Tong Yang, Ruian Duan, Jianyuan Lu, Shenjiang Zhang, Huichen Dai, B. Liu
The sizes of routing table in backbone routers continue to keep a rapid growth and some of them currently increase up to 400K entries [1]. An effective solution to deflate the large table is the routing table compression. Meanwhile, there is an increasingly urgent demand for fast routing update mainly due to the change of network topology and new emerging Internet functionalities. Furthermore, the Internet link transmission speed has scaled up to 100Gbps commercially and towards 400Gbps Ethernet for laboratory experiments, resulting in a raring need of ultra-fast routing lookup. To achieve high performance, backbone routers must gracefully handle the three issues simultaneously: routing table Compression, fast routing Lookup, and fast incremental Update (CLUE), while previous works often only concentrate on one of the three dimensions. To address these issues, we propose a complete set of solutions-CLUE, by improving previous works and adding a novel incremental update mechanism. CLUE consists of three parts: a routing table compression algorithm, an improved parallel lookup mechanism, and a new fast incremental update mechanism. The routing table compression algorithm is based on ONRTC algorithm [2], a base for fast TCAM parallel lookup and fast update of TCAM. The second part is the improvement of the logical caching scheme for dynamic load balancing parallel lookup mechanism [3]. The third one is the conjunction of the trie, TCAM and redundant prefixes update algorithm. We analyze the performance of CLUE by mathematical proof, and draw the conclusion that speedup factor is proportional to the hit rate of redundant prefixes in the worst case, which is also confirmed by experimental results. Large-scale experimental results show that, compared with the mechanism in [3], CLUE only needs about 71% TCAM entries, 4.29% update time, and 3/4 dynamic redundant prefixes for the same throughput when using four TCAMs. In addition, CLUE has another advantage over the mechanism in [3] - the frequent interactions between control plane and data plane caused by redundant prefixes update can be avoided.
{"title":"CLUE: Achieving Fast Update over Compressed Table for Parallel Lookup with Reduced Dynamic Redundancy","authors":"Tong Yang, Ruian Duan, Jianyuan Lu, Shenjiang Zhang, Huichen Dai, B. Liu","doi":"10.1109/ICDCS.2012.79","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.79","url":null,"abstract":"The sizes of routing table in backbone routers continue to keep a rapid growth and some of them currently increase up to 400K entries [1]. An effective solution to deflate the large table is the routing table compression. Meanwhile, there is an increasingly urgent demand for fast routing update mainly due to the change of network topology and new emerging Internet functionalities. Furthermore, the Internet link transmission speed has scaled up to 100Gbps commercially and towards 400Gbps Ethernet for laboratory experiments, resulting in a raring need of ultra-fast routing lookup. To achieve high performance, backbone routers must gracefully handle the three issues simultaneously: routing table Compression, fast routing Lookup, and fast incremental Update (CLUE), while previous works often only concentrate on one of the three dimensions. To address these issues, we propose a complete set of solutions-CLUE, by improving previous works and adding a novel incremental update mechanism. CLUE consists of three parts: a routing table compression algorithm, an improved parallel lookup mechanism, and a new fast incremental update mechanism. The routing table compression algorithm is based on ONRTC algorithm [2], a base for fast TCAM parallel lookup and fast update of TCAM. The second part is the improvement of the logical caching scheme for dynamic load balancing parallel lookup mechanism [3]. The third one is the conjunction of the trie, TCAM and redundant prefixes update algorithm. We analyze the performance of CLUE by mathematical proof, and draw the conclusion that speedup factor is proportional to the hit rate of redundant prefixes in the worst case, which is also confirmed by experimental results. Large-scale experimental results show that, compared with the mechanism in [3], CLUE only needs about 71% TCAM entries, 4.29% update time, and 3/4 dynamic redundant prefixes for the same throughput when using four TCAMs. In addition, CLUE has another advantage over the mechanism in [3] - the frequent interactions between control plane and data plane caused by redundant prefixes update can be avoided.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"17 1","pages":"678-687"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90459854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sungju Huh, Jonghun Yoo, Myungsun Kim, Seongsoo Hong
While Linux is the most favored operating system for an open source-based cloud data center, it falls short of expectations when it comes to fair share multicore scheduling. The primary task scheduler of the mainline Linux kernel, CFS, cannot provide a desired level of fairness in a multicore system. CFS uses a weight-based load balancing mechanism to evenly distribute task weights among all cores. Contrary to expectations, this mechanism cannot guarantee fair share scheduling since balancing loads among cores has nothing to do with bounding differences in the virtual runtimes of tasks. To make matters worse, CFS allows a persistent load imbalance among cores. This paper presents a virtual runtime-based task migration algorithm which directly bounds the maximum virtual runtime difference among tasks. For a given pair of cores, our algorithm periodically partitions run able tasks into two groups depending on their virtual runtimes and assigns each group to a dedicated core. In doing so, it bounds the load difference between two cores by the largest weight in the task set and makes the core with larger virtual runtimes receive a larger load and thus run more slowly. It bounds the virtual runtime difference of any pair of tasks running on these cores by a constant. We have implemented the algorithm into the Linux kernel 2.6.38.8. Experimental results show that the maximal virtual runtime difference is 50.53 time units while incurring only 0.14% more run-time overhead than CFS.
{"title":"Providing Fair Share Scheduling on Multicore Cloud Servers via Virtual Runtime-based Task Migration Algorithm","authors":"Sungju Huh, Jonghun Yoo, Myungsun Kim, Seongsoo Hong","doi":"10.1109/ICDCS.2012.33","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.33","url":null,"abstract":"While Linux is the most favored operating system for an open source-based cloud data center, it falls short of expectations when it comes to fair share multicore scheduling. The primary task scheduler of the mainline Linux kernel, CFS, cannot provide a desired level of fairness in a multicore system. CFS uses a weight-based load balancing mechanism to evenly distribute task weights among all cores. Contrary to expectations, this mechanism cannot guarantee fair share scheduling since balancing loads among cores has nothing to do with bounding differences in the virtual runtimes of tasks. To make matters worse, CFS allows a persistent load imbalance among cores. This paper presents a virtual runtime-based task migration algorithm which directly bounds the maximum virtual runtime difference among tasks. For a given pair of cores, our algorithm periodically partitions run able tasks into two groups depending on their virtual runtimes and assigns each group to a dedicated core. In doing so, it bounds the load difference between two cores by the largest weight in the task set and makes the core with larger virtual runtimes receive a larger load and thus run more slowly. It bounds the virtual runtime difference of any pair of tasks running on these cores by a constant. We have implemented the algorithm into the Linux kernel 2.6.38.8. Experimental results show that the maximal virtual runtime difference is 50.53 time units while incurring only 0.14% more run-time overhead than CFS.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"99 1","pages":"606-614"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81026105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Zou, Xitao Wen, Kai Chen, Shan Huang, Yan Chen, Yongqiang Liu, Yong-Ping Xia, Chengchen Hu
Our measurements on production data center traffic together with recently reported results suggest that data center networks suffer from long-lived congestion caused by core network over subscription and unbalanced workload placement. In contrast to traditional traffic engineering approaches that optimize flow routing, in this paper, we explore the opportunity to address the continuous congestion via optimizing VM placement in virtualized data centers. To this end, we present Virtual Knotter, an efficient online VM placement algorithm to reduce congestion with controllable VM migration traffic as well as low time complexity. Our evaluation with both real and synthetic traffic patterns shows that Virtual Knotter performs close to the baseline algorithm in terms of link unitization, with only 5%-10% migration traffic of the baseline algorithm. Furthermore, Virtual Knotter decreases link congestion time by 53% for the production data center traffic.
{"title":"VirtualKnotter: Online Virtual Machine Shuffling for Congestion Resolving in Virtualized Datacenter","authors":"S. Zou, Xitao Wen, Kai Chen, Shan Huang, Yan Chen, Yongqiang Liu, Yong-Ping Xia, Chengchen Hu","doi":"10.1109/ICDCS.2012.25","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.25","url":null,"abstract":"Our measurements on production data center traffic together with recently reported results suggest that data center networks suffer from long-lived congestion caused by core network over subscription and unbalanced workload placement. In contrast to traditional traffic engineering approaches that optimize flow routing, in this paper, we explore the opportunity to address the continuous congestion via optimizing VM placement in virtualized data centers. To this end, we present Virtual Knotter, an efficient online VM placement algorithm to reduce congestion with controllable VM migration traffic as well as low time complexity. Our evaluation with both real and synthetic traffic patterns shows that Virtual Knotter performs close to the baseline algorithm in terms of link unitization, with only 5%-10% migration traffic of the baseline algorithm. Furthermore, Virtual Knotter decreases link congestion time by 53% for the production data center traffic.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"10 1","pages":"12-21"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82358388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Enhua Tan, Lei Guo, Songqing Chen, Xiaodong Zhang, Y. Zhao
Spam content is surging with an explosive increase of user generated content (UGC) on the Internet. Spammers often insert popular keywords or simply copy and paste recent articles from the Web with spam links inserted, attempting to disable content-based detection. In order to effectively detect spam in user generated content, we first conduct a comprehensive analysis of spamming activities on a large commercial UGC site in 325 days covering over 6 million posts and nearly 400 thousand users. Our analysis shows that UGC spammers exhibit unique non-textual patterns, such as posting activities, advertised spam link metrics, and spam hosting behaviors. Based on these non-textual features, we show via several classification methods that a high detection rate could be achieved offline. These results further motivate us to develop a runtime scheme, BARS, to detect spam posts based on these spamming patterns. The experimental results demonstrate the effectiveness and robustness of BARS.
