Read can be cached in memory, speed is about 4GB/s. If your entity is about 100kb, you can do 40,000 get() in a second.
A put() needs about 3 writes and 1 read, each writes needs at least 10ms seek time. Considering the network latency and disk write time, most entities cannot be written more than 5 times in a second. 2010/2/3 marcdmarc <[email protected]>: > Hello, > > I am trying to get clarification on a statistic given by Brett > Slatkin's google i/o talk on building scalable apps on app engine. > This is the talk I am referencing. > http://sites.google.com/site/io/building-scalable-web-applications-with-google-app-engine > > In the discussion, Brett mentions writes have a rate of 100 seeks per > second where the size and shape of your data actually determining the > write throughput of an entity. He then goes on to say that "You can > think of this as being the maximum write throughput for a single > entity on disk." > > To me, this statement means that a single entity can be written up to > a maximum of 100 times per second. I would like to clarify that my > interpretation of Brett's statement is correct. > > If anyone could clarify my understanding to be correct, I would > appreciate any input that people have. > > Best, > > Marc > > -- > 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. > > -- 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.
