Fully Transparent Client-Side Caching for Key-Value Store Applications Using FPGAs

Distributed key-value stores are rapidly evolving to serve the needs of high-performance web services and large-scale cloud computing applications. It is desirable to search directly over an encrypted key value (KV) store, as data is increasingly stored in the cloud. Encrypted, distributed and searchable key- value stores have been the focus of research, where a data owner outsources his key-value store to a remote server in the cloud in the encrypted form, yet still keeping it searchable. In this paper, we explore the encrypted KV store with the secure multi-client query support. In particular, the data owner can authorize multiple trustable clients (third parties) and allow them to search its encrypted database over KV store. The design goal is to ensure the data confidentiality and query privacy. From the data owner's perspective, the authorized query should not leak too much information thus causing threats to its private database. From clients' perspective, they have the explicit requirement that the query values should not be exposed to the data owner. We design two encryption schemes and token generation methods to satisfy different requirements. To validate the effciency of our protocols, we implement the system prototype to evaluate their performance.

Various key-value (KV) stores are widely employed for data management to support Internet services as they offer higher efficiency, scalability, and availability than relational database systems. The log-structured merge tree (LSM-tree) based KV stores have attracted growing attention because they can eliminate random writes and maintain acceptable read performance. Recently, as the price per unit capacity of NAND flash decreases, solid state disks (SSDs) have been extensively adopted in enterprise-scale data centers to provide high I/O bandwidth and low access latency. However, it is inefficient to naively combine LSM-tree-based KV stores with SSDs, as the high parallelism enabled within the SSD cannot be fully exploited. Current LSM-tree-based KV stores are designed without assuming SSD's multi-channel architecture.To address this inadequacy, we propose LOCS, a system equipped with a customized SSD design, which exposes its internal flash channels to applications, to work with the LSM-tree-based KV store, specifically LevelDB in this work. We extend LevelDB to explicitly leverage the multiple channels of an SSD to exploit its abundant parallelism. In addition, we optimize scheduling and dispatching polices for concurrent I/O requests to further improve the efficiency of data access. Compared with the scenario where a stock LevelDB runs on a conventional SSD, the throughput of storage system can be improved by more than 4X after applying all proposed optimization techniques.

We propose novel load balancers for key-value data stores running as a service over geographically distributed data centers. We assume that the key-value store has the following properties: (i) The requests (e.g., put/write, get/read, copy, etc.) can be directed to any one of the cluster nodes regardless of which cluster nodes store the information; (ii) Different objects can have different number of replicas and applications can set their desired consistency levels; and (iii) it is possible for intermediate (authorized) proxies to query/learn cluster topology and key space to node mappings. We propose two load balancing strategies that would be useful under these assumptions: (i) Static strategy that makes assignment decisions solely based on where the majority of the hosting nodes are located for a given key. (ii) Dynamic strategy where proxy nodes actively probe the performance of different cluster nodes as a function of their location (i.e., which data center they belong) and key-specific operational parameters (e.g., consistency level and replication factor) to select the best cluster node to serve each request. Our evaluations show that 2× gains for average read/write delays against random load balancers, while dynamic approach significantly outperforming the static approach between 60th and 90th percentiles.

Key-value stores, such as Memcached, have been used to scale web services since the beginning of the Web 2.0 era. Data center real estate is expensive, and several industry experts we have spoken to have suggested that a significant portion of their data center space is devoted to key value stores. Despite its wide-spread use, there is little in the way of hardware specialization for increasing the efficiency and density of Memcached; it is currently deployed on commodity servers that contain high-end CPUs designed to extract as much instruction-level parallelism as possible. Out-of-order CPUs, however have been shown to be inefficient when running Memcached. To address Memcached efficiency issues, we propose two architectures using 3D stacking to increase data storage efficiency. Our first 3D architecture, Mercury, consists of stacks of ARM Cortex-A7 cores with 4GB of DRAM, as well as NICs. Our second architecture, Iridium, replaces DRAM with NAND Flash to improve density. We explore, through simulation, the potential efficiency benefits of running Memcached on servers that use 3D-stacking to closely integrate low-power CPUs with NICs and memory. With Mercury we demonstrate that density may be improved by 2.9X, power efficiency by 4.9X, throughput by 10X, and throughput per GB by 3.5X over a state-of-the-art server running optimized Memcached. With Iridium we show that density may be increased by 14X, power efficiency by 2.4X, and throughput by 5.2X, while still meeting latency requirements for a majority of requests.