{"title":"Spammer Behavior Analysis and Detection in User Generated Content on Social Networks","authors":"Enhua Tan, Lei Guo, Songqing Chen, Xiaodong Zhang, Y. Zhao","doi":"10.1109/ICDCS.2012.40","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.40","url":null,"abstract":"Spam content is surging with an explosive increase of user generated content (UGC) on the Internet. Spammers often insert popular keywords or simply copy and paste recent articles from the Web with spam links inserted, attempting to disable content-based detection. In order to effectively detect spam in user generated content, we first conduct a comprehensive analysis of spamming activities on a large commercial UGC site in 325 days covering over 6 million posts and nearly 400 thousand users. Our analysis shows that UGC spammers exhibit unique non-textual patterns, such as posting activities, advertised spam link metrics, and spam hosting behaviors. Based on these non-textual features, we show via several classification methods that a high detection rate could be achieved offline. These results further motivate us to develop a runtime scheme, BARS, to detect spam posts based on these spamming patterns. The experimental results demonstrate the effectiveness and robustness of BARS.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"29 1","pages":"305-314"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78917455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Internet based service providers, such as Amazon, Google, Yahoo etc, build their data centers (IDC) across multiple regions to provide reliable and low latency of services to clients. Ever-increasing service demand, complexity of services and growing client population cause enormous power consumptions by these IDCs incurring a major part of their running costs. Modern electric power grid provides a feasible way to dynamically and efficiently manage the electricity cost of distributed IDCs based on the Locational Marginal Pricing (LMP) policy. While recent works exploit LMP by electricity-price based geographic load distribution, the dynamic workload and high volatility of electricity prices induce highly volatile power demand and critical power peak problem. The benefit of cost minimization via geographic load distribution is counterbalanced with the high cost incurred by violating the peak power. In this paper, we study the dynamic control of electricity cost to provide low volatility in power demand and shaving of power peaks. To this end, a Model Predictive Control (MPC) electricity cost minimization problem is formulated based on a time-continuous differential model. The proposed solution minimizes electricity costs, provides low variation in power demand by penalizing the change in workload and alleviates the power peaks by tracking the available power budget. By providing extensive simulation results based on real-life electricity price traces we show the effectiveness of our approach.
