Hi dear Rob: I use two I/O data servers, one of them acts as metadata server, when i run pvfs2-cp /mnt/pvfs2/abc.ts ~/ the read speed can reach 11MBytes/s but when i mount the pvfs2 system to /mnt/pvfs2 entry and then run cp abc.ts ~/ the speed only can reach 4Mbytes/s . how can i solve this problem ??? i know it's slower ,but why only reach 50 persent .
Rob Ross wrote: > Hi, > > You must stop the servers and clients and modify the config file to > list the new server, yes. You will not lose any data on the original > servers. > > Rob > > On Oct 21, 2009, at 8:32 PM, xiechangcai wrote: > >> Hi,Rob >> I'm a PVFS2 user , >> I have a question, when i add one more i/o data server, >> I must change all the servers config file,and then restart >> pvfs2-server on all servers? >> is this true ? >> The original data on the I/O data servers can be lost ? >> >> >> 2009-10-22 >> xiechangcai >> 发件人： Rob Ross >> 发送时间： 2009-10-22 02:08:05 >> 收件人： Chris Worley >> 抄送： pvfs2-users >> 主题： Re: [Pvfs2-users] File affinity and CPU resource scheduling >> concernswhen using compute node as a PVFS server >> Hi Chris, >> Yes, you can certainly run PVFS servers on compute nodes. That's what >> we used to do all the time back in "the day", but it's still possible. >> The file system does not migrate files. In part this is because it >> would dramatically complicate metadata management, in part because we >> are frequently running in environments where there's no locality to >> exploit. >> You can choose to distribute over fewer (or just one) node, and there >> is functionality to discover where a file is stored, so you can map >> your computation onto the storage. >> Obviously yes, doing work on some other node will slow down >> computation on that node, how much depends on many things. >> Rob >> On Oct 21, 2009, at 12:40 PM, Chris Worley wrote: >> > I haven't looked at PVFS for nearly a decade, so my understanding >> > could be way out of date. Sorry if this is a stupid question; I'm >> > hoping PVFS might fill some requirements I'm looking at. >> > >> > Is it typical to use compute nodes as PVFS file servers? Is it even >> > possible (i.e. it isn't w/ Lustre)? >> > >> > If so, while striping across I/O nodes looks to be the default, is >> > there any provision for file affinity... i.e. files migrating to the >> > nodes using them? >> > >> > If striping is the only choice, and compute nodes serve the I/O too, >> > then a job running on one set of nodes could be using files striped >> > across another set of nodes in use by another job, causing both jobs >> > to loose performance, correct? >> > >> > Are there any links to PVFS performance over IB? >> > >> > Thanks, >> > >> > Chris >> _______________________________________________ >> Pvfs2-users mailing list >> [email protected] >> http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users > > _______________________________________________ Pvfs2-users mailing list [email protected] http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users
