Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation最新文献
Pub Date : 2023-05-26DOI: 10.48550/arXiv.2305.17222
Midhul Vuppalapati, Giannis Fikioris, R. Agarwal, Asaf Cidon, Anurag Khandelwal, É. Tardos
We consider the problem of fair resource allocation in a system where user demands are dynamic, that is, where user demands vary over time. Our key observation is that the classical max-min fairness algorithm for resource allocation provides many desirable properties (e.g., Pareto efficiency, strategy-proofness, and fairness), but only under the strong assumption of user demands being static over time. For the realistic case of dynamic user demands, the max-min fairness algorithm loses one or more of these properties. We present Karma, a new resource allocation mechanism for dynamic user demands. The key technical contribution in Karma is a credit-based resource allocation algorithm: in each quantum, users donate their unused resources and are assigned credits when other users borrow these resources; Karma carefully orchestrates the exchange of credits across users (based on their instantaneous demands, donated resources and borrowed resources), and performs prioritized resource allocation based on users' credits. We theoretically establish Karma guarantees related to Pareto efficiency, strategy-proofness, and fairness for dynamic user demands. Empirical evaluations over production workloads show that these properties translate well into practice: Karma is able to reduce disparity in performance across users to a bare minimum while maintaining Pareto-optimal system-wide performance.
{"title":"Karma: Resource Allocation for Dynamic Demands","authors":"Midhul Vuppalapati, Giannis Fikioris, R. Agarwal, Asaf Cidon, Anurag Khandelwal, É. Tardos","doi":"10.48550/arXiv.2305.17222","DOIUrl":"https://doi.org/10.48550/arXiv.2305.17222","url":null,"abstract":"We consider the problem of fair resource allocation in a system where user demands are dynamic, that is, where user demands vary over time. Our key observation is that the classical max-min fairness algorithm for resource allocation provides many desirable properties (e.g., Pareto efficiency, strategy-proofness, and fairness), but only under the strong assumption of user demands being static over time. For the realistic case of dynamic user demands, the max-min fairness algorithm loses one or more of these properties. We present Karma, a new resource allocation mechanism for dynamic user demands. The key technical contribution in Karma is a credit-based resource allocation algorithm: in each quantum, users donate their unused resources and are assigned credits when other users borrow these resources; Karma carefully orchestrates the exchange of credits across users (based on their instantaneous demands, donated resources and borrowed resources), and performs prioritized resource allocation based on users' credits. We theoretically establish Karma guarantees related to Pareto efficiency, strategy-proofness, and fairness for dynamic user demands. Empirical evaluations over production workloads show that these properties translate well into practice: Karma is able to reduce disparity in performance across users to a bare minimum while maintaining Pareto-optimal system-wide performance.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"1 1","pages":"645-662"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89867685","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}
Pub Date : 2023-05-23DOI: 10.48550/arXiv.2305.14270
Haonan Lu, Shuai Mu, S. Sen, Wyatt Lloyd
Strictly serializable datastores greatly simplify the development of correct applications by providing strong consistency guarantees. However, existing techniques pay unnecessary costs for naturally consistent transactions, which arrive at servers in an order that is already strictly serializable. We find these transactions are prevalent in datacenter workloads. We exploit this natural arrival order by executing transaction requests with minimal costs while optimistically assuming they are naturally consistent, and then leverage a timestamp-based technique to efficiently verify if the execution is indeed consistent. In the process of designing such a timestamp-based technique, we identify a fundamental pitfall in relying on timestamps to provide strict serializability, and name it the timestamp-inversion pitfall. We find timestamp-inversion has affected several existing works. We present Natural Concurrency Control (NCC), a new concurrency control technique that guarantees strict serializability and ensures minimal costs -- i.e., one-round latency, lock-free, and non-blocking execution -- in the best (and common) case by leveraging natural consistency. NCC is enabled by three key components: non-blocking execution, decoupled response control, and timestamp-based consistency check. NCC avoids timestamp-inversion with a new technique: response timing control, and proposes two optimization techniques, asynchrony-aware timestamps and smart retry, to reduce false aborts. Moreover, NCC designs a specialized protocol for read-only transactions, which is the first to achieve the optimal best-case performance while ensuring strict serializability, without relying on synchronized clocks. Our evaluation shows that NCC outperforms state-of-the-art solutions by an order of magnitude on many workloads.
