Showing papers on "Rollback published in 2016"

The two-stage Aegean extension, from localized to distributed, a result of slab rollback acceleration

Abstract: Back-arc extension in the Aegean, which was driven by slab rollback since 45 Ma, is described here for the first time in two stages. From Middle Eocene to Middle Miocene, deformation was localized ...

Transaction Healing: Scaling Optimistic Concurrency Control on Multicores

Abstract: Today's main-memory databases can support very high transaction rate for OLTP applications. However, when a large number of concurrent transactions contend on the same data records, the system performance can deteriorate significantly. This is especially the case when scaling transaction processing with optimistic concurrency control (OCC) on multicore machines. In this paper, we propose a new concurrency-control mechanism, called transaction healing, that exploits program semantics to scale the conventional OCC towards dozens of cores even under highly contended workloads. Transaction healing captures the dependencies across operations within a transaction prior to its execution. Instead of blindly rejecting a transaction once its validation fails, the proposed mechanism judiciously restores any non-serializable operation and heals inconsistent transaction states as well as query results according to the extracted dependencies. Transaction healing can partially update the membership of read/write sets when processing dependent transactions. Such overhead, however, is largely reduced by carefully avoiding false aborts and rearranging validation orders. We implemented the idea of transaction healing in TheDB, a main-memory database prototype that provides full ACID guarantee with a scalable commit protocol. By evaluating TheDB on a 48-core machine with two widely-used benchmarks, we confirm that transaction healing can scale near-linearly, yielding significantly higher transaction rate than the state-of-the-art OCC implementations.

Lock-free Transactions without Rollbacks for Linked Data Structures

Abstract: Non-blocking data structures allow scalable and thread-safe accesses to shared data. They provide individual operations that appear to execute atomically. However, it is often desirable to execute multiple operations atomically in a transactional manner. Previous solutions, such as software transactional memory (STM) and transactional boosting, manage transaction synchronization in an external layer separated from the data structure's own thread-level concurrency control. Although this reduces programming effort, it leads to overhead associated with additional synchronization and the need to rollback aborted transactions.In this work, we present a new methodology for transforming high-performance lock-free linked data structures into high-performance lock-free transactional linked data structures without revamping the data structures' original synchronization design. Our approach leverages the semantic knowledge of the data structure to eliminate the overhead of false conflicts and rollbacks. We encapsulate all operations, operands, and transaction status in a transaction descriptor, which is shared among the nodes accessed by the same transaction. We coordinate threads to help finish the remaining operations of delayed transactions based on their transaction descriptors. When transaction fails, we recover the correct abstract state by reversely interpreting the logical status of a node.In our experimental evaluation using transactions with randomly generated operations, our lock-free transactional lists and skiplist outperform the transactional boosted ones by 40% on average and as much as 125% for large transactions. They also outperform the alternative STM-based approaches by a factor of 3 to 10 across all scenarios. More importantly, we achieve 4 to 6 orders of magnitude less spurious aborts than the alternatives.

Method and system for processing distributed transaction

Abstract: Provided are a method and a system for processing distributed transaction. The method comprises: after a transaction branch processing unit corresponding to each transaction branch of distributed transaction receives a transaction branch SQL statement, the transaction branch SQL statement being sent to an isolation controller for locking operation; the isolation controller inquiring from a database to obtain each data line corresponding to the transaction branch SQL statement, and after inquiring from a transaction lock table of the database to obtain a locking record corresponding to each data line, through writing the locking records into the transaction lock table, to lock the data lines which are not locked in each data line of the distributed transaction; the locking records including global transaction identifiers of the distributed transaction; after locking operation is successful, the transaction branch processing unit executing the transaction branch SQL statement; and after the transaction branch processing unit receives the a transaction branch submission instruction or a transaction branch rollback instruction, indicating an isolation controller to delete the locking records corresponding to the global transaction identifiers from the transaction lock table according to the global transaction identifiers.

On Effective and Efficient Quality Management for Approximate Computing

Abstract: Approximate computing, where computation quality is traded off for better performance and/or energy savings, has gained significant tractions from both academia and industry. With approximate computing, we expect to obtain acceptable results, but how do we make sure the quality of the final results are acceptable? This challenging problem remains largely unexplored. In this paper, we propose an effective and efficient quality management framework to achieve controlled quality-efficiency tradeoffs. To be specific, at the offline stage, our solution automatically selects an appropriate approximator configuration considering rollback recovery for large occasional errors with minimum cost under the target quality requirement. Then during the online execution, our framework judiciously determines when and how to rollback, which is achieved with cost-effective yet accurate quality predictors that synergistically combine the outputs of several basic light-weight predictors. Experimental results demonstrate that our proposed solution can achieve 11% to 23% energy savings compared to existing solutions under the target quality requirement.

Atomic RMI: A Distributed Transactional Memory Framework

Abstract: This paper presents Atomic RMI, a distributed transactional memory framework that supports the control flow model of execution. Atomic RMI extends Java RMI with distributed transactions that can run on many Java virtual machines located on different network nodes. Our system employs SVA, a fully-pessimistic concurrency control algorithm that provides exclusive access to shared objects and supports rollback and fault tolerance. SVA is capable of achieving a relatively high level of parallelism by interweaving transactions that access the same objects and by making transactions that do not share objects independent of one another. It also allows any operations within transactions, including irrevocable ones, like system calls, and provides an unobtrusive API. Our evaluation shows that in most cases Atomic RMI performs better than fine grained mutual-exclusion and read/write locking mechanisms. Atomic RMI also performs better than an optimistic transactional memory in environments with high contention and a high ratio of write operations, while being competitive otherwise.

Instant Recovery with Write-Ahead Logging: Page Repair, System Restart, Media Restore, and System Failover, Second Edition

Abstract: Traditional theory and practice of write-ahead logging and of database recovery focus on three failure classes: transaction failures (typically due to deadlocks) resolved by transaction rollback; system failures (typically power or software faults) resolved by restart with log analysis, "redo," and "undo" phases; and media failures (typically hardware faults) resolved by restore operations that combine multiple types of backups and log replay. The recent addition of single-page failures and single-page recovery has opened new opportunities far beyond the original aim of immediate, lossless repair of single-page wear-out in novel or traditional storage hardware. In the contexts of system and media failures, efficient single-page recovery enables on-demand incremental "redo" and "undo" as part of system restart or media restore operations. This can give the illusion of practically instantaneous restart and restore: instant restart permits processing new queries and updates seconds after system reboot and instant restore permits resuming queries and updates on empty replacement media as if those were already fully recovered. In the context of node and network failures, instant restart and instant restore combine to enable practically instant failover from a failing database node to one holding merely an out-of-date backup and a log archive, yet without loss of data, updates, or transactional integrity. In addition to these instant recovery techniques, the discussion introduces self-repairing indexes and much faster offline restore operations, which impose no slowdown in backup operations and hardly any slowdown in log archiving operations. The new restore techniques also render differential and incremental backups obsolete, complete backup commands on a database server practically instantly, and even permit taking full up-to-date backups without imposing any load on the database server. Compared to the first version of this book, this second edition adds sections on applications of single-page repair, instant restart, single-pass restore, and instant restore. Moreover, it adds sections on instant failover among nodes in a cluster, applications of instant failover, recovery for file systems and data files, and the performance of instant restart and instant restore.

Transparent Speculative Parallelization of Discrete Event Simulation Applications Using Global Variables

Abstract: Parallelizing (compute-intensive) discrete event simulation (DES) applications is a classical approach for speeding up their execution and for making very large/complex simulation models tractable. This has been historically achieved via parallel DES (PDES) techniques, which are based on partitioning the simulation model into distinct simulation objects (somehow resembling objects in classical object-oriented programming), whose states are disjoint, which are executed concurrently and rely on explicit event-exchange (or event-scheduling) primitives as the means to support mutual dependencies and notification of their state updates. With this approach, the application developer is necessarily forced to reason about state separation across the objects, thus being not allowed to rely on shared information, such as global variables, within the application code. This implicitly leads to the shift of the user-exposed programming model to one where sequential-style global variable accesses within the application code are not allowed. In this article we remove this limitation by providing support for managing global variables in the context of DES code developed in ANSI-C, which gets automatically parallelized. Particularly, we focus on speculative (also termed optimistic) PDES systems that run on top of multi-core machines, where simulation objects can concurrently process their events with no guarantee of causal consistency and actual violations of causality rules are recovered through rollback/recovery schemes. In compliance with the nature of speculative processing, in our proposal global variables are transparently mapped to multi-versions, so as to avoid any form of safety predicate verification upon their updates. Consistency is ensured via the introduction of a new rollback/recovery scheme based on detecting global variables' reads on non-correct versions. At the same time, efficiency in the execution is guaranteed by managing multi-version variables' lists via non-blocking algorithms. Furthermore, the whole approach is fully transparent, being it based on automatized instrumentation of the application software (particularly ELF objects). Hence the programmer is exposed to the classical (and easy to code) sequential-style programming scheme while accessing any global variable. An experimental assessment of our proposal, based on a suite of case study applications, run on top of an off-the-shelf Linux machine equipped with 32 CPU-cores and 64 GB of RAM, is also presented.

