11 Hits in 4.3 sec


Ruslan Nikolaev, Godmar Back
2013 Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles - SOSP '13  
VirtuOS's user library dispatches system calls directly to service domains using an exceptionless system call model, avoiding the cost of a system call trap in many cases.  ...  Thus, Vir-tuOS may provide a suitable basis for kernel decomposition while retaining compatibility with existing applications and good performance.  ...  Exception-less system calls [48] avoid this overhead.  ... 
doi:10.1145/2517349.2522719 dblp:conf/sosp/NikolaevB13 fatcat:eolqsbmsbfbppeheykl4toswsm

Running application specific kernel code by a just-in-time compiler

Ake Koomsin, Yasushi Shinjo
2015 Proceedings of the 8th Workshop on Programming Languages and Operating Systems - PLOS '15  
Our system call scripting runs with less overhead because we use a Just-In-Time (JIT) compiler. To evaluate our idea, we ported the LuaJIT compiler into the FreeBSD 10.1 x86 kernel.  ...  We modified Memcached to use system call scripting that processes multiple UDP GET requests at a time.  ...  FlexSC does not only avoid using exceptions which cause cache pollution, it also makes system call batching possible.  ... 
doi:10.1145/2818302.2818305 dblp:conf/sosp/KoomsinS15 fatcat:p74peurnqzcshdypxooksg3ura

New Mechanism for Fast System Calls [article]

Till Miemietz
2021 arXiv   pre-print
System calls have no place on the fast path of microsecond-scale systems. However, kernel bypass prevents the OS from controlling and supervising access to the hardware.  ...  FlexSC: flexible sys- tem call scheduling with exception-less system calls.  ...  The eXpress data path: Fast and flexible system-call aggregation.  ... 
arXiv:2112.10106v1 fatcat:bhlcttdkwbclhgbohhubi3viwy

Added Concurrency to Improve MPI Performance on Multicore

Humaira Kamal, Alan Wagner
2012 2012 41st International Conference on Parallel Processing  
We discuss the characteristics of the benchmarks with regards to trade-offs between the added costs and benefits.  ...  Fine-Grain (FG-MPI) extends the MPICH2 implementation of MPI and implements an integrated runtime system to allow multiple MPI processes to execute concurrently inside an OS-process.  ...  This work was supported in part by the Institute for Computing, Information and Cognitive Systems (ICICS) at UBC.  ... 
doi:10.1109/icpp.2012.15 dblp:conf/icpp/KamalW12 fatcat:2pkukyyi75cxnc7zm3frxrbi34

D5.2 Mechanisms For Network Service Dynamics And Peerformance

Felipe Huici, Costin Raiciu, Emil Matus, George Tsolis, Claudio Pisa, Stefano Salsano, Francesco Lombardo, Nicola Blefari-Melazzi, Giuseppe Bianchi, Louise Krug, Paul Veitch, Philip Eardley (+9 others)
2018 Zenodo  
FlexSC: Flexible System Call Scheduling with Exceptionless System Calls. In Proceedings of the 9th USENIX Conference on Operating Systems Design and //  ...  Kubernetes' main role is as a tool that lets us schedule containers across multiple hosts. Kubernetes automatically schedules pods to the less loaded system based on CPU and memory load.  ... 
doi:10.5281/zenodo.1230527 fatcat:y6vusoihsbapdihon2jpgpbzta


Robert Krahn, Bohdan Trach, Anjo Vahldiek-Oberwagner, Thomas Knauth, Pramod Bhatotia, Christof Fetzer
2018 Proceedings of the Thirteenth EuroSys Conference on - EuroSys '18  
We have implemented Pesos as a fully-functional storage system supporting many useful end-to-end storage features, and a range of effective performance optimizations.  ...  Third-party storage services pose the risk of integrity and confidentiality violations as the current storage policy enforcement mechanisms are spread across many layers in the system stack.  ...  To overcome this issue, we use an asynchronous system call interface as proposed by FlexSC [69] and adopted by Scone [3] .  ... 
doi:10.1145/3190508.3190518 dblp:conf/eurosys/KrahnTVKBF18 fatcat:voi2b2rc6nexlon43fahgg2on4

Slashing the Disaggregation Tax in Heterogeneous Data Centers with FractOS

Lluís Vilanova, Lina Maudlej, Shai Bergman, Till Miemietz, Matthias Hille, Nils Asmussen, Michael Roitzsch, Hermann Härtig, Mark Silberstein
2022 Zenodo  
in a disaggregated system.  ...  Disaggregated heterogeneous data centers promise higher efficiency, lower total costs of ownership, and more flexibility for data-center operators.  ...  FractOS has only a handful of system calls for manipulating Memory and Request objects (Table 1 ).  ... 
doi:10.5281/zenodo.6558297 fatcat:vqqrxmakkbbexmno6ihwtj5gza

AnyCall: Fast and Flexible System-Call Aggregation

Luis Gerhorst, Benedict Herzog, Stefan Reif, Wolfgang Schröder-Preikschat, Timo Hönig
Operating systems rely on system calls to allow the controlled communication of isolated processes with the kernel and other processes.  ...  This allows for very fast system calls interleaved with error checking and processing logic using only a single user/kernel transition.  ...  FlexSC: Flexible System Call Jones, Anna Klein, Peter Michaleas, Lauren Milechin, Julie Mullen, An- Scheduling with Exception-Less System Calls.  ... 
doi:10.48550/arxiv.2201.13160 fatcat:muryy577pbdovlbzc3flinjlzq

Network and storage stack specialisation for performance

Ilias Marinos, Apollo-University Of Cambridge Repository, Apollo-University Of Cambridge Repository, Robert Watson
With thorough evaluation of my systems, I illustrate how specialisation and greater microarchitectural awareness coul [...]  ...  The system software in these environments, however, is struggling to keep up with the increase in demand: contemporary network and storage stacks, as well as related APIs (e.g., BSD socket API) follow  ...  FlexSC [SS10; SS11] identified that cache pollution and pipeline flushing are the primary factors of system-call overhead, and proposed an exception-less implementation of the system call interface by  ... 
doi:10.17863/cam.35541 fatcat:w7hmudhmvzaktkxudgsg6mihee

Protecting applications using trusted execution environments

Christian Priebe, Peter Pietzuch, Engineering And Physical Sciences Research Council
We explore this in the context of three systems that deal with the protection of TEE applications and their host interfaces: SGX-LKL is a library operating system that can run full unmodified applications  ...  within TEEs with a minimal general-purpose host interface.  ...  In addition, it also makes memory accesses oblivious to prevent leakage FlexSC [313] first introduced the idea of exception-less asynchronous execution of system calls for improved system call performance  ... 
doi:10.25560/84843 fatcat:5iei362jgjc2xjwjpesxogp4oy

Privacy-Preserving Social Search: Primitives and Realisation

To further improve the security of the system, this thesis reviews the underlying cryptographic primitives used by the system and propose a new cryptographic primitive to address an attack with a moderate  ...  To mitigate the data breach issue in online social networks, this thesis builds an encrypted search system.  ...  Given a dataset D and a positive integer count threshold k, a data point p is a distance-based outlier in D if it has less than k neighbours. Otherwise, it is called an inlier.  ... 
doi:10.26180/5e9cd4b7483eb fatcat:youemnagozhtpfnwmodissse7i