if request/second dropped, nothing could be done. latency has nothing to do with request/second. if nothing else, it will increase the instance count, google have no control over request/second.
On Wed, Mar 14, 2012 at 9:47 AM, thecheatah <thechea...@gmail.com> wrote: > Hi, > > I am noticing that the latency on my HR based application went up > significantly. My app does a simple read and a write. It is taking > over 1 second to do this operation. In M/S the this operation was < > 100ms > > Even under multi threading, my machines are not processing as many > requests as my M/S app could handle. My costs have gone up by 50% > after having switched from M/S. Is this normal? > > Last night a single machine handled about 6-7 requests/second. Today > it has dropped to 4. Nothing has changed. The request are generated by > devices and thus are very consistent. > > It seems that the latency on the HR datastore is causing my cost to > increase. I have no control over this latency. Is this something I can > get money back for? > > Ravneet > > -- > 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-appengine@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. > > -- 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-appengine@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.
