Vector approximate nearest neighbor search (ANNS) underpins search engines, recommendation systems, and advertising services. Recent advances in ANNS indexes make CPU a cost-effective choice for serving million-scale, in-memory vector search, yet per-core throughput remains constrained by memory access latency of vector reading and the compute intensity of distance evaluations in production deployments. With the growing scale of the business and advances in hardware, modern CCD-based multi-core CPUs have been widely deployed for high throughput in our services. However, we find that simply increasing core counts does not yield optimal performance scaling. To improve the efficiency of more cores from the CCD-based architecture, we analyze the distributions of real-world requests in our production environments. We observe high access locality in vector search in our online services and low cache utilization, resulting from overlooking the multi-chiplet nature of CCD based CPUs. Hence, we propose a workload- and hardware-aware thread orchestration framework at CCD-level that (i) provides a uniform interface for both inter-query parallel HNSW search and intra-query parallel IVF search, (ii) achieves cache-friendly and workload-adaptive mapping of task dispatching, and (iii) employs CCD-aware task stealing to address load imbalance. Applied to real production workloads from search, recommendation, and advertising services of Xiaohongshu (RedNote), our approach delivers up to 3.7x higher throughput and 30-90% reductions in P50 and P999 latency. In detail, compared with the original framework, the cache-miss ratio decreases by 6-30%, and the total CPU stall is reduced by 20-80%.

Many cloud databases provide fine-grained regular snapshots and sparsely deleted snapshots based on importance, and dynamically maintain large-scale snapshots to ensure data security and mine the value of cold data. However, in existing snapshot technologies, the write amplification feature of Copy-on-Write (CoW) introduces additional expensive I/O operations in a cloud environment. In Redirect-on-Write (RoW), the modified data blocks are scattered among the snapshots, resulting in a dependency between the snapshots, which seriously affects the recovery performance. In this paper, we observed that access to snapshots has the characteristics of locality and continuity. We therefore propose an efficient Batch-Based Snapshot index, called BBS, which batches snapshot indexes according to database workload and access behavior of snapshots. Specifically, we use two key techniques: Shared-Subtrees Indexing and Batch-Based Dividing, to perform split dependency of the snapshot index. The snapshot index dependency chain is divided into batches, and there is no dependency on snapshot indexes between batches. In-batch snapshot indexes reduce memory overhead by sharing subtrees. The index can directly locate data blocks instead of iterative traversal. At the same time, the design of the snapshot index deletion method is adapted to the snapshot sparse deletion model. We have implemented a working system in Ceph. Evaluation results on datasets demonstrate that, compared with existing techniques, BBS can effectively balance the overhead between index memory capacity and recovery time.

Emerging persistent memory (PM) technologies offer data persistence at close-to-DRAM latency, causing the legacy multi-layer storage stack to become a bottleneck. On the other hand, PM improves I/O efficiency while also introducing unique hardware features that require software modifications to exploit them. In this paper, we propose HYTE, a native table storage engine for hybrid memory, which abstracts the data service for the database’s table. HYTE performs a cross-layer design across the file system and storage engine to avoid the pitfalls of layered abstraction and provides SQL-compatible APIs. Meanwhile, it co-designs with PM’s properties to unlock the hardware’s performance potential. Furthermore, HYTE is hotness-aware and equipped with a suite of lightweight, customized fetching and eviction strategies. Our evaluation shows that HYTE can perform up to 1.4-7.2× better than existing state-of-the-art PM-based storage systems in industry and academia.

With the rapid development of storage and network technology, emerging high-performance hardware is being widely applied to the distributed storage cluster. However, existing distributed storage systems employing multi-layer abstractions to provide table data services result in leaving high-speed hardware under-exploited. In this paper, we propose TEngine, a native distributed table storage engine designed for NVMe SSD and RDMA. The key is that TEngine removes the file abstraction to construct table structures on the device directly. For metadata service, TEngine designs a decoupled single metadata server, reducing distributed coordination, easing the burden on the metadata node, and enabling localized data node access. For data service, TEngine optimizes the parallel processing capability of NVMe devices by integrating upper-level multi-thread parallel operations with lower-level NVMe devices' parallel I/O processing. Moreover, TEngine introduces a periodic pull-based data synchronization approach to transform data pushing into periodic data pulling, which offloads the synchronization burden from the leader to the followers. The experimental results show that TEngine outperforms state-of-the-art distributed storage systems using the same hardware environment.

With the development of AI generated content and LLM (Large Language Model), demands of vector management have brought prosperity to vector databases. However, the status that vectors cannot be retrieved before being indexed, harms timeliness of vector databases. Updating indexes immediately when adding new vectors, reduces throughput of storage. Due to this contradiction, when facing streaming data, using vector database solely in vector services cannot have it both ways: real-time searches and high-throughput storage. This paper proposes a vector buffer engine, Neos. It is designed for real-time unindexed-vector searches on streaming input and buffering vectors with high throughput before loading them into vector databases. On one hand, we build a lightweight storage on raw NVMe device and liberate throughput from indexes, to maximize storage performance. On the other hand, we realize direct NVMe-GPUs 110 stack and a CPU-GPU heterogeneous task architecture for low-latency unindexed-vector searches on streaming data. Experiments show that our approach performs with 1.5x to 3.4x bandwidth, as low as 20% latency compared to existing 110 stacks, and up to orders-of-magnitude higher vector storage throughput under concurrent RIW workloads. Further, N eos can handle real-time unindexed - vector searches with millisecond-level latency on streaming input, a capability that current vector systems lack.

The increasing capacity and reducing cost of the main memory made in-memory data analytics systems widely deployed as they could provide higher throughput and lower latency. Since the data resides in memory, computational throughput becomes a crucial factor in the performance of these systems rather than disk accesses. Single instruction multiple data (SIMD) is an effective mechanism to improve computational performance, which has been well studied to accelerate data analytics systems. However, the state-of-the-art methods focus on using SIMD more efficiently while neglecting scalar execution units.In this paper, we present the hybrid execution framework (HEF) to co-utilize SIMD and scalar execution units for the data analytics workload. We also extend the concept of pack to eliminate the data dependency between adjacent instructions, achieving shorter instruction execution intervals. Experimental results show that the hybrid execution achieves up to 2.38× and 1.45× better performance compared with the purely scalar and SIMD implementation on the star schema benchmark (SSB) queries, respectively. Besides, HEF performs better than the state-of-the-art system Voila for a majority of queries in SSB under all data scales.

Embedded systems have evolved tremendously in recent years. We perform a study on SQLite and find that the multiple layers of abstraction drastically reduce bandwidth utilization. To minimize the bandwidth loss in the I/O path, we propose Lunar, a novel native table storage engine. Lunar performs a cross-layer design across the database and file system to avoid the pitfalls of multi-layer abstraction while providing SQL-compatible APIs. It employs a type-aware storage layout that considers the access patterns of different data types. Then, Lunar designs a variable-size allocator to reduce fragmentation and optimize RAM and I/O bandwidth usage. Further, considering the limited resources on embedded devices, Lunar employs a modular architecture that enables selecting modules on demand. It also offers optional consistency modes to make a trade-off between resource consumption and consistency. Experiments show that Lunar achieves higher bandwidth utilization, outperforming state-of-the-art approaches while consuming fewer resources.

Virtualization brings the benefits of utilization and scalability to the multi-tenant cloud platforms. However, the hypervisor, as one of the foundations in virtualization, is challenging to survive under various malicious attacks due to its large attack surface. This article presents a novel group detection framework for the hypervisor code integrity, called Outlier . In an Outlier group, each host contains two parts. One is a distributed detection protocol, called Co-protocol , and the other is a detection interface, called Checker . The Co-protocol constructs trust for the integrity detection within an Outlier group. With the Co-protocol, each Checker conducts reliable integrity detection on the hypervisor code, and then the potential “outlier” host is perceived. We implement our Outlier prototype on the Xen hypervisor and evaluate its overhead. Experiments show that the introduction of the Outlier has few impacts on the performance of the virtualized systems.

