Anuroop Desu, Udaya L. N. Puvvadi, Tyler Stachecki, Sagar Vishwakarma, Sadegh Khalili, K. Ghose, B. Sammakia
Data center operators generally overprovision IT and cooling capacities to address unexpected utilization increases that can violate service quality commitments. This results in energy wastage. To reduce this wastage, we introduce HCP (Holistic Capacity Provisioner), a service latency aware management system for dynamically provisioning the server and cooling capacity. Short-term load prediction is used to adjust the online server capacity to concentrate the workload onto the smallest possible set of online servers. Idling servers are completely turned off based on a separate long-term utilization predictor. HCP targets data centers that use chilled air cooling and varies the cooling provided commensurately, using adjustable aperture tiles and speed control of the blower fans in the air handler. An HCP prototype supporting a server heterogeneity is evaluated with real-world workload traces/requests and realizes up to 32% total energy savings while limiting the 99th-percentile and average latency increases to at most 6.67% and 3.24%, respectively, against a baseline system where all servers are kept online.
{"title":"Latency-Aware Dynamic Server and Cooling Capacity Provisioner for Data Centers","authors":"Anuroop Desu, Udaya L. N. Puvvadi, Tyler Stachecki, Sagar Vishwakarma, Sadegh Khalili, K. Ghose, B. Sammakia","doi":"10.1145/3472883.3487015","DOIUrl":"https://doi.org/10.1145/3472883.3487015","url":null,"abstract":"Data center operators generally overprovision IT and cooling capacities to address unexpected utilization increases that can violate service quality commitments. This results in energy wastage. To reduce this wastage, we introduce HCP (Holistic Capacity Provisioner), a service latency aware management system for dynamically provisioning the server and cooling capacity. Short-term load prediction is used to adjust the online server capacity to concentrate the workload onto the smallest possible set of online servers. Idling servers are completely turned off based on a separate long-term utilization predictor. HCP targets data centers that use chilled air cooling and varies the cooling provided commensurately, using adjustable aperture tiles and speed control of the blower fans in the air handler. An HCP prototype supporting a server heterogeneity is evaluated with real-world workload traces/requests and realizes up to 32% total energy savings while limiting the 99th-percentile and average latency increases to at most 6.67% and 3.24%, respectively, against a baseline system where all servers are kept online.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86954190","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}
A. F. Baarzi, G. Kesidis, Carlee Joe-Wong, Mohammad Shahrad
Serverless computing is a rapidly growing paradigm in the cloud industry that envisions functions as the computational building blocks of an application. Instead of forcing the application developer to provision cloud resources for their application, the cloud provider provisions the required resources for each function "under the hood." In this work, we envision virtual serverless providers (VSPs) to aggregate serverless offerings. In doing so, VSPs allow developers (and businesses) to get rid of vendor lock-in problems and exploit pricing and performance variation across providers by adaptively utilizing the best provider at each time, forcing the providers to compete to offer cheaper and superior services. We discuss the merits of a VSP and show that serverless systems are well-suited to cross-provider aggregation, compared to virtual machines. We propose a VSP system architecture and implement an initial version. Using experimental evaluations, our preliminary results show that a VSP can improve maximum sustained throughput by 1.2x to 4.2x, reduces SLO violations by 98.8%, and improves the total invocations' costs by 54%.
{"title":"On Merits and Viability of Multi-Cloud Serverless","authors":"A. F. Baarzi, G. Kesidis, Carlee Joe-Wong, Mohammad Shahrad","doi":"10.1145/3472883.3487002","DOIUrl":"https://doi.org/10.1145/3472883.3487002","url":null,"abstract":"Serverless computing is a rapidly growing paradigm in the cloud industry that envisions functions as the computational building blocks of an application. Instead of forcing the application developer to provision cloud resources for their application, the cloud provider provisions the required resources for each function \"under the hood.\" In this work, we envision virtual serverless providers (VSPs) to aggregate serverless offerings. In doing so, VSPs allow developers (and businesses) to get rid of vendor lock-in problems and exploit pricing and performance variation across providers by adaptively utilizing the best provider at each time, forcing the providers to compete to offer cheaper and superior services. We discuss the merits of a VSP and show that serverless systems are well-suited to cross-provider aggregation, compared to virtual machines. We propose a VSP system architecture and implement an initial version. Using experimental evaluations, our preliminary results show that a VSP can improve maximum sustained throughput by 1.2x to 4.2x, reduces SLO violations by 98.8%, and improves the total invocations' costs by 54%.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"62 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87070111","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}
Giorgos Xanthakis, Giorgos Saloustros, Nikos Batsaras, Anastasios Papagiannis, A. Bilas
Key-value (KV) separation is a technique that introduces randomness in the I/O access patterns to reduce I/O amplification in LSM-based key-value stores. KV separation has a significant drawback that makes it less attractive: Delete and update operations in modern workloads result in frequent and expensive garbage collection (GC) in the value log. In this paper, we design and implement Parallax, which proposes hybrid KV placement to reduce GC overhead significantly and increases the benefits of using a log. We first model the benefits of KV separation for different KV pair sizes. We use this model to classify KV pairs in three categories small, medium, and large. Then, Parallax uses different approaches for each KV category: It always places large values in a log and small values in place. For medium values it uses a mixed strategy that combines the benefits of using a log and eliminates GC overhead as follows: It places medium values in a log for all but the last few (typically one or two) levels in the LSM structure, where it performs a full compaction, merges values in place, and reclaims log space without the need for GC. We evaluate Parallax against RocksDB that places all values in place and BlobDB that always performs KV separation. We find that Parallax increases throughput by up to 12.4x and 17.83x, decreases I/O amplification by up to 27.1x and 26x, and increases CPU efficiency by up to 18.7x and 28x, respectively, for all but scan-based YCSB workloads.
{"title":"Parallax","authors":"Giorgos Xanthakis, Giorgos Saloustros, Nikos Batsaras, Anastasios Papagiannis, A. Bilas","doi":"10.1145/3472883.3487012","DOIUrl":"https://doi.org/10.1145/3472883.3487012","url":null,"abstract":"Key-value (KV) separation is a technique that introduces randomness in the I/O access patterns to reduce I/O amplification in LSM-based key-value stores. KV separation has a significant drawback that makes it less attractive: Delete and update operations in modern workloads result in frequent and expensive garbage collection (GC) in the value log. In this paper, we design and implement Parallax, which proposes hybrid KV placement to reduce GC overhead significantly and increases the benefits of using a log. We first model the benefits of KV separation for different KV pair sizes. We use this model to classify KV pairs in three categories small, medium, and large. Then, Parallax uses different approaches for each KV category: It always places large values in a log and small values in place. For medium values it uses a mixed strategy that combines the benefits of using a log and eliminates GC overhead as follows: It places medium values in a log for all but the last few (typically one or two) levels in the LSM structure, where it performs a full compaction, merges values in place, and reclaims log space without the need for GC. We evaluate Parallax against RocksDB that places all values in place and BlobDB that always performs KV separation. We find that Parallax increases throughput by up to 12.4x and 17.83x, decreases I/O amplification by up to 27.1x and 26x, and increases CPU efficiency by up to 18.7x and 28x, respectively, for all but scan-based YCSB workloads.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"83 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83818739","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}
With user-facing apps adopting serverless computing, good latency performance of serverless platforms has become a strong fundamental requirement. However, it is difficult to achieve this on platforms today due to the design of their underlying control and data planes that are particularly ill-suited to short-lived functions with unpredictable arrival patterns. We present Atoll, a serverless platform, that overcomes the challenges via a ground-up redesign of the control and data planes. In Atoll, each app is associated with a latency deadline. Atoll achieves its per-app request latency goals by: (a) partitioning the cluster into (semi-global scheduler, worker pool) pairs, (b) performing deadline-aware scheduling and proactive sandbox allocation, and (c) using a load balancing layer to do sandbox-aware routing, and automatically scale the semi-global schedulers per app. Our results show that Atoll reduces missed deadlines by ~66x and tail latencies by ~3x compared to state-of-the-art alternatives.
