No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Comprehensive Characterization of an Open Source Document Search Engine
Abstract
This work performs a thorough characterization and analysis of the open source Lucene search library. The article describes in detail the architecture, functionality, and micro-architectural behavior of the search engine, and investigates prominent online document search research issues. In particular, we study how intra-server index partitioning affects the response time and throughput, explore the potential use of low power servers for document search, and examine the sources of performance degradation ands the causes of tail latencies. Some of our main conclusions are the following: (a) intra-server index partitioning can reduce tail latencies but with diminishing benefits as incoming query traffic increases, (b) low power servers given enough partitioning can provide same average and tail response times as conventional high performance servers, (c) index search is a CPU-intensive cache-friendly application, and (d) C-states are the main culprits for performance degradation in document search.
... Still, these search systems can sometimes not guarantee reliable and accurate information, but still, these systems provide better results than performing the task manually by experts. ese tools often do not provide precise information because the IR system [6] returns information to Internet users based on specific retrieval criteria. For instance, it fetches web documents based on the subject/title as given. ...
... Association rules can be used as a trigger for pre-fetching documents while loading a page from a distant site to reduce user perceived latency. Association rules in WUM provide the relationship between web pages that frequently appear next to one another in user sessions [6,7]. ...
Due to the exponential growth of Internet users and traffic, information seekers depend highly on search engines to extract relevant information. Due to the accessibility of a large amount of textual, audio, video etc., contents, the responsibility of search engines has increased. The search engine provides relevant information to Internet users concerning their query, based on content, link structure, etc. However, it does not guarantee the correctness of the information. The performance of a search engine is highly dependent upon the ranking module. The performance of the ranking module is dependent upon the link structure of web pages, which analyze through Web structure mining (WSM) and their content, which analyzes through Web content mining (WCM). Web mining plays a vital role in computing the rank of web pages. This article presents web mining types, techniques, tools, algorithms, and their challenges. Further, it provides a critical comprehensive survey for the researchers by presenting different features of web pages, which are essential to check their quality. In this work, authors presented different approaches/techniques, algorithms and evaluation approaches in previous researches and identified some critical issues in page ranking and web mining, which provide future directions for the researchers working in the area.
... Still, these search systems are sometimes not able to provide guarantee about reliable and accurate information but still, these systems provide better results than performing the task manually by experts. Many times these tools do not provide precise information because the IR system [4] returns information to internet users based on some specific retrieval criteria. For instance, it fetches web documents based on subject/title as given. ...
div>Purpose: Due to the exponential growth of internet users and internet traffic, information seekers are highly dependent upon search engines to extract relevant information. Due to the accessibility of a large amount of textual, audio, video etc. contents, the responsibility of search engines has increased.
Design/methodology/approach: The search engine provides relevant information to internet users concerning to their query; based on content, link structure etc. However, it does not provide the guarantee of the correctness of the information. The performance of a search engine is highly dependent upon the ranking module. The performance of the ranking module is dependent upon the link structure of web pages, which analyse through Web structure mining (WSM) and their content, which analyses through Web content mining (WCM). Web mining plays an important role in computing the rank of web pages.
Findings: In this article, web mining types, techniques, tools, algorithms and their challenges are presented. Further, it provides a critical comprehensive survey for the researchers by presenting different features of web pages, which are important to check the quality of web pages.
Originality: In this work, authors presented different approaches/techniques, algorithms and evaluation approaches in previous researches and identified some critical issues in page ranking & web mining, which provide future directions for the researchers, working in the area.</div
... Still, these search systems are sometimes not able to provide guarantee about reliable and accurate information but still, these systems provide better results than performing the task manually by experts. Many times these tools do not provide precise information because the IR system [4] returns information to internet users based on some specific retrieval criteria. For instance, it fetches web documents based on subject/title as given. ...
div>Purpose: Due to the exponential growth of internet users and internet traffic, information seekers are highly dependent upon search engines to extract relevant information. Due to the accessibility of a large amount of textual, audio, video etc. contents, the responsibility of search engines has increased.
Design/methodology/approach: The search engine provides relevant information to internet users concerning to their query; based on content, link structure etc. However, it does not provide the guarantee of the correctness of the information. The performance of a search engine is highly dependent upon the ranking module. The performance of the ranking module is dependent upon the link structure of web pages, which analyse through Web structure mining (WSM) and their content, which analyses through Web content mining (WCM). Web mining plays an important role in computing the rank of web pages.
Findings: In this article, web mining types, techniques, tools, algorithms and their challenges are presented. Further, it provides a critical comprehensive survey for the researchers by presenting different features of web pages, which are important to check the quality of web pages.
Originality: In this work, authors presented different approaches/techniques, algorithms and evaluation approaches in previous researches and identified some critical issues in page ranking & web mining, which provide future directions for the researchers, working in the area.</div
... The PDF file is universal no matter in Windows or UNIX system. Compared with other electronic documents, PDF has many advantages [22]. Lucene's internal parser can directly extract database format files and plain text format files without relying on third-party plug-ins. ...
In order to improve the search performance of rich text content, a cloud search engine system based on rich text content is designed. On the basis of traditional search engine hardware system, several hardware devices such as Solr index server, collector, Chinese word segmentation device and searcher are installed, and the data interface is adjusted. On the basis of hardware equipment and database support, this paper uses the open source Apache Tika framework to obtain the metadata of rich text documents, implements word segmentation according to the rich text content and semantics, and calculates the weight of each keyword. Input search keywords, establish a text index, use BM25 algorithm to calculate the similarity between keywords and text, and output the search results of rich text according to the similarity calculation results. The experimental results show that the design system has high recall rate, high throughput, and the construction time of each data item index in different files is short, which improves the search efficiency and search accuracy.
Reducing the long tail of the query latency distribution in modern warehouse scale computers is critical for improving performance and quality of service of workloads such as Web Search and Memcached. Traditional turbo boost increases a processor's voltage and frequency during a coarse-grain sliding window, boosting all queries that are processed during that window. However, the inability of such a technique to pinpoint tail queries for boosting limits its tail reduction benefit. In this work, we propose Adrenaline, an approach to leverage finer granularity, 10's of nanoseconds, voltage boosting to effectively rein in the tail latency with query-level precision. Two key insights underlie this work. First, emerging finer granularity voltage/frequency boosting is an enabling mechanism for intelligent allocation of the power budget to precisely boost only the queries that contribute to the tail latency; and second, per-query characteristics can be used to design indicators for proactively pinpointing these queries, triggering boosting accordingly. Based on these insights, Adrenaline effectively pinpoints and boosts queries that are likely to increase the tail distribution and can reap more benefit from the voltage/frequency boost. By evaluating under various workload configurations, we demonstrate the effectiveness of our methodology. We achieve up to a 2.50x tail latency improvement for Memcached and up to a 3.03x for Web Search over coarse-grained DVFS given a fixed boosting power budget. When optimizing for energy reduction, Adrenaline achieves up to a 1.81x improvement for Memcached and up to a 1.99x for Web Search over coarse-grained DVFS.
Modern "warehouse scale computers" (WSCs) continue to be embraced as homogeneous computing platforms. However, due to frequent machine replacements and upgrades, modern WSCs are in fact composed of diverse commodity microarchitectures and machine configurations. Yet, current WSCs are architected with the assumption of homogeneity, leaving a potentially significant performance opportunity unexplored.
In this paper, we expose and quantify the performance impact of the "homogeneity assumption" for modern production WSCs using industry-strength large-scale web-service workloads. In addition, we argue for, and evaluate the benefits of, a heterogeneity-aware WSC using commercial web-service production workloads including Google's web-search. We also identify key factors impacting the available performance opportunity when exploiting heterogeneity and introduce a new metric, opportunity factor, to quantify an application's sensitivity to the heterogeneity in a given WSC. To exploit heterogeneity in "homogeneous" WSCs, we propose "Whare-Map," the WSC Heterogeneity Aware Mapper that leverages already in-place continuous profiling subsystems found in production environments. When employing "Whare-Map", we observe a cluster-wide performance improvement of 15% on average over heterogeneity--oblivious job placement and up to an 80% improvement for web-service applications that are particularly sensitive to heterogeneity.
Ensuring the quality of service (QoS) for latency-sensitive applications while allowing co-locations of multiple applications on servers is critical for improving server utilization and reducing cost in modern warehouse-scale computers (WSCs). Recent work relies on static profiling to precisely predict the QoS degradation that results from performance interference among co-running applications to increase the number of "safe" co-locations. However, these static profiling techniques have several critical limitations: 1) a priori knowledge of all workloads is required for profiling, 2) it is difficult for the prediction to capture or adapt to phase or load changes of applications, and 3) the prediction technique is limited to only two co-running applications.
To address all of these limitations, we present Bubble-Flux, an integrated dynamic interference measurement and online QoS management mechanism to provide accurate QoS control and maximize server utilization. Bubble-Flux uses a Dynamic Bubble to probe servers in real time to measure the instantaneous pressure on the shared hardware resources and precisely predict how the QoS of a latency-sensitive job will be affected by potential co-runners. Once "safe" batch jobs are selected and mapped to a server, Bubble-Flux uses an Online Flux Engine to continuously monitor the QoS of the latency-sensitive application and control the execution of batch jobs to adapt to dynamic input, phase, and load changes to deliver satisfactory QoS. Batch applications remain in a state of flux throughout execution. Our results show that the utilization improvement achieved by Bubble-Flux is up to 2.2x better than the prior static approach.
