Re: [Gluster-users] cannot create a new volume with a brick that used to be part of a deleted volume?
Hello, what I regularly do: 1) Create a snapshot (btrfs) of Brick 2) reassemble the snapshots into an new (Snapshot-) Gluster-Volume When Reassembling the snapshots I have to remove all xattr's and .gluster-Directory. Since btrfs is painfully slow in deleting, I would prefer an option to reuse the Content, wich should be valid for the new (Snapshot-) Gluster-Volume... Greetings, Jörg Am 20.09.2012 20:56, schrieb Doug Hunley: On Thu, Sep 20, 2012 at 2:47 PM, Joe Julian j...@julianfamily.org wrote: Because it's a vastly higher priority to preserve data. Just because I delete a volume doesn't mean I want the data deleted. In fact, more often than not, it's quite the opposite. The barrier to data loss is high, and it should remain high. OK, again I'll ask: what is a typical scenario for me as a gluster admin to delete a volume and want to add one (or more) of its former bricks to another volume and keep that data in tact? I can't think of a real world example. But I assume they exist as this is the model taken by gluster.. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Gluster's read performance
Small files is sort of a misconception. Initial file ops include a small amount of overhead, with a lookup, the filename is hashed, the dht subvolume is selected and the request is sent to that subvolume. If it's a replica, the request is sent to each replica in that subvolume set (usually 2). If it is a replica, all the replicas have to respond. If one or more have pending flags or there's an attribute mismatch, either some self heal action has to take place, or a split-brain is determined. If the file doesn't exