Interrupt-driven systems can be collapsed due to frequent NIC interrupts under heavy network traffic. To mitigate this problem, a high-performance communication mechanism SBIM based on real-time OS RTLinux is designed...Interrupt-driven systems can be collapsed due to frequent NIC interrupts under heavy network traffic. To mitigate this problem, a high-performance communication mechanism SBIM based on real-time OS RTLinux is designed and implemented. A new concept of semi-polling is presented. With state-based semi-polling mechanism and lightweight buffering algorithm, interrupt frequency is reduced and the performance for short packet is significantly ameliorated. The experimental results indicate that the throughputs of SBIM for 64byte and 1500byte packets are 394Mbps and 895Mbps in Gigabit Ethernet environments, which show that the performance of SBIM surpasses that of other mechanisms.展开更多
Web based Computing Resource Publishing is a efficient way to provide additional computing capacity for users who need more computing resources than that they themselves could afford by making use of idle computing re...Web based Computing Resource Publishing is a efficient way to provide additional computing capacity for users who need more computing resources than that they themselves could afford by making use of idle computing resources in the Web.Extensibility and reliability are crucial for agent publishing. The parent child agent framework and primary slave agent framework were proposed respectively and discussed in detail.展开更多
Cooperation of multi-domain massively parallel processor systems in computing grid environment provides new opportunities for multisite job scheduling. At the same time, in the area of co-allocation, heterogeneity, ne...Cooperation of multi-domain massively parallel processor systems in computing grid environment provides new opportunities for multisite job scheduling. At the same time, in the area of co-allocation, heterogeneity, network adaptability and scalability raise the challenge for the international design of multisite job scheduling models and algorithms. It presents multisite job scheduling schema through the introduction of multisite job scheduling model and the performance model under the grid environment. It introduces two job multisite and cooperative scheduling models and algorithms with the core of the optimal and greedy-heuristic resource selection strategies. Meanwhile, compared with single and multisite cooperative scheduling models and algorithms introduced by Sabin, Yahyapour and other persons, the validity and advance of the scheduling model and the performance model herein are proved.展开更多
文摘Interrupt-driven systems can be collapsed due to frequent NIC interrupts under heavy network traffic. To mitigate this problem, a high-performance communication mechanism SBIM based on real-time OS RTLinux is designed and implemented. A new concept of semi-polling is presented. With state-based semi-polling mechanism and lightweight buffering algorithm, interrupt frequency is reduced and the performance for short packet is significantly ameliorated. The experimental results indicate that the throughputs of SBIM for 64byte and 1500byte packets are 394Mbps and 895Mbps in Gigabit Ethernet environments, which show that the performance of SBIM surpasses that of other mechanisms.
基金Sponsored by National Nature Science Foundation of China.
文摘Web based Computing Resource Publishing is a efficient way to provide additional computing capacity for users who need more computing resources than that they themselves could afford by making use of idle computing resources in the Web.Extensibility and reliability are crucial for agent publishing. The parent child agent framework and primary slave agent framework were proposed respectively and discussed in detail.
基金This work was supported in part by the National Natural Science Foundation of China （Grant No. 90412001） the National Grand Fundamental Research 973 Program of China （Grant No. G2005CB321806）.
文摘Cooperation of multi-domain massively parallel processor systems in computing grid environment provides new opportunities for multisite job scheduling. At the same time, in the area of co-allocation, heterogeneity, network adaptability and scalability raise the challenge for the international design of multisite job scheduling models and algorithms. It presents multisite job scheduling schema through the introduction of multisite job scheduling model and the performance model under the grid environment. It introduces two job multisite and cooperative scheduling models and algorithms with the core of the optimal and greedy-heuristic resource selection strategies. Meanwhile, compared with single and multisite cooperative scheduling models and algorithms introduced by Sabin, Yahyapour and other persons, the validity and advance of the scheduling model and the performance model herein are proved.
