Showing papers on "Server published in 2014"

Cache in the air: exploiting content caching and delivery techniques for 5G systems

Abstract: The demand for rich multimedia services over mobile networks has been soaring at a tremendous pace over recent years. However, due to the centralized architecture of current cellular networks, the wireless link capacity as well as the bandwidth of the radio access networks and the backhaul network cannot practically cope with the explosive growth in mobile traffic. Recently, we have observed the emergence of promising mobile content caching and delivery techniques, by which popular contents are cached in the intermediate servers (or middleboxes, gateways, or routers) so that demands from users for the same content can be accommodated easily without duplicate transmissions from remote servers; hence, redundant traffic can be significantly eliminated. In this article, we first study techniques related to caching in current mobile networks, and discuss potential techniques for caching in 5G mobile networks, including evolved packet core network caching and radio access network caching. A novel edge caching scheme based on the concept of content-centric networking or information-centric networking is proposed. Using trace-driven simulations, we evaluate the performance of the proposed scheme and validate the various advantages of the utilization of caching content in 5G mobile networks. Furthermore, we conclude the article by exploring new relevant opportunities and challenges.

A reconfigurable fabric for accelerating large-scale datacenter services

Abstract: Datacenter workloads demand high computational capabilities, flexibility, power efficiency, and low cost. It is challenging to improve all of these factors simultaneously. To advance datacenter capabilities beyond what commodity server designs can provide, we have designed and built a composable, reconfigurablefabric to accelerate portions of large-scale software services. Each instantiation of the fabric consists of a 6x8 2-D torus of high-end Stratix V FPGAs embedded into a half-rack of 48 machines. One FPGA is placed into each server, accessible through PCIe, and wired directly to other FPGAs with pairs of 10 Gb SAS cablesIn this paper, we describe a medium-scale deployment of this fabric on a bed of 1,632 servers, and measure its efficacy in accelerating the Bing web search engine. We describe the requirements and architecture of the system, detail the critical engineering challenges and solutions needed to make the system robust in the presence of failures, and measure the performance, power, and resilience of the system when ranking candidate documents. Under high load, the largescale reconfigurable fabric improves the ranking throughput of each server by a factor of 95% for a fixed latency distribution--- or, while maintaining equivalent throughput, reduces the tail latency by 29%

Secure Deduplication with Efficient and Reliable Convergent Key Management

Abstract: Data deduplication is a technique for eliminating duplicate copies of data, and has been widely used in cloud storage to reduce storage space and upload bandwidth. Promising as it is, an arising challenge is to perform secure deduplication in cloud storage. Although convergent encryption has been extensively adopted for secure deduplication, a critical issue of making convergent encryption practical is to efficiently and reliably manage a huge number of convergent keys. This paper makes the first attempt to formally address the problem of achieving efficient and reliable key management in secure deduplication. We first introduce a baseline approach in which each user holds an independent master key for encrypting the convergent keys and outsourcing them to the cloud. However, such a baseline key management scheme generates an enormous number of keys with the increasing number of users and requires users to dedicatedly protect the master keys. To this end, we propose Dekey , a new construction in which users do not need to manage any keys on their own but instead securely distribute the convergent key shares across multiple servers. Security analysis demonstrates that Dekey is secure in terms of the definitions specified in the proposed security model. As a proof of concept, we implement Dekey using the Ramp secret sharing scheme and demonstrate that Dekey incurs limited overhead in realistic environments.

Virtual Machines: Versatile Platforms for Systems and Processes

Abstract: Virtual Machine technology applies the concept of virtualization to an entire machine, circumventing real machine compatibility constraints and hardware resource constraints to enable a higher degree of software portability and flexibility. Virtual machines are rapidly becoming an essential element in computer system design. They provide system security, flexibility, cross-platform compatibility, reliability, and resource efficiency. Designed to solve problems in combining and using major computer system components, virtual machine technologies play a key role in many disciplines, including operating systems, programming languages, and computer architecture. For example, at the process level, virtualizing technologies support dynamic program translation and platform-independent network computing. At the system level, they support multiple operating system environments on the same hardware platform and in servers. Historically, individual virtual machine techniques have been developed within the specific disciplines that employ them (in some cases they aren’t even referred to as “virtual machines?), making it difficult to see their common underlying relationships in a cohesive way. In this text, Smith and Nair take a new approach by examining virtual machines as a unified discipline. Pulling together cross-cutting technologies allows virtual machine implementations to be studied and engineered in a well-structured manner. Topics include instruction set emulation, dynamic program translation and optimization, high level virtual machines (including Java and CLI), and system virtual machines for both single-user systems and servers. * Examines virtual machine technologies across the disciplines that use them—operating systems, programming languages and computer architecture—defining a new and unified discipline. * Reviewed by principle researchers at Microsoft, HP, and by other industry research groups. * Written by two authors who combine several decades of expertise in computer system research and development, both in academia and industry.

Hacking Blind

Abstract: We show that it is possible to write remote stack buffer overflow exploits without possessing a copy of the target binary or source code, against services that restart after a crash. This makes it possible to hack proprietary closed-binary services, or open-source servers manually compiled and installed from source where the binary remains unknown to the attacker. Traditional techniques are usually paired against a particular binary and distribution where the hacker knows the location of useful gadgets for Return Oriented Programming (ROP). Our Blind ROP (BROP) attack instead remotely finds enough ROP gadgets to perform a write system call and transfers the vulnerable binary over the network, after which an exploit can be completed using known techniques. This is accomplished by leaking a single bit of information based on whether a process crashed or not when given a particular input string. BROP requires a stack vulnerability and a service that restarts after a crash. We implemented Braille, a fully automated exploit that yielded a shell in under 4,000 requests (20 minutes) against a contemporary nginx vulnerability, yaSSL + MySQL, and a toy proprietary server written by a colleague. The attack works against modern 64-bit Linux with address space layout randomization (ASLR), no-execute page protection (NX) and stack canaries.

I know what your packet did last hop: using packet histories to troubleshoot networks

Abstract: The complexity of networks has outpaced our tools to debug them; today, administrators use manual tools to diagnose problems In this paper, we show how packet histories--the full stories of every packet's journey through the network--can simplify network diagnosis To demonstrate the usefulness of packet histories and the practical feasibility of constructing them, we built NetSight, an extensible platform that captures packet histories and enables applications to concisely and flexibly retrieve packet histories of interest Atop NetSight, we built four applications that illustrate its flexibility: an interactive network debugger, a live invariant monitor, a path-aware history logger, and a hierarchical network profiler On a single modern multi-core server, NetSight can process packet histories for the traffic of multiple 10 Gb/s links For larger networks, NetSight scales linearly with additional servers and scales even further with straightforward additions to hardware- and hypervisor-based switches

New Algorithms for Secure Outsourcing of Modular Exponentiations

Abstract: With the rapid development of cloud services, the techniques for securely outsourcing the prohibitively expensive computations to untrusted servers are getting more and more attention in the scientific community. Exponentiations modulo a large prime have been considered the most expensive operations in discrete-logarithm-based cryptographic protocols, and they may be burdensome for the resource-limited devices such as RFID tags or smartcards. Therefore, it is important to present an efficient method to securely outsource such operations to (untrusted) cloud servers. In this paper, we propose a new secure outsourcing algorithm for (variable-exponent, variable-base) exponentiation modulo a prime in the two untrusted program model. Compared with the state-of-the-art algorithm, the proposed algorithm is superior in both efficiency and checkability. Based on this algorithm, we show how to achieve outsource-secure Cramer-Shoup encryptions and Schnorr signatures. We then propose the first efficient outsource-secure algorithm for simultaneous modular exponentiations. Finally, we provide the experimental evaluation that demonstrates the efficiency and effectiveness of the proposed outsourcing algorithms and schemes.

Management of an academic HPC cluster: The UL experience

Abstract: The intensive growth of processing power, data storage and transmission capabilities has revolutionized many aspects of science. These resources are essential to achieve high-quality results in many application areas. In this context, the University of Luxembourg (UL) operates since 2007 an High Performance Computing (HPC) facility and the related storage by a very small team. The aspect of bridging computing and storage is a requirement of UL service - the reasons are both legal (certain data may not move) and performance related. Nowadays, people from the three faculties and/or the two Interdisciplinary centers within the UL, are users of this facility. More specifically, key research priorities such as Systems Bio-medicine (by LCSB) and Security, Reliability & Trust (by SnT) require access to such HPC facilities in order to function in an adequate environment. The management of HPC solutions is a complex enterprise and a constant area for discussion and improvement. The UL HPC facility and the derived deployed services is a complex computing system to manage by its scale: at the moment of writing, it consists of 150 servers, 368 nodes (3880 computing cores) and 1996 TB of shared storage which are all configured, monitored and operated by only three persons using advanced IT automation solutions based on Puppet [1], FAI [2] and Capistrano [3]. This paper covers all the aspects in relation to the management of such a complex infrastructure, whether technical or administrative. Most design choices or implemented approaches have been motivated by several years of experience in addressing research needs, mainly in the HPC area but also in complementary services (typically Web-based). In this context, we tried to answer in a flexible and convenient way many technological issues. This experience report may be of interest for other research centers and universities belonging either to the public or the private sector looking for good if not best practices in cluster architecture and management.

Media delivery platform

Abstract: A method of delivering an audio and/or visual media file including, for example, one or more of full or partial master recordings of songs, musical compositions, ringtones, videos, films, television shows, personal recordings, animation and combinations thereof, over the air wirelessly, from one or more servers to an electronic device with or without an Internet connection, said method comprising transmitting and audio and/or visual media file in compressed format to said electronic device, and wherein the electronic device is effective to receive said audio and/or visual file and playback said audio and/or visual content on demand by a user.

Towards energy proportionality for large-scale latency-critical workloads

Abstract: Reducing the energy footprint of warehouse-scale computer (WSC) systems is key to their affordability, yet difficult to achieve in practice. The lack of energy proportionality of typical WSC hardware and the fact that important workloads (such as search) require all servers to remain up regardless of traffic intensity renders existing power management techniques ineffective at reducing WSC energy use.We present PEGASUS, a feedback-based controller that significantly improves the energy proportionality of WSC systems, as demonstrated by a real implementation in a Google search cluster. PEGASUS uses request latency statistics to dynamically adjust server power management limits in a fine-grain manner, running each server just fast enough to meet global service-level latency objectives. In large cluster experiments, PEGASUS reduces power consumption by up to 20%. We also estimate that a distributed version of PEGASUS can nearly double these savings

Dynamic Searchable Encryption via Blind Storage

Abstract: Dynamic Searchable Symmetric Encryption allows a client to store a dynamic collection of encrypted documents with a server, and later quickly carry out keyword searches on these encrypted documents, while revealing minimal information to the server. In this paper we present a new dynamic SSE scheme that is simpler and more efficient than existing schemes while revealing less information to the server than prior schemes, achieving fully adaptive security against honest-but-curious servers. We implemented a prototype of our scheme and demonstrated its efficiency on datasets from prior work. Apart from its concrete efficiency, our scheme is also simpler: in particular, it does not require the server to support any operation other than upload and download of data. Thus the server in our scheme can be based solely on a cloud storage service, rather than a cloud computation service as well, as in prior work. In building our dynamic SSE scheme, we introduce a new primitive called Blind Storage, which allows a client to store a set of files on a remote server in such a way that the server does not learn how many files are stored, or the lengths of the individual files, as each file is retrieved, the server learns about its existence (and can notice the same file being downloaded subsequently), but the file's name and contents are not revealed. This is a primitive with several applications other than SSE, and is of independent interest.

Cloud Computing: Survey on Energy Efficiency

Abstract: Cloud computing is today’s most emphasized Information and Communications Technology (ICT) paradigm that is directly or indirectly used by almost every online user. However, such great significance comes with the support of a great infrastructure that includes large data centers comprising thousands of server units and other supporting equipment. Their share in power consumption generates between 1.1p and 1.5p of the total electricity use worldwide and is projected to rise even more. Such alarming numbers demand rethinking the energy efficiency of such infrastructures. However, before making any changes to infrastructure, an analysis of the current status is required. In this article, we perform a comprehensive analysis of an infrastructure supporting the cloud computing paradigm with regards to energy efficiency. First, we define a systematic approach for analyzing the energy efficiency of most important data center domains, including server and network equipment, as well as cloud management systems and appliances consisting of a software utilized by end users. Second, we utilize this approach for analyzing available scientific and industrial literature on state-of-the-art practices in data centers and their equipment. Finally, we extract existing challenges and highlight future research directions.

When Does the Devil Make Work? An Empirical Study of the Impact of Workload on Worker Productivity

Abstract: We analyze a large, detailed operational data set from a restaurant chain to shed new light on how workload defined as the number of tables or diners that a server simultaneously handles affects servers' performance measured as sales and meal duration. We use an exogenous shock---the implementation of labor scheduling software---and time-lagged instrumental variables to disentangle the endogeneity between demand and supply in this setting. We show that servers strive to maximize sales and speed efforts simultaneously, depending on the relative values of sales and speed. As a result, we find that, when the overall workload is small, servers expend more and more sales efforts with the increase in workload at a cost of slower service speed. However, above a certain workload threshold, servers start to reduce their sales efforts and work more promptly with the further rise in workload. In the focal restaurant chain, we find that this saturation point is currently not reached and, counterintuitively, the chain can reduce the staffing level and achieve both significantly higher sales an estimated 3% increase and lower labor costs an estimated 17% decrease. This paper was accepted by Noah Gans, special issue on business analytics.

Bundled authorization requests

Abstract: A framework, which conforms to the OAuth standard, involves a generic OAuth authorization server that can be used by multiple resource servers in order to ensure that access to resources stored on those resource servers is limited to access to which the resource owner consents. Each resource server registers, with the OAuth authorization server, metadata for that resource server, indicating scopes that are recognized by the resource server. The OAuth authorization server refers to this metadata when requesting consent from a resource owner on behalf of a client application, so that the consent will be of an appropriate scope. The OAuth authorization server refers to this metadata when constructing an access token to provide to the client application for use in accessing the resources on the resource server. The OAuth authorization server uses this metadata to map issued access tokens to the scopes to which those access tokens grant access.

A System for Denial-of-Service Attack Detection Based on Multivariate Correlation Analysis

Abstract: Interconnected systems, such as Web servers, database servers, cloud computing servers and so on, are now under threads from network attackers. As one of most common and aggressive means, denial-of-service (DoS) attacks cause serious impact on these computing systems. In this paper, we present a DoS attack detection system that uses multivariate correlation analysis (MCA) for accurate network traffic characterization by extracting the geometrical correlations between network traffic features. Our MCA-based DoS attack detection system employs the principle of anomaly based detection in attack recognition. This makes our solution capable of detecting known and unknown DoS attacks effectively by learning the patterns of legitimate network traffic only. Furthermore, a triangle-area-based technique is proposed to enhance and to speed up the process of MCA. The effectiveness of our proposed detection system is evaluated using KDD Cup 99 data set, and the influences of both non-normalized data and normalized data on the performance of the proposed detection system are examined. The results show that our system outperforms two other previously developed state-of-the-art approaches in terms of detection accuracy.

ElastiCon: an elastic distributed sdn controller

Abstract: Software Defined Networking (SDN) has become a popular paradigm for centralized control in many modern networking scenarios such as data centers and cloud. For large data centers hosting many hundreds of thousands of servers, there are few thousands of switches that need to be managed in a centralized fashion, which cannot be done using a single controller node. Previous works have proposed distributed controller architectures to address scalability issues. A key limitation of these works, however, is that the mapping between a switch and a controller is statically configured, which may result in uneven load distribution among the controllers as traffic conditions change dynamically. To address this problem, we propose ElastiCon, an elastic distributed controller architecture in which the controller pool is dynamically grown or shrunk according to traffic conditions. To address the load imbalance caused due to spatial and temporal variations in the traffic conditions, ElastiCon automatically balances the load across controllers thus ensuring good performance at all times irrespective of the traffic dynamics. We propose a novel switch migration protocol for enabling such load shifting, which conforms with the Openflow standard. We further design the algorithms for controller load balancing and elasticity. We also build a prototype of ElastiCon and evaluate it extensively to demonstrate the efficacy of our design.

Expressive, Efficient, and Revocable Data Access Control for Multi-Authority Cloud Storage

Abstract: Data access control is an effective way to ensure the data security in the cloud Due to data outsourcing and untrusted cloud servers, the data access control becomes a challenging issue in cloud storage systems Ciphertext-Policy Attribute-based Encryption (CP-ABE) is regarded as one of the most suitable technologies for data access control in cloud storage, because it gives data owners more direct control on access policies However, it is difficult to directly apply existing CP-ABE schemes to data access control for cloud storage systems because of the attribute revocation problem In this paper, we design an expressive, efficient and revocable data access control scheme for multi-authority cloud storage systems, where there are multiple authorities co-exist and each authority is able to issue attributes independently Specifically, we propose a revocable multi-authority CP-ABE scheme, and apply it as the underlying techniques to design the data access control scheme Our attribute revocation method can efficiently achieve both forward security and backward security The analysis and simulation results show that our proposed data access control scheme is secure in the random oracle model and is more efficient than previous works