Scale-out datacenters mandate high per-server throughput to get the maximum benefit from the large TCO investment. Emerging applications (e.g., data serving and web search) that run in these datacenters operate on vast datasets that are not accommodated by on-die caches of existing server chips. Large caches reduce the die area available for cores and lower performance through long access latency when instructions are fetched. Performance on scale-out workloads is maximized through a modestly-sized last-level cache that captures the instruction footprint at the lowest possible access latency.
In this work, we introduce a methodology for designing scalable and efficient scale-out server processors. Based on a metric of performance-density, we facilitate the design of optimal multi-core configurations, called pods. Each pod is a complete server that tightly couples a number of cores to a small last-level cache using a fast interconnect. Replicating the pod to fill the die area yields processors which have optimal performance density, leading to maximum per-chip throughput. Moreover, as each pod is a stand-alone server, scale-out processors avoid the expense of global (i.e., inter-pod) interconnect and coherence. These features synergistically maximize throughput, lower design complexity, and improve technology scalability. In 20nm technology, scale-out chips improve throughput by 5x-6.5x over conventional and by 1.6x-1.9x over emerging tiled organizations.
As much of the world's computing continues to move into the cloud, the overprovisioning of computing resources to ensure the performance isolation of latency-sensitive tasks, such as web search, in modern datacenters is a major contributor to low machine utilization. Being unable to accurately predict performance degradation due to contention for shared resources on multicore systems has led to the heavy handed approach of simply disallowing the co-location of high-priority, latency-sensitive tasks with other tasks. Performing this precise prediction has been a challenging and unsolved problem.
In this paper, we present Bubble-Up, a characterization methodology that enables the accurate prediction of the performance degradation that results from contention for shared resources in the memory subsystem. By using a bubble to apply a tunable amount of "pressure" to the memory subsystem on processors in production datacenters, our methodology can predict the performance interference between co-locate applications with an accuracy within 1% to 2% of the actual performance degradation. Using this methodology to arrive at "sensible" co-locations in Google's production datacenters with real-world large-scale applications, we can improve the utilization of a 500-machine cluster by 50% to 90% while guaranteeing a high quality of service of latency-sensitive applications.
Reliability at massive scale is one of the biggest challenges we face at Amazon.com, one of the largest e-commerce operations in the world; even the slightest outage has significant financial consequences and impacts customer trust. The Amazon.com platform, which provides services for many web sites worldwide, is implemented on top of an infrastructure of tens of thousands of servers and network components located in many datacenters around the world. At this scale, small and large components fail continuously and the way persistent state is managed in the face of these failures drives the reliability and scalability of the software systems. This paper presents the design and implementation of Dynamo, a highly available key-value storage system that some of Amazon's core services use to provide an "always-on" experience. To achieve this level of availability, Dynamo sacrifices consistency under certain failure scenarios. It makes extensive use of object versioning and application-assisted conflict resolution in a manner that provides a novel interface for developers to use.
Emerging scale-out workloads require extensive amounts of computational resources. However, data centers using modern server hardware face physical constraints in space and power, limiting further expansion and calling for improvements in the computational density per server and in the per-operation energy. Continuing to improve the computational resources of the cloud while staying within physical constraints mandates optimizing server efficiency to ensure that server hardware closely matches the needs of scale-out workloads.
In this work, we introduce CloudSuite, a benchmark suite of emerging scale-out workloads. We use performance counters on modern servers to study scale-out workloads, finding that today's predominant processor micro-architecture is inefficient for running these workloads. We find that inefficiency comes from the mismatch between the workload needs and modern processors, particularly in the organization of instruction and data memory systems and the processor core micro-architecture. Moreover, while today's predominant micro-architecture is inefficient when executing scale-out workloads, we find that continuing the current trends will further exacerbate the inefficiency in the future. In this work, we identify the key micro-architectural needs of scale-out workloads, calling for a change in the trajectory of server processors that would lead to improved computational density and power efficiency in data centers.
Interactive web services increasingly drive critical business workloads such as search, advertising, games, shopping, and finance. Whereas optimizing parallel programs and distributed server systems have historically focused on average latency and throughput, the primary metric for interactive applications is instead consistent responsiveness, i.e., minimizing the number of requests that miss a target latency. This paper is the first to show how to generalize work-stealing, which is traditionally used to minimize the makespan of a single parallel job, to optimize for a target latency in interactive services with multiple parallel requests.
