back to article LexisNexis open sources Hadoop challenger

A super-computer architecture that crunches big data for banks, police, and spooks will soon be open sourced as a super-fast alternative to the Googlesque Hadoop. LexisNexis Risk Solutions is opening up its High Performance Computing Cluster (HPCC), a system written in C++ that it claims is four-times faster than Hadoop when …

COMMENTS

This topic is closed for new posts.
Mushroom

To reignite the C++/ Java debate once again...

Simply because I think its funny, and interesting.

This is the perfect type of system to write in C++ (or D?)

High performance required per node, years in the making, tuned up to its eyeballs to run JSON (eh, did I read that or make it up)... I'm assuming you write your logic in C++ as well though. In any case, this is absolutely the right tool for the job, as the C++ bods will no doubt crow about.

For the 95% (just made that up, did you like it?) of other coding duties, it has been surpassed by other languages that have different compromises that are better suite for the domain they are in.

So, dare I say it, C++ is extremely good in its domain, but it really should stay there.

Let the bun fight commence!

0
0
Go

That's not much of a debate.

The right tool for the job choosing thing is accepted wisdom, though just what this boils down to is at least partly taste and preference. Acknowledge that and there's very little left to get religious about. But do care what you ask for, you just might get it. To wit:

That made-up 95% is the "routine tasks like programming" that gets outsourced to India.

See what I did there? At your service, sir.

0
0
Silver badge
Alien

"Years in the making"

Yup, C++ can take away that feather and put it in its cap, I have no beef with that.

Not everyone can afford enough C++ coders and years though.

No beef icon? A cattle mutilator, then.

0
0

1000 nodes

I'm not going to get into an argument of C++ vs Java, but note that if you have 1000 hadoop nodes, that gives you 12-24PB of storage. Regardless of performance, its the storage that has an edge there, along with the layers on top.

that said, lots of room to improve hadoop performance and job startup time, contributions are welcome.

0
0

This post has been deleted by a moderator

Silver badge
Holmes

What!

"The company has not yet announced which open-source license it will use, but it will not be a copy-left license, the company said, permitting for derivations and improvements bearing the HPCC name."

I do think that copy-left does not mean what the author of these words thinks it means.

0
0
This topic is closed for new posts.

Forums