Cloud computing is convenient to provide adequate resources for tenants. However, since multiple tenants share the underlying hardware resources, malicious tenants can use the shared processor to launch cache-based attacks. Such attacks can help malicious tenants steal private data of other tenants bypassing isolation mechanisms provided by the system, resulting in information leakage. Moreover, Spectre and Meltdown vulnerabilities can even extract memory contents arbitrarily with the help of cache attacks. Therefore, cache-based attacks pose a serious threat to the security of cloud platforms. To defeat such attacks, many detection methods have been proposed. However, most methods induce high false positives because they completely rely on the hardware performance counters (HPCs) and detect attacks with static criteria. To solve this problem, this article proposes a self-feedback detector named CBA-Detector to detect cache-based attacks in real time. Specifically, CBA-Detector first uses machine learning technologies to create models for identifying suspicious programs with abnormal hardware behaviors, then analyzes suspicious programs from the instruction level to identify real attacks and provide feedback. Based on the feedback, the models can be updated to further improve their detection accuracy. As our experiments show, CBA-Detector can accurately identify cache-based attacks in real time and introduces a little overhead. Besides, the misjudgment rate decreases with the running time.

Although real-time analytics on the up-to-date dataset has become an emerging demand, many big data systems are still designed for offline analytics. Particularly, for critical applications like Fintech,transactional data ingestionensures a timely, always-correct, and scalable dataset. To carry out append-only ingestion, existing OLTP/HTAP systems are based on strict transactions with imperfect scalability, while NoSQL-like systems support scalable but relaxed transactions. How to ensure essential transactional guarantees without harming scalability seems to be a non-trivial issue. This paper proposesKarstto bring transactional data ingestion for existing offline analytics. We notice that blockingtwo-phase commit(2PC) to resolve transactional data ingestion is a performance killer for the partitioned analytical systems. Karst introduces a scalable protocol calledmetadata-oriented commit(MOC) that converts each distributed transaction into multiple partial transactions to avoid 2PC. Moreover, to ingest massive data into plenty of partitions, Karst also employs lazy persistence, lightweight logging, and optimized data traffic. In experiments, Karst could achieve up to about 2x$\sim$10x performance over relevant systems and also shows remarkable scalability.

Distributed in-memory computing systems have dramatic performance improvement over traditional disk-based systems, which makes them widely used in large-scale data processing applications. Unfortunately, uneven and unpredictable data distributions caused by data skew have a significant impact on the performance. In Spark, when data skew happens, some tasks will process much more data than other tasks and become the performance bottleneck. The traditional approaches to handling data skew are based on sampling and repartitioning, which incur additional overhead. In this paper, we divide data skew in distributed data processing systems into intra-node and inter-node skew. Based on data stealing, we proposed DS2to handle both intra-node and inter-node data skew. It aims to improve the performance under data skew, without involving additional overhead. DS2first balances the skewed data distribution in the local and then handles the inter-node skew by RDMA during execution. It achieves up to 2.96× speedup on the aggregation operator and 2.81× speedup on the join operator.

With the development of the big data ecosystem, large-scale data analytics has become more prevalent in the past few years. Apache Spark, etc., provide a flexible approach for scalable processing upon massive data. However, they are not designed for handling computing-intensive workloads due to the restrictions of JVM runtime. In contrast, GPU has been the de facto accelerator for graphics rendering and deep learning in recent years. Nevertheless, the current architecture makes it difficult to take advantage of GPUs and other accelerators in the big data world.

Most database systems rely on complex multi-layer and compatibility-oriented storage stacks, which results in sub-optimal database management system (DBMS) performance and significant write amplification. A heavy storage stack can be tolerated in the slow disk era because its storage overhead is completely overlapped by hardware delay. However, with advances in storage technologies, emerging NVMe devices have reached the same level of latency as software, which in turn has caused the storage stack to become a new bottleneck. On the other hand, NVMe devices not only improve I/O efficiency but also introduce distinctive hardware features that require software modifications to take advantage of themTo fully exploit the hardware potential of NVMe devices, we propose a lightweight native storage stack called Lightstack to minimize the software overhead. The core of Lightstack is an efficient table storage engine, LATTE, which abstracts the essential data service of the database's 2D table. LATTE is designed from the ground up to use NVMe devices efficiently. It directly accesses NVMe devices to reduce single I/O latency and utilizes a parallel scheduling strategy to leverage multiple deep I/O queues and CPU cores. Besides, undo logging on heterogeneous storage is proposed to mitigate the write amplification further. We also implement a working prototype and evaluate it with standard benchmarks on the Intel Optane DC P4800X NVMe SSD and the DC P3608 Series NVMe SSD. Experimental results show that LATTE has up to 3.6-6.5× the throughput of MySQL's InnoDB and MyRocks engines, with latency as low as 28% in the same hardware environment.

Nowadays, GPUs have achieved high throughput computing by running plenty of threads. However, owing to disjoint memory spaces of discrete CPU-GPU systems, exploiting CPU and GPU within a data processing pipeline is a non-trivial issue, which can only be resolved by the coarse-grained workflow of “copy-kernel-copy” or its variants in essence. There is an underlying bottleneck caused by frequent inter-processor invocations for fine-grained batch sizes. This article presents XeFlow that enables streamlined execution by leveraging hardware mechanisms inside new generation GPUs. XeFlow significantly reduces costly explicit copy and kernel launching within existing fashions. As an alternative, XeFlow introduces persistent operators that continuously process data through shared topics, which establish efficient inter-processor data channels via hardware page faults. Compared with the default “copy-kernel-copy” method, XeFlow shows up to 2.4χ 3.1χ performance advantages in both coarse-grained and fine-grained pipeline execution. To demonstrate its potentials, this article also evaluates two GPU-accelerated applications, including data encoding and OLAP query.

To fully utilize the resources of a main memory database cluster, we additionally take the independent parallelism into account to parallelize multiple pipelines of one query. However, scheduling resources to multiple pipelines is an intractable problem. Traditional static approaches to this problem may lead to a serious waste of resources and suboptimal execution order of pipelines, because it is hard to predict the actual data distribution and fluctuating workloads at compile time. In response, we propose a dynamic scheduling algorithm, List with Filling and Preemption (LFPS), based on two novel techniques. (1) Adaptive filling improves resource utilization by issuing more extra pipelines to adaptively fill idle resource “holes” during execution. (2) Rank-based preemption strictly guarantees scheduling the pipelines on the critical path first at run time. Interestingly, the latter facilitates the former filling idle “holes” with best efforts to finish multiple pipelines as soon as possible. We implement LFPS in our prototype database system. Under the workloads of TPC-H, experiments show our work improves the finish time of parallelizable pipelines from one query up to 2.5X than a static approach and 2.1X than a serialized execution.

SIMD is an instruction set in mainstream processors, which provides the data level parallelism to accelerate the performance of applications. However, its advantages diminish when applications suffer from heavy cache misses. To eliminate cache misses in SIMD vectorization, we present interleaved multi-vectorizing (IMV) in this paper. It interleaves multiple execution instances of vectorized code to hide memory access latency with more computation. We also propose residual vectorized states to solve the control flow divergence in vectorization. IMV can make full use of the data parallelism in SIMD and the memory level parallelism through prefetching. It reduces cache misses, branch misses and computation overhead to significantly speed up the performance of pointer-chasing applications, and it can be applied to executing entire query pipelines. As experimental results show, IMV achieves up to 4.23X and 3.17X better performance compared with the pure scalar implementation and the pure SIMD vectorization, respectively.

To fully use the advanced resources of a main memory database cluster, we take independent parallelism into account to parallelize multiple pipelines of one query. However, scheduling resources to multiple pipelines is an intractable problem. Traditional static approaches to this problem may lead to a serious waste of resources and suboptimal execution order of pipelines, because it is hard to predict the actual data distribution and fluctuating workloads at compile time. In response, we propose a dynamic scheduling algorithm, List with Filling and Preemption (LFPS), based on two techniques. (1) Adaptive filling improves resource utilization by issuing more extra pipelines to adaptively fill idle resource "holes" during execution. (2) Cost-based preemption strictly guarantees scheduling the pipelines on a critical path first at run time. We implement LFPS in our prototype database system. Under the workloads of TPC-H, experiments show our work improves the finish time of parallelizable pipelines from one query up to 2.3X than a static approach and 1.7X than a serialized execution.

Hardware techniques and environments underwent significant transformations in the field of information technology, represented by high-performance processors and hardware accelerators characterized by abundant heterogeneous parallelism, nonvolatile memory with hybrid storage hierarchies, and RDMA-enabled high-speed network. Recent hardware trends in these areas deeply affect data management and analysis applications. In this paper, we first introduce the development trend of the new hardware in computation, storage, and network dimensions. Then, the related research techniques which affect the upper data management system design are reviewed. Finally, challenges and opportunities are addressed for the key technologies of data management and analysis in new hardware environments.

With the emergence of the big data age, the issue of how to obtain valuable knowledge from a dataset efficiently and accurately has attracted increasingly attention from both academia and industry. This paper presents a Parallel Random Forest (PRF) algorithm for big data on the Apache Spark platform. The PRF algorithm is optimized based on a hybrid approach combining dataparallel and task-parallel optimization. From the perspective of data-parallel optimization, a vertical data-partitioning method is performed to reduce the data communication cost effectively, and a data-multiplexing method is performed is performed to allow the training dataset to be reused and diminish the volume of data. From the perspective of task-parallel optimization, a dual parallel approach is carried out in the training process of RF, and a task Directed Acyclic Graph (DAG) is created according to the parallel training process of PRF and the dependence of the Resilient Distributed Datasets (RDD) objects. Then, different task schedulers are invoked for the tasks in the DAG. Moreover, to improve the algorithm's accuracy for large, high-dimensional, and noisy data, we perform a dimension-reduction approach in the training process and a weighted voting approach in the prediction process prior to parallelization. Extensive experimental results indicate the superiority and notable advantages of the PRF algorithm over the relevant algorithms implemented by Spark MLlib and other studies in terms of the classification accuracy, performance, and scalability. With the expansion of the scale of the random forest model and the Spark cluster, the advantage of the PRF algorithm is more obvious.

Emerging resistive random-access memory (RRAM) can provide non-volatile memory storage but also intrinsic logic for matrix-vector multiplication, which is ideal for low-power and high-throughput data analytics accelerator performed in memory. However, the existing RRAM-based computing device is mainly assumed on a multi-level analog computing, whose result is sensitive to process non-uniformity as well as additional AD- conversion and I/O overhead. This paper explores the data analytics accelerator on binary RRAM-crossbar. Accordingly, one distributed in-memory computing architecture is proposed with design of according component and control protocol. Both memory array and logic accelerator can be implemented by RRAM-crossbar purely in binary, where logic-memory pairs can be distributed with protocol of control bus. Based on numerical results for fingerprint matching that is mapped on the proposed RRAM-crossbar, the proposed architecture has shown 2.86x faster speed, 154x better energy efficiency, and 100x smaller area when compared to the same design by CMOS-based ASIC.

In the cloud platform, the startup security of guest virtual machines (VMs) can be guaranteed by existing techniques such as TBoot, however, how to monitor and guarantee their runtime security seems to be a non-trivial challenge, when they are exposed to the Internet. For a practical cloud system, security and performance are two important issues. In this paper, we propose a dynamic framework called CloudMon to detect kernel rootkits and guarantee the runtime security of guest VMs. CloudMon is transparent to a guest VM, neither requires its specific system information, nor has to one-on-one run with it. Meanwhile, CloudMon detects kernel rootkits through self-adjusting monitoring on memory with an acceptable overhead. A working prototype of CloudMon is implemented based on Xen. The case studies on security show that CloudMon is effective to detect kernel rootkits in guest VMs, while the performance experiments demonstrate that it brings a low performance overhead.

The emerging resistive random-access-memory (RRAM) crossbar provides an intrinsic fabric for matrix-vector multiplication, which can be leveraged as power efficient linear embedding hardware for data analytics such as compressive sensing. As the matrix elements are represented by resistance of RRAM cells, it imposes constraints for the embedding matrix due to limited RRAM programming resolution. A random Boolean embedding can be efficiently mapped to the RRAM crossbar but suffers from poor performance. Learning-based embedding matrices can deliver optimized performance but are continuous-valued which prevents it from being mapped to RRAM crossbar structure directly. In this paper, we have proposed one algorithm that can find an optimal Boolean embedding matrix for a given learned real-valued embedding matrix, so that it can be effectively mapped to the RRAM crossbar structure while high performance is preserved. The numerical experiments demonstrate that the proposed optimized Boolean embedding can reduce the embedding distortion by 2.7x, and image recovery error by 2.5x compared to the random Boolean embedding, both mapped on RRAM crossbar. In addition, optimized Boolean embedding on RRAM crossbar exhibits 10x faster speed, 17x better energy efficiency, and three orders of magnitude smaller area with slight accuracy penalty, when compared to the optimized real-valued embedding on CMOS ASIC platform.

As energy has become one of the key operating costs in running a data center and power waste commonly exists, it is essential to reduce energy inefficiency inside data centers. In this paper, we develop an innovative framework, calledPowerTracer, for diagnosing energy inefficiency and saving power. Inside the framework, we first present a resource tracing method based on request tracing in multi-tier services of black boxes. Then, we propose a generalized methodology of applying a request tracing approach for energy inefficiency diagnosis and power saving in multi-tier service systems. With insights into service performance and resource consumption of individual requests, we develop (1) a bottleneck diagnosis tool that pinpoints the root causes of energy inefficiency, and (2) a power saving method that enables dynamic voltage and frequency scaling (DVFS) with online request tracing. We implement a prototype of PowerTracer, and conduct extensive experiments to validate its effectiveness. Our tool analyzes several state-of-the-practice and state-of-the-art DVFS control policies and uncovers existing energy inefficiencies. Meanwhile, the experimental results demonstrate that PowerTracer outperforms its peers in power saving.

Virtualization plays a vital role in building the infrastructure of clouds, and isolation is considered as one of its important features. However, we demonstrate with practical measurements that there exist two kinds of isolation problems in current virtualized systems, due to cache interference in a multi-core processor. That is, one virtual machine could degrade the performance or obtain the load information of another virtual machine, which running on a same physical machine. Then we present a time-sensitive contention management approach (TSAC) for allocating resources dynamically in the virtual machine monitor, in which virtual machines are controlled to share some physical resources (e.g., CPU or page color) in a dynamical manner, in order to enforce isolation between the virtual machines without sacrificing performance of the virtualized system. We have implemented a working prototype based on Xen, evaluated the implemented prototype with experiments, and experimental results show that TSAC could significantly improve isolation of virtualization. Specifically, compared to the default Xen, TSAC could improve the performance of the victim virtual machine by up to about 78 percent, and perform well in blocking its cache-based load information leakage.

Image processing in conventional logic-memory I/O-integrated systems will incur significant communication congestion at memory I/Os for excessive big image data at exa-scale. This paper explores an in-memory machine learning on neural network architecture by utilizing the newly introduced domain-wall nanowire, called DW-NN. We show that all operations involved in machine learning on neural network can be mapped to a logic-in-memory architecture by non-volatile domain-wall nanowire. Domain-wall nanowire based logic is customized for in machine learning within image data storage. As such, both neural network training and processing can be performed locally within the memory. The experimental results show that system throughput in DW-NN is improved by 11.6x and the energy efficiency is improved by 92x when compared to conventional image processing system.

With the development and popularization of cloud computing, more and more services and applications are migrated to cloud for the sake of low cost, high availability and excellent performance. As the foundation of cloud computing, virtualization technology integrates and reallocates the computing capability, storage and network resource fairly among virtual machines and provides a full-featured, isolated and reliable hardware environment for various operating systems. Owe to the virtualization technology, computing capability of virtual machines has achieved fantastic performance, some even achieve near native speed. However, low I/O performance is still a bottleneck, especially in I/O intensive applications. The leading causes include redundant data copy and frequent VM exits. Focusing on network I/O optimization, we design and implement virtsocket, a new network socket library in virtualization scenario which utilizes shared memory for data transmission. A ring buffer data structure stores I/O requests of virtual machine which is triggered to issue all requests with only one hypercall according to scheduler. Data referred in the I/O requests is read directly from virtual machine memory by host machine kernel module with interfaces provided by modified hypervisor. Experimental results show that throughput is improved by hundreds of times when compared with original virtualization scenario, and the latency also achieves a remarkable reduction. Both throughput and latency performance exceed existing para-virtualization solutions.

As an important cornerstone for clouds, virtualization plays a vital role in building this emerging infrastructure. Virtual machines (VMs) with a variety of workloads may run simultaneously on a physical machine in the cloud platform. The scheduling algorithm used in Xen schedules virtual CPUs (VCPUs) of a VM asynchronously and guarantees the proportion of the CPU time allocated to the VM. This proportional sharing (PS) method is beneficial as it simplifies the implementation of CPU scheduling in the virtual machine monitor (VMM), and can deliver near-native performance for some workloads. However, when workloads in VMs are concurrent applications such as multithreaded programs with the synchronization operation, it has been demonstrated that this method in the VMM can reduce the performance, due to the negative impact of virtualization on synchronization. To address this issue, we present a hybrid scheduling framework for CPU management in the VMM to adapt to the diversity of VMs running simultaneously on a physical machine. We implement a hybrid scheduler based on Xen, and experimental results indicate that the hybrid CPU management method is feasible to mitigate the negative influence of virtualization on synchronization, and improve the performance of concurrent applications in the virtualized system, while maintaining the performance of high-throughput applications.

Recent cost analysis shows that the server cost still dominates the total cost of high-scale data centers or cloud systems. In this paper, we argue for a new twist on the classical resource provisioning problem: heterogeneous workloads are a fact of life in large-scale data centers, and current resource provisioning solutions do not act upon this heterogeneity. Our contributions are threefold: first, we propose a cooperative resource provisioning solution, and take advantage of differences of heterogeneous workloads so as to decrease their peak resources consumption under competitive conditions; second, for four typical heterogeneous workloads: parallel batch jobs, web servers, search engines, and MapReduce jobs, we build an agile system PhoenixCloud that enables cooperative resource provisioning; and third, we perform a comprehensive evaluation for both real and synthetic workload traces. Our experiments show that our solution could save the server cost aggressively with respect to the noncooperative solutions that are widely used in state-of-the-practice hosting data centers or cloud systems: for example, EC2, which leverages the statistical multiplexing technique, or RightScale, which roughly implements the elastic resource provisioning technique proposed in related state-of-the-art work.

With multi-core processors becoming popular, exploiting their computational potential becomes an urgent matter. The functionality of multiple standalone computer systems can be aggregated into a single hardware computer by virtualization, giving efficient usage of the hardware and decreased cost for power. Some principles of operating systems can be applied directly to virtual machine systems, however virtualization disrupts the basis of spinlock synchronization in the guest operating system, which results in performance degradation of concurrent workloads such as parallel programs or multi-threaded programs in virtual machines.

System virtualization can aggregate the functionality of multiple standalone computer systems into a single hardware computer. It is significant to virtualize the computing nodes with multi-core processors in the cluster system, in order to promote the usage of the hardware while decrease the cost of the power. In the virtualized cluster system, multiple virtual machines are running on a computing node. However, it is a challenging issue to automatically balance the workload in virtual machines on each physical computing node, which is different from the traditional cluster system's load balance. In this paper, we propose a management framework for the virtualized cluster system, and present an automatic performance tuning strategy to balance the workload in the virtualized cluster system. We implement a working prototype of the management framework (VEMan) based on Xen, and test the performance of the tuning strategy on a virtualized heterogeneous cluster system. The experimental result indicates that the management framework and tuning strategy are feasible to improve the performance of the virtualized cluster system.

Virtualization is a new area for research in recent years, and virtualization technology can bring convenience to the management of computing resources. Together with the development of the network and the network computing, it gives the virtualization technology more scenarios. The cloud computing technology uses the virtualization technology as while. With the development of the technology, it meets some security problems, such as rootkit attacks and malignant tampers. Malicious programs can plug into the system, and be booted at the any time of the virtualized system. There is little theoretical research on booting a trusted virtualized system. We propose an active trusted model in order to give a theoretical model for not only analyzing the state of a virtualized system, but also helping to design trusted virtual machine application. TBoot is a project to boot a trusted virtual machine. We use our model to illustrate that TBoot can boot a trusted virtual machine theoretically.

The virtualization technology makes it feasible that multiple guest operating systems run on a single physical machine. It is the virtual machine monitor that dynamically maps the virtual CPU of virtual machines to physical CPUs according to the scheduling strategy. The scheduling strategy in Xen schedules virtual CPUs of a virtual machines asynchronously while guarantees the proportion of the CPU time corresponding to its weight, maximizing the throughput of the system. However, this scheduling strategy may deteriorate the performance when the virtual machine is used to execute the concurrent applications such as parallel programs or multithreaded programs. In this paper, we analyze the CPU scheduling problem in the virtual machine monitor theoretically, and the result is that the asynchronous CPU scheduling strategy will waste considerable physical CPU time when the system workload is the concurrent application. Then, we present a hybrid scheduling framework for the CPU scheduling in the virtual machine monitor. There are two types of virtual machines in the system: the high-throughput type and the concurrent type. The virtual machine can be set as the concurrent type when the majority of its workload is concurrent applications in order to reduce the cost of synchronization. Otherwise, it is set as the high-throughput type as the default. Moreover, we implement the hybrid scheduling framework based on Xen, and we will give a description of our implementation in details. At last, we test the performance of the presented scheduling framework and strategy based on the multi-core platform, and the experiment result indicates that the scheduling framework and strategy is feasible to improve the performance of the virtual machine system.

Load balancing plays a key role in workload scheduling policies which count in the performance improvement of parallel applications. A critical problem of load balancing is to make a reasonable definition of load index. Unfortunately, few studies provided enough scientific justifications for the choice of load indices. In this paper, a reasonable approach for defining a load index based on factor analysis theory is introduced, which is helpful to reasonable designs of workload scheduling algorithms. An example testing on an accounting log of the CM-5 parallel machine is presented to show the usage of this method.

The economic mechanism is very suitable for solving the problem of resource management in the grid computing environment, and it can guarantee the interest of participators in the grid with fairness and efficiency. In this paper, we propose an economics-based resource management framework for grid computing, and then we focus on how to determine the price of resources with the economic mechanism. We present a general equilibrium method for general resources and a double auction method for special resources in the grid environment respectively. Simulations are performed and the experimental results indicate that the two methods are effective for corresponding application scenarios.