We design a new adaptive work stealing policy, called tail-control, that reduces the number of requests that miss a target latency. It uses instantaneous request progress, system load, and a target latency to choose when to parallelize requests with stealing, when to admit new requests, and when to limit parallelism of large requests. We implement this approach in the Intel Thread Building Block (TBB) library and evaluate it on real-world workloads and synthetic workloads. The tail-control policy substantially reduces the number of requests exceeding the desired target latency and delivers up to 58% relative improvement over various baseline policies. This generalization of work stealing for multiple requests effectively optimizes the number of requests that complete within a target latency, a key metric for interactive services.
Online Search (OLS) is a key component of many popular Internet services. Datacenters running OLS consume significant amounts of energy. However, reducing their energy is challenging due to their tight response time requirements. A key aspect of OLS is that each user query goes to all or many of the nodes in the cluster, so that the overall time budget is dictated by the tail of the replies' latency distribution; replies see latency variations both in the network and compute. Previous work proposes to achieve load-proportional energy by slowing down the computation at lower datacenter loads based directly on response times (i.e., at lower loads, the proposal exploits the average slack in the time budget provisioned for the peak load). In contrast, we propose TimeTrader to reduce energy by exploiting the latency slack in the sub-critical replies which arrive before the deadline (e.g., 80% of replies are 3-4x faster than the tail). This slack is present at all loads and subsumes the previous work's load-related slack. While the previous work shifts the leaves' response time distribution to consume the slack at lower loads, TimeTrader reshapes the distribution at all loads by slowing down individual sub-critical nodes without increasing missed deadlines. TimeTrader exploits slack in both the network and compute budgets. Further, TimeTrader leverages Earliest Deadline First scheduling to largely decouple critical requests from the queuing delays of sub-critical requests which can then be slowed down without hurting critical requests. A combination of real-system measurements and at-scale simulations shows that without adding to missed deadlines, TimeTrader saves 15% and 40% energy at 90% and 30% loading, respectively, in a datacenter with 512 nodes, whereas previous work saves 0% and 30%. Further, as a proof-of-concept, we build a small-scale real implementation to evaluate TimeTrader and show 10-30% energy savings.
Modern "warehouse scale computers" (WSCs) continue to be embraced as homogeneous computing platforms. However, due to frequent machine replacements and upgrades, modern WSCs are in fact composed of diverse commodity microarchitectures and machine configurations. Yet, current WSCs are architected with the assumption of homogeneity, leaving a potentially significant performance opportunity unexplored.
In this paper, we expose and quantify the performance impact of the "homogeneity assumption" for modern production WSCs using industry-strength large-scale web-service workloads. In addition, we argue for, and evaluate the benefits of, a heterogeneity-aware WSC using commercial web-service production workloads including Google's web-search. We also identify key factors impacting the available performance opportunity when exploiting heterogeneity and introduce a new metric, opportunity factor, to quantify an application's sensitivity to the heterogeneity in a given WSC. To exploit heterogeneity in "homogeneous" WSCs, we propose "Whare-Map," the WSC Heterogeneity Aware Mapper that leverages already in-place continuous profiling subsystems found in production environments. When employing "Whare-Map", we observe a cluster-wide performance improvement of 15% on average over heterogeneity--oblivious job placement and up to an 80% improvement for web-service applications that are particularly sensitive to heterogeneity.
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 naïve 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.
Web search as a service is very impressive. Web search runs on thousands of servers which perform search on an index of billions of web pages. The search results must be both relevant to the user queries and reach the user in a fraction of a second. A web search service must guarantee the same QoS at all times even at the peak incoming traffic load. Not unjustifiably the web search service has attracted a lot of research attention. Despite the high research interest web search has gained, there are still plenty unknown about the functionality and the architecture of web search benchmarks. Much research has been done using commercial web search engines, like Bing or Google, but many details of these search engines are, of course, not disclosed to the public. We take an academically accepted web search benchmark and we perform a thorough characterization and analysis of it. We shed light in to the architecture and the functionality of the benchmark. We also investigate some prominent web search research issues. In particular, we study how intra-server index partitioning affects the response time and throughput and we also explore the potential use of low power servers for web search. Our results show that intra-server partitioning can reduce tail latencies and that low power servers given enough partitioning can provide same response times as conventional high performance servers.