Piccolo: A Fast and Efficient Rollback System for Virtual Machine Clusters

Abstract: Rollback is an effective technique to resume the system execution from a recorded intermediate state upon failures. However, in virtualized environments, rollback of a virtual machine cluster (VMC) produces high network traffic and long service disruption, consequentially imposing significant overhead both on network and applications. In this paper, we propose Piccolo, a fast and efficient rollback system, to restore a VMC from snapshot files over datacenter network. We exploit the similarity among VMC snapshots and leverage multicast to deliver the identical pages across VMs placed on disperse hosts, thereby bypassing transmission of a large number of unnecessary pages. %Second, we analyze the impact on network traffic of varying VM placements in datacenter network, formulate the traffic aware placement as an optimization problem, and design a two-tier approximation algorithm that efficiently solves the problem. In addition to presenting Piccolo, we detail its implementation, and evaluate it by a set of experiments. The results show that Piccolo could achieve a significant reduction in terms of total sent data, network traffic and rollback latency compared to the existing generic rollback techniques.

Data backup and recovery method and data backup and recovery device based on snapshot online rollback

Abstract: The invention discloses a data backup and recovery method and a data backup and recovery device based on snapshot online rollback. The method comprises the steps of in establishing a snapshot by a user, performing address dividing on a source roll according to block grade, and allocating a COW metadata set for recording COW information of the source roll; when a snapshot rollback instruction is received, firstly notifying a snapshot proxy for performing brushing processing, notifying a snapshot module after brushing processing is finished, and starting a background data rollback thread; copying data on the snapshot roll on the source roll by the background data rollback thread according to the COW information of the metadata set; and on the condition that a read-write request exists in the source roll in the rollback process, performing re-directioned reading and delayed writing according to whether COW is performed on the data block number of a read-write source roll and the current rollback process. The data backup and recovery method and the data backup and recovery device can realize data backup of a certain time point of the source roll; and through supplied online rollback technology, interruption of data accessing into the source roll is not required, thereby quickly restoring the data on the source roll to an available snapshot time point for supplying services to host applications.

Visual data-analytics of large-scale parallel discrete-event simulations

Abstract: Parallel discrete-event simulation (PDES) is an important tool in the codesign of extreme-scale systems because PDES provides a cost-effective way to evaluate designs of high-performance computing systems. Optimistic synchronization algorithms for PDES, such as Time Warp, allow events to be processed without global synchronization among the processing elements. A rollback mechanism is provided when events are processed out of timestamp order. Although optimistic synchronization protocols enable the scalability of large-scale PDES, the performance of the simulations must be tuned to reduce the number of rollbacks and provide an improved simulation runtime. To enable efficient large-scale optimistic simulations, one has to gain insight into the factors that affect the rollback behavior and simulation performance. We developed a tool for ROSS model developers that gives them detailed metrics on the performance of their large-scale optimistic simulations at varying levels of simulation granularity. Model developers can use this information for parameter tuning of optimistic simulations in order to achieve better runtime and fewer rollbacks. In this work, we instrument the ROSS optimistic PDES framework to gather detailed statistics about the simulation engine. We have also developed an interactive visualization interface that uses the data collected by the ROSS instrumentation to understand the underlying behavior of the simulation engine. The interface connects real time to virtual time in the simulation and provides the ability to view simulation data at different granularities. We demonstrate the usefulness of our framework by performing a visual analysis of the dragonfly network topology model provided by the CODES simulation framework built on top of ROSS. The instrumentation needs to minimize overhead in order to accurately collect data about the simulation performance. To ensure that the instrumentation does not introduce unnecessary overhead, we perform a scaling study that compares instrumented ROSS simulations with their noninstrumented counterparts in order to determine the amount of perturbation when running at different simulation scales.