A key-value store (KVS), such as memcached and Redis, is widely used as a caching layer to augment the slower persistent backend storage in data centers. DRAM-based KVS provides fast key-value access, but its scalability is limited by the cost, power and space needed by the machine cluster to support a large amount of DRAM. This paper offers a 10X to 100X cheaper solution based on flash storage and hardware accelerators. In BlueCache key-value pairs are stored in flash storage and all KVS operations, including the flash controller are directly implemented in hardware. Furthermore, BlueCache includes a fast interconnect between flash controllers to provide a scalable solution. We show that BlueCache has 4.18X higher throughput and consumes 25X less power than a flash-backed KVS software implementation on x86 servers. We further show that BlueCache can outperform DRAM-based KVS when the latter has more than 7.4% misses for a read-intensive aplication. BlueCache is an attractive solution for both rack-level appliances and data-center-scale key-value cache.

Motivation: Data centers are a critical component of modern IT infrastructure but are also among the worst environmental offenders through their increasing energy usage and the resulting large carbon footprints. Efficient management of data centers, including power management, networking, and cooling infrastructure, is hence crucial to sustainability. In the absence of a 'first-principles' approach to manage these complex components and their interactions, data-driven approaches have become attractive and tenable.Results: We present a temporal data mining solution to model and optimize performance of data center chillers, a key component of the cooling infrastructure. It helps bridge raw, numeric, time-series information from sensor streams toward higher level characterizations of chiller behavior, suitable for a data center engineer. To aid in this transduction, temporal data streams are first encoded into a symbolic representation, next run-length encoded segments are mined to form frequent motifs in time series, and finally these metrics are evaluated by their contributions to sustainability. A key innovation in our application is the ability to intersperse don't care transitions (e.g., transients) in continuous-valued time series data, an advantage we inherit by the application of frequent episode mining to symbolized representations of numeric time series. Our approach provides both qualitative and quantitative characterizations of the sensor streams to the data center engineer, to aid him in tuning chiller operating characteristics. This system is currently being prototyped for a data center managed by HP and experimental results from this application reveal the promise of our approach.

A large amount of data are stored in geographically distributed data centers interconnected by the Internet. The power consumption for running the servers storing the data and inter-data center network transport for data update among the multiple data copies stored in different data centers impose a significant operational cost on cloud service providers. Few research places data replicas in the data centers by jointly taking both electricity consumption and network transport into account under the user access latency requirement constraints. However, there is an intrinsic tradeoff between the electricity consumption of the data centers and the network transport cost for data update. In this paper, we tackle the problem of data placement in data centers with the aim to minimize the operational cost under user access latency requirements, assuming all the data have K copies. We propose an effective algorithm, Latency-aware and operational Cost minimization Data Placement (LCDP), which partitions the data into multiple data groups according to the data access rates and greedily selects K data centers incurring the minimum cost for each data in each data group. We prove that algorithm LCDP is \(\frac{1}{2} \ln |\mathrm {U}|\)-approximation to the data placement problem, where \(|\mathrm {U}|\) is the number of users. Our simulation results demonstrate that the proposed algorithm can effectively reduce the power consumption cost, the network transport cost, and the operational cost of the data centers.

Cloud Security is still considered one of the main factors inhibiting the diffusion of the Cloud Computing paradigm. Potential Cloud Service Customers (CSCs) do not trust delegating every kind of resources and data to external Cloud Service Providers (CSPs). The problem grows in complexity due to the increasing adoption of complex supply chains: CSPs that offer Sofware-as-a-Service (SaaS) cloud services often do not have their own data centers, but just acquire resources and services from other CSPs. This makes ithard, if not impossible, to ascribe the responsibility of a securityincident. A possible solution is the adoption of Security ServiceLevel Agreements (SLAs): CSPs should deliver services withan SLA that details each guarantee offered in terms of security, and CSCs should be able to compare offerings from differentCSPs and verify that SLAs are respected during service lifecycle. This paper shows how it is possible to build up a per-serviceSecurity SLA in a chain of cloud services, proposing asolution based on a security evaluation technique to comparedifferent cloud service supply chains based on their SecuritySLAs.