Interactive services, such as Web search, recommendations, games, and finance, must respond quickly to satisfy customers. Achieving this goal requires optimizing tail (e.g., 99th+ percentile) latency. Although every server is multi-core, parallelizing individual requests to reduce tail latency is challenging because (1) service demand is unknown when requests arrive; (2) blindly parallelizing all requests quickly oversubscribes hardware resources; and (3) parallelizing the numerous short requests will not improve tail latency. This paper introduces Few-to-Many (FM) incremental parallelization, which dynamically increases parallelism to reduce tail latency. FM uses request service demand profiles and hardware parallelism in an offline phase to compute a policy, represented as an interval table, which specifies when and how much software parallelism to add. At runtime, FM adds parallelism as specified by the interval table indexed by dynamic system load and request execution time progress. The longer a request executes, the more parallelism FM adds. We evaluate FM in Lucene, an open-source enterprise search engine, and in Bing, a commercial Web search engine. FM improves the 99th percentile response time up to 32% in Lucene and up to 26% in Bing, compared to prior state-of-the-art parallelization. Compared to running requests sequentially in Bing, FM improves tail latency by a factor of two. These results illustrate that incremental parallelism is a powerful tool for reducing tail latency.
Reliability at massive scale is one of the biggest challenges we face at Amazon.com, one of the largest e-commerce operations in the world; even the slightest outage has significant financial consequences and impacts customer trust. The Amazon.com platform, which provides services for many web sites worldwide, is implemented on top of an infrastructure of tens of thousands of servers and network components located in many datacenters around the world. At this scale, small and large components fail continuously and the way persistent state is managed in the face of these failures drives the reliability and scalability of the software systems.
This paper presents the design and implementation of Dynamo, a highly available key-value storage system that some of Amazon's core services use to provide an "always-on" experience. To achieve this level of availability, Dynamo sacrifices consistency under certain failure scenarios. It makes extensive use of object versioning and application-assisted conflict resolution in a manner that provides a novel interface for developers to use.
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
The commoditization of hardware, data center economies of scale, and Internet-scale workload growth all demand greater power efficiency to sustain scalability. Traditional enterprise workloads, which are typically memory and I/O bound, have been well served by chip multiprocessors com- prising of small, power-efficient cores. Recent advances in mobile computing have led to modern small cores capable of delivering even better power efficiency. While these cores can deliver performance-per-Watt efficiency for data center workloads, small cores impact application quality-of-service robustness, and flexibility, as these workloads increasingly invoke computationally intensive kernels. These challenges constitute the price of efficiency. We quantify efficiency for an industry-strength online web search engine in production at both the microarchitecture- and system-level, evaluating search on server and mobile-class architectures using Xeon and Atom processors.
Traditionally, the efficiency and effectiveness of search systems have both been of great interest to the information retrieval community. However, an in-depth analysis on the interplay between the response latency of web search systems and users' search experience has been missing so far. In order to fill this gap, we conduct two separate studies aiming to reveal how response latency affects the user behavior in web search. First, we conduct a controlled user study trying to understand how users perceive the response latency of a search system and how sensitive they are to increasing delays in response. This study reveals that, when artificial delays are introduced into the response, the users of a fast search system are more likely to notice these delays than the users of a slow search system. The introduced delays become noticeable by the users once they exceed a certain threshold value. Second, we perform an analysis using a large-scale query log obtained from Yahoo web search to observe the potential impact of increasing response latency on the click behavior of users. This analysis demonstrates that latency has an impact on the click behavior of users to some extent. In particular, given two content-wise identical search result pages, we show that the users are more likely to perform clicks on the result page that is served with lower latency.
A web search query made to Microsoft Bing is currently parallelized by distributing the query processing across many servers. Within each of these servers, the query is, however, processed sequentially. Although each server may be processing multiple queries concurrently, with modern multicore servers, parallelizing the processing of an individual query within the server may nonetheless improve the user's experience by reducing the response time. In this paper, we describe the issues that make the parallelization of an individual query within a server challenging, and we present a parallelization approach that effectively addresses these challenges. Since each server may be processing multiple queries concurrently, we also present a adaptive resource management algorithm that chooses the degree of parallelism at run-time for each query, taking into account system load and parallelization efficiency. As a result, the servers now execute queries with a high degree of parallelism at low loads, gracefully reduce the degree of parallelism with increased load, and choose sequential execution under high load. We have implemented our parallelization approach and adaptive resource management algorithm in Bing servers and evaluated them experimentally with production workloads. The experimental results show that the mean and 95th-percentile response times for queries are reduced by more than 50% under light or moderate load. Moreover, under high load where parallelization adversely degrades the system performance, the response times are kept the same as when queries are executed sequentially. In all cases, we observe no degradation in the relevance of the search results.
