These slides were presented at FOSDEM, the conference where I just spoke about FB & HBase. I went to the talk.
There were some glaringly obvious problems that came out during the Q&A. Someone asked how many regions he had. Didnt know. Are you network or IO or CPU bottlenecked? Didn't know. Too many of the results for HBase and other DBs, he just said "I'm not sure what's going on here".
The publisher was a grad student who seemed to have done this work for his masters. I'm glad we have ppl interested in analyzing HBase, but you need to understand that this is not a thorough evaluation. The main thing for him was learning how all these DBs worked at a high level and thinking of novel benchmark scenarios.
Sent from my iPhone
On Feb 11, 2011, at 7:32 AM, "Stack" <[EMAIL PROTECTED]> wrote:
> That paper looked like complete nonsense. The slide on HBase has
> misunderstandings about how we work. The data size is miniscule.
> We get slower when you add nodes (?).
> On Fri, Feb 11, 2011 at 7:01 AM, David Engfer <[EMAIL PROTECTED]> wrote:
>> Not sure what the issue was there with HBase, but would this be much
>> improved if they tried it again with 0.90?
>> David Engfer