{"title":"Atoll","authors":"","doi":"10.1145/3472883.3486981","DOIUrl":"https://doi.org/10.1145/3472883.3486981","url":null,"abstract":"With user-facing apps adopting serverless computing, good latency performance of serverless platforms has become a strong fundamental requirement. However, it is difficult to achieve this on platforms today due to the design of their underlying control and data planes that are particularly ill-suited to short-lived functions with unpredictable arrival patterns. We present Atoll, a serverless platform, that overcomes the challenges via a ground-up redesign of the control and data planes. In Atoll, each app is associated with a latency deadline. Atoll achieves its per-app request latency goals by: (a) partitioning the cluster into (semi-global scheduler, worker pool) pairs, (b) performing deadline-aware scheduling and proactive sandbox allocation, and (c) using a load balancing layer to do sandbox-aware routing, and automatically scale the semi-global schedulers per app. Our results show that Atoll reduces missed deadlines by ~66x and tail latencies by ~3x compared to state-of-the-art alternatives.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"76 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86181303","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}
Li Liu, Haoliang Wang, An Wang, Mengbai Xiao, Yue Cheng, Songqing Chen
Containerization is becoming increasingly popular, but unfortunately, containers often fail to deliver the anticipated performance with the allocated resources. In this paper, we first demonstrate the performance variance and degradation are significant (by up to 5x) in a multi-tenant environment where containers are co-located. We then investigate the root cause of such performance degradation. Contrary to the common belief that such degradation is caused by resource contention and interference, we find that there is a gap between the amount of CPU a container reserves and actually gets. The root cause lies in the design choices of today's Linux scheduling mechanism, which we call Forced Runqueue Sharing and Phantom CPU Time. In fact, there are fundamental conflicts between the need to reserve CPU resources and Completely Fair Scheduler's work-conserving nature, and this contradiction prevents a container from fully utilizing its requested CPU resources. As a proof-of-concept, we implement a new resource configuration mechanism atop the widely used Kubernetes and Linux to demonstrate its potential benefits and shed light on future scheduler redesign. Our proof-of-concept, compared to the existing scheduler, improves the performance of both batch and interactive containerized apps by up to 5.6x and 13.7x.
{"title":"Mind the Gap: Broken Promises of CPU Reservations in Containerized Multi-tenant Clouds","authors":"Li Liu, Haoliang Wang, An Wang, Mengbai Xiao, Yue Cheng, Songqing Chen","doi":"10.1145/3472883.3486997","DOIUrl":"https://doi.org/10.1145/3472883.3486997","url":null,"abstract":"Containerization is becoming increasingly popular, but unfortunately, containers often fail to deliver the anticipated performance with the allocated resources. In this paper, we first demonstrate the performance variance and degradation are significant (by up to 5x) in a multi-tenant environment where containers are co-located. We then investigate the root cause of such performance degradation. Contrary to the common belief that such degradation is caused by resource contention and interference, we find that there is a gap between the amount of CPU a container reserves and actually gets. The root cause lies in the design choices of today's Linux scheduling mechanism, which we call Forced Runqueue Sharing and Phantom CPU Time. In fact, there are fundamental conflicts between the need to reserve CPU resources and Completely Fair Scheduler's work-conserving nature, and this contradiction prevents a container from fully utilizing its requested CPU resources. As a proof-of-concept, we implement a new resource configuration mechanism atop the widely used Kubernetes and Linux to demonstrate its potential benefits and shed light on future scheduler redesign. Our proof-of-concept, compared to the existing scheduler, improves the performance of both batch and interactive containerized apps by up to 5.6x and 13.7x.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"39 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74223704","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}
Over the past few years, networking advances have spurred fundamental transformations in cloud computing. Technologies such as software defined networking, network virtualization, and high-bisection fabrics have simplified cloud design and operation, brought exciting new workloads to the cloud, and helped lower the bar to cloud adoption. Networking is poised to bring even more interesting and fundamental transformations to the cloud over the next few years. In this talk, I will describe several promising networking ideas, spanning high-performance fabrics and network stacks, programmable hardware, abstractions for network automation, and novel inter-domain protocols and services. I will discuss the tantalizing opportunities these ideas offer for cloud computing, and the fundamental new research and practical challenges they introduce. I will conclude my talk with observations on what it would take for our research community to make rapid and meaningful progress in this space.
{"title":"Networking and Cloud: A Match Made in Heaven","authors":"Aditya Akella","doi":"10.1145/3472883.3517037","DOIUrl":"https://doi.org/10.1145/3472883.3517037","url":null,"abstract":"Over the past few years, networking advances have spurred fundamental transformations in cloud computing. Technologies such as software defined networking, network virtualization, and high-bisection fabrics have simplified cloud design and operation, brought exciting new workloads to the cloud, and helped lower the bar to cloud adoption. Networking is poised to bring even more interesting and fundamental transformations to the cloud over the next few years. In this talk, I will describe several promising networking ideas, spanning high-performance fabrics and network stacks, programmable hardware, abstractions for network automation, and novel inter-domain protocols and services. I will discuss the tantalizing opportunities these ideas offer for cloud computing, and the fundamental new research and practical challenges they introduce. I will conclude my talk with observations on what it would take for our research community to make rapid and meaningful progress in this space.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74372255","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. Lim, Bogdan Stelea, Xueyuan Han, Thomas Pasquier
Despite the wide usage of container-based cloud computing, container auditing for security analysis relies mostly on built-in host audit systems, which often lack the ability to capture high-fidelity container logs. State-of-the-art reference-monitor-based audit techniques greatly improve the quality of audit logs, but their system-wide architecture is too costly to be adapted for individual containers. Moreover, these techniques typically require extensive kernel modifications, making it difficult to deploy in practical settings. In this paper, we present saBPF (secure audit BPF), an extension of the eBPF framework capable of deploying secure system-level audit mechanisms at the container granularity. We demonstrate the practicality of saBPF in Kubernetes by designing an audit framework, an intrusion detection system, and a lightweight access control mechanism. We evaluate saBPF and show that it is comparable in performance and security guarantees to audit systems from the literature that are implemented directly in the kernel.