Energy management and reduction is one of the major challenges in the Cloud industry's data centres. The Uptime Institute's 2012 report, the industry's leading authority, highlighted the crisis in data centre energy management. 30% of data centres will run out of power, space and cooling in 2012. On average there's a 90% energy overhead in data centre operations, yet 55% of servers use less than 10% of their capacity. The 500,000 data centres worldwide have a server electricity consumption of 400 Billion kWh/year (approx $40 Billion ) which is growing at 12% CAGR, yet only 11% of the centres monitor their consumption. The global CO2 emissions of these centres, is equivalent to the airline industry, 2% of global emissions. It is expected that by 2020 20% of Europe's electrical energy will be data centre related. Data centre cooling requirements also have an enormous hydro footprint. A 1 MW data centre in a U.S-type climate has an annual hydro footprint of 99 million litres/annum Yet studies have shown that operational energy savings of 40% and substantial reductions in physical space, cooling requirements and water consumption can be achieved, where comprehensive and effective energy monitoring and management systems are employed. These can deliver a ROI within months, and further savings which extend over the centre's lifetime. The technologies which have the potential to deliver these benefits, DCIM (Data Centre Infrastructure Management) systems have only emerged in the last 3 to 4 years and are still in their infancy. Not surprisingly, a new global industry providing innovative, green, sustainable data centre technologies will be worth €45 Billion by 2016. The main barriers to effective monitoring/management is instrumentation and training. Vast volumes of data are gathered and must be competently analysed. Most monitoring systems, involve some form of physical metering and cabling and downtime, a major challenge when 10's thousands of servers are involved. Furthermore, all approaches physical and hybrid approaches limit the level of monitoring visibility to the server, individual processes cannot be monitored. A spin-out company from University College Dublin Ireland, Stratergia, has developed a unique data centre energy management system PAPILLON. It is totally software-based, measuring every server's energy consumption in real-time. It is intuitive to use, operates on any platform and can be installed in hours without any downtime or retrofitting. It uses a client-server type architecture. Software agents on servers communicate periodically, to a master server which has power models for each server type. Using the power models, the master computes in real-time and saves in a data base, all relevant energy information of the centre. In operation, Papillon identifies and quantifies energy saving actions that can be implemented, and coupled with electricity network data, more sustainable energy sources can be introduced into the power input of the centre. Papillon has been trialled at Swedish Compare Testlab and is one of the core tools being installed at state-of-the-art data centres at Kajaani, Finland and Cenit, Spain for a new international EU-funded Masters programme in green, sustainable data centre management.

Cloud computing provides distributed computing resources such as servers, storage and applications to the end users through data centers. The data centers are geographically located at different locations. The client applications or requests being serviced by cloud service providers on “pay per use”. So, different pricing models are adapted to compute the cost and revenue of the data centers. The cost of VM is computed depending on its placement in the data centers through broker policies. So, the broker policies have a significant role in evaluating the cost of the VM which directly impacts on revenue of the service provider. In the computing competition, the VM cost should be minimized by which service demand will be maximized. Moreover, the response time and processing time of the data centers need to be minimized to posses commendatory Quality of Service. In this work, we propose a new service broker policy to minimize the total cost. The total cost considers the VM cost and the data transfer cost. The proposed mechanism also reduces the response time and data processing time of the data centers. The proposed policy is simulated in Cloud Analyst. We examine the performance of the proposed mechanism with ten different scenarios. Finally, we compare performance results with respect to VM cost, data transfer cost, total cost, processing time and response time of data centers with the existing policies and observe better than these.

The count of datacenters is drastically increasing as the need for cloud computing is increasing day by day. Datacenters are the major electricity consumers in the world (Khan et al. in IEEE Trans Cloud Comput, 2019 []). Successful cloud service providers (CSP) such as Google, Amazon, and Microsoft are having a huge number of datacenters worldwide with hundreds of servers (PMs) to satisfy their customers’ requirements (Wang et al. in Comput Netw 161, 2019 []; Cheng et al. in Heterogeneity aware workload management in distributed sustainable datacenters. In: IEEE 28th International Parallel and Distributed Processing Symposium, 2014 []). Servers along with their network and cooling equipment require a huge amount of energy to operate. A study has shown that data centers will use around 3–13% of global electricity in 2030 compared to 1% in 2010 (Anders et al. in MDPI Challenges, 2015 []). Data centers not only consume a lot of energy but also release a lot of greenhouse gas (GHG). Energy consumption and carbon dioxide emission of datacenters are the major concerns of cloud service providers (CSPs). The benefits of cloud datacenters are given to us by the cost of global warming since the servers used in datacenters dissipate a lot of heat (Xu et al. in IEEE Trans Sustain Comput 4(1), 2019 []). Implementation of holistic approaches such as advanced frameworks, power-efficient electronic devices, and well-designed cooling and heating equipment are not sufficient to address the problem of energy consumption. Effective use of servers in datacenters will help the CSPs to face the energy efficiency challenge to a greater extent. Allocating services to power-efficient PMs and reducing the count of running PMs are the best practices followed in datacenters. The purpose of this survey is to study different kinds of algorithms used in datacenters in recent years to achieve energy efficiency targets and to minimize carbon dioxide emissions.

Service level agreements (SLAs) gain more and more importance in the area of cloud computing. An SLA is a contract between a customer and a cloud service provider (CSP) in which the CSP guarantees functional and non-functional quality of service parameters for cloud services. Since CSPs have to pay for the hardware used as well as penalties for violating SLAs, they are eager to fulfill these agreements while at the same time optimizing the utilization of their resources.In this paper we examine SLA-aware VM scheduling strategies for cloud data centers. The service level objectives considered are resource usage and availability. The sample resources are CPU and RAM. They can be overprovisioned by the CSPs which is the main leverage to increase their revenue. The availability of a VM is affected by migrating it within and between data centers. To get realistic results, we simulate the effect of the strategies using the FederatedCloudSim framework and real-world workload traces of business-critical VMs.Our evaluation shows that there are considerable differences between the scheduling strategies in terms of SLA violations and the number of migrations. From all strategies considered, the combination of the Minimization of Migrations strategy for VM selection and the Worst Fit strategy for host selection achieves the best results.

Log-Structure Merge tree (LSM-tree) has been one of the mainstream indexes in key-value systems supporting a variety of write-intensive Internet applications in today’s data centers. However, the performance of LSM-tree is seriously hampered by constantly occurring compaction procedures, which incur significant write amplification and degrade the write throughput. To alleviate the performance degradation caused by compactions, we introduce a lightweight compaction tree (LWC-tree), a variant of LSM-tree index optimized for minimizing the write amplification and maximizing the system throughput. The lightweight compaction drastically decreases write amplification by appending data in a table and only merging the metadata that have much smaller size. Using our proposed LWC-tree, we have implemented three key-value LWC-stores on different storage mediums including Shingled Magnetic Recording (SMR) drives, Solid State Drives (SSD), and conventional Hard Disk Drives (HDDs). The LWC-store is particularly optimized for SMR drives, as it eliminates the multiplicative I/O amplification from both LSM-trees and SMR drives. Due to the lightweight compaction procedure, LWC-store reduces the write amplification by a factor of up to 5× compared to the popular LevelDB key-value store. Moreover, the random write throughput of the LWC-tree on SMR drives is significantly improved by up to 467% even compared with LevelDB on conventional HDDs. Furthermore, LWC-tree has wide applicability and delivers impressive performance improvement in various conditions, including different storage mediums (i.e., SMR, HDD, SSD) and various value sizes and access patterns (i.e., uniform and Zipfian).

Energy consumption in data center is currently the main focus of many large-scale enterprises and cloud service providers. Dynamic virtual machine (VM) consolidation technologies are widely used to improve resource utilization of data centers and reduce energy. They try to identify the poorly utilized physical hosts and make the most of the resources. Then idle hosts can be switched to sleep or active mode, meanwhile considering the real-time fluctuation of service workload. In this paper, we propose a Reinforcement Learning (RL) based Virtual Machine Consolidation (RL-VMC) framework with an application to the cloud data center operation. The RL-VMC method uses an agent corresponding to a VM planner to interact with the environment, which encapsulates the data center running state, and learns the optimal policy to determine the migration mapping from VMs to physical hosts. Specifically, we adopt the on-policy method State-Action-Reward-State-Action (SARSA) in RL-VMC, which learns from experience to get the optimal VMs migration strategy and manage the host power mode as well. Additionally, we use the PBRS technology to speed up the convergence of the RL-VMC. Experimental results show that the RL-VMC method can adapt to the dynamic workload maintaining an improved balance between energy consumption and Service Level Agreements (SLA).

With the fast proliferation of cloud computing, major cloud service providers, e.g., Amazon, Google, Facebook, etc., have been deploying more and more geographically distributed data centers to provide customers with better reliability and quality of services. A basic demand in such a geo-distributed data center system is to transfer bulk volumes of data from one data center to another. Geographic distribution and large delay-tolerance of such inter-data-center bulk data transfers provide cloud service providers opportunities to optimize the operating cost. Most existing studies on inter-data-center bulk data transfers focus on minimizing the network bandwidth cost. However, the energy-cost of the bulk data transfers, which also accounts for a large proportion of operating cost in the data centers, still remains unexplored. This is an important problem, especially in the multi-electricity-market environment, where the electricity price exhibits both spatial and temporal diversities. In this paper, we systematically study the problem of how to route and schedule inter-data-center bulk data transfers to minimize the energy-cost for geo-distributed data centers. We model this problem as a min-cost multi-commodity flow problem and develop an efficient two-stage optimization method to solve it. Extensive evaluations with real-life inter-data-center network and electricity prices show that our method brings significant energy-cost savings over existing bulk data transfer methods.