Optimistic crash recovery without changing application messages

Optimistic Crash Recovery without Changing Application Messages

We present an optimistic crash recovery technique without any communication overhead during normal operations of the distributed system. Our technique does not append any information to the application messages, it does not suffer from the domino effect, and each processor rolls back at most once during recovery. We present three distributed rollback algorithms, their complexities, and correctn...

Crash Recovery

DEFINITION In contrast to transaction aborts, a crash is typically a major failure by which the state of the current database is lost or parts of storage media are unrecoverable (destroyed). Based on log data from a stable log, also called temporary log file, and the inconsistent and/or outdated state of the permanent database, system recovery has to reconstruct the most recent transaction-cons...

Efficient Transparent Optimistic Rollback Recovery for Distributed Application Programs

Existing rollback-recovery methods using consistent checkpointing may cause high overhead for applications that frequently send output to the “outside world,” since a new consistent checkpoint must be written before the output can be committed, whereas existing methods using optimistic message logging may cause large delays in committing output, since processes may buffer received messages arbi...

Detecting Locally Stable Predicates Without Modifying Application Messages

In this paper, we give an efficient algorithm to determine whether a locally stable predicate has become true in an underlying computation. Examples of locally stable predicates include termination and deadlock. Our algorithm does not require application messages to be modified to carry control information (e.g., vector timestamps), nor does it inhibit events (or actions) of the underlying comp...

Truthfulness of More Optimistic vs Less Optimistic Messages for Patients With Advanced Cancer.