cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Peter Schuller <>
Subject Re: Cassandra benchmarking on Rackspace Cloud
Date Mon, 19 Jul 2010 17:30:11 GMT
Another thing: Is the py_stress traffic definitely non-determinstic
such that each client will generate a definitely unique series of
requests? If all clients are deterministically requesting the same
sequence of keys, it would otherwise be plausible that they end up in
effective lock-step, if the bottleneck is serialized but the result of
it goes out in parallel to all clients.

(This is probably not the case but I'm not sure off hand about whether
there is anything in Cassandra's implementation that might be
compatible with this hypothesis, in terms of how concurrent requests
for the same key will be handled.)

/ Peter Schuller

View raw message