Web Traces Research Articles

Identifying Users Across Social Tagging Systems

How much do tagging activities tell about a user? Is it possible to identify people in Delicious based on the tags, which they use in Flickr? In this paper we study those questions and investigate whether users can be identified across social tagging systems. We combine two kinds of information: their user ids and their tags. We introduce and compare a variety of approaches to measure the distance between user profiles for identification. With the best performing combination we achieve, depending on the actual settings, accuracies of between 60% and 80% which demonstrates that the traces of Web 2.0 users can reveal quite much about their identity.

Machine Learning-Based Scaling Management for Kubernetes Edge Clusters

Kubernetes, the container orchestrator for cloud-deployed applications, offers automatic scaling for the application provider in order to meet the ever-changing intensity of processing demand. This auto-scaling feature can be customized with a parameter set, but those management parameters are static while incoming Web request dynamics often change, not to mention the fact that scaling decisions are inherently reactive, instead of being proactive. We set the ultimate goal of making cloud-based applications' management easier and more effective. We propose a Kubernetes scaling engine that makes the auto-scaling decisions apt for handling the actual variability of incoming requests. In this engine various machine learning forecast methods compete with each other via a short-term evaluation loop in order to always give the lead to the method that suits best the actual request dynamics. We also introduce a compact management parameter for the cloud-tenant application provider to easily set their sweet spot in the resource over-provisioning vs. SLA violation trade-off. We motivate our scaling solution with analytical modeling and evaluation of the current Kubernetes behavior. The multi-forecast scaling engine and the proposed management parameter are evaluated both in simulations and with measurements on our collected Web traces to show the improved quality of fitting provisioned resources to service demand. We find that with just a few, but fundamentally different, and competing forecast methods, our auto-scaler engine, implemented in Kubernetes, results in significantly fewer lost requests with just slightly more provisioned resources compared to the default baseline.

Performance Assessment of Time Series Forecasting Models for Cloud Datacenter Networks’ Workload Prediction

The resource scaling has been influential in enabling the cloud service providers to provision the resources on-demand effectively. The prior estimation of workloads helps in addressing the scaling issues arises due to dynamic nature of the resource demands. In this paper, we evaluate six different forecasting approaches over real world workload data traces of web and cloud servers. The entire analysis is carried out three times as three different functions are used to measure the deviation in forecasts. The three forecast error measures are root mean squared error, mean absolute error, and mean absolute scaled error. We also carried out a statistical evaluation using Friedman test and Finner post-hoc analysis. The study concludes that the auto ARIMA process outperforms other models and achieves the best rank in the statistical analysis.

Information Market for Web Browsing

Browsing privacy solutions are faced with an uphill battle to deployment. Many operate counter to the economic objectives of popular online services (e.g., by completely blocking ads) and do not provide enough incentive for users who may be subject to performance degradation for deploying them. In this study, we take a step towards realizing a system for online privacy that is mutually beneficial to users and online advertisers: an information market. This system not only maintains economic viability for online services, but provides users with financial compensation to encourage them to participate. We prototype and evaluate an information market that provides privacy and revenue to users while preserving and sometimes improving their Web performance. We evaluate feasibility of the market via a one month field study with 63 users and find that users are indeed willing to sell their browsing information. We also use Web traces of millions of users to drive a simulation study to evaluate the system at scale. We find that the system can indeed be profitable to both users and online advertisers.

Stochastic Resource Provisioning for Containerized Multi-Tier Web Services in Clouds

Under today's bursty web traffic, the fine-grained per-container control promises more efficient resource provisioning for web services and better resource utilization in cloud datacenters. In this paper, we present Two -stage S tochastic P rogramming R esource A llocator (2SPRA). It optimizes resource provisioning for containerized n-tier web services in accordance with fluctuations of incoming workload to accommodate predefined SLOs on response latency. In particular, 2SPRA is capable of minimizing resource over-provisioning by addressing dynamics of web traffic as workload uncertainty in a native stochastic optimization model. Using special-purpose OpenOpt optimization framework, we fully implement 2SPRA in Python and evaluate it against three other existing allocation schemes, in a Docker-based CoreOS Linux VMs on Amazon EC2. We generate workloads based on four real-world web traces of various traffic variations: AOL, WorldCup98, ClarkNet, and NASA. Our experimental results demonstrate that 2SPRA achieves the minimum resource over-provisioning outperforming other schemes. In particular, 2SPRA allocates only 6.16 percent more than application's actual demand on average and at most 7.75 percent in the worst case. It achieves 3x further reduction in total resources provisioned compared to other schemes delivering overall cost-savings of 53.6 percent on average and up to 66.8 percent. Furthermore, 2SPRA demonstrates consistency in its provisioning decisions and robust responsiveness against workload fluctuations.