{"title":"Dynamic Control of Electricity Cost with Power Demand Smoothing and Peak Shaving for Distributed Internet Data Centers","authors":"Jianguo Yao, Xue Liu, Wenbo He, Ashikur Rahman","doi":"10.1109/ICDCS.2012.67","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.67","url":null,"abstract":"Internet based service providers, such as Amazon, Google, Yahoo etc, build their data centers (IDC) across multiple regions to provide reliable and low latency of services to clients. Ever-increasing service demand, complexity of services and growing client population cause enormous power consumptions by these IDCs incurring a major part of their running costs. Modern electric power grid provides a feasible way to dynamically and efficiently manage the electricity cost of distributed IDCs based on the Locational Marginal Pricing (LMP) policy. While recent works exploit LMP by electricity-price based geographic load distribution, the dynamic workload and high volatility of electricity prices induce highly volatile power demand and critical power peak problem. The benefit of cost minimization via geographic load distribution is counterbalanced with the high cost incurred by violating the peak power. In this paper, we study the dynamic control of electricity cost to provide low volatility in power demand and shaving of power peaks. To this end, a Model Predictive Control (MPC) electricity cost minimization problem is formulated based on a time-continuous differential model. The proposed solution minimizes electricity costs, provides low variation in power demand by penalizing the change in workload and alleviates the power peaks by tracking the available power budget. By providing extensive simulation results based on real-life electricity price traces we show the effectiveness of our approach.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"30 1","pages":"416-424"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77329687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Radio Frequency (RF) based technologies play an important role in indoor localization, since Radio Signal Strength (RSS) is easily achieved by various wireless devices without additional cost. Among these, radio map based technologies (also referred as fingerprinting technologies) are attractive. They are able to accurately localize the targets without introducing many reference nodes. Therefore, their hardware cost is low. However, this technology has two fatal limitations. First, it is hard to localize multiple objects, since radio map has to collect all the RSS information when targets are at different possible positions. But due to the multipath phenomenon, different number of target nodes at different positions often generates different multipath signals. So when the target object number is unknown, constructing a radio map of multiple objects is almost impossible. Second, environment changes will generate different multipath signals and severely disturb the RSS measurement, making laborious retraining inevitable. In this paper, we propose a novel method, called Line-Of-Sight (LOS) map matching. It leverages frequency diversity of wireless nodes to eliminate the multipath behavior, making RSS more reliable than before. These reliable RSS signals are able to construct the radio map, which only reserves the LOS signal among nodes. We call it LOS radio map. The number of objects and environment changes will not affect the LOS signal between the targets and reference nodes. Such map is able to be constructed easily and require no training if reference nodes are carefully redeployed. Our basic idea is to utilize the frequency diversity of each wireless node to transmit data in different spectrum channel. Then it solves the optimization problem to get the LOS signal. Our experiments are based on TelosB sensor platform with three reference nodes. It shows that the accuracy will not decrease when localizing multiple targets in a dynamic environment. It outperforms the traditional methods by about60%. More importantly, no calibration is required in such environment. Furthermore, our approach presents attractive flexibility, making it more appropriate for general RF-based localization studies than just the radio map based localization.
{"title":"Localizing Multiple Objects in an RF-based Dynamic Environment","authors":"Xiaonan Guo, Dian Zhang, L. Ni","doi":"10.1109/ICDCS.2012.49","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.49","url":null,"abstract":"Radio Frequency (RF) based technologies play an important role in indoor localization, since Radio Signal Strength (RSS) is easily achieved by various wireless devices without additional cost. Among these, radio map based technologies (also referred as fingerprinting technologies) are attractive. They are able to accurately localize the targets without introducing many reference nodes. Therefore, their hardware cost is low. However, this technology has two fatal limitations. First, it is hard to localize multiple objects, since radio map has to collect all the RSS information when targets are at different possible positions. But due to the multipath phenomenon, different number of target nodes at different positions often generates different multipath signals. So when the target object number is unknown, constructing a radio map of multiple objects is almost impossible. Second, environment changes will generate different multipath signals and severely disturb the RSS measurement, making laborious retraining inevitable. In this paper, we propose a novel method, called Line-Of-Sight (LOS) map matching. It leverages frequency diversity of wireless nodes to eliminate the multipath behavior, making RSS more reliable than before. These reliable RSS signals are able to construct the radio map, which only reserves the LOS signal among nodes. We call it LOS radio map. The number of objects and environment changes will not affect the LOS signal between the targets and reference nodes. Such map is able to be constructed easily and require no training if reference nodes are carefully redeployed. Our basic idea is to utilize the frequency diversity of each wireless node to transmit data in different spectrum channel. Then it solves the optimization problem to get the LOS signal. Our experiments are based on TelosB sensor platform with three reference nodes. It shows that the accuracy will not decrease when localizing multiple targets in a dynamic environment. It outperforms the traditional methods by about60%. More importantly, no calibration is required in such environment. Furthermore, our approach presents attractive flexibility, making it more appropriate for general RF-based localization studies than just the radio map based localization.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"30 1","pages":"576-585"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72842670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traditional Infrastructure-as-a-Service offerings provide customers with large numbers of fixed-size virtual machine (VM) instances with resource allocations that are designed to meet application demands. With application demands varying over time, cloud providers gain efficiencies through resource consolidation and over-commitment. For cloud customers, however, this leads to inefficient use of the cloud resources they have purchased. To address cloud customers' dynamic application requirements, we present a new cloud resource offering, called v-Bundle, which makes flexible the exchange of resource capacity among multiple VM instances belonging to the same customer. Specifically targeting network resources, for each customer application, we first use DHT-based techniques to achieve an initial VM placement that minimizes its use of the data center network's bi-section bandwidth. When VMs' networking requirements change, the customer can then use v-Bundle to trade the networking resources allocated to her application. v-Bundle maintains information about network resources with any-cast tree-based methods implemented as extensions of the Pastry pub-sub core. Experimental evaluations show that the approach can scale well to thousands of hosts and VMs, and that v-Bundle can provide customers with better bandwidth utilization and improved application quality of service through borrowing extra bandwidth when needed, at no additional cost in terms of the total resources allocated to the customer.
