[Gluster-users] understanding dht value

Hi, I am trying to make sense of the hash values that get assigned/used by DHT. /brick1/vol and /brick2/vol are the directories that are being used as bricks in a distributed replicated volume. [root@glusterhackervm3 glus]# getfattr -n trusted.glusterfs.dht -e hex /brick1/vol

Re: [Gluster-users] understanding dht value

Here's an article explaining how dht works. The hash maps are per-directory. https://joejulian.name/blog/dht-misses-are-expensive/ On 11/08/2016 11:04 AM, Ankireddypalle Reddy wrote: Hi, I am trying to make sense of the hash values that get assigned/used by DHT. /brick1/vol

Re: [Gluster-users] Looking for use cases / opinions

We haven’t decided how the JBODS would be configured. They would likely be SAS attached without a raid controller for improved performance. I run large ZFS arrays this way, but only in single server NFS setups right now. Mounting each hard drive as it’s own brick would probably give the most

Re: [Gluster-users] understanding dht value

Thanks for pointing to the article. I have been following the article all the way. What intrigues me is the dht values associated with sub directories. [root@glusterhackervm3 glus]# getfattr -n trusted.glusterfs.dht -e hex /brick2/vol getfattr: Removing leading '/' from absolute path names #

Re: [Gluster-users] understanding dht value

> Thanks for pointing to the article. I have been following the article all the > way. What intrigues me is the dht values associated with sub directories. > [root@glusterhackervm3 glus]# getfattr -n trusted.glusterfs.dht -e hex > /brick2/vol > getfattr: Removing leading '/' from absolute path

[Gluster-users] Automation of single server addition to replica

Hello All, I'd like to automate a gluster replica cluster in a way that allows me to later add single servers on the fly. I can't seem to understand from the docs how I might achieve this. It seems logical that a replica cluster needs to have at least 2 servers initially, but

Re: [Gluster-users] Automation of single server addition to replica

Replicas are defined in the order bricks are listed in the volume create command. So gluster volume create myvol replica 2 server1:/data/brick1 server2:/data/brick1 server3:/data/brick1 server4:/data/brick1 will replicate between server1 and server2 and replicate between server3 and server4.

Re: [Gluster-users] Gfapi memleaks, all versions

Apologies for delay in response, it took me a while to switch here. As someone pointed rightly in the discussion above. The start and stop of a VM via libvirt (virsh) will at least call 2 glfs_new/glfs_init/glfs_fini calls. In fact there are 3 calls involved 2 (mostly for stat, read headers and

Re: [Gluster-users] Automation of single server addition to replica

Il 09 nov 2016 1:23 AM, "Joe Julian" ha scritto: > > Replicas are defined in the order bricks are listed in the volume create command. So gluster volume create myvol replica 2 server1:/data/brick1 server2:/data/brick1 server3:/data/brick1 server4:/data/brick1 will replicate

Re: [Gluster-users] Looking for use cases / opinions

Hi Thomas, thats a huge storage. What I can say from my usecase - dont use Gluster directly if the files are small. I dont know, if the file count matters, but if the files are small (few KiB), Gluster takes ages to remove for example. Doing the same in a VM with e.g. ext4 disk on the very same

Re: [Gluster-users] [Gluster-devel] posix_acl_access [Invalid argument] will cause any issue due to timeout

You should be able to get the fix in 3.7.18. Rajesh has posted a fix http://review.gluster.org/#/c/15798/ in release-3.7 branch. On Tue, Nov 8, 2016 at 7:30 PM, ABHISHEK PALIWAL wrote: > Hi, > > I am getting the below message in file is flooded with these logs > > >

[Gluster-users] REMINDER: Gluster Community Bug Triage meeting (Today)

Hi, This meeting is scheduled for anyone, who is interested in learning more about, or assisting with the Bug Triage. Meeting details: - location: #gluster-meeting on Freenode IRC (https://webchat.freenode.net/?channels=gluster-meeting ) - date: every Tuesday - time: 12:00 UTC (in

[Gluster-users] Minutes: Gluster Community Bug Triage meeting (8th November 2016)

Hi all, The minutes of today's meeting: Meeting summary agenda: https://public.pad.fsfe.org/p/gluster-bug-triage (Saravanakmr, 12:01:19) Roll call (Saravanakmr, 12:01:28) Next week’s meeting host (Saravanakmr, 12:05:25) ACTION: skoduri will host bug triage meeting on

Re: [Gluster-users] Looking for use cases / opinions

On 8/11/2016 9:58 PM, Thomas Wakefield wrote: Still looking for use cases and opinions for Gluster in an education / HPC environment. Thanks. Sorry, whats a HPC environment? -- Lindsay Mathieson ___ Gluster-users mailing list

Re: [Gluster-users] Looking for use cases / opinions

On 8/11/2016 11:38 PM, Thomas Wakefield wrote: High Performance Computing, we have a small cluster on campus of about 50 linux compute servers. D'oh! I should have thought of that. Are you looking at replication (2 or 3)/disperse or pure disperse? -- Lindsay Mathieson

Re: [Gluster-users] Looking for use cases / opinions

On 8/11/2016 11:43 PM, Lindsay Mathieson wrote: Are you looking at replication (2 or 3)/disperse or pure disperse? I need to go to bed ... I meant Distributed/Replicated :) or Distributed/Disperse -- Lindsay Mathieson ___ Gluster-users mailing

[Gluster-users] posix_acl_access [Invalid argument] will cause any issue due to timeout

Hi, I am getting the below message in file is flooded with these logs [2016-09-22 20:25:33.102737] I [dict.c:473:dict_get] (-->/usr/lib64/glusterfs/3.7.9/xlator/debug/io-stats.so(io_stats_lookup_cbk+0x166) [0x2ace40d9c816]

Re: [Gluster-users] Looking for use cases / opinions

Still looking for use cases and opinions for Gluster in an education / HPC environment. Thanks. > On Nov 4, 2016, at 2:05 PM, Thomas Wakefield wrote: > > Everyone, thanks in advance. > > We are looking to add a large filesystem to our compute facility at GMU. We > are

Re: [Gluster-users] Looking for use cases / opinions

High Performance Computing, we have a small cluster on campus of about 50 linux compute servers. > On Nov 8, 2016, at 8:37 AM, Lindsay Mathieson > wrote: > > On 8/11/2016 9:58 PM, Thomas Wakefield wrote: >> Still looking for use cases and opinions for Gluster in

Re: [Gluster-users] Looking for use cases / opinions

I think we are leaning towards erasure coding with 3 or 4 copies. But open to suggestions. > On Nov 8, 2016, at 8:43 AM, Lindsay Mathieson > wrote: > > On 8/11/2016 11:38 PM, Thomas Wakefield wrote: >> High Performance Computing, we have a small cluster on