Experience distributing objects in an SMMP OS

Appavoo, Jonathan; Silva, Dilma Da; Krieger, Orran; Auslander, Marc; Ostrowski, M.; Rosenburg, Bryan S.; Waterland, Amos; Wisniewski, Robert W.; Xenidis, Jimi; Stumm, Michael; Soares, Livio

doi:10.1145/1275517.1275518

Cited by 34 publications

(27 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The omni-kernel has some structural similarity to OS architectures [13], [14], [15], [16] whose design is dominated by multi-core scalability concerns. As in these systems, the loose coupling of resources in omni-kernel encourages partitioning, distribution, and replication, all of which are conducive to OS scalability [17], [18].…”

Section: Dependencies Load Sharing and Scalabilitymentioning

confidence: 99%

“…Resources both exchange and share state in their operation, so partitioning, distribution, and replication [13], [17], [18] are carefully employed to avoid shared state on critical paths. The OKRT object system provides a convenient basis for implementing these techniques and for managing state that is distributed among resources.…”

Section: Omni-kernel Runtime (Okrt)mentioning

confidence: 99%

See 1 more Smart Citation

Omni-Kernel: An Operating System Architecture for Pervasive Monitoring and Scheduling

Kvalnes

Johansen

Renesse

et al. 2015

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Abstract-The omni-kernel architecture is designed around pervasive monitoring and scheduling. Motivated by new requirements in virtualized environments, this architecture ensures that all resource consumption is measured, that resource consumption resulting from a scheduling decision is attributable to an activity, and that scheduling decisions are fine-grained. Vortex, implemented for multi-core x86-64 platforms, instantiates the omni-kernel architecture, providing a wide range of operating system functionality and abstractions. With Vortex, we experimentally demonstrated the efficacy of the omni-kernel architecture to provide accurate scheduler control over resource allocation despite competing workloads. Experiments involving Apache, MySQL, and Hadoop quantify the cost of pervasive monitoring and scheduling in Vortex to be below 6 percent of CPU consumption.

show abstract

Section: Dependencies Load Sharing and Scalabilitymentioning

confidence: 99%

Section: Omni-kernel Runtime (Okrt)mentioning

confidence: 99%

Omni-Kernel: An Operating System Architecture for Pervasive Monitoring and Scheduling

Kvalnes

Johansen

Renesse

et al. 2015

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…Scalable reference counters. RadixVM's scheme for reference counting, Refcache, inherits ideas from sloppy counters [6], Scalable NonZero Indicators (SNZI) [12], distributed counters [2], shared vs. local counts in Modula-2+ [11], and approximate counters [8]. All of these techniques speed up increment and decrement using per-core counters, and require significantly more work to find the true total value.…”

Section: Related Workmentioning

confidence: 99%

RadixVM

Clements¹,

Kaashoek²,

Zeldovich³

2013

Proceedings of the 8th ACM European Conference on Computer Systems

View full text Add to dashboard Cite

RadixVM is a new virtual memory system design that enables fully concurrent operations on shared address spaces for multithreaded processes on cache-coherent multicore computers. Today, most operating systems serialize operations such as mmap and munmap, which forces application developers to split their multithreaded applications into multiprocess applications, hoard memory to avoid the overhead of returning it, and so on. RadixVM removes this burden from application developers by ensuring that address space operations on non-overlapping memory regions scale perfectly. It does so by combining three techniques: 1) it organizes metadata in a radix tree instead of a balanced tree to avoid unnecessary cache line movement; 2) it uses a novel memory-efficient distributed reference counting scheme; and 3) it uses a new scheme to target remote TLB shootdowns and to often avoid them altogether. Experiments on an 80 core machine show that RadixVM achieves perfect scalability for non-overlapping regions: if several threads mmap or munmap pages in parallel, they can run completely independently and induce no cache coherence traffic.

show abstract

“…To improve kernel scalability, some researchers propose to build new operating systems for multiprocessor architectures. For example, K42 [2] and Tornado [4], which are designed in the object-oriented manner, can achieve both locality and scalability on multiprocessors. However, the scalability is not yet known on large-scale multicores.…”

Section: Research On Kernel Parallel Scalabilitymentioning

confidence: 99%

“…While the scalability issue of operating systems has been studied in context of multiprocessor system (e.g., SMP machine) [2]- [4], the issue on multicore system is unique. First, the number of cores in multicore systems can be much larger than the number of processors in a multiprocessor system, which makes the scalability an even acute issue.…”

Section: Introductionmentioning

confidence: 99%

Comparing Operating Systems Scalability on Multicore Processors by Microbenchmarking

Cui

Chen

Shi

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYMulticore processor architectures have become ubiquitous in today's computing platforms, especially in parallel computing installations, with their power and cost advantages. While the technology trend continues towards having hundreds of cores on a chip in the foreseeable future, an urgent question posed to system designers as well as application users is whether applications can receive sufficient support on today's operating systems for them to scale to many cores. To this end, people need to understand the strengths and weaknesses on their support on scalability and to identify major bottlenecks limiting the scalability, if any. As open-source operating systems are of particular interests in the research and industry communities, in this paper we choose three operating systems (Linux, Solaris and FreeBSD) to systematically evaluate and compare their scalability by using a set of highly-focused microbenchmarks for broad and detailed understanding their scalability on an AMD 32-core system. We use system profiling tools and analyze kernel source codes to find out the root cause of each observed scalability bottleneck. Our results reveal that there is no single operating system among the three standing out on all system aspects, though some system(s) can prevail on some of the system aspects. For example, Linux outperforms Solaris and FreeBSD significantly for file-descriptor-and process-intensive operations. For applications with intensive sockets creation and deletion operations, Solaris leads FreeBSD, which scales better than Linux. With the help of performance tools and source code instrumentation and analysis, we find that synchronization primitives protecting shared data structures in the kernels are the major bottleneck limiting system scalability.

show abstract

Experience distributing objects in an SMMP OS

Cited by 34 publications

References 72 publications

Omni-Kernel: An Operating System Architecture for Pervasive Monitoring and Scheduling

Omni-Kernel: An Operating System Architecture for Pervasive Monitoring and Scheduling

RadixVM

Comparing Operating Systems Scalability on Multicore Processors by Microbenchmarking

Contact Info

Product

Resources

About