Resource management scheme based on ubiquitous data analysis.

Resource management of the main memory and process handler is critical to enhancing the system performance of a web server. Owing to the transaction delay time that affects incoming requests from web clients, web server systems utilize several web processes to anticipate future requests. This procedure is able to decrease the web generation time because there are enough processes to handle the incoming requests from web browsers. However, inefficient process management results in low service quality for the web server system. Proper pregenerated process mechanisms are required for dealing with the clients' requests. Unfortunately, it is difficult to predict how many requests a web server system is going to receive. If a web server system builds too many web processes, it wastes a considerable amount of memory space, and thus performance is reduced. We propose an adaptive web process manager scheme based on the analysis of web log mining. In the proposed scheme, the number of web processes is controlled through prediction of incoming requests, and accordingly, the web process management scheme consumes the least possible web transaction resources. In experiments, real web trace data were used to prove the improved performance of the proposed scheme.

A COOPERATIVE MODEL FOR PREFERENCE-BASED INFORMATION SHARING IN NARROW BANDWIDTH NETWORKS

Users of wide area network applications are usually concerned about both response time and content validity. The common solution of client-side caching that reuses cached content based on arbitrary time-to-live may not be applicable in narrow bandwidth environment, where heavy load is imposed on sparse transmission abilities. In such cases, some users may wait for a long time for fresh content extracted from the origin server although they would settle for obsolescent content, while other users may receive the cached copy which is considered valid, although they would be ready to wait longer for fresher content. In this work, a new model for caching is introduced, where clients introduce preferences regarding their expectations for the time they are willing to wait, and the level of obsolescence they are willing to tolerate. The cache manager considers user preferences, and is capable of balancing the relative importance of each dimension. A cost model is used to determine which of the following three alternatives is most promising: delivery of a local cached copy, delivery of a copy from a cooperating cache, or delivery of a fresh copy from the origin server. The proposed model is proven to be useful by experiments that used both synthetic data and real Web traces simulation. The experiments reveal that using the proposed model, it becomes possible to meet client needs with reduced latency. We also show the benefit of cache cooperation in increasing hit ratios and reducing latency. A prototype of the proposed model was built and deployed on real-world environment demonstrating how users can set preferences towards Web pages, and how cache managers are affected.

Palaeonvironmental and palaeoecological significance of flamingo-like footprints in shallow-lacustrine rocks: An example from the Oligocene–Miocene Vinchina Formation, Argentina

