Re: [boost] NuDB: A fast key/value insert-only database for SSD drives in C++11

Subject: Re: [boost] NuDB: A fast key/value insert-only database for SSD drives in C++11
From: Vinnie Falco (vinnie.falco_at_[hidden])
Date: 2017-03-29 00:49:27

On Tue, Mar 28, 2017 at 8:26 PM, Lee Clagett via Boost
<boost_at_[hidden]> wrote:
> This is simulating a write I/O error, not a power failure. Even with
> the assumption that a returned `fsync` has fully stored the data on
> disk, the recovery algorithm could be opening a log file which called
> `write` but never returned from `fsync`. That file could have enough
> "space" for a bucket, but lack the proper contents of the bucket
> itself. There is an inherent race between writing and the completion of
> an `fsync` that will go unnoticed by the current recovery algorithm on
> some filesystem configurations.

Okay, I can almost understand what you're saying. Perhaps a bit more
guidance would help. Can you walk me through the scenario you're
describing, making reference to the current commit algorithm? Its
here:
https://github.com/vinniefalco/NuDB/blob/master/include/nudb/impl/basic_store.ipp#L559

My goals is to improve the fail_file used in the tests to capture your case.

Thanks