// > googleappengine.blogspot.com|http://twitter.com/app_engine > > -- > 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]<google-appengine%[email protected]> > . > For more options, visit this group at > http://groups.google.com/group/google-appengine?hl=en. > > -- 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.