{"title":"v-Bundle: Flexible Group Resource Offerings in Clouds","authors":"Liting Hu, K. D. Ryu, D. D. Silva, K. Schwan","doi":"10.1109/ICDCS.2012.61","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.61","url":null,"abstract":"Traditional Infrastructure-as-a-Service offerings provide customers with large numbers of fixed-size virtual machine (VM) instances with resource allocations that are designed to meet application demands. With application demands varying over time, cloud providers gain efficiencies through resource consolidation and over-commitment. For cloud customers, however, this leads to inefficient use of the cloud resources they have purchased. To address cloud customers' dynamic application requirements, we present a new cloud resource offering, called v-Bundle, which makes flexible the exchange of resource capacity among multiple VM instances belonging to the same customer. Specifically targeting network resources, for each customer application, we first use DHT-based techniques to achieve an initial VM placement that minimizes its use of the data center network's bi-section bandwidth. When VMs' networking requirements change, the customer can then use v-Bundle to trade the networking resources allocated to her application. v-Bundle maintains information about network resources with any-cast tree-based methods implemented as extensions of the Pastry pub-sub core. Experimental evaluations show that the approach can scale well to thousands of hosts and VMs, and that v-Bundle can provide customers with better bandwidth utilization and improved application quality of service through borrowing extra bandwidth when needed, at no additional cost in terms of the total resources allocated to the customer.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"47 1","pages":"406-415"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91148276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ken C. K. Lee, K. Bankar, Baihua Zheng, Chi-Yin Chow, Honggang Wang
Database-generated dynamic web pages (db-pages, in short), whose contents are created on the fly by web applications and databases, are now prominent in the web. However, many of them cannot be searched by existing search engines. Accordingly, we develop a novel search engine named Dash, which stands for Db-pAge Search, to support db-page search. Dash determines db-pages possibly generated by a target web application and its database through exploring the application code and the related database content and supports keyword search on those db-pages. In this paper, we present its system design and focus on the efficiency issue. To minimize costs incurred for collecting, maintaining, indexing and searching a massive number of db-pages that possibly have overlapped contents, Dash derives and indexes db-page fragments in place of db-pages. Each db-page fragment carries a disjointed part of a db-page. To efficiently compute and index db-page fragments from huge datasets, Dash is equipped with MapReduce based algorithms for database crawling and db-page fragment indexing. Besides, Dash has a top-k search algorithm that can efficiently assemble db-page fragments into db-pages relevant to search keywords and return the k most relevant ones. The performance of Dash is evaluated via extensive experimentation.
{"title":"Dash: A Novel Search Engine for Database-Generated Dynamic Web Pages","authors":"Ken C. K. Lee, K. Bankar, Baihua Zheng, Chi-Yin Chow, Honggang Wang","doi":"10.1109/ICDCS.2012.53","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.53","url":null,"abstract":"Database-generated dynamic web pages (db-pages, in short), whose contents are created on the fly by web applications and databases, are now prominent in the web. However, many of them cannot be searched by existing search engines. Accordingly, we develop a novel search engine named Dash, which stands for Db-pAge Search, to support db-page search. Dash determines db-pages possibly generated by a target web application and its database through exploring the application code and the related database content and supports keyword search on those db-pages. In this paper, we present its system design and focus on the efficiency issue. To minimize costs incurred for collecting, maintaining, indexing and searching a massive number of db-pages that possibly have overlapped contents, Dash derives and indexes db-page fragments in place of db-pages. Each db-page fragment carries a disjointed part of a db-page. To efficiently compute and index db-page fragments from huge datasets, Dash is equipped with MapReduce based algorithms for database crawling and db-page fragment indexing. Besides, Dash has a top-k search algorithm that can efficiently assemble db-page fragments into db-pages relevant to search keywords and return the k most relevant ones. The performance of Dash is evaluated via extensive experimentation.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"49 1","pages":"435-444"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87401718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaohui Liang, Xu Li, R. Lu, Xiaodong Lin, Xuemin Shen
In this paper, we consider service-oriented mobile social networks (S-MSNs) and propose a Secure and Efficient service Review (SEER) system to enable user feedback. Each service provider independently maintains a SEER system for itself, which collects and stores user reviews about its services without requiring any central trusted authority. The service reviews can then be made available to interested users in making wise service selection decisions. We identify three unique service review attacks and then develop sophisticated security mechanisms for SEER to deal with these attacks. Specifically, SEER enables users to distributedly and cooperatively submit their reviews in an integrated chain form by using hierarchical and aggregate signature techniques. It discourages service providers to reject, modify or delete their reviews. The integrity of reviews is therefore improved. Through security analysis and performance evaluation, we show that SEER effectively resists the service review attacks and achieves significantly better performance in terms of submission rate and delay than a service review system that does not adopt user cooperation or the chain review structure.
