Do you have your benchmarking code available somewhere? Its hard to give a general answer, but we'd be happy to have a look at what causes the slow down in your use case.
jake Sent from my phone, please excuse typos and brevity. On Mar 21, 2014 4:42 AM, "Reihane Boghrati" <[email protected]> wrote: > Hi, > > I am running experiments with different kinds of workloads using Neo4j > client-server architecture. > When I run the system with actions that query the database, my observed > throughput is constant > throughout the experiment. However, with a mix of read (query) and write > (update to nodes and > edge creation/deletion) actions, the throughput starts high and drops > after hundreds of seconds. > The drop is sharp from a thousand to a few hundred actions per second. > This happens only when > my workload is multi-threaded. (The throughput does not drop with one > thread.) > > Is there a good explanation for this? > > -- > You received this message because you are subscribed to the Google Groups > "Neo4j" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > For more options, visit https://groups.google.com/d/optout. > -- You received this message because you are subscribed to the Google Groups "Neo4j" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
