RestoreMaster may not receive all acks. for the last command, i.e., finishRestore,
because RestoreLoaders and RestoreAppliers exit immediately after sending the ack.
If the ack is lost, it will not be resent.
This commit also removes some unneeded code.
This commit passes 50k random tests without errors.
1) Use the runRYWTransaction for simple DB access
2) Replace some printf with TraceEvent
3) Remove printf not used in debugging
4) Avoid wait inside the condition in loop-choose-when for
the core routine of restore worker, loader and applier.
5) Rename Restore.actor.cpp to RestoreWorker.actor.cpp since
the file only has functionalities related to restore worker.
Passed correctness test
1) Add sendBatchRequests and getBatchReplies
sendBatchRequests is a generic actor to send requests without
processing replies.
getBatchReplies is similar to sendBatchRequests expect that
it returns the reply to caller.
2) Share applier interface to loaders by using RequestStream,
instead of using DB.
Create RestoreSysInfo struct, similar purpose as DBInfo, for
the restore system information that are shared among restore workers.
The current code uses one restore interface to handle the work
for all restore roles, i.e., master, loader and applier.
This makes it harder to review or maintain or scale.
This commit split the restore into multiple roles by mimicing FDB
transaction system:
1) It uses a RestoreWorker as the process to host restore roles;
This commit assumes one restore role per RestoreWorker; but
it should be easy to extend to support multiple roles per RestoreWorker;
2) It creates 3 restore roles:
RestoreMaster: Coordinate the restore process and send commands to the other two roles;
RestoreLoader: Parse backup files to mutations and send mutations to appliers;
RestoreApplier: Sort received mutations and apply them to DB in order.
Compilable version. To be tested in correctness.
Meng Xu