Hi, loading write-behind on client side would help, since write-behind caches the write buffer and writes that data to server at a later point of time. regards, On Thu, Nov 20, 2008 at 11:36 PM, Aleynikov, Serge <Serge.Aleynikov at gs.com>wrote: > Would the booster, writebehind or iothreads translators provide any help > in this setup to reduce potential blocking of the local client writer due to > NFS slowness? > > ------------------------------ > *From:* basavanagowda at gmail.com [mailto:basavanagowda at gmail.com] *On > Behalf Of *Basavanagowda Kanur > *Sent:* Thursday, November 20, 2008 10:37 AM > *To:* Aleynikov, Serge > *Cc:* gluster-users at gluster.org > *Subject:* Re: Gluster setup question > > > > On Thu, Nov 20, 2008 at 9:01 PM, Aleynikov, Serge <Serge.Aleynikov at gs.com>wrote: > >> I built it from glusterfs-1.3.12.tag.gz source. >> > > my replies in previous mail hold good. > > >> ------------------------------ >> *From:* basavanagowda at gmail.com [mailto:basavanagowda at gmail.com] *On >> Behalf Of *Basavanagowda Kanur >> *Sent:* Wednesday, November 19, 2008 10:50 PM >> *To:* Aleynikov, Serge >> *Cc:* gluster-users at gluster.org >> *Subject:* Re: Gluster setup question >> >> Serge, >> I am assuming you are not using source code from repository. >> If you are using source code directly from repository, then answers >> below might not hold good. Please mention the version, if you are using from >> source repository. >> >> On Thu, Nov 20, 2008 at 6:13 AM, Aleynikov, Serge <Serge.Aleynikov at gs.com >> > wrote: >> >>> Hi, >>> >>> I am running several clients writing to local disk that are setup to >>> replicate data to N glusterfs server processes that use NFS for storing this >>> data. I have the following questions: >>> >>> 1. Does every write of a process to a local directory managed by >>> glusterfs client involve syncronous replication of data to glusterfs server? >>> >> yes. it involves synchronous replication. >> >> glusterfs--mailine--3.0--patch-621 (onwards) in our source repository has >> an AFR feature called quick-unwind, which would make replication >> asychronous. >> >> 2. Is it possible that if NFS is slow on the glusterfs server side, >>> then writing to local disk of a process on the glusterfs client's machine >>> would block? >>> >> yes. fops on glusterfs will block. >> >>> Thanks. >>> >>> Serge >>> >>> _______________________________________________ >>> Gluster-users mailing list >>> Gluster-users at gluster.org >>> http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users >>> >>> >> >> >> -- >> gowda >> >> > > > -- > gowda > > > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users > > -- Raghavendra G -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zresearch.com/pipermail/gluster-users/attachments/20081121/70a8d60c/attachment.htm
