Log In Sign Up

Detecting Incorrect Behavior of Cloud Databases as an Outsider

by   Cheng Tan, et al.

Cloud DBs offer strong properties, including serializability, sometimes called the gold standard database correctness property. But cloud DBs are complicated black boxes, running in a different administrative domain from their clients; thus, clients might like to know whether the DBs are meeting their contract. A core difficulty is that the underlying problem here, namely verifying serializability, is NP-complete. Nevertheless, we hypothesize that on real-world workloads, verifying serializability is tractable, and we treat the question as a systems problem, for the first time. We build Cobra, which tames the underlying search problem by blending a new encoding of the problem, hardware acceleration, and a careful choice of a suitable SMT solver. cobra also introduces a technique to address the challenge of garbage collection in this context. cobra improves over natural baselines by at least 10x in the problem size it can handle, while imposing modest overhead on clients.


page 1

page 2

page 3

page 4


CWD: A Machine Learning based Approach to Detect Unknown Cloud Workloads

Workloads in modern cloud data centers are becoming increasingly complex...

Handling Trust in A Cloud Based Multi Agent System

Cloud computing is an opened and distributed network that guarantees acc...

Secure Consistency Verification for Untrusted Cloud Storage by Public Blockchains

This work presents ContractChecker, a Blockchain-based security protocol...

Efficient Black-box Checking of Snapshot Isolation in Databases

Snapshot isolation (SI) is a prevalent weak isolation level that avoids ...

Verifying Equivalence of Database-Driven Applications

This paper addresses the problem of verifying equivalence between a pair...