Abstract
Large scale distributed data stores rely on optimistic replication to scale and remain highly available in the face of network partitions. Managing data without coordination results in eventually consistent data stores that allow for concurrent data updates. These systems often use anti-entropy mechanisms (like Merkle Trees) to detect and repair divergent data versions across nodes. However, in practice hash-based data structures are too expensive for large amounts of data and create too many false conflicts. Another aspect of eventual consistency is detecting write conflicts. Logical clocks are often used to track data causality, necessary to detect causally concurrent writes on the same key. However, there is a nonnegligible metadata overhead per key, which also keeps growing with time, proportional with the node churn rate. Another challenge is deleting keys while respecting causality: while the values can be deleted, perkey metadata cannot be permanently removed without coordination. We introduce a new causality management framework for eventually consistent data stores, that leverages node logical clocks (Bitmapped Version Vectors) and a new key logical clock (Dotted Causal Container) to provides advantages on multiple fronts: 1) a new efficient and lightweight anti-entropy mechanism; 2) greatly reduced per-key causality metadata size; 3) accurate key deletes without permanent metadata. © IFIP International Federation for Information Processing 2015.

Abstract
Strongly consistent systems supporting distributed transactions can be prone to high latency and do not tolerate partitions. The present trend of using weaker forms of consistency, to achieve high availability, poses notable challenges in writing applications due to the lack of linearizability, e.g., to ensure global invariants, or perform mutator operations on a distributed datatype. This paper addresses a specific problem: the exactly-once transfer of a "quantity" from one node to another on an unreliable network (coping with message duplication, loss, or reordering) and without any form of global synchronization. This allows preserving a global property (the sum of quantities remains unchanged) without requiring global linearizability and only through using pairwise interactions between nodes, therefore allowing partitions in the system. We present the novel quantity-transfer algorithm while focusing on a specific use-case: a redistribution protocol to keep the quantities in a set of nodes balanced; in particular, averaging a shared real number across nodes. Since this is a work in progress, we briefly discuss the correctness of the protocol, and we leave potential extensions and empirical evaluations for future work.

Abstract
Data aggregation is a fundamental building block of modern distributed systems. Averaging based approaches, commonly designated gossip-based, are an important class of aggregation algorithms as they allow all nodes to produce a result, converge to any required accuracy, and work independently from the network topology. However, existing approaches exhibit many dependability issues when used in faulty and dynamic environments. This paper describes and evaluates a fault tolerant distributed aggregation technique, Flow Updating, which overcomes the problems in previous averaging approaches and is able to operate on faulty dynamic networks. Experimental results show that this novel approach outperforms previous averaging algorithms; it self-adapts to churn and input value changes without requiring any periodic restart, supporting node crashes and high levels of message loss, and works in asynchronous networks. Realistic concerns have been taken into account in evaluating Flow Updating, like the use of unreliable failure detectors and asynchrony, targeting its application to realistic environments.

Abstract
Pure operation-based (op-based) Conflict-free Replicated Data Types (CRDTs) are generic and very efficient as they allow for compact solutions in both sent messages and state size. Although the pure op-based model looks promising, it is still not fully understood in terms of practical implementation. In this paper, we explain the challenges faced in implementing pure op-based CRDTs in a real system: the well-known in-memory cache key-value store Redis. Our purpose of choosing Redis is to implement a multi-master replication feature, which the current system lacks. The experience demonstrates that pure op-based CRDTs can be implemented in existing systems with minor changes in the original API. © 2016 Copyright held by the owner/author(s).

Abstract
State-based CRDTs allow updates on local replicas without remote synchronization. Once these updates are propagated, possible conflicts are resolved deterministically across all replicas. d-CRDTs bring significant advantages in terms of the size of messages exchanged between replicas during normal operation. However, when a replica joins the system after a network partition, it needs to receive the updates it missed and propagate the ones performed locally. Current systems solve this by exchanging the full state bidirectionally or by storing additional metadata along the CRDT. We introduce the concept of join-decomposition for state-based CRDTs, a technique orthogonal and complementary to delta-mutation, and propose two synchronization methods that reduce the amount of information exchanged, with no need to modify current CRDT definitions. © 2016 Copyright held by the owner/author(s).

Abstract
Conflict-free Replicated Data Types (CRDTs) are data abstractions (registers, counters, sets, maps, among others) that provide a relaxed consistency model called Eventual Consistency. Current designs for CRDT counters do not scale, having a size linear with the number of both active and retired nodes (i.e., nodes that leave the system permanently after previously manipulating the value of the counter). In this paper we present a new counter design called Borrow-Counter, that provides a mechanism for the retirement of transient nodes, keeping the size of the counter linear with the number of active nodes.