Applying NFV and SDN to LTE mobile core gateways, the functions placement problem

Abstract: With the rapid growth of user data, service innovation, and the persistent necessity to reduce costs, today's mobile operators are faced with severe challenges. In networking, two new concepts have emerged aiming at cost reduction, increase of network scalability and service flexibility, namely Network Functions Virtualization (NFV) and Software Defined Networking (SDN). NFV proposes to run the mobile network functions as software instances on commodity servers or datacenters (DC), while SDN supports a decomposition of the mobile network into control-plane and data-plane functions. Whereas these new concepts are considered as very promising drivers to design cost efficient mobile network architectures, limited attention has been drawn to the network load and infringed data-plane delay imposed by introducing NFV or SDN. We argue that within a widely-spanned mobile network, there is in fact a high potential to combine both concepts. Taking load and delay into account, there will be areas of the mobile network rather benefiting from an NFV deployment with all functions virtualized, while for other areas, an SDN deployment with functions decomposition is more advantageous. We refer to this problem as the functions placement problem. We propose a model that resolves the functions placement and aims at minimizing the transport network load overhead against several parameters such as data-plane delay, number of potential datacenters and SDN control overhead. We illustrate our proposed concept along with a concrete use case example.

Tales of the Tail: Hardware, OS, and Application-level Sources of Tail Latency

Abstract: Interactive services often have large-scale parallel implementations. To deliver fast responses, the median and tail latencies of a service's components must be low. In this paper, we explore the hardware, OS, and application-level sources of poor tail latency in high throughput servers executing on multi-core machines.We model these network services as a queuing system in order to establish the best-achievable latency distribution. Using fine-grained measurements of three different servers (a null RPC service, Memcached, and Nginx) on Linux, we then explore why these servers exhibit significantly worse tail latencies than queuing models alone predict. The underlying causes include interference from background processes, request re-ordering caused by poor scheduling or constrained concurrency models, suboptimal interrupt routing, CPU power saving mechanisms, and NUMA effects.We systematically eliminate these factors and show that Memcached can achieve a median latency of 11 μs and a 99.9th percentile latency of 32 μs at 80% utilization on a four-core system. In comparison, a naive deployment of Memcached at the same utilization on a single-core system has a median latency of 100 μs and a 99.9th percentile latency of 5 ms. Finally, we demonstrate that tradeoffs exist between throughput, energy, and tail latency.

Can We Beat DDoS Attacks in Clouds

Abstract: Cloud is becoming a dominant computing platform. Naturally, a question that arises is whether we can beat notorious DDoS attacks in a cloud environment. Researchers have demonstrated that the essential issue of DDoS attack and defense is resource competition between defenders and attackers. A cloud usually possesses profound resources and has full control and dynamic allocation capability of its resources. Therefore, cloud offers us the potential to overcome DDoS attacks. However, individual cloud hosted servers are still vulnerable to DDoS attacks if they still run in the traditional way. In this paper, we propose a dynamic resource allocation strategy to counter DDoS attacks against individual cloud customers. When a DDoS attack occurs, we employ the idle resources of the cloud to clone sufficient intrusion prevention servers for the victim in order to quickly filter out attack packets and guarantee the quality of the service for benign users simultaneously. We establish a mathematical model to approximate the needs of our resource investment based on queueing theory. Through careful system analysis and real-world data set experiments, we conclude that we can defeat DDoS attacks in a cloud environment.

Adaptive Resource Provisioning for the Cloud Using Online Bin Packing

Abstract: Data center applications present significant opportunities for multiplexing server resources. Virtualization technology makes it easy to move running application across physical machines. In this paper, we present an approach that uses virtualization technology to allocate data center resources dynamically based on application demands and support green computing by optimizing the number of servers actively used. We abstract this as a variant of the relaxed on-line bin packing problem and develop a practical, efficient algorithm that works well in a real system. We adjust the resources available to each VM both within and across physical servers. Extensive simulation and experiment results demonstrate that our system achieves good performance compared to the existing work.

