An update. As an experiment, instead of sending the requests sequentially in the loop I now send every request from within a new thread. It improved things quite a bit. The requests arrive to the server milliseconds apart. The end result is that the client is done within about 5 seconds for the same work load that used to take 12 sec/item (overall that's about 2 orders of magnitude faster)
However, instead of 200-500 ms it now takes more than 4 _seconds_ for a single request to complete on the server. Assuming app engine allocates 30 handlers per app you would think 25 items could have been processed at the same time as not much else was happening in the app at the same time. However it definitely looks like all the requests were processed by the same single handler. Any clues? -- You received this message because you are subscribed to the Google Groups "Google App Engine" group. To post to this group, send email to google-appeng...@googlegroups.com. To unsubscribe from this group, send email to google-appengine+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/google-appengine?hl=en.