Much of the success of the Internet services model can be attributed to the popularity of a class of workloads that we call Online Data-Intensive (OLDI) services. These work-loads perform significant computing over massive data sets per user request but, unlike their offline counterparts (such as MapReduce computations), they require responsiveness in the sub-second time scale at high request rates. Large search products, online advertising, and machine translation are examples of workloads in this class. Although the load in OLDI services can vary widely during the day, their energy consumption sees little variance due to the lack of energy proportionality of the underlying machinery. The scale and latency sensitivity of OLDI workloads also make them a challenging target for power management techniques. We investigate what, if anything, can be done to make OLDI systems more energy-proportional. Specifically, we evaluate the applicability of active and idle low-power modes to reduce the power consumed by the primary server components (processor, memory, and disk), while maintaining tight response time constraints, particularly on 95th-percentile latency. Using Web search as a representative example of this workload class, we first characterize a production Web search workload at cluster-wide scale. We provide a fine-grain characterization and expose the opportunity for power savings using low-power modes of each primary server component. Second, we develop and validate a performance model to evaluate the impact of processor- and memory-based low-power modes on the search latency distribution and consider the benefit of current and foreseeable low-power modes. Our results highlight the challenges of power management for this class of workloads. In contrast to other server workloads, for which idle low-power modes have shown great promise, for OLDI workloads we find that energy-proportionality with acceptable query latency can only be achieved using coordinated, full- system active low-power modes.
In this paper, we present EETCO: an estimation and exploration tool that provides qualitative assessment of data center design decisions on Total-Cost-of-Ownership (TCO) and environmental impact. It can capture the implications of many parameters including server performance, power, cost, and Mean-Time-To-Failure (MTTF). The tool includes a model for spare estimation needed to account for server failures and performance variability. The paper describes the tool model and its implementation, and presents experiments that explore tradeoffs offered by different server configurations, performance variability, MTTF, 2D vs 3D-stacked processors, and ambient temperature. These experiments reveal, for the data center configurations used in this study, several opportunities for profit and optimization in the datacenter ecosystem: (i) servers with different computing performance and power consumption merit exploration to minimize TCO and the environmental impact, (ii) performance variability is desirable if it comes with a drastic cost reduction, (iii) shorter processor MTTF is beneficial if it comes with a moderate processor cost reduction, (iv) increasing by few degrees the ambient datacenter temperature reduces the environmental impact with a minor increase in the TCO and (v) a higher cost for a 3D-stacked processor with shorter MTTF and higher power consumption can be preferred, over a conventional 2D processor, if it offers a moderate performance increase.
The distribution of videos over the Internet is drastically transforming how media is consumed and monetized. Content providers, such as media outlets and video subscription services, would like to ensure that their videos do not fail, start up quickly, and play without interruptions. In return for their investment in video stream quality, content providers expect less viewer abandonment, more viewer engagement, and a greater fraction of repeat viewers, resulting in greater revenues. The key question for a content provider or a content delivery network (CDN) is whether and to what extent changes in video quality can cause changes in viewer behavior. Our work is the first to establish a causal relationship between video quality and viewer behavior, taking a step beyond purely correlational studies. To establish causality, we use Quasi-Experimental Designs, a novel technique adapted from the medical and social sciences. We study the impact of video stream quality on viewer behavior in a scientific data-driven manner by using extensive traces from Akamai's streaming network that include 23 million views from 6.7 million unique viewers. We show that viewers start to abandon a video if it takes more than 2 s to start up, with each incremental delay of 1 s resulting in a 5.8% increase in the abandonment rate. Furthermore, we show that a moderate amount of interruptions can decrease the average play time of a viewer by a significant amount. A viewer who experiences a rebuffer delay equal to 1% of the video duration plays 5% less of the video in comparison to a similar viewer who experienced no rebuffering. Finally, we show that a viewer who experienced failure is 2.32% less likely to revisit the same site within a week than a similar viewer who did not experience a failure.
Search is the most heavily used web application in the world and is still growing at an extraordinary rate. Understanding the behaviors of web search engines, therefore, is becoming increasingly important to the design and deployment of data center systems hosting search engines. In this paper, we study three search query traces collected from real world web search engines in three different search service providers. The first part of our study is to uncover the patterns hidden in the query traces by analyzing the variations, frequencies, and locality of query requests. Our analysis reveals that, contradicted to some previous studies, real-world query traces do not follow well-defined probability models, such as Poisson distribution and log-normal distribution. The second part of our study is to deploy the real query traces and three synthetic traces generated using probability models proposed by other researchers on a Nutch based search engine. The measured performance data from the deployments further confirm that synthetic traces do not accurately reflect the real traces. We develop an evaluation tool that can collect performance metrics on-line with negligible overhead. The performance metrics include average response time, CPU utilization, Disk accesses, and cycles-per-instructions, etc. The third of our study is to compare the search engine with representative benchmarks, namely Gridmix, SPECweb2005, TPC-C, SPECCPU2006, and HPCC, with respect to basic architecture-level characteristics and performance metrics, such as instruction mix, processor pipeline stall breakdown, memory access latency, and disk accesses. The experimental results show that web search engines have a high percentage of load/store instructions, but have good cache/memory performance. We hope those results presented in this paper will enable system designers to gain insights on optimizing systems hosting search engines.
The web today is increasingly characterized by social and real-time signals, which we believe represent two frontiers in information retrieval. In this paper, we present Early bird, the core retrieval engine that powers Twitter's real-time search service. Although Early bird builds and maintains inverted indexes like nearly all modern retrieval engines, its index structures differ from those built to support traditional web search. We describe these differences and present the rationale behind our design. A key requirement of real-time search is the ability to ingest content rapidly and make it searchable immediately, while concurrently supporting low-latency, high-throughput query evaluation. These demands are met with a single-writer, multiple-reader concurrency model and the targeted use of memory barriers. Early bird represents a point in the design space of real-time search engines that has worked well for Twitter's needs. By sharing our experiences, we hope to spur additional interest and innovation in this exciting space.
Emerging scale-out workloads require extensive amounts of computational resources. However, data centers using modern server hardware face physical constraints in space and power, limiting further expansion and calling for improvements in the computational density per server and in the per-operation energy. Continuing to improve the computational resources of the cloud while staying within physical constraints mandates optimizing server efficiency to ensure that server hardware closely matches the needs of scale-out workloads. In this work, we introduce CloudSuite, a benchmark suite of emerging scale-out workloads. We use performance counters on modern servers to study scale-out workloads, finding that today's predominant processor micro-architecture is inefficient for running these workloads. We find that inefficiency comes from the mismatch between the workload needs and modern processors, particularly in the organization of instruction and data memory systems and the processor core micro-architecture. Moreover, while today's predominant micro-architecture is inefficient when executing scale-out workloads, we find that continuing the current trends will further exacerbate the inefficiency in the future. In this work, we identify the key micro-architectural needs of scale-out workloads, calling for a change in the trajectory of server processors that would lead to improved computational density and power efficiency in data centers.
The importance of a Web page is an inherently subjective matter, which depends on the readers interests, knowledge and attitudes. But there is still much that can be said objectively about the relative importance of Web pages. This paper describes PageRank, a mathod for rating Web pages objectively and mechanically, effectively measuring the human interest and attention devoted to them. We compare PageRank to an idealized random Web surfer. We show how to efficiently compute PageRank for large numbers of pages. And, we show how to apply PageRank to search and to user navigation.
We survey many of the measures used to describe and evaluate the efficiency and effectiveness of large-scale search services. These measures, herein visualized versus verbalized, reveal a domain rich in complexity and scale. We cover six principle facets of search: the query space, users' query sessions, user behavior, operational requirements, the content space, and user demographics. While this paper focuses on measures, the measurements themselves raise questions and suggest avenues of further investigation.
In current commercial Web search engines, queries are processed in the conjunctive mode, which requires the search engine to compute the intersection of a number of posting lists to determine the documents matching all query terms. In practice, the intersection operation takes a significant fraction of the query processing time, for some queries dominating the total query latency. Hence, efficient posting list intersection is critical for achieving short query latencies. In this work, we focus on improving the performance of posting list intersection by leveraging the compute capabilities of recent multicore systems. To this end, we consider various coarse-grained and fine-grained parallelization models for list intersection. Specifically, we present an algorithm that partitions the work associated with a given query into a number of small and independent tasks that are subsequently processed in parallel. Through a detailed empirical analysis of these alternative models, we demonstrate that exploiting parallelism at the finest-level of granularity is critical to achieve the best performance on multicore systems. On an eight-core system, the fine-grained parallelization method is able to achieve more than five times reduction in average query processing time while still exploiting the parallelism for high query throughput.
Much of the success of the Internet services model can be attributed to the popularity of a class of workloads that we call Online Data-Intensive (OLDI) services. These workloads perform significant computing over massive data sets per user request but, unlike their offline counterparts (such as MapReduce computations), they require responsiveness in the sub-second time scale at high request rates. Large search products, online advertising, and machine translation are examples of workloads in this class. Although the load in OLDI services can vary widely during the day, their energy consumption sees little variance due to the lack of energy proportionality of the underlying machinery. The scale and latency sensitivity of OLDI workloads also make them a challenging target for power management techniques. We investigate what, if anything, can be done to make OLDI systems more energy-proportional. Specifically, we evaluate the applicability of active and idle low-power modes to reduce the power consumed by the primary server components (processor, memory, and disk), while maintaining tight response time constraints, particularly on 95th-percentile latency. Using Web search as a representative example of this workload class, we first characterize a production Web search workload at cluster-wide scale. We provide a fine-grain characterization and expose the opportunity for power savings using low-power modes of each primary server component. Second, we develop and validate a performance model to evaluate the impact of processor- and memory-based low-power modes on the search latency distribution and consider the benefit of current and foreseeable low-power modes. Our results highlight the challenges of power management for this class of workloads. In contrast to other server workloads, for which idle low-power modes have shown great promise, for OLDI workloads we find that energy-proportionality with acceptable query latency can only be achieved using coordinated, full-system active low-power modes.
As computation continues to move into the cloud, the computing platform of interest no longer resembles a pizza box or a refrigerator, but a warehouse full of computers. These new large datacenters are quite different from traditional hosting facilities of earlier times and cannot be viewed simply as a collection of co-located servers. Large portions of the hardware and software resources in these facilities must work in concert to efficiently deliver good levels of Internet service performance, something that can only be achieved by a holistic approach to their design and deployment. In other words, we must treat the datacenter itself as one massive warehouse-scale computer (WSC). We describe the architecture of WSCs, the main factors influencing their design, operation, and cost structure, and the characteristics of their software base. We hope it will be useful to architects and programmers of today's WSCs, as well as those of future many-core platforms which may one day implement the equivalent of today's WSCs on a single board.
Amenable to extensive parallelization, Google's web search application lets different queries run on different processors and, by partitioning the overall index, also lets a single query use multiple processors. to handle this workload, Googless architecture features clusters of more than 15,000 commodity-class PCs with fault tolerant software. This architecture achieves superior performance at a fraction of the cost of a system built from fewer, but more expensive, high-end servers.
Brawny cores still beat wimpy cores, most of the time
- Hölzle Urs
Urs Hölzle. 2010. Brawny cores still beat wimpy cores, most of the time. IEEE Micro 30, 4 (2010), 1-2.
Latency is everywhere and it costs you sales-How to crush it
- Todd Hoff
Todd Hoff. 2009. Latency is everywhere and it costs you sales-How to crush it. High Scalability. Retrieved April 9,
2019 from http://www.highscalability.com/latency-everywhere-and-it-costs-you-sales-how-crush-it.
Work stealing for interactive services to meet target latency
- J Li
- K Agrawal
- S Elnikety
- Y He
- I Lee
- C Lu
- K S Mckinley
J. Li, K. Agrawal, S. Elnikety, Y. He, I. Lee, C. Lu, K. S. McKinley, et al. 2016. Work stealing for interactive services
to meet target latency. In Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel
Programming. ACM, New York, NY, 14.
Exploiting processor heterogeneity in interactive services
- Yuxiong Shaolei Ren
- Sameh He
- Kathryn S Elnikety
- Mckinley
Shaolei Ren, Yuxiong He, Sameh Elnikety, and Kathryn S. McKinley. 2013. Exploiting processor heterogeneity in
interactive services. In Proceedings of the 10th International Conference on Autonomic Computing (ICAC'13). 45-58.
Earlybird: Real-time search at Twitter
- Michael Busch
- Krishna Gade
- Brian Larson
- Patrick Lok
- Samuel Luckenbill
- James Lin
Lucene Scoring Explanation. Retrieved April 9 209 from lucene
- Lucene
Lucene. 2012. Lucene Scoring Explanation. Retrieved April 9, 209 from lucene.apache.org/core/4_0_0/core/org/
apache/lucene/search/similarities/TFIDFSimilarity.html.
Lucene Variable Integer Format
- Lucene
Lucene. 2012. Lucene Variable Integer Format. Retrieved April 9, 2019 from https://lucene.apache.org/core/4_0_0/
core/org/apache/lucene/store/DataOutput.html#write VInt(int).
Hinrich Schütze, Introduction to Information Retrieval
- D Christopher
- Prabhakar Manning
- Raghavan
Urs Hölzle, Web Search for a Planet: The Google Cluster Architecture
- André Luiz
- Jeffrey Barroso
- Dean
- Apache
Apache. 2012. Nutch Crawl Tutorial. Retrieved April 9, 2019 from https://wiki.apache.org/nutch/NutchTutorial.
- Christopher D Manning
- Prabhakar Raghavan
- Hinrich Schütze
Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. 2008. Introduction to Information Retrieval. Vol.
Manning Prabhakar Raghavan and Hinrich Schütze
- D Christopher
- Hinrich Manning Prabhakar Raghavan
- Schütze