Re: [Gluster-users] Slow write times to gluster disk

Hi Pat, I'm assuming you are using gluster native (fuse mount). If it helps, you could try mounting it via gluster NFS (gnfs) and then see if there is an improvement in speed. Fuse mounts are slower than gnfs mounts but you get the benefit of avoiding a single point of failure. Unlike fuse

Re: [Gluster-users] "Fake" distributed-replicated volume

On 04/07/2017 11:34 PM, Jamie Lawrence wrote: Greetings, Glusterites - I have a suboptimal situation, and am wondering if there is any way to create a replica-3 distributed/replicated volume with three machines. I saw in the docs that the create command will fail with multiple bricks on the

Re: [Gluster-users] Server source code installation

On Fri, Apr 7, 2017 at 11:24 PM, Tahereh Fattahi wrote: > Hi > I have 3 gluster servers and one volume. Know, I want to change the source > code of serves and install again. > Is it enough to stop and delete the volume, make and install the code? Or > before installation I

Re: [Gluster-users] hanging httpd processes.

On Sat, Apr 8, 2017 at 12:02 AM, Alvin Starr wrote: > Thanks for the help. > > That seems to have fixed it. > > We were seeing hangs clocking up at a rate of a few hundred a day and for > the last week there have been none. > > > Thanks for confirming this. Good to know one of

[Gluster-users] Slow write times to gluster disk

Hi, We noticed a dramatic slowness when writing to a gluster disk when compared to writing to an NFS disk. Specifically when using dd (data duplicator) to write a 4.3 GB file of zeros: * on NFS disk (/home): 9.5 Gb/s * on gluster disk (/gdata): 508 Mb/s The gluser disk is 2 bricks joined

Re: [Gluster-users] hanging httpd processes.

Thanks for the help. That seems to have fixed it. We were seeing hangs clocking up at a rate of a few hundred a day and for the last week there have been none. On 03/31/2017 05:54 AM, Mohit Agrawal wrote: Hi, As you have mentioned client/server version in thread it shows package version

[Gluster-users] "Fake" distributed-replicated volume

Greetings, Glusterites - I have a suboptimal situation, and am wondering if there is any way to create a replica-3 distributed/replicated volume with three machines. I saw in the docs that the create command will fail with multiple bricks on the same peer; is there a way around that/some other

[Gluster-users] Server source code installation

Hi I have 3 gluster servers and one volume. Know, I want to change the source code of serves and install again. Is it enough to stop and delete the volume, make and install the code? Or before installation I should delete some files or folders? ___

Re: [Gluster-users] rebalance fix layout necessary

Volume type: Disperse Volume 8+2 = 1080 bricks First time added 8+2 * 3 sets and it started giving issue in listing folder. so, remounted mount point and it was working fine. Second added 8+2 *13 sets and it also had the same issue. when listing folder it was returning an empty folder or not

Re: [Gluster-users] [Gluster-devel] Glusterfs meta data space consumption issue

Means if old data is present in brick and volume is not present then it should be visible in our brick dir /opt/lvmdir/c2/brick? On Fri, Apr 7, 2017 at 3:04 PM, Ashish Pandey wrote: > > If you are creating a fresh volume, then it is your responsibility to have > clean

Re: [Gluster-users] [Gluster-devel] Glusterfs meta data space consumption issue

If you are creating a fresh volume, then it is your responsibility to have clean bricks. I don't think gluster will give you a guarantee that it will be cleaned up. So you have to investigate if you have any previous data on that brick. What I meant was that you have to find out the number

Re: [Gluster-users] [Gluster-devel] Glusterfs meta data space consumption issue

Hi Ashish, I don't think so that count of files on mount point and .glusterfs/ will remain same. Because I have created one file on the gluster mount poing but on .glusterfs/ it increased by 3 in numbers. Reason behind that is it creates .glusterfs/xx/xx/x... which is two parent dir and

Re: [Gluster-users] [Gluster-devel] Glusterfs meta data space consumption issue

HI Ashish, Even if there is a old data then it should be clear by gluster it self right? or you want to do it manually? Regards, Abhishek On Fri, Apr 7, 2017 at 1:31 PM, Ashish Pandey wrote: > > Are you sure that the bricks which you used for this volume was not having >

Re: [Gluster-users] Glusterfs meta data space consumption issue

Is there any update ?? On Thu, Apr 6, 2017 at 12:45 PM, ABHISHEK PALIWAL wrote: > Hi, > > We are currently experiencing a serious issue w.r.t volume space usage by > glusterfs. > > In the below outputs, we can see that the size of the real data in /c > (glusterfs