{"title":"NCC: Natural Concurrency Control for Strictly Serializable Datastores by Avoiding the Timestamp-Inversion Pitfall","authors":"Haonan Lu, Shuai Mu, S. Sen, Wyatt Lloyd","doi":"10.48550/arXiv.2305.14270","DOIUrl":"https://doi.org/10.48550/arXiv.2305.14270","url":null,"abstract":"Strictly serializable datastores greatly simplify the development of correct applications by providing strong consistency guarantees. However, existing techniques pay unnecessary costs for naturally consistent transactions, which arrive at servers in an order that is already strictly serializable. We find these transactions are prevalent in datacenter workloads. We exploit this natural arrival order by executing transaction requests with minimal costs while optimistically assuming they are naturally consistent, and then leverage a timestamp-based technique to efficiently verify if the execution is indeed consistent. In the process of designing such a timestamp-based technique, we identify a fundamental pitfall in relying on timestamps to provide strict serializability, and name it the timestamp-inversion pitfall. We find timestamp-inversion has affected several existing works. We present Natural Concurrency Control (NCC), a new concurrency control technique that guarantees strict serializability and ensures minimal costs -- i.e., one-round latency, lock-free, and non-blocking execution -- in the best (and common) case by leveraging natural consistency. NCC is enabled by three key components: non-blocking execution, decoupled response control, and timestamp-based consistency check. NCC avoids timestamp-inversion with a new technique: response timing control, and proposes two optimization techniques, asynchrony-aware timestamps and smart retry, to reduce false aborts. Moreover, NCC designs a specialized protocol for read-only transactions, which is the first to achieve the optimal best-case performance while ensuring strict serializability, without relying on synchronized clocks. Our evaluation shows that NCC outperforms state-of-the-art solutions by an order of magnitude on many workloads.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"293 1","pages":"305-323"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75412065","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}
To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system, called Walle, as the foundation. Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration. Specifically, the compute container is based on Mobile Neural Network (MNN), a tensor compute engine along with the data processing and model execution libraries, which are exposed through a refined Python thread-level virtual machine (VM) to support diverse ML tasks and concurrent task execution. The core of MNN is the novel mechanisms of operator decomposition and semi-auto search, sharply reducing the workload in manually optimizing hundreds of operators for tens of hardware backends and further quickly identifying the best backend with runtime optimization for a computation graph. The data pipeline introduces an on-device stream processing framework to enable processing user behavior data at source. The deployment platform releases ML tasks with an efficient push-then-pull method and supports multi-granularity deployment policies. We evaluate Walle in practical e-commerce application scenarios to demonstrate its effectiveness, efficiency, and scalability. Extensive micro-benchmarks also highlight the superior performance of MNN and the Python thread-level VM. Walle has been in large-scale production use in Alibaba, while MNN has been open source with a broad impact in the community.
{"title":"Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning","authors":"Chengfei Lv, Chaoyue Niu, Renjie Gu, Xiaotang Jiang, Zhaode Wang, B. Liu, Ziqi Wu, Qiulin Yao, Congyu Huang, Panos Huang, Tao Huang, Hui Shu, Jinde Song, Bingzhang Zou, Peng Lan, Guohuan Xu, Fei Wu, Shaojie Tang, Fan Wu, Guihai Chen","doi":"10.48550/arXiv.2205.14833","DOIUrl":"https://doi.org/10.48550/arXiv.2205.14833","url":null,"abstract":"To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system, called Walle, as the foundation. Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration. Specifically, the compute container is based on Mobile Neural Network (MNN), a tensor compute engine along with the data processing and model execution libraries, which are exposed through a refined Python thread-level virtual machine (VM) to support diverse ML tasks and concurrent task execution. The core of MNN is the novel mechanisms of operator decomposition and semi-auto search, sharply reducing the workload in manually optimizing hundreds of operators for tens of hardware backends and further quickly identifying the best backend with runtime optimization for a computation graph. The data pipeline introduces an on-device stream processing framework to enable processing user behavior data at source. The deployment platform releases ML tasks with an efficient push-then-pull method and supports multi-granularity deployment policies. We evaluate Walle in practical e-commerce application scenarios to demonstrate its effectiveness, efficiency, and scalability. Extensive micro-benchmarks also highlight the superior performance of MNN and the Python thread-level VM. Walle has been in large-scale production use in Alibaba, while MNN has been open source with a broad impact in the community.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"38 1","pages":"249-265"},"PeriodicalIF":0.0,"publicationDate":"2022-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86966095","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}
Pub Date : 2022-05-13DOI: 10.48550/arXiv.2205.06911
Wen Zhang, Eric Sheng, M. Chang, Aurojit Panda, Shmuel Sagiv, S. Shenker
Modern web applications serve large amounts of sensitive user data, access to which is typically governed by data-access policies. Enforcing such policies is crucial to preventing improper data access, and prior work has proposed many enforcement mechanisms. However, these prior methods either alter application semantics or require adopting a new programming model; the former can result in unexpected application behavior, while the latter cannot be used with existing web frameworks. Blockaid is an access-policy enforcement system that preserves application semantics and is compatible with existing web frameworks. It intercepts database queries from the application, attempts to verify that each query is policy-compliant, and blocks queries that are not. It verifies policy compliance using SMT solvers and generalizes and caches previous compliance decisions for better performance. We show that Blockaid supports existing web applications while requiring minimal code changes and adding only modest overheads.
{"title":"Blockaid: Data Access Policy Enforcement for Web Applications","authors":"Wen Zhang, Eric Sheng, M. Chang, Aurojit Panda, Shmuel Sagiv, S. Shenker","doi":"10.48550/arXiv.2205.06911","DOIUrl":"https://doi.org/10.48550/arXiv.2205.06911","url":null,"abstract":"Modern web applications serve large amounts of sensitive user data, access to which is typically governed by data-access policies. Enforcing such policies is crucial to preventing improper data access, and prior work has proposed many enforcement mechanisms. However, these prior methods either alter application semantics or require adopting a new programming model; the former can result in unexpected application behavior, while the latter cannot be used with existing web frameworks. Blockaid is an access-policy enforcement system that preserves application semantics and is compatible with existing web frameworks. It intercepts database queries from the application, attempts to verify that each query is policy-compliant, and blocks queries that are not. It verifies policy compliance using SMT solvers and generalizes and caches previous compliance decisions for better performance. We show that Blockaid supports existing web applications while requiring minimal code changes and adding only modest overheads.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"386 9 1","pages":"701-718"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80224233","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}
Pub Date : 2021-07-08DOI: 10.3929/ETHZ-B-000494008
Lukas Burkhalter, Nicolas Küchler, Alexander Viand, Hossein Shafagh, Anwar Hithnawi
As increasingly more sensitive data is being collected to gain valuable insights, the need to natively integrate privacy controls in data analytics frameworks is growing in importance. Today, privacy controls are enforced by data curators with full access to data in the clear. However, a plethora of recent data breaches show that even widely trusted service providers can be compromised. Additionally, there is no assurance that data processing and handling comply with the claimed privacy policies. This motivates the need for a new approach to data privacy that can provide strong assurance and control to users. This paper presents Zeph, a system that enables users to set privacy preferences on how their data can be shared and processed. Zeph enforces privacy policies cryptographically and ensures that data available to third-party applications complies with users' privacy policies. Zeph executes privacy-adhering data transformations in real-time and scales to thousands of data sources, allowing it to support large-scale low-latency data stream analytics. We introduce a hybrid cryptographic protocol for privacy-adhering transformations of encrypted data. We develop a prototype of Zeph on Apache Kafka to demonstrate that Zeph can perform large-scale privacy transformations with low overhead.
{"title":"Zeph: Cryptographic Enforcement of End-to-End Data Privacy","authors":"Lukas Burkhalter, Nicolas Küchler, Alexander Viand, Hossein Shafagh, Anwar Hithnawi","doi":"10.3929/ETHZ-B-000494008","DOIUrl":"https://doi.org/10.3929/ETHZ-B-000494008","url":null,"abstract":"As increasingly more sensitive data is being collected to gain valuable insights, the need to natively integrate privacy controls in data analytics frameworks is growing in importance. Today, privacy controls are enforced by data curators with full access to data in the clear. However, a plethora of recent data breaches show that even widely trusted service providers can be compromised. Additionally, there is no assurance that data processing and handling comply with the claimed privacy policies. This motivates the need for a new approach to data privacy that can provide strong assurance and control to users. This paper presents Zeph, a system that enables users to set privacy preferences on how their data can be shared and processed. Zeph enforces privacy policies cryptographically and ensures that data available to third-party applications complies with users' privacy policies. Zeph executes privacy-adhering data transformations in real-time and scales to thousands of data sources, allowing it to support large-scale low-latency data stream analytics. We introduce a hybrid cryptographic protocol for privacy-adhering transformations of encrypted data. We develop a prototype of Zeph on Apache Kafka to demonstrate that Zeph can perform large-scale privacy transformations with low overhead.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"1 1","pages":"387-404"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91529073","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}
Jie Zhang, Miryeong Kwon, Donghyun Gouk, Sungjoon Koh, Chan-Seop Lee, Mohammad Alian, Myoungjun Chun, M. Kandemir, N. Kim, Jihong Kim, Myoungsoo Jung
A modern datacenter server aims to achieve high energy efficiency by co-running multiple applications. Some of such applications (e.g., web search) are latency sensitive. Therefore, they require low-latency I/O services to fast respond to requests from clients. However, we observe that simply replacing the storage devices of servers with Ultra-Low-Latency (ULL) SSDs does not notably reduce the latency of I/O services, especially when co-running multiple applications. In this paper, we propose FLASHSHARE to assist ULL SSDs to satisfy different levels of I/O service latency requirements for different co-running applications. Specifically, FLASHSHARE is a holistic cross-stack approach, which can significantly reduce I/O interferences among co-running applications at a server without any change in applications. At the kernel-level, we extend the data structures of the storage stack to pass attributes of (co-running) applications through all the layers of the underlying storage stack spanning from the OS kernel to the SSD firmware. For given attributes, the block layer and NVMe driver of FLASHSHARE differently manage the I/O scheduler and interrupt handler of NVMe. We also enhance the NVMe controller and cache layer at the SSD firmware-level, by dynamically partitioning DRAM in the ULL SSD and adjusting its caching strategies to meet diverse user requirements. The evaluation results demonstrate that FLASHSHARE can shorten the average and 99th-percentile turnaround response times of co-running applications by 22% and 31%, respectively.
{"title":"FlashShare: Punching Through Server Storage Stack from Kernel to Firmware for Ultra-Low Latency SSDs","authors":"Jie Zhang, Miryeong Kwon, Donghyun Gouk, Sungjoon Koh, Chan-Seop Lee, Mohammad Alian, Myoungjun Chun, M. Kandemir, N. Kim, Jihong Kim, Myoungsoo Jung","doi":"10.5555/3291168.3291203","DOIUrl":"https://doi.org/10.5555/3291168.3291203","url":null,"abstract":"A modern datacenter server aims to achieve high energy efficiency by co-running multiple applications. Some of such applications (e.g., web search) are latency sensitive. Therefore, they require low-latency I/O services to fast respond to requests from clients. However, we observe that simply replacing the storage devices of servers with Ultra-Low-Latency (ULL) SSDs does not notably reduce the latency of I/O services, especially when co-running multiple applications. In this paper, we propose FLASHSHARE to assist ULL SSDs to satisfy different levels of I/O service latency requirements for different co-running applications. Specifically, FLASHSHARE is a holistic cross-stack approach, which can significantly reduce I/O interferences among co-running applications at a server without any change in applications. At the kernel-level, we extend the data structures of the storage stack to pass attributes of (co-running) applications through all the layers of the underlying storage stack spanning from the OS kernel to the SSD firmware. For given attributes, the block layer and NVMe driver of FLASHSHARE differently manage the I/O scheduler and interrupt handler of NVMe. We also enhance the NVMe controller and cache layer at the SSD firmware-level, by dynamically partitioning DRAM in the ULL SSD and adjusting its caching strategies to meet diverse user requirements. The evaluation results demonstrate that FLASHSHARE can shorten the average and 99th-percentile turnaround response times of co-running applications by 22% and 31%, respectively.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"1 1","pages":"477-492"},"PeriodicalIF":0.0,"publicationDate":"2018-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76475284","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}
Ahmed Alquraan, Hatem Takruri, Mohammed Alfatafta, S. Al-Kiswany
We present a comprehensive study of 136 system failures attributed to network-partitioning faults from 25 widely used distributed systems. We found that the majority of the failures led to catastrophic effects, such as data loss, reappearance of deleted data, broken locks, and system crashes. The majority of the failures can easily manifest once a network partition occurs: They require little to no client input, can be triggered by isolating a single node, and are deterministic. However, the number of test cases that one must consider is extremely large. Fortunately, we identify ordering, timing, and network fault characteristics that significantly simplify testing. Furthermore, we found that a significant number of the failures are due to design flaws in core system mechanisms.We found that the majority of the failures could have been avoided by design reviews, and could have been discovered by testing with network-partitioning fault injection. We built NEAT, a testing framework that simplifies the coordination of multiple clients and can inject different types of network-partitioning faults. We used NEAT to test seven popular systems and found and reported 32 failures.
