he distributed network of the supercomputer centers for collaborative research

The article is devoted to the project of the creation of the distributed network of the supercomputer centers for collaborative research. The key technique for improving the availability and efficiency of the supercomputer centers is the integration of the centers into a joint distributed network. This technique allows to redistribute the workload between resources by the redirecting of the user’s jobs from one center job queue to another depending on the instant resource usage.
The pilot project of the supercomputer centers distributed network is based on Joint Supercomputer Center in Moscow and Siberian Supercomputer Center in Novosibirsk. The centers communicate by the secure high-performance link. The results of the communication environment research are presented. (In Russian).