cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hiller, Dean" <Dean.Hil...@nrel.gov>
Subject Re: cassandra performance looking great...
Date Fri, 07 Sep 2012 14:37:17 GMT
Now that would be cool.  Right now though, tooooo many other features need
to be added like a GUI on top of the ad-hoc query tool is the next top
priority so one can do any S-SQL statement and ad-hoc query the heck out
of a noSQL store.

We may even be able to optimize our queries to be even faster with a new
lookahead nested loop join that we have not implemented yet which fetches
the next block of data before we needed it for comparisons.  (DBMS only
has nested block loop join which blocks on disk I/O each time it reads a
block).

Dean

On 9/7/12 8:22 AM, "Edward Capriolo" <edlinuxguru@gmail.com> wrote:

>Try to get Cassandra running the TPH-C benchmarks and beat oracle :)
>
>On Fri, Sep 7, 2012 at 10:01 AM, Hiller, Dean <Dean.Hiller@nrel.gov>
>wrote:
>> So we wrote 1,000,000 rows into cassandra and ran a simple
>>S-SQL(Scalable SQL) query of
>>
>>
>> PARTITIONS n(:partition) SELECT n FROM TABLE as n WHERE n.numShares >=
>>:low and n.pricePerShare >= :price
>>
>> It ran in 60ms
>>
>> So basically playOrm is going to support millions of rows per
>>partition.  This is great news.  We expect the join performance to be
>>very similar since the trees of pricePerShare and numShares are really
>>no different than the join trees.
>>
>> Sooooo, millions of rows per partition and as many partitions as you
>>want, it scales wonderfullyŠ..CASSANDRA ROCKS!!!!
>>
>> Behind the scenes, there is a wide row per partition per index so the
>>above query behind the scenes has two rows each with 1,000,000 columns.
>>
>> Later,
>> Dean


Mime
View raw message