This article describes the lacustrine trace-fossil assemblage of the Late Oligocene–Early Miocene Vinchina Formation of northwest Argentina. The thick (> 5000 m) continental succession of the formation is essentially fluvial with thin aeolian and lacustrine intervals. The trace-fossil assemblage from the lacustrine facies is dominated by bird footprints, notably flamingo-like palmate bird footprints, and also contains invertebrate traces. The assemblage is of contrasting composition with those of the ubiquitous fluvial facies of the Vinchina Formation. We identify the possible trace maker of the web-footed bird footprints and infer the palaeoenvironmental and palaeoecological meaning of the lacustrine trace-fossil assemblage of the Vinchina Formation. The lacustrine succession is mainly composed of wave-rippled fine-grained sandstones and siltstones and wave-rippled heterolithic facies, with subordinate laminated mudstone and medium-grained sandstone with parallel lamination or cross-bedding. Metre-scale shallowing-upward cycles are typical and desiccation cracks were observed in a single bedding plane. The analysed interval was deposited in a wave-dominated littoral zone of a shallow permanent lake basin. Ichnofossils were found mostly in three trampled horizons of the upper part of the analysed succession. The trace-fossil assemblage is dominated by Phoenicopterichnum isp. (flamingo-like footprints), slender bird tracks without web traces, and triangular and fusiform hypichnial ridges (interpreted as bird undertracks). The remaining trace fossils are Lockeia siliquaria (bivalve resting trace), Rusophycus isp. (shallow arthropod burrow), Taenidium barretti (endostratal meniscate burrow) and small hypichnial double knobs (possible beak probing marks). Neoichnological observations on modern Chilean flamingo footprints ( Phoenicopterus chilensis) suggest that Phoenicopterichnum isp. is morphologically akin to modern flamingo footprints, although its average size is slightly smaller. The likely producers of the fossil footprints are members of the Palaelodidae and Phoenicopteridae, which are recorded in South America since the Late Oligocene. Phoenicopterichnum isp. appears in cuasi-parallel trackways with short pace length and forming a low angle with ripple crests. By comparison with observations of modern flamingo behaviour during this study and of shorebird studies from the literature, these tracks and trackways likely reflect flock-feeding behaviour (probably filter feeding) in a subaqueous belt parallel to the waterline. Invertebrate ichnofossils that appear on the same slabs from trampled horizons are mainly triangular and fusiform hypichnial ridges, while Phoenicopterichnum isp. and sparse small hypichnial double knobs also occur. In consequence, it is possible that these birds were foraging on small invertebrates (represented by Lockeia siliquaria, Rusophycus isp. and probably Taenidium barretti) in the coast of the Vinchina lake. The only fossil evidence for these invertebrates is the impression of articulated valves probably belonging to a small mollusc (potential producer of Lockeia). Trace-fossil assemblages dominated by flamingo-like footprints (including ichnogenera Phoenicopterichnum, Culcitapeda and similar unnamed tracks) are indicative of alkaline and/or saline waters, as suggested by the specialised filter-feeding mechanism of Late Oligocene to modern Phoenicopteriformes. These particular assemblages are distinguished as a subset within the “shorebird ichnofacies” with a definite palaeoenvironmental and palaeoecological meaning: the Phoenicopterichnum ichnosubfacies.

Autonomous learning of load and traffic patterns to improve cluster utilization

Adaptive clustering aims at improving cluster utilization for varying load and traffic patterns. Locality-based least-connection with replication (LBLCR) scheduling that comes with Linux is designed to help improve cluster utilization through adaptive clustering. A key issue with LBLCR, however, is that cluster performance depends much on a single threshold value that is used to determine adaptation. Once set, the threshold remains fixed, regardless of the load and traffic patterns. If a cluster of PCs is to adapt to different traffic patterns for high utilization, a good threshold has to be selected and used dynamically. We present in this paper an adaptive clustering framework that autonomously learns and adapts to different load and traffic patterns at runtime with no administrator intervention. The cluster is configured once and for all. As the patterns change, the cluster automatically expands/contracts to meet the changing demands. At the same time, the patterns are proactively learned so that when similar patterns emerge in the future, the cluster knows what to do to improve utilization. We have implemented this autonomous learning method and compared it with LBLCR using published Web traces. Experimental results indicate that our autonomous learning method produces high performance scalability and adaptability for different patterns. On the other hand LBLCR-based clustering suffers from performance scalability and adaptability for different traffic patterns since it is not designed to obtain good threshold values and use them at runtime.

A Long-Range Dependent Model for Network Traffic with Flow-Scale Correlations

For more than a decade, it has been observed that network traffic exhibits long-range dependence and many models have been proposed relating this property to heavy-tailed flow durations. However, none of these models consider correlations at flow scale. Such correlations exist and will become more prominent in the future Internet with the emergence of flow-aware control mechanisms correlating a flow's transmission to its characteristics (size, duration, etc.). In this article, we study the impact of the correlation between flow rates and durations on the long-range dependence of aggregate traffic. Our results extend those of existing models by showing that two possible regimes of long-range dependence exist at different time scales. The long-range dependence in each regime can be stronger or weaker than standard predictions, depending on the conditional statistics between the flow rates and durations. In the independent case, our proposed model consistently reduces to former approaches. The pertinence of our model is validated on real web traffic traces, and its ability to accurately explain the Hurst parameter is validated on both web traces and numerical simulations.

