Bingbing Liu, On Fri, Mar 12, 2010 at 1:36 PM, Bingbing Liu <rucb...@gmail.com> wrote:
> We did some test on on Cassandra, and the benchmark is from Section 7 of > the BigTable paper “Bigtable: A Distributed Storage System for Structured > Data”, the benchmark task includes: random write, random read, sequential > write, and sequential read. The test results made us puzzled. We use a > cluster of 5 nodes (each node has a 4 cores cpu , 4G memory).The data for > test is a table with 4,000,000 records each of which is 1000 bytes. The > test results are as follows: > Sequential write: 875124 ms > Sequential read: 1972588 ms > Random read: 43331738 ms > Random write: 20193484 ms > We wondered why the speed of sequential write are so faster than the speed > of sequential read, and why the speed of sequential write are so faster than > that of random write? We think that the speed of read should be faster than > that of data write, but the results are just the opposite, would you please > give us some explanations, thanks a lot! > Please read the BigTable paper, carefully, again. They have similar characteristics and describe why this is the case. I think you'll find that behavior you observed is quite consistent with the theory of it all (and reading the text to which Jonathan has pointed you, will essentially give you the same reasons). It is part and parcel of the storage architecture of "BigTable" type systems. - m.