{"title":"Secure Namespaced Kernel Audit for Containers","authors":"S. Lim, Bogdan Stelea, Xueyuan Han, Thomas Pasquier","doi":"10.1145/3472883.3486976","DOIUrl":"https://doi.org/10.1145/3472883.3486976","url":null,"abstract":"Despite the wide usage of container-based cloud computing, container auditing for security analysis relies mostly on built-in host audit systems, which often lack the ability to capture high-fidelity container logs. State-of-the-art reference-monitor-based audit techniques greatly improve the quality of audit logs, but their system-wide architecture is too costly to be adapted for individual containers. Moreover, these techniques typically require extensive kernel modifications, making it difficult to deploy in practical settings. In this paper, we present saBPF (secure audit BPF), an extension of the eBPF framework capable of deploying secure system-level audit mechanisms at the container granularity. We demonstrate the practicality of saBPF in Kubernetes by designing an audit framework, an intrusion detection system, and a lightweight access control mechanism. We evaluate saBPF and show that it is comparable in performance and security guarantees to audit systems from the literature that are implemented directly in the kernel.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88520294","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. Ramakrishnan, J. Rexford, Hakim Weatherspoon, S. Peter, F. Ozcan, Mehul Shah
Open Research Problems in the Cloud Panel.
云面板中的开放研究问题。
{"title":"Open Research Problems in the Cloud","authors":"R. Ramakrishnan, J. Rexford, Hakim Weatherspoon, S. Peter, F. Ozcan, Mehul Shah","doi":"10.1145/3472883.3517124","DOIUrl":"https://doi.org/10.1145/3472883.3517124","url":null,"abstract":"Open Research Problems in the Cloud Panel.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"60 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73718797","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}
Kalev Alpernas, Aurojit Panda, L. Ryzhyk, Shmuel Sagiv
Serverless platforms aim to simplify the deployment, scaling, and management of cloud applications. Serverless applications are inherently distributed, and are executed using shortlived ephemeral processes. The use of short-lived ephemeral processes simplifies application scaling and management, but also means that existing approaches to monitoring distributed systems and detecting bugs cannot be applied to serverless applications. In this paper we propose Watchtower, a framework that enables runtime monitoring of serverless applications. Watchtower takes program properties as inputs, and can detect cases where applications violate these properties. We design Watchtower to minimize application changes, and to scale at the same rate as the application. We achieve the former by instrumenting libraries rather than application code, and the latter by structuring Watchtower as a serverless application. Once a bug is found, developers can use the Watchtower debugger to identify and address the root cause of the bug.
{"title":"Cloud-Scale Runtime Verification of Serverless Applications","authors":"Kalev Alpernas, Aurojit Panda, L. Ryzhyk, Shmuel Sagiv","doi":"10.1145/3472883.3486977","DOIUrl":"https://doi.org/10.1145/3472883.3486977","url":null,"abstract":"Serverless platforms aim to simplify the deployment, scaling, and management of cloud applications. Serverless applications are inherently distributed, and are executed using shortlived ephemeral processes. The use of short-lived ephemeral processes simplifies application scaling and management, but also means that existing approaches to monitoring distributed systems and detecting bugs cannot be applied to serverless applications. In this paper we propose Watchtower, a framework that enables runtime monitoring of serverless applications. Watchtower takes program properties as inputs, and can detect cases where applications violate these properties. We design Watchtower to minimize application changes, and to scale at the same rate as the application. We achieve the former by instrumenting libraries rather than application code, and the latter by structuring Watchtower as a serverless application. Once a bug is found, developers can use the Watchtower debugger to identify and address the root cause of the bug.","PeriodicalId":91949,"journal":{"name":"Proceedings of the ... ACM Symposium on Cloud Computing [electronic resource] : SOCC ... ... SoCC (Conference)","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74282458","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：