Fleets: Scalable Services in a Factored Operating System
Current monolithic operating systems are designed for uniprocessor systems, and their architecture reflects this. The rise of multicore and cloud computing is drastically changing the tradeoffs in operating system design. The culture of scarce computational resources is being replaced with one of ab...
| Main Authors: | , , , , , , , , |
|---|---|
| Other Authors: | |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/61640 |
| _version_ | 1826210246923649024 |
|---|---|
| author | Wentzlaff, David Gruenwald, Charles, III Beckmann, Nathan Belay, Adam Kasture, Harshad Modzelewski, Kevin Youseff, Lamia Miller, Jason E. Agarwal, Anant |
| author2 | Anant Agarwal |
| author_facet | Anant Agarwal Wentzlaff, David Gruenwald, Charles, III Beckmann, Nathan Belay, Adam Kasture, Harshad Modzelewski, Kevin Youseff, Lamia Miller, Jason E. Agarwal, Anant |
| author_sort | Wentzlaff, David |
| collection | MIT |
| description | Current monolithic operating systems are designed for uniprocessor systems, and their architecture reflects this. The rise of multicore and cloud computing is drastically changing the tradeoffs in operating system design. The culture of scarce computational resources is being replaced with one of abundant cores, where spatial layout of processes supplants time multiplexing as the primary scheduling concern. Efforts to parallelize monolithic kernels have been difficult and only marginally successful, and new approaches are needed. This paper presents fleets, a novel way of constructing scalable OS services. With fleets, traditional OS services are factored out of the kernel and moved into user space, where they are further parallelized into a distributed set of concurrent, message-passing servers. We evaluate fleets within fos, a new factored operating system designed from the ground up with scalability as the first-order design constraint. This paper details the main design principles of fleets, and how the system architecture of fos enables their construction. We describe the design and implementation of three critical fleets (network stack, page allocation, and file system) and compare with Linux. These comparisons show that fos achieves superior performance and has better scalability than Linux for large multicores; at 32 cores, fos's page allocator performs 4.5 times better than Linux, and fos's network stack performs 2.5 times better. Additionally, we demonstrate how fleets can adapt to changing resource demand, and the importance of spatial scheduling for good performance in multicores. |
| first_indexed | 2024-09-23T14:46:46Z |
| id | mit-1721.1/61640 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T14:46:46Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | mit-1721.1/616402019-04-10T15:45:09Z Fleets: Scalable Services in a Factored Operating System Wentzlaff, David Gruenwald, Charles, III Beckmann, Nathan Belay, Adam Kasture, Harshad Modzelewski, Kevin Youseff, Lamia Miller, Jason E. Agarwal, Anant Anant Agarwal Computer Architecture multicore scalable operating system Current monolithic operating systems are designed for uniprocessor systems, and their architecture reflects this. The rise of multicore and cloud computing is drastically changing the tradeoffs in operating system design. The culture of scarce computational resources is being replaced with one of abundant cores, where spatial layout of processes supplants time multiplexing as the primary scheduling concern. Efforts to parallelize monolithic kernels have been difficult and only marginally successful, and new approaches are needed. This paper presents fleets, a novel way of constructing scalable OS services. With fleets, traditional OS services are factored out of the kernel and moved into user space, where they are further parallelized into a distributed set of concurrent, message-passing servers. We evaluate fleets within fos, a new factored operating system designed from the ground up with scalability as the first-order design constraint. This paper details the main design principles of fleets, and how the system architecture of fos enables their construction. We describe the design and implementation of three critical fleets (network stack, page allocation, and file system) and compare with Linux. These comparisons show that fos achieves superior performance and has better scalability than Linux for large multicores; at 32 cores, fos's page allocator performs 4.5 times better than Linux, and fos's network stack performs 2.5 times better. Additionally, we demonstrate how fleets can adapt to changing resource demand, and the importance of spatial scheduling for good performance in multicores. 2011-03-09T18:45:21Z 2011-03-09T18:45:21Z 2011-03-09 http://hdl.handle.net/1721.1/61640 MIT-CSAIL-TR-2011-012 13 p. application/pdf |
| spellingShingle | multicore scalable operating system Wentzlaff, David Gruenwald, Charles, III Beckmann, Nathan Belay, Adam Kasture, Harshad Modzelewski, Kevin Youseff, Lamia Miller, Jason E. Agarwal, Anant Fleets: Scalable Services in a Factored Operating System |
| title | Fleets: Scalable Services in a Factored Operating System |
| title_full | Fleets: Scalable Services in a Factored Operating System |
| title_fullStr | Fleets: Scalable Services in a Factored Operating System |
| title_full_unstemmed | Fleets: Scalable Services in a Factored Operating System |
| title_short | Fleets: Scalable Services in a Factored Operating System |
| title_sort | fleets scalable services in a factored operating system |
| topic | multicore scalable operating system |
| url | http://hdl.handle.net/1721.1/61640 |
| work_keys_str_mv | AT wentzlaffdavid fleetsscalableservicesinafactoredoperatingsystem AT gruenwaldcharlesiii fleetsscalableservicesinafactoredoperatingsystem AT beckmannnathan fleetsscalableservicesinafactoredoperatingsystem AT belayadam fleetsscalableservicesinafactoredoperatingsystem AT kastureharshad fleetsscalableservicesinafactoredoperatingsystem AT modzelewskikevin fleetsscalableservicesinafactoredoperatingsystem AT yousefflamia fleetsscalableservicesinafactoredoperatingsystem AT millerjasone fleetsscalableservicesinafactoredoperatingsystem AT agarwalanant fleetsscalableservicesinafactoredoperatingsystem |