News for hackers. Stuff that matters.
Re:MySQL is bazillion times faster than MemSQL by roel_v on Tuesday June 26, 2012 @03:07PM (#4163632)
"And what's different is that MemSQL translates you SQL query into extremely efficient C++ code."

What does this mean? Does the SQL get converted into actual C++ source code, then compiled with an internal C++ compiler? That seems like a weird thing to do. Or is it translated directly into an AST? If yes, I can't imagine other db's not doing it? I don't understand the claim being made here.

Re:MySQL is bazillion times faster than MemSQL by jhugg on Tuesday June 26, 2012 @03:27PM (#4163705)
Yes, they compile SQL statements into linux binaries using a bundled GNU compiler toolchain.

I am also curious if there is some way the developers have demonstrated the benefits of this approach vs. what other systems do. Most of the CPU time in a simple query in VoltDB is spent in networking, validating and suffering the cache-miss pain of walking index data structures. I can't see clearly how compiling to native code makes any of that much faster.

Re:MySQL is bazillion times faster than MemSQL by tigerBL00D on Tuesday June 26, 2012 @04:17PM (#4163894)
In-memory storage layer is very efficient. There are no buffer pool pages to manage or cache misses that result in I/O. That puts an accent on what goes on between storage engine and network, that is on query execution. Tight loops in native code is a good way to cut down on CPU cycles required to evaluate a query.