{"title":"SEER: A Secure and Efficient Service Review System for Service-Oriented Mobile Social Networks","authors":"Xiaohui Liang, Xu Li, R. Lu, Xiaodong Lin, Xuemin Shen","doi":"10.1109/ICDCS.2012.46","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.46","url":null,"abstract":"In this paper, we consider service-oriented mobile social networks (S-MSNs) and propose a Secure and Efficient service Review (SEER) system to enable user feedback. Each service provider independently maintains a SEER system for itself, which collects and stores user reviews about its services without requiring any central trusted authority. The service reviews can then be made available to interested users in making wise service selection decisions. We identify three unique service review attacks and then develop sophisticated security mechanisms for SEER to deal with these attacks. Specifically, SEER enables users to distributedly and cooperatively submit their reviews in an integrated chain form by using hierarchical and aggregate signature techniques. It discourages service providers to reject, modify or delete their reviews. The integrity of reviews is therefore improved. Through security analysis and performance evaluation, we show that SEER effectively resists the service review attacks and achieves significantly better performance in terms of submission rate and delay than a service review system that does not adopt user cooperation or the chain review structure.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"40 1","pages":"647-656"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82371088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Data center networks typically have many paths connecting each host pair to achieve high bisection bandwidth for arbitrary communication patterns. Fully utilizing the bisection bandwidth may require flows between the same source and destination pair to take different paths. However, existing routing protocols have little support for load-sensitive adaptive routing. We propose DARD, a Distributed Adaptive Routing architecture for Data center networks. DARD allows each end host to move traffic from overloaded paths to under loaded paths without central coordination. We use an Open Flow implementation and simulations to show that DARD can effectively use a data center network's bisection bandwidth under both static and dynamic traffic patterns. It outperforms previous solutions based on random path selection by 10%, and performs similarly to previous work that assigns flows to paths using a centralized controller. We use competitive game theory to show that DARD's path selection algorithm makes progress in every step and converges to a Nash equilibrium in finite steps. Our evaluation results suggest that DARD can achieve a close-to-optimal solution in practice.
{"title":"DARD: Distributed Adaptive Routing for Datacenter Networks","authors":"Xin Wu, Xiaowei Yang","doi":"10.1109/ICDCS.2012.69","DOIUrl":"https://doi.org/10.1109/ICDCS.2012.69","url":null,"abstract":"Data center networks typically have many paths connecting each host pair to achieve high bisection bandwidth for arbitrary communication patterns. Fully utilizing the bisection bandwidth may require flows between the same source and destination pair to take different paths. However, existing routing protocols have little support for load-sensitive adaptive routing. We propose DARD, a Distributed Adaptive Routing architecture for Data center networks. DARD allows each end host to move traffic from overloaded paths to under loaded paths without central coordination. We use an Open Flow implementation and simulations to show that DARD can effectively use a data center network's bisection bandwidth under both static and dynamic traffic patterns. It outperforms previous solutions based on random path selection by 10%, and performs similarly to previous work that assigns flows to paths using a centralized controller. We use competitive game theory to show that DARD's path selection algorithm makes progress in every step and converges to a Nash equilibrium in finite steps. Our evaluation results suggest that DARD can achieve a close-to-optimal solution in practice.","PeriodicalId":6300,"journal":{"name":"2012 IEEE 32nd International Conference on Distributed Computing Systems","volume":"32 1","pages":"32-41"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83110211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：