For what it’s worth, our datastore is written in C++ and very similar to C* in terms of functionality and semantics; whatever performance delta there is there, it mostly comes down to reducing I/O and taking advantage of locality of reference(both in actual I/O, but also in terms of accessing memory/data-structures whatever). There is no real benefit to moving to another language in order to better address those.
@markpapadakis On Dec 19, 2013, at 11:56 PM, Roman Vasilyev <rvasil...@netflix.com> wrote: > This is what I expected as an answer, that effort just fully destroying any > benefits. > All what I can hear is just better not touch stuff which works and find > improvements different way. > Change (algorithms/caching/...) where I agree, and seems like bottleneck will > be FS I/O or network delays. > > Just want to thank you for all answers on my question. > > ------ Original Message ------ > From: "Eric Evans" <eev...@sym-link.com> > To: dev@cassandra.apache.org; "Roman Vasilyev" <rvasil...@netflix.com> > Sent: 12/19/2013 1:47:03 PM > Subject: Re: C* engine > >> [ Roman Vasilyev ] >>> Don't want to rise "holy war". Just let me share my crazy thoughts. >>> I believe it could improve Cassandra speed and robustness. >> >> That's an awfully large reset button you want to press, presumably the >> benefits will justify the enormity of effort? What are we talking >> here, 10x improvement? 100x improvement? More? >> >>> What people will say if I propose to have Cassandra engine written >>> in C/C++, and this engine will give you ability to run extensions in >>> Java, Groovy and bunch other languages like Perl/Python/Ruby? >> >> No one can stop you from working on this; Good luck >> >> >> P.S. Please subscribe to the list (dev-subsrc...@cassandra.apache.org) >> >> -- >> Eric Evans >> eev...@sym-link.com >