Group Testing Based Detection of Web Service DDoS Attackers

The Distributed Denial of Service attack (DDoS) is one of the major threats to network security that exhausts network bandwidth and resources. Recently, an efficient approach Live Baiting was proposed for detecting the identities of DDoS attackers in web service using low state overhead without requiring either the models of legitimate requests nor anomalous behavior. However, Live Baiting has two limitations. First, the detection algorithm adopted in Live Baiting starts with a suspects list containing all clients, which leads to a high false positive probability especially for large web service with a huge number of clients. Second, Live Baiting adopts a fixed threshold based on the expected number of requests in each bucket during the detection interval without the consideration of daily and weekly traffic variations. In order to address the above limitations, we first distinguish the clients activities (Active and Non-Active clients during the detection interval) in the detection process and then further propose a new adaptive threshold based on the Change Point Detection method, such that we can improve the false positive probability and avoid the dependence of detection on sites and access patterns. Extensive trace-driven simulation has been conducted on real Web trace to demonstrate the detection efficiency of the proposed scheme in comparison with the Live Baiting detection scheme.

Preliminary Report on Hominid and Other Vertebrate Footprints from the Late Quaternary Strata of Jeju Island, Korea

Numerous footprints attributable to hominids, artiodactyla, proboscidea, carnivores, and birds have been preserved in the Late Quarternary strata of Jeju Island, Korea, which is composed of volcaniclastic sediments deposited in a shoreline environment. The hominid footprints are 12–26 cm long and 6–12 cm wide and are characterized by impressions of medial arch, heel, and ball. These are considered to have been made by at least nine humans of different sites. The artiodactyl footprints are up to 8 cm in length and are characterized by impressions of paired hooves. The diverse range of footprint sizes indicate herds of artiodactyls, composed of juvenile, young, and adult. The footprints attributable to proboscideans are characterized by large circular tracks about 40 cm in diameter. The carnivore footprints are generally characterized by impressions of pads and toes. Diverse bird footprints are recognized on the basis of size, length/width ratio, interdigital angles, curvature of digits, and the presence or absence of web and hallux traces. Fish trails, diverse invertebrate trace fossils, and body fossils are also observed. These fossils extended the knowledge of their rarely reported geographic distribution throughout the world and also enable the paleoenvironment and paleoecology of the strata to be interpreted.

Utilizing Binary Rewriting for Improving End-Host Security

Conventional methods supporting Java binary security mainly rely on the security of the host Java Virtual Machine (JVM). However, malicious Java binaries keep exploiting the vulnerabilities of JVMs, escaping their sandbox restrictions and allowing attacks on end-user systems. Administrators must confront the difficulties and dilemmas brought on by security upgrades. On the other hand, binary rewriting techniques have been advanced to allow users to enforce security policies directly on the mobile code. They have the advantages of supporting a richer set of security policies and a self-constrained written code. However, the high administrative and performance overhead caused by security configuration and code rewriting have prevented rewriters from becoming a practical security tool. In this paper, we address these problems by integrating binary code rewriters with Web caching proxies and build the security system called PB-JARS, a Proxy-based JAva Rewriting System. PB-JARS works as a complimentary system to existing JVM security mechanisms by placing another line of defense between users and their end-user systems. It gives system administrators centralized security control and management for the mobile code and security policies. We evaluated PB-JARS using a real Java binary traffic model derived from analyzing real Web trace records. Our results show that adding binary rewriting to a Web caching system can be very efficient in improving end-host security at a low cost.

DESIGN AND IMPLEMENTATION OF A P2P COOPERATIVE PROXY CACHE SYSTEM

In this paper, we design and implement a P2P cooperative proxy caching system based on a novel P2P cooperative proxy caching scheme. To effectively locate the cached web documents, a TTL-based routing protocol is proposed to manage the query and response messages in the P2P cooperative proxy cache system. Furthermore, we design a predict query-route algorithm to improve the TTL-based routing protocol by adding extra information in the query message packets. To select a suitable cache replacement algorithm for the P2P cooperative proxy cache system, three different cache replacement algorithms, LRU, LFU and SIZE, are evaluated using web trace based performance studies on the implemented P2P cooperative proxy cache system. The experimental results show that LRU is an overall better cache replacement algorithm for the P2P proxy cache system although SIZE based cache replacement approach produces slightly better cache hit ratio when cache size is very small. The performance studies also demonstrate that the proposed message routing protocols significantly improve the performance of the P2P cooperative proxy cache system, in terms of cache hit ratio, byte hit ratio, user request latency, and the number of query messages generated in the proxy cache system, compared to the flooding based message routing protocol.

Optimal Replica Placement under TTL-Based Consistency

Geographically replicating popular objects in the Internet speeds up content distribution at the cost of keeping the replicas consistent and up-to-date. The overall effectiveness of replication can be measured by the total communication cost consisting of client accesses and consistency management, both of which depend on the locations of the replicas. This paper investigates the problem of placing replicas under the widely used TTL-based consistency scheme. A polynomial-time algorithm is proposed to compute the optimal placement of a given number of replicas in a network. The new replica placement scheme is compared, using real Internet topologies and Web traces, against two existing approaches which do not consider consistency management or assume invalidation-based consistency scheme. The factors affecting their performance are identified and discussed

An analytical approach to providing controllable differentiated quality of service in Web servers

Provisioning quality of service (QoS) in Web servers has gained immense importance because Web servers are a major part of the Internet. To deliver the pledged QoS, Web service providers need control over the allocation of the resources in their Web servers. Control is also necessary for reaching the optimal resource allocation through proper service differentiation. In this paper, we propose and investigate an analytic approach that enables the service providers to deploy a differentiated service policy that offers this control. The proposed service policy is configurable by tunable control parameters. We devise the relationships between the performance measures and these parameters by adopting a unique queuing theoretic approach. Once these relationships are established, we describe how these parameters can be set to their most appropriate values depending on the objectives of the service providers. We illustrate the usefulness of our approach by conducting the analysis on a real Web trace.

Modeling correlations in web traces and implications for designing replacement policies

A number of web cache-related algorithms, such as replacement and prefetching policies, rely on specific characteristics present in the sequence of requests for efficient performance. Further, there is an increasing need to synthetically generate long traces of web requests for studying the performance of algorithms and systems related to the web. These reasons motivate us to obtain a simple and accurate model of web request traces. Our Markovian model precisely captures the degrees to which temporal correlations and document popularity influence web trace requests. We describe a mathematical procedure to extract the model parameters from real traces and generate synthetic traces using these parameters. This procedure is verified by standard statistical analysis. We also validate the model by comparing the hit ratios for real traces and their synthetic counterparts under various caching algorithms. As an important by-product, the model provides guidelines for designing efficient replacement algorithms. We obtain optimal algorithms given the parameters of the model. We also introduce a spectrum of practicable, high-performance algorithms that adapt to the degree of temporal correlation present in the request sequence, and discuss related implementation concerns.

Preferential treatment for short flows to reduce web latency

In this paper, we propose short flow differentiating (SFD) algorithm to reduce the user-perceived web latency. This algorithm gives short flows preferential treatment. We implement SFD algorithm as a simple differentiated services policy and evaluate its performance in simulation. We find that SFD algorithm reduces the transmission latency of short flows and the response time to retrieve representative web pages by about 30%. Using web traces, we demonstrate that 99% web pages would be transferred faster. SFD penalizes long flows, but the penalty is well bounded. We further evaluate how different schemes trade-off the performance between short and long flows.

Fair scheduling in Internet routers

Input buffered switch architecture has become attractive for implementing high performance routers and expanding use of the Internet sees an increasing need for quality of service. It is challenging to provide a scheduling technique that is both highly efficient and fair in resource allocation. In this paper, we first introduce an iterative fair scheduling (IFS) scheme for input buffered switches that supports fair bandwidth distribution among the flows and achieves asymptotically 100 percent throughput. The IFS is evaluated both under synthetic workload and with Web traces from the Internet. Compared to the commonly used synthetic input, our simulation results reveal significant difference in performance when the real network traffic is employed. We then consider fair scheduling under various buffer management mechanisms and analyze their impact on the fairness in bandwidth allocation. Our studies indicate that early packet discard in anticipation of congestion is necessary and per-flow based buffering is effective for protecting benign users from being adversely affected by misbehaving traffic. Buffer allocation according to bandwidth reservation is especially helpful when the input traffic is highly bursty.

Caching and Scheduling for Broadcast Disk Systems

Unicast connections lead to performance and scalability problems when a large client population attempts to access the same data. Broadcast push and broadcast disk technology address the problem by broadcasting data items from a server to a large number of clients. Broadcast disk performance depends mainly on caching strategies at the client site and on how the broadcast is scheduled at the server site. An on-line broadcast disk paging strategy makes caching decisions without knowing future page requests or access probabilities. This paper gives new implementations of existing on-line algorithms and reports on extensive empirical investigations. The gray algorithm [Khanna and Liberatore 2000] always outperformed other on-line strategies on both synthetic and Web traces. Moreover, caching limited the skewness of broadcast schedules, and led to favor efficient caching algorithms over refined scheduling strategies when the cache was large.