Implementation of the simplified communication mechanism in the cloud of high performance computations
DOI:
https://doi.org/10.15587/1729-4061.2017.98896Keywords:
mechanism of simplified communication, high-performance data processing, binary compatibility, clusterAbstract
Constructing a system with traditional resources, based on the concept of high-performance computations (HPC) and data processing in the cloud, fully reveals new addressing problems. In the course of processing the data, it discovers many other unexplored scientific problems. One of these problems is to reduce the network expenditures on a virtual cluster in the cloud with HPC. In order to solve this problem, the work presented proposes a mechanism of simplified communication (SCM) to optimize the intra-cluster network performance, which intercepts packets at the level below that of network, and verifies whether it is meant for a coresident virtual machine. Compared with TCP, the introduced protocol of simplified communication (SCP) makes it possible to avoid the slow start phase, and to use a smaller header for a data packet, which improves the intra-domain and extra-domain throughput. To implement SCM inside the system, we also integrated XenLoop. A dispatched packet is sent through the FIFO channel, which is opened by XenLoop. This realization supports binary compatibility for the applications that use a standard socket interface. Throughput of the intra-domain communication in the system with SCM improves by about one and a half, while relative time of a reference test with a set of NAS-tags is lower. Experimental comparison of indicators for SCP and a protocol of remote memory access (RMAP) shows that SCP is 7.8–7.9 % faster than RMAP.
References
- Melnyk, V., Pekh, P., Melnyk, K., Bahnyuk, N., Zhyharevych, O. (2016). Design and implementation of inter-domain communication mechanism for high performance data processing. Eastern-European Journal of Enterprise Technologies, 1 (9 (79)), 10–15. doi: 10.15587/1729-4061.2016.60629
- Melnyk, V., Bahnyuk, N., Melnyk, K. (2015). Influence of high performance sockets on data processing intensity. ScienceRise, 6 (2 (11)), 38–48. doi: 10.15587/2313-8416.2015.44380
- Melnyk, V., Zhyharevych, O., Melnyk, K. (2015). High production of java sockets (HPJS) for helth clouds in science. Proceedings of National Aviation University, 64 (3). doi: 10.18372/2306-1472.64.9041
- Melnyk, V. M., Pekh, P. A., Melnyk, K. V., Zhyharevych, O. K. (2015). Significance of the socket programming for the laboratory with intensive data communications. Computer-integrated technologies: education, science and industry, 20, 67–71.
- Barham, P., Dragovic, B., Fraser, K., Hand, S., Harris, T., Ho, A. et. al. (2003). Xen and the art of virtualization. Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles – SOSP ’03. doi: 10.1145/945445.945462
- Pratt, I. (2007). Xen Virtualization. Linux world 2005 Virtualization BOF Presentation.
- Chisnall, D. (2007). The Definitive Guide to the Xen Hypervisor. Prentice Hall.
- Menon, A., Cox, A. L., Zwaenepoel, W.(2006). Optimizing network virtualization in Xen. In 2006 USENIX Annual Technical Conference. Boston, Massachusetts, USA, 15–28.
- Wang, J., Wright, K.-L., Gopalan, K. (2009). XenLoop: a transparent high performance inter-VM network loopback. Cluster Computing, 12 (2), 141–152. doi: 10.1007/s10586-009-0079-x
- Kim, K., Kim, C., Jung, S.-I., Shin, H.-S., Kim, J.-S. (2008). Inter-domain socket communications supporting high performance and full binary compatibility on Xen. Proceedings of the Fourth ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments – VEE ’08. doi: 10.1145/1346256.1346259
- Amdahl's Law. Available at: http://home.wlu.edu/~whaleyt/classes/parallel/topics/amdahl.html
- Liu, J., Huang, W., Abali, B., Panda, D. K. (2006). High Performance VMM-Bypass I/O in Virtual Machines. USENIX Annual Technical Conference archive.
- Hines, M. R., Gopalan, K. (2007). MemX. Proceedings of the 3rd International Workshop on Virtualization Technology in Distributed Computing – VTDC ’07. doi: 10.1145/1408654.1408656
- Deshpande, U., Wang, B., Haque, S., Hines, M., Gopalan, K. (2010). MemX: Virtualization of Cluster-Wide Memory. 2010 39th International Conference on Parallel Processing. doi: 10.1109/icpp.2010.74
- Kim, J.-S., Kim, K., Jung, S.-I., Ha, S. (2003). Design and implementation of a user-level Sockets layer over Virtual Interface Architecture. Concurrency and Computation: Practice and Experience, 15 (7-8), 727–749. doi: 10.1002/cpe.721
- Son, S., Kim, J., Lim, E., Jung, S. (2004). SOP: A Socket Interface for TOEs. In Internet and Multimedia Systems and Applications.
- Clark, D. D. (1982). Window and acknowledgement strategy in TCP. RFC 813. Internet Engineering Task Force. doi: 10.17487/rfc0813
- Menon, A., Santos, J. R., Turner, Y., Janakiraman, G. (John), Zwaenepoel, W. (2005). Diagnosing performance overheads in the xen virtual machine environment. Proceedings of the 1st ACM/USENIX International Conference on Virtual Execution Environments – VEE ’05. doi: 10.1145/1064979.1064984
- Network bandwidth testing. Available at: http://semenushkin.ru/2010/07/01/тестирование-пропускной-способности
- Bailey, D. H., Barszcz, E., Barton, J. T., Browning, D. S., Carter, R. L., Dagum, L. et. al. (1991). The Nas Parallel Benchmarks. International Journal of High Performance Computing Applications, 5 (3), 63–73. doi: 10.1177/109434209100500306
- Overview of some cluster performance measurement systems. Available at: http://www.ixbt.com/cpu/cluster-benchtheory.shtml
- Netperf: A Network Performance Benchmark. Revision 2.0. Hewlett-Packard Company. Available at: http://www.netperf.org/netperf/training/Netperf.html
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2017 Vasyl Melnyk, Nataliya Bahnyuk, Kateryna Melnyk, Oksana Zhyharevych, Natalia Panasyuk
This work is licensed under a Creative Commons Attribution 4.0 International License.
The consolidation and conditions for the transfer of copyright (identification of authorship) is carried out in the License Agreement. In particular, the authors reserve the right to the authorship of their manuscript and transfer the first publication of this work to the journal under the terms of the Creative Commons CC BY license. At the same time, they have the right to conclude on their own additional agreements concerning the non-exclusive distribution of the work in the form in which it was published by this journal, but provided that the link to the first publication of the article in this journal is preserved.
A license agreement is a document in which the author warrants that he/she owns all copyright for the work (manuscript, article, etc.).
The authors, signing the License Agreement with TECHNOLOGY CENTER PC, have all rights to the further use of their work, provided that they link to our edition in which the work was published.
According to the terms of the License Agreement, the Publisher TECHNOLOGY CENTER PC does not take away your copyrights and receives permission from the authors to use and dissemination of the publication through the world's scientific resources (own electronic resources, scientometric databases, repositories, libraries, etc.).
In the absence of a signed License Agreement or in the absence of this agreement of identifiers allowing to identify the identity of the author, the editors have no right to work with the manuscript.
It is important to remember that there is another type of agreement between authors and publishers – when copyright is transferred from the authors to the publisher. In this case, the authors lose ownership of their work and may not use it in any way.
