[Gluster-users] How to compile,install gluster client on Mac os x
Hi all, glusterfs client support Mac os x,But do not see the details of the software compiler ,install and test documents; How to compile, install? How features state gluster client support MAC OS x Has anyone ever used it.I want to test the gluster client running on Mac os x . best regards. zhangbing 您是不是要找:cluster client 但是没有看到详细的软件编译和使用文档 ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] [Gluster-devel] Feature support: development of metadata service xlator plugin in glusterfs.
Thank you for your reply. In glusterfs,Some metadata information is recorded in the file's extended attr in all bricks, For example EC volume, N+M mode, stat file requires N+M command, file write, requires M+M lock, record file length, and also N+M setattr command, Finally n+m unlock command; if have metadataserver,All metadata related operations only one command to metadata server; As the old topic, MKDIR requires that all the DHT children should be executed Mkdir; Another difficult problem, lack of centralized metadata; disk recovery performance is not able to get a massive upgrade;Such as EC N+M volume, disk reconstruction, and only bricks n+m to participate in the reconstruction;Rebuilding 1TB takes several hours; The use of metadata, the data can be dispersed to all the disk,Disk failure, a lot of disk can be involved in the reconstruction; How to solve these difficulties. At 2015-06-21 05:31:58, Vijay Bellur vbel...@redhat.com wrote: On Friday 19 June 2015 10:43 PM, 张兵 wrote: Hi all In the use of the glusterfs ,found file system commands a lot, such as stat, lookup,setfattr, the very influence system performance, especially with EC volume. The use of glusterfs code architecture and add metadata server xlater and achieve similar GFS architecture; so, the same set of software, users can choose their own metadata server or not to choose the metadata server; How do you expect the metadata server to aide performance here? There would be network trips to the metadata servers to set/fetch necessary information. If the intention is to avoid the penalty of having to fetch information from disk, we have been investigating the possibility of loading md-cache as part of the brick process graph to avoid hitting the disk for repetitive fetch of attributes extended attributes. I expect that to be mainlined soon. If you have other ideas on how a metadata server can improve performance, that would be interesting to know. Regards, Vijay ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Feature support: development of metadata service xlator plugin in glusterfs.
Hi all In the use of the glusterfs ,found file system commands a lot, such as stat, lookup,setfattr, the very influence system performance, especially with EC volume. The use of glusterfs code architecture and add metadata server xlater and achieve similar GFS architecture; so, the same set of software, users can choose their own metadata server or not to choose the metadata server; I would like to have some suggestions on the development of metadata service xlator plugin in glusterfs. best regards zhangbing___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] how about all bricks in one process with multi-thread
Hi all I test glusterfs performance ,In my storage node ,I have 16 disks ,one disk as a glusterfs brick; when volume run,there is 16 glusterfsd process running ,one gluterfsd occupy10% cpu ,all 16 bricks occupy all cpu ; I want decrease system cpu occupy ,why not all bricks in one process with multi-thread; Is there any try all bricks in one process; best regard. James ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Compatibility issues window2008 nfs client and NFS ganesha+glusterfs
Hi all, Compatibility issues window2008 nfs client and NFS ganesha+glusterfs; 您是不是要找:wind window2008 supports as client nfs,But using ganesha+glusterfs as nfs server; Error IO when reading and writing file on window2008; There are tests of this way (window2008 nfs client + glusterfs+ganesha nfs server) ; This should be very important for the application of models. best regards James window2008 支持作为nfs client ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Why have problems gluster and kernel nfs
Hi all, I Install gluster in one node,disable gluster nfs and export nfs by kernel nfs server,they are in the same linux system; another linux client mount nfs path,when dd file on the nfs mount point;Sometimes the io return error; Who knows what is the reason, if there is a corresponding kernel patch. thanks! best regards ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Why have problems gluster and kernel nfs
Hi all, I Install gluster in one node,disable gluster nfs and export nfs by kernel nfs server,they are in the same linux system; another linux client mount nfs path,when dd file on the nfs mount point;Sometimes the io return error; Who knows what is the reason, if there is a corresponding kernel patch. thanks! best regards___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] talk about enhance gluster nfs performance
Hi all, How To enhance the gluster performance of NFS, when EC, the network transmission time long processing time, effect of NFS IOPS; In our tests, each EC IO needs 1ms(Gigabit Network), NFS can only handle 1000 IOPs ;NFS protocol message and the process in the same process,The process will block the NFS protocol message received; Why not the received nfs message packet and nfs protocol processing process isolation Or NFS multi thread; By the way, the progress of gluster epool multithread, if use epool multithread ,can solve the problem gluster nfs performance.? Best regards 您是不是要找:cluster nfs ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] why dd write fail, when nfs ha failover
Hi,all I install two centos6.2 os,mount gluster volume ,and then expert path through Linux kernel nfs ,I install ctdb for iP failover,all is normal, when one node fail,another node takeover. But dd write Will fail, ,dd rewrite ok why write fail when takeover. -- 发自我的网易邮箱手机智能版 ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] How to tune glusterfs performance
Hi all: How to tune glusterfs performance;is there any Effectiveparameters can beoptimizedtoimprove thewrite performance!linux kernel nfssupportasyncasynchronous mode,which can promote perfomance,Areclusterfs native clientcan modifyittoasynchronous mode___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] How to ensure the new data write to other bricks, if one brick offline of gluster distributed volume
Hi all How to ensure the new data write to other bricks, if one brick offline of gluster distributed volume ; the client can write data that originally on offline bricks to other online bricks ; the distributed volume crash, even if one brick offline; it's so unreliable when the failed brick online ,how to join the original distribute volume; don't want the new write data can't write in distrubuted volume; Thanks Regards James ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users