{"title":"BurstRadar","authors":"Raj Joshi, Ting Qu, M. Chan, B. Leong, B. T. Loo","doi":"10.1145/3265723.3265731","DOIUrl":"https://doi.org/10.1145/3265723.3265731","url":null,"abstract":"Microbursts can degrade application performance in datacenters by causing increased latency, jitter and packet loss. The detection of microbursts and identification of the contributing flows is the first step towards mitigating this problem. Unfortunately, microbursts are unpredictable and typically last for 10's or 100's of μs and the high line rates (> 10 Gbps) in modern datacenter networks further exacerbate the problem. In this paper, we show that modern programmable switching ASICs have made it practical to detect and characterize microbursts at high line rates. Our system, called BurstRadar, operates in the dataplane and monitors microbursts by capturing the telemetry information for only the packets involved in microbursts. We have implemented a prototype of BurstRadar on a Barefoot Tofino switch using the P4 programming language. Our evaluation on a multi-gigabit testbed using microburst traffic distributions from Facebook's production network shows that BurstRadar incurs 10 times less data collection and processing overhead than existing solutions. Furthermore, BurstRadar can handle simultaneous microburst traffic on multiple egress ports while consuming very few resources in the switching ASIC.","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116148305","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}
YoungGyoun Moon, Ilwoo Park, Seungeon Lee, KyoungSoo Park
{"title":"Accelerating Flow Processing Middleboxes with Programmable NICs","authors":"YoungGyoun Moon, Ilwoo Park, Seungeon Lee, KyoungSoo Park","doi":"10.1145/3265723.3265744","DOIUrl":"https://doi.org/10.1145/3265723.3265744","url":null,"abstract":"Software network functions are increasingly popular as they promise operational flexibility unconstrained by physical limitations. However, meeting the stringent requirements of high throughput and low latency in modern networks is often challenging on commodity hardware as network bandwidth is upgraded to 10s of Gbps and the number of concurrent flows grows. To address the problem, we explore the potential of harnessing modern programmable network interface cards (NICs) to dynamically offload stateful operations of network functions. We identify a set of candidate operations that can be offloaded to programmable NICs, and gauge the expected benefits in terms of CPU load reduction and throughput and latency improvement. We also consider challenges in offloading stateful operations to programmable NICs.","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129887225","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}
{"title":"Semantic-Aware Virtual Reality Video Streaming","authors":"Yue Leng, Chi-Chun Chen, Qiuyue Sun, Jian Huang, Yuhao Zhu","doi":"10.1145/3265723.3265738","DOIUrl":"https://doi.org/10.1145/3265723.3265738","url":null,"abstract":"Virtual reality (VR) technologies have huge potential to enable radically new applications, among which spherical panoramic (a.k.a., 360°) video streaming is on the verge of hitting the critical mass. Current VR systems treat 360° VR content as plain RGB pixels, similar to conventional planar frames, resulting in significant waste in data transfer and client-side processing. In this paper, we make the case that next-generation VR platforms can take advantage of semantics information inherent to VR content so as to improve the streaming and processing efficiency. To that end, we present SVR, a semantic-aware VR system that utilizes the object information in VR frames for content indexing and streaming. SVR exploits the key observation that end-users' viewing behaviors tend to be object-oriented. Instead of streaming entire frames, SVR delivers miniature frames that cover only the tracked visual objects in VR videos. We implement SVR prototype with a real hardware board and demonstrate that it achieves up to 34% network bandwidth reduction along with 21% device power saving.","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"1985 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130496843","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}
{"title":"Proceedings of the 9th Asia-Pacific Workshop on Systems","authors":"","doi":"10.1145/3265723","DOIUrl":"https://doi.org/10.1145/3265723","url":null,"abstract":"","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132013395","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}
{"title":"A Lightweight and Fine-grained File System Sandboxing Framework","authors":"Ashish Bijlani, U. Ramachandran","doi":"10.1145/3265723.3265734","DOIUrl":"https://doi.org/10.1145/3265723.3265734","url":null,"abstract":"File system sandboxing is a useful technique for protecting sensitive data from untrusted binaries. However, existing approaches do not allow fine-grained control over policy enforcement, require superuser privileges, or incur high performance overhead. This paper proposes SandFS, a lightweight and fine-grained file system sandboxing framework for unprivileged users and applications. We have designed SandFS as a stackable in-kernel file system that can be safely be extended at runtime from the userspace to enforce custom security policies in the kernel and offer near-native performance. With SandFS, multiple sandboxing layers could be stacked on top of each other, with each higher layer further enforcing its own policies to provide a restricted view of the lower. Our evaluation of SandFS with real-world workload shows that it imposes less than 10% performance overhead.","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129121035","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}
{"title":"An Empirical Study on NVM-based Block I/O Caches","authors":"Geonhee Lee, H. Lee, Juwon Lee, B. Kim, S. Min","doi":"10.1145/3265723.3265741","DOIUrl":"https://doi.org/10.1145/3265723.3265741","url":null,"abstract":"This paper presents an empirical study on block I/O caches when combining the performance benefits of emerging NVM storages and the cost-effectiveness of secondary storages. Current state-of-the-art I/O caching solutions are designed around the performance characteristics of SSDs, and our study reveals that using them with NVM storages does not fully reap the benefits of I/O devices with near-DRAM latencies. With fast NVM storages, locating data must be handled efficiently, but the sophisticated yet complex data structures used in existing designs impose significant overheads by substantially increasing the hit time. As this design approach is suboptimal for accessing fast I/O devices, we suggest several architectural designs to exploit the performance of NVM storages.","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"24 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127359884","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}
{"title":"Detecting Data Center Cooling Problems Using a Data-driven Approach","authors":"C. Chen, Guosai Wang, Jiao Sun, W. Xu","doi":"10.1145/3265723.3265730","DOIUrl":"https://doi.org/10.1145/3265723.3265730","url":null,"abstract":"Cooling problems are common in data centers and many of them are hard to detect especially the hidden. These problems affect overall system dependability, performance and power efficiency. We propose a novel method to detect the cooling problems. Using common monitoring data available in most data centers, such as environmental temperature and hardware status, we build a workload-independent cooling profile for each server. With the cooling profiles, we are able to detect two types of both transient and lasting cooling failures. We detect transient failures by comparing the observed temperature with the model prediction, while we detect lasting failures by comparing the cooling profiles among different servers. We demonstrate the general applicability of our detection methods in three production data centers with vastly different scale, server types and workload, and detect several real cooling problems that have been hidden for months.","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123861463","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}
{"title":"Analysis and Optimizations of Java Full Garbage Collection","authors":"Haoyu Li, Mingyu Wu, Haibo Chen","doi":"10.1145/3265723.3265735","DOIUrl":"https://doi.org/10.1145/3265723.3265735","url":null,"abstract":"Java runtime frees applications from manual memory management by its automatic garbage collection (GC), at the cost of stop-the-world pauses. State-of-the-art collectors leverage multiple generations, which will inevitably suffer from a full GC phase scanning the whole heap and induce a pause tens of times longer than normal collections, which largely affects both throughput and latency of the entire system. In this paper, we analyze the full GC performance of HotSpot Parallel Scavenge garbage collector comprehensively and study its algorithm design in depth. We find out that heavy dependencies among heap regions cause poor thread utilization. Furthermore, many heap regions contain mostly live objects (referred to as dense regions), which are unnecessary to collect. To solve these problems, we introduce two kinds of optimizations: allocating shadow regions dynamically as compaction destination to eliminate region dependencies and skipping dense regions to reduce GC workload. Evaluation results show the optimizations lead to averagely 2.6X (up to 4.5X) improvement in full GC throughput and thereby boost the application performance by 18.2% on average (58.4% at best).","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133986036","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}
{"title":"CryptZip","authors":"Yiwen Shao, Sa Wang, Yungang Bao","doi":"10.1145/3265723.3265726","DOIUrl":"https://doi.org/10.1145/3265723.3265726","url":null,"abstract":"Ideal homomorphic encryption is theoretically achievable but impractical in reality due to tremendous computing overhead. Homomorphically encrypted databases, such as CryptDB, leverage replication with partially homomorphic encryption schemes to support different SQL queries over encrypted data directly. These databases reach a balance between security and efficiency, but incur considerable storage overhead, especially when making backups. Unfortunately, general data compression techniques exhibit inefficiency on encrypted data. We present CryptZip, a backup and recovery system that could highly reduce the backup storage cost of encrypted databases. The key idea is to leverage the metadata information of encryption schemes and selectively backup one or several columns among semantically redundant columns. The experimental results show that CryptZip could reduce up to 90.5% backup storage cost on TPC-C benchmark.","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123172025","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}
Seungwook Han, Sungjin Lee, Sangwook Shane Hahn, Jihong Kim
{"title":"SyncGC: A Synchronized Garbage Collection Technique for Reducing Tail Latency in Cassandra","authors":"Seungwook Han, Sungjin Lee, Sangwook Shane Hahn, Jihong Kim","doi":"10.1145/3265723.3265737","DOIUrl":"https://doi.org/10.1145/3265723.3265737","url":null,"abstract":"Data-center applications running on distributed databases often suffer from unexpectedly high response time fluctuation which is caused by long tail latency. In this paper, we find that long tail latency of user writes is mainly created by the interference with garbage collection (GC) tasks running in various system layers. In order to address the tail latency problem, we propose a synchronized garbage collection technique, called SyncGC. By scheduling multiple GC instances to execute in sync with each other in an overlapped manner, SyncGC prevents user requests from being interfered with GC instances, thereby minimizing their negative impacts on tail latency. Our experimental results with Cassandra show that SyncGC reduces the 99.99th-percentile tail latency and the maximum latency by 35% and 37%, on average, respectively.","PeriodicalId":397157,"journal":{"name":"Proceedings of the 9th Asia-Pacific Workshop on Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126491477","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}