{"title":"An Analysis of Network-Partitioning Failures in Cloud Systems","authors":"Ahmed Alquraan, Hatem Takruri, Mohammed Alfatafta, S. Al-Kiswany","doi":"10.5555/3291168.3291173","DOIUrl":"https://doi.org/10.5555/3291168.3291173","url":null,"abstract":"We present a comprehensive study of 136 system failures attributed to network-partitioning faults from 25 widely used distributed systems. We found that the majority of the failures led to catastrophic effects, such as data loss, reappearance of deleted data, broken locks, and system crashes. The majority of the failures can easily manifest once a network partition occurs: They require little to no client input, can be triggered by isolating a single node, and are deterministic. However, the number of test cases that one must consider is extremely large. Fortunately, we identify ordering, timing, and network fault characteristics that significantly simplify testing. Furthermore, we found that a significant number of the failures are due to design flaws in core system mechanisms.We found that the majority of the failures could have been avoided by design reviews, and could have been discovered by testing with network-partitioning fault injection. We built NEAT, a testing framework that simplifies the coordination of multiple clients and can inject different types of network-partitioning faults. We used NEAT to test seven popular systems and found and reported 32 failures.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"56 1","pages":"51-68"},"PeriodicalIF":0.0,"publicationDate":"2018-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88516898","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}
R. Alagappan, Aishwarya Ganesan, Jing Liu, A. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau
We introduce situation-aware updates and crash recovery (SAUCR), a new approach to performing replicated data updates in a distributed system. SAUCR adapts the update protocol to the current situation: with many nodes up, SAUCR buffers updates in memory; when failures arise, SAUCR flushes updates to disk. This situation-awareness enables SAUCR to achieve high performance while offering strong durability and availability guarantees. We implement a prototype of SAUCR in ZooKeeper. Through rigorous crash testing, we demonstrate that SAUCR significantly improves durability and availability compared to systems that always write only to memory. We also show that SAUCR's reliability improvements come at little or no cost: SAUCR's overheads are within 0%-9% of a purely memory-based system.
{"title":"Fault-Tolerance, Fast and Slow: Exploiting Failure Asynchrony in Distributed Systems","authors":"R. Alagappan, Aishwarya Ganesan, Jing Liu, A. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau","doi":"10.5555/3291168.3291197","DOIUrl":"https://doi.org/10.5555/3291168.3291197","url":null,"abstract":"We introduce situation-aware updates and crash recovery (SAUCR), a new approach to performing replicated data updates in a distributed system. SAUCR adapts the update protocol to the current situation: with many nodes up, SAUCR buffers updates in memory; when failures arise, SAUCR flushes updates to disk. This situation-awareness enables SAUCR to achieve high performance while offering strong durability and availability guarantees. We implement a prototype of SAUCR in ZooKeeper. Through rigorous crash testing, we demonstrate that SAUCR significantly improves durability and availability compared to systems that always write only to memory. We also show that SAUCR's reliability improvements come at little or no cost: SAUCR's overheads are within 0%-9% of a purely memory-based system.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"1 1","pages":"390-408"},"PeriodicalIF":0.0,"publicationDate":"2018-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90896193","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}
Keeping communication private has become increasingly important in an era of mass surveillance and state-sponsored attacks. While hiding the contents of a conversation has well-known solutions, hiding the associated metadata (participants, duration, etc.) remains a challenge, especially if one cannot trust ISPs or proxy servers. This paper describes a communication system called Pung that provably hides all content and metadata while withstanding global adversaries. Pung is a key-value store where clients deposit and retrieve messages without anyone-- including Pung's servers--learning of the existence of a conversation. Pung is based on private information retrieval, which we make more practical for our setting with new techniques. These include a private multiretrieval scheme, an application of the power of two choices, and batch codes. These extensions allow Pung to handle 103× more users than prior systems with a similar threat model.
{"title":"Unobservable Communication over Fully Untrusted Infrastructure","authors":"Sebastian Angel, Srinath T. V. Setty","doi":"10.15781/T20R9MP4D","DOIUrl":"https://doi.org/10.15781/T20R9MP4D","url":null,"abstract":"Keeping communication private has become increasingly important in an era of mass surveillance and state-sponsored attacks. While hiding the contents of a conversation has well-known solutions, hiding the associated metadata (participants, duration, etc.) remains a challenge, especially if one cannot trust ISPs or proxy servers. This paper describes a communication system called Pung that provably hides all content and metadata while withstanding global adversaries. Pung is a key-value store where clients deposit and retrieve messages without anyone-- including Pung's servers--learning of the existence of a conversation. Pung is based on private information retrieval, which we make more practical for our setting with new techniques. These include a private multiretrieval scheme, an application of the power of two choices, and batch codes. These extensions allow Pung to handle 103× more users than prior systems with a similar threat model.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"15 1","pages":"551-569"},"PeriodicalIF":0.0,"publicationDate":"2016-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81551039","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}
Andrew Quinn, David Devecsery, Peter M. Chen, J. Flinn
Dynamic information flow tracking (DIFT) is an important tool in many domains, such as security, debugging, forensics, provenance, configuration troubleshooting, and privacy tracking. However, the usability of DIFT is currently limited by its high overhead; complex information flow queries can take up to two orders of magnitude longer to execute than the original execution of the program. This precludes interactive uses in which users iteratively refine queries to narrow down bugs, leaks of private data, or performance anomalies.JetStream applies cluster computing to parallelize and accelerate information flow queries over past executions. It uses deterministic record and replay to time slice executions into distinct contiguous chunks of execution called epochs, and it tracks information flow for each epoch on a separate core in the cluster. It structures the aggregation of information flow data from each epoch as a streaming computation. Epochs are arranged in a sequential chain from the beginning to the end of program execution; relationships to program inputs (sources) are streamed forward along the chain, and relationships to program outputs (sinks) are streamed backward. Jet-Stream is the first system to parallelize DIFT across a cluster. Our results show that JetStream queries scale to at least 128 cores over a wide range of applications. JetStream accelerates DIFT queries to run 12-48 times faster than sequential queries; in most cases, queries run faster than the original execution of the program.
{"title":"JetStream: Cluster-Scale Parallelization of Information Flow Queries","authors":"Andrew Quinn, David Devecsery, Peter M. Chen, J. Flinn","doi":"10.5555/3026877.3026912","DOIUrl":"https://doi.org/10.5555/3026877.3026912","url":null,"abstract":"Dynamic information flow tracking (DIFT) is an important tool in many domains, such as security, debugging, forensics, provenance, configuration troubleshooting, and privacy tracking. However, the usability of DIFT is currently limited by its high overhead; complex information flow queries can take up to two orders of magnitude longer to execute than the original execution of the program. This precludes interactive uses in which users iteratively refine queries to narrow down bugs, leaks of private data, or performance anomalies.JetStream applies cluster computing to parallelize and accelerate information flow queries over past executions. It uses deterministic record and replay to time slice executions into distinct contiguous chunks of execution called epochs, and it tracks information flow for each epoch on a separate core in the cluster. It structures the aggregation of information flow data from each epoch as a streaming computation. Epochs are arranged in a sequential chain from the beginning to the end of program execution; relationships to program inputs (sources) are streamed forward along the chain, and relationships to program outputs (sinks) are streamed backward. Jet-Stream is the first system to parallelize DIFT across a cluster. Our results show that JetStream queries scale to at least 128 cores over a wide range of applications. JetStream accelerates DIFT queries to run 12-48 times faster than sequential queries; in most cases, queries run faster than the original execution of the program.","PeriodicalId":90294,"journal":{"name":"Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation","volume":"1 1","pages":"451-466"},"PeriodicalIF":0.0,"publicationDate":"2016-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83159182","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}
Proceedings of the -- USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Symposium on Operating Systems Design and Implementation
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：