Reconciling high server utilization and sub-millisecond quality-of-service

Abstract: The simplest strategy to guarantee good quality of service (QoS) for a latency-sensitive workload with sub-millisecond latency in a shared cluster environment is to never run other workloads concurrently with it on the same server. Unfortunately, this inevitably leads to low server utilization, reducing both the capability and cost effectiveness of the cluster.In this paper, we analyze the challenges of maintaining high QoS for low-latency workloads when sharing servers with other workloads. We show that workload co-location leads to QoS violations due to increases in queuing delay, scheduling delay, and thread load imbalance. We present techniques that address these vulnerabilities, ranging from provisioning the latency-critical service in an interference aware manner, to replacing the Linux CFS scheduler with a scheduler that provides good latency guarantees and fairness for co-located workloads. Ultimately, we demonstrate that some latency-critical workloads can be aggressively co-located with other workloads, achieve good QoS, and that such co-location can improve a datacenter's effective throughput per TCO-$ by up to 52%.

Dynamic Searchable Encryption via Blind Storage.

Abstract: Dynamic Searchable Symmetric Encryption allows a client to store a dynamic collection of encrypted documents with a server, and later quickly carry out keyword searches on these encrypted documents, while revealing minimal information to the server. In this paper we present a new dynamic SSE scheme that is simpler and more efficient than existing schemes while revealing less information to the server than prior schemes, achieving fully adaptive security against honest-but-curious servers. We implemented a prototype of our scheme and demonstrated its efficiency on datasets from prior work. Apart from its concrete efficiency, our scheme is also simpler: in particular, it does not require the server to support any operation other than upload and download of data. Thus the server in our scheme can be based solely on a cloud storage service, rather than a cloud computation service as well, as in prior work. In building our dynamic SSE scheme, we introduce a new primitive called Blind Storage, which allows a client to store a set of files on a remote server in such a way that the server does not learn how many files are stored, or the lengths of the individual files; as each file is retrieved, the server learns about its existence (and can notice the same file being downloaded subsequently), but the file’s name and contents are not revealed. This is a primitive with several applications other than SSE, and is of independent interest.

System and method for authorizing access to access-controlled environments

Abstract: Systems and methods are provided for authorizing a user to access an access-controlled environment. The system includes a system server platform that communicates with fixed PC's, servers and mobile devices (e.g., smartphones) operated by users. The systems and methods described herein enable a series of operations whereby a user attempting to access an access-controlled environment is prompted to biometrically authenticate using the user's preregistered mobile device. Biometric authentication can include capturing images of the user's biometric features, encoding the features as a biometric identifier, comparing the biometric identifier to a previously generated biometric identifier and determining liveness. In addition, the authentication system can further authorize the user and electronically grant access to the access-controlled environment. In this manner the secure authentication system can, based on biometric authentication, authorize a user's access to devices, online services, physical locations or any networked environment that require user authorization.

iAware: Making Live Migration of Virtual Machines Interference-Aware in the Cloud

Abstract: Large-scale datacenters have been widely used to host cloud services, which are typically allocated to different virtual machines (VMs) through resource multiplexing across shared physical servers. Although recent studies have primarily focused on harnessing live migration of VMs to achieve load balancing and power saving among different servers, there has been little attention on the incurred performance interference and cost on both source and destination servers during and after such VM migration. To avoid potential violations of service-level-agreement (SLA) demanded by cloud applications, this paper proposes iAware, a lightweight interference-aware VM live migration strategy. It empirically captures the essential relationships between VM performance interference and key factors that are practically accessible through realistic experiments of benchmark workloads on a Xen virtualized cluster platform. iAware jointly estimates and minimizes both migration and co-location interference among VMs, by designing a simple multi-resource demand-supply model. Extensive experiments and complementary large-scale simulations are conducted to validate the performance gain and runtime overhead of iAware in terms of I/O and network throughput, CPU consumption, and scalability, compared to the traditional interference-unaware VM migration approaches. Moreover, we demonstrate that iAware is flexible enough to cooperate with existing VM scheduling or consolidation policies in a complementary manner, such that the load balancing or power saving can still be achieved without sacrificing performance.

