Answers are grounded in this paper and cite their sources.
Evaluates Lustre's performance for data copying and calculations in a supercomputing environment, suggesting efficient data management.
This paper proposes a solution based on the distributed parallel file system Lustre for fast data copying and simultaneous calculations on the Super Computer Govorun located in LIT JINR and the computing cluster NCX located in LHEP JINR, included a fault-tolerance mode based on Lustre components and Pacemaker/Corosync software packages. The developed architecture is built on modern server equipment with a high-speed connection to the Ethernet 400 Gbps network between different buildings of the Institute. The results of testing the performance of the distributed parallel file system Lustre are presented, obtained on the basis of the IOR software utility, which operates on the basis of MPI technology.
No takes yet. Share an insight, caveat, or question.
Belyakov et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: