Datamation: A Quarter of a Century and Four Orders of Magnitude Later

Cluster Computing(2011)

引用 0|浏览0
暂无评分
摘要
The combination of the high-performance psort sorting library and of a carefully tuned desktop-class cluster allowed us to improve the previous record on the Datamation sort benchmark by over an order of magnitude, sorting a million 100 byte records from disk to disk in a few dozen milliseconds. Of the many implementation and configuration choices we faced, the most crucial were judicious data placement and access patterns on disk, adoption of UDP sockets instead of MPI, careful pruning of virtually all system daemons, and rejection of ``on demand'' frequency scaling.
更多
查看译文
关键词
frequency scaling,careful pruning,desktop-class cluster,datamation sort benchmark,dozen millisecond,high-performance psort,byte record,access pattern,judicious data placement,configuration choice,linux,sorting,message passing,latency,cluster,protocols,transport protocols,benchmark testing,switches
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要