Efficient disaster recovery across heterogeneous storage systems

Abstract: Systems for storage system rollover and rollback. A data mover agent is installed on a source storage system to capture disaster recovery data and send to a target system. Upon receiving a rollover event signal, a virtualized controller creates one or more replica user virtual machines running on the target system that serve to replicate functions of the user virtual machines from the source storage system. The virtualized controller on the target system converts the target disaster recovery data from a first format to a second format to facilitate use of the target disaster recovery data by the replica user virtual machines. Rollback is initiated when the target system receives a rollback event signal. Differences in the data that have occurred between the rollover event and the rollback signal are calculated and sent to the rollback system. The calculated differences are applied to a registered snapshot on the rollback system.

Automatic application error detection and rollback

Abstract: An automatic application error detection and rollback service can manage access to at least two versions of an application based on error reports. The versions of the application can include a previous version and a new version that can be an updated version of the previous version. Access to the previous version of the application may include a previous version URL and access to the new version of the application may include a new version URL. The rollback service may provide the new version URL to a plurality of clients. The rollback service may then receive error information of the new version for at least one individual client of a plurality of clients running the new version. Based on the error information, the rollback service may automatically change the new version URL to the previous version URL for the at least one individual client.

Data assimilation in discrete event simulations - a rollback based Sequential Monte Carlo approach

Abstract: Data assimilation is an analysis technique which aims to incorporate measured observations into a dynamic system model in order to produce accurate estimates of the current state variables of the system. Although data assimilation is conventionally applied in continuous system models, it is also a desired ability for its discrete event counterpart. However, data assimilation has not been well studied in discrete event simulations yet. This paper researches data assimilation problems in discrete event simulations, and proposes a rollback based implementation of the Sequential Monte Carlo (SMC) method - the rollback based SMC method. To evaluate the accuracy of the proposed method, an identical-twin experiment in a discrete event traffic case is carried out and the results are presented and analyzed.

Opacity proof for CaPR+ algorithm

Abstract: In this paper, we describe an enhanced Automatic Checkpointing and Partial Rollback algorithm(CaPR+) to realize Software Transactional Memory(STM) that is based on continuous conflict detection, lazy versioning with automatic checkpointing, and partial rollback. Further, we provide a proof of correctness of CaPR+ algorithm, in particular, Opacity, a STM correctness criterion, that precisely captures the intuitive correctness guarantees required of transactional memories. The algorithm provides a natural way to realize a hybrid system of pure aborts and partial rollbacks. We have also implemented the algorithm, and shown its effectiveness with reference to the Red-black tree micro-benchmark and STAMP benchmarks. The results obtained demonstrate the effectiveness of the Partial Rollback mechanism over pure abort mechanisms, particularly in applications consisting of large transaction lengths.

Extended-HyperWall: Hardware support for rollback secure virtualization

Abstract: Virtualization is a vital part of computing today. Rollback is an important feature to be supported by virtualization. However, hackers leverage rollback and pose serious security threats to systems running in a virtualized environment. The aim of this paper is to identify such security threats and propose a comprehensive solution. In this paper, we propose Extended-HyperWall architecture as a solution to security of Virtual Machines (VMs) in a fully virtualized environment. Extended-HyperWall architecture is an integration of HyperWall with Rollback Sensitive Data Memory with Architecture Assistance (RSDM-A). HyperWall is a system that proposes hardware support to ensure confidentiality and integrity of a VM's data, with an assumption that hypervisor cannot be trusted. RSDM-A is an architectural support to a virtualized system that separates rollback sensitive data from rollback non-sensitive data which is one of the major causes of threats that arises due to rollback. Extended-HyperWall integrates CIP-table (Confidentiality and Integrity Table to ensure confidentiality and integrity of data) and RSDM-table (Rollback Sensitive Data Memory to protect the system from rollback attacks). The paper illustrates the design of Extended-HyperWall, and its implementation on the Xen Hypervisor kernel for testing and analysis.

Software management method and apparatus

Abstract: The invention provides a software management method. The method comprises the steps of receiving a version rollback instruction input for software input by a user; judging a currently installed first version of software and at least one second version lower than the first version meet a version rollback rule or not; if yes, collecting related information of performing version rollback for the software; and performing version rollback operation of the software according to the related information. The invention furthermore provides a software management apparatus. By utilizing the method and apparatus, the security of the software of the installed second version lower than the first version is ensured and the data security of the user is guaranteed; new and old versions of the software in a software rollback process can be quickly uninstalled and installed, so that zero user operation in uninstallation and installation processes is ensured and automated uninstallation and installation are realized; and meanwhile, personalized demand configuration of the user can be automatically realized in the uninstallation and installation processes, so that the user experience is greatly improved.

Rollback method and apparatus for upgraded mobile terminal version

Abstract: The invention discloses a rollback method and apparatus for an upgraded mobile terminal version. The apparatus comprises an obtaining module, a rollback module, and a restarting module. The obtaining module is used for obtaining a rollback difference packet of a corresponding system version when a mobile terminal receives a system version rollback command; the rollback module is used for restarting a mobile terminal system to carry out the rollback difference packet writing operation; and the restarting module is used for restarting the mobile terminal system again. According to the invention, the version rollback operation is consistent with the upgrading operation and can be executed conveniently; and after the rollback operation, the user data can be kept. Moreover, the operation is simple and system risk is low. Besides, a few network bandwidths are occupied during different packet rollback and usage.

Transaction consistency achieving method and system for isomerous data compound object

Abstract: The invention discloses a transaction consistency achieving method and a transaction consistency achieving system for an isomerous data compound object. The method comprises the following steps: S1, starting, S2, preparation, and S3, execution. The step S1 of starting comprises: initiating a transaction request: providing various different types of data sources, and requesting transaction processing on the data sources; setting basic information of transactions to be processed; the step S2 of preparation comprises: preprocessing the transactions: respectively altering data of each data source of each transaction to obtain an initial processing result; storing progress information of the transaction: acquiring and storing information of each process in the transaction processing process; the step S3 of execution comprises: checking all progress states of the transaction in sequence; judging whether all the transaction progresses are successful: finally altering and submitting the data according to altering results, or performing data rollback. According to the transaction consistency achieving method and the transaction consistency achieving system for the isomerous data compound object, the transaction consistency of the isomerous data compound object is maintained.

Automatic backup and rollback method and device

Abstract: The invention provides an application program backup and rollback method and device. An executive user only needs to set an input parameter set in advance. In the actual backup and rollback processes, the executive user only needs to issue an application program backup or rollback instruction, and other processes do not need to be executed. All the backup or rollback processes are automatically executed, and accordingly rollback accuracy and backup efficiency can be improved.

Efficient disaster rollback across heterogeneous storage systems

Abstract: Systems for storage system rollover and rollback. A data mover agent is installed on a source storage system to capture disaster recovery data and send to a target system. Upon receiving a rollover event signal, a virtualized controller creates one or more replica user virtual machines running on the target system that serve to replicate functions of the user virtual machines from the source storage system. The virtualized controller on the target system converts the target disaster recovery data from a first format to a second format to facilitate use of the target disaster recovery data by the replica user virtual machines. Rollback is initiated when the target system receives a rollback event signal. Differences in the data that have occurred between the rollover event and the rollback signal are calculated and sent to the rollback system. The calculated differences are applied to a registered snapshot on the rollback system.

Using Rollback Avoidance to Mitigate Failures in Next-Generation Extreme-Scale Systems

Abstract: High-performance computing (HPC) systems enable scientists to numerically model complex phenomena in many important physical systems. The next major milestone in the development of HPC systems is the construction of the first supercomputer capable executing more than an exaflop, 10 floating point operations per second. On systems of this scale, failures will occur much more frequently than on current systems. As a result, resilience is a key obstacle to building next-generation extreme-scale systems. Coordinated checkpointing is currently the most widely-used mechanism for handling failures on HPC systems. Although coordinated checkpointing remains effective on current systems, increasing the scale of today’s systems to build next-generation systems will increase the cost of fault tolerance as more and more time is taken away from the application to protect against or recover from failure. Rollback avoidance techniques seek to mitigate the cost of checkpoint/restart by allowing an application to continue its execution rather than rolling back to

Streamlined creation and updating of OLAP analytic databases

Abstract: The technology disclosed relates to creating and frequently updating multiple online analytic processing (OLAP) analytic databases from an online transaction processing (OLTP) transaction updatable system that includes transaction commit, rollback, and field level security capabilities. It also relates to transparently decoupling extraction from rebuilding of frequently updated OLAP analytic databases from the OLTP transaction updatable system.

Configuration rollback method and device

Abstract: The invention provides a configuration rollback method and device. The method comprises the following steps of: executing a no command corresponding to a target forward configuration command while needing to cancel configuration corresponding to the target forward configuration command in current configuration; and executing pre-set target operation used for cancelling the configuration corresponding to the target forward configuration command if the no command corresponding to the target forward configuration command is failed to execute. By means of application of the embodiment of the invention, the rollback failure condition due to the fact that the no command corresponding to the forward configuration command does not exist can be avoided.

A Gateway-Centered Workflow Rollback Decision Model Toward Autonomous Workflow Process Recovery

Abstract: In enacting a workflow process model, it is very important to control and trace each instance's execution as well as to keep it recoverable. Especially, the recoverability issue implies that the underlying workflow management system is able to not only provide an automatic error-detection functionality on its running exceptions but also to equip a very autonomous recovery mechanism to deal with the detected exceptional and risky situations. As a theoretical approach to resolve the autonomous workflow recovery issue, this paper tries to formalize a rollback-point decision tree structure based upon gateway-activities of a corresponding workflow process model, which is named as a gateway-centered workflow rollback decision model. We strongly believe that the proposed model ought be one of those impeccable trials and pioneering contributions to improve and advance the capability of recovery in enacting workflow process models.

Method of controlling rollback in a continuously variable transmission

Abstract: A control system for a vehicle having an infinitely variable transmission (IVT) having a ball planetary variator (CVP), providing a smooth and controlled operation. In some embodiments, the control system implements a rollback prevention sub-module. The rollback prevention sub-module is adapted to receive a number of signals, for example, a signal indicative of a transmission output shaft speed and a signal indicative of a commanded CVP shift actuator position. In some embodiments, the rollback prevention sub-module determines a correction value to be applied to the commanded CVP shift actuator position. The correction value is based at least in part on the transmission output shaft speed signal. In some embodiments, the rollback prevention sub-module is adapted to monitor and determine the deactivation of a CVP shift actuator.

Distributed transaction realization method

Abstract: The invention discloses a distributed transaction realization method. The realization method comprises the steps of 1: in a distributed system, applying addition, deletion and modification operations of data to a database and a message queue first when a module of an application initiates a distributed transaction, and performing overall submitting or rollback; and 2: asynchronously extracting the data from the message queue and submitting the data to the other database by the other module in the application. Compared with the prior art, the distributed transaction realization method has the advantages that the performance of the distributed transaction can be effectively improved, the concurrent processing capability of the application using the distributed transaction is enhanced, the user experience of the application using the distributed transaction is improved, the practicality is high, the application range is wide, and the popularization is easy.

Methods for detecting out-of-order sequencing during journal recovery and devices thereof

Abstract: A method, non-transitory computer readable medium and storage server computing device that allocates monotonically increasing sequence numbers to storage operations based on an order of the storage operations corresponding entries in a log. The storage operations are sequenced including by identifying a subset of the storage operations that are parallelizable. A file system data structure is allocated and populated with data associated with one of the storage operations. A determination is made when a rollback is detected based on whether a replay ledger index field of the file system data structure comprises one of the sequence numbers that is greater than another one of the sequence number corresponding to the one of the storage operations. The another one of the sequence numbers is inserted into the replay ledger index field, when the determining indicates that a rollback is not detected.

Server version updating method and device

Abstract: The invention discloses a server version updating method and device, and relates to the technical field of servers. The method includes the steps that a version updating file is obtained; the ratio of servers conducting version updating in a server cluster is determined according to the version updating file; the servers to be updated in the server cluster are determined according to the ratio; the version updating file is pushed to the servers to be updated to update the versions of the servers to be updated. By means of the scheme, when it is found that the version updating file has problems, rollback can be conducted in time, and normal service processing of the server cluster will not be affected.