Distributed storage. Mirror algo extension for automatic recovery.

Hi.

I'm pleased to announce sixth release of the distributed storage subsystem, which allows to form a storage on top of remote and local nodes, which in turn can be exported to another storage as a node to form tree-like storages.

This release includes mirroring algorithm extension, which allows to store 'age' of the given node on the underlying media.

In this case, if failed node gets new media, which does not contain correct 'age' (unique id assigned to the whole storage during initialization time), the whole node will be marked as dirty and eventually resynced.

This allows to have completely transparent failure recovery - failed node can be just turned off, its hardware fixed and then turned on. DST core will detect connection reset and automatically reconnect when node is ready and resync if needed without any special administrator's steps.

This patchset has been split into 4 parts:
0 - this introduction
1 - core files
2 - network state machine
3 - documentation and algorithms

Hope they all will find its way into mail lists.

Further TODO list includes:
* new redundancy algorithm (complex, low priority)
* some thoughts about distributed filesystem tightly connected to DST

Thank you.

Homepage:
http://tservice.net.ru/~s0mbre/old/?section=projects&item=dst

	Evgeniy Polyakov