moonlander

But the author fails to prove that fsync() is in any way the bottleneck for common I/O operations in everyday use of a smartphone.

This makes very little sense. The author shows a fsync() benchmark comparing an actualy fsync (Pixel on ext4 without nobarrier) with a nobarrier (no-op fsync) alternative. The only thing this benchmark shows is that a no-op is faster than the real thing.

I am using SQLite (yeah) for blockchain data and the C++ LEMON library for in-memory graph operations. Every module is able to update incrementally.

You're right, done except for the footer! Thanks for your input!

Backend is up again, sorry :) .

Yes, computation is done in memory and is reasonably fast, with some clever caching. Right now the backend server is overloaded - I am working on it and you will be able to try it with custom addresses very soon.

I wish I had seen this earlier! :) Thank you!

Thank you extrapolate and ajaimk! Yes, the backend is suffering a bit - but it will be back in a few minutes.

This is just a very limited demo of what BitIodine can do! For more info click on "About" or wait till new features ("Get insights") make it to the web interface.