The mystery machine: end-to-end performance analysis of large-scale internet services

Abstract: Current debugging and optimization methods scale poorly to deal with the complexity of modern Internet services, in which a single request triggers parallel execution of numerous heterogeneous software components over a distributed set of computers The Achilles' heel of current methods is the need for a complete and accurate model of the system under observation: producing such a model is challenging because it requires either assimilating the collective knowledge of hundreds of programmers responsible for the individual components or restricting the ways in which components interactFortunately, the scale of modern Internet services offers a compensating benefit: the sheer volume of requests serviced means that, even at low sampling rates, one can gather a tremendous amount of empirical performance observations and apply "big data" techniques to analyze those observations In this paper, we show how one can automatically construct a model of request execution from pre-existing component logs by generating a large number of potential hypotheses about program behavior and rejecting hypotheses contradicted by the empirical observations We also show how one can validate potential performance improvements without costly implementation effort by leveraging the variation in component behavior that arises naturally over large numbers of requests to measure the impact of optimizing individual components or changing scheduling behaviorWe validate our methodology by analyzing performance traces of over 13 million requests to Facebook servers We present a detailed study of the factors that affect the end-to-end latency of such requests We also use our methodology to suggest and validate a scheduling optimization for improving Facebook request latency

Duet: cloud scale load balancing with hardware and software

Abstract: Load balancing is a foundational function of datacenter infrastructures and is critical to the performance of online services hosted in datacenters. As the demand for cloud services grows, expensive and hard-to-scale dedicated hardware load balancers are being replaced with software load balancers that scale using a distributed data plane that runs on commodity servers. Software load balancers offer low cost, high availability and high flexibility, but suffer high latency and low capacity per load balancer, making them less than ideal for applications that demand either high throughput, or low latency or both. In this paper, we present Duet, which offers all the benefits of software load balancer, along with low latency and high availability -- at next to no cost. We do this by exploiting a hitherto overlooked resource in the data center networks -- the switches themselves. We show how to embed the load balancing functionality into existing hardware switches, thereby achieving organic scalability at no extra cost. For flexibility and high availability, Duet seamlessly integrates the switch-based load balancer with a small deployment of software load balancer. We enumerate and solve several architectural and algorithmic challenges involved in building such a hybrid load balancer. We evaluate Duet using a prototype implementation, as well as extensive simulations driven by traces from our production data centers. Our evaluation shows that Duet provides 10x more capacity than a software load balancer, at a fraction of a cost, while reducing latency by a factor of 10 or more, and is able to quickly adapt to network dynamics including failures.

TrustedDB: A Trusted Hardware-Based Database with Privacy and Data Confidentiality

Abstract: Traditionally, as soon as confidentiality becomes a concern, data are encrypted before outsourcing to a service provider. Any software-based cryptographic constructs then deployed, for server-side query processing on the encrypted data, inherently limit query expressiveness. Here, we introduce TrustedDB, an outsourced database prototype that allows clients to execute SQL queries with privacy and under regulatory compliance constraints by leveraging server-hosted, tamper-proof trusted hardware in critical query processing stages, thereby removing any limitations on the type of supported queries. Despite the cost overhead and performance limitations of trusted hardware, we show that the costs per query are orders of magnitude lower than any (existing or) potential future software-only mechanisms. TrustedDB is built and runs on actual hardware, and its performance and costs are evaluated here.

The Design and Implementation of the FreeBSD Operating System

Abstract: As in earlier Addison-Wesley books on the UNIX-based BSD operating system, Kirk McKusick and George Neville-Neil deliver here the most comprehensive, up-to-date, and authoritative technical information on the internal structure of open source FreeBSD Readers involved in technical and sales support can learn the capabilities and limitations of the system; applications developers can learn effectively and efficiently how to interface to the system; system administrators can learn how to maintain, tune, and configure the system; and systems programmers can learn how to extend, enhance, and interface to the systemThe authors provide a concise overview of FreeBSD's design and implementation Then, while explaining key design decisions, they detail the concepts, data structures, and algorithms used in implementing the systems facilities As a result, readers can use this book as both a practical reference and an in-depth study of a contemporary, portable, open source operating systemThis book: Details the many performance improvements in the virtual memory system Describes the new symmetric multiprocessor support Includes new sections on threads and their scheduling Introduces the new jail facility to ease the hosting of multiple domains Updates information on networking and interprocess communicationAlready widely used for Internet services and firewalls, high-availability servers, and general timesharing systems, the lean quality of FreeBSD also suits the growing area of embedded systems Unlike Linux, FreeBSD does not require users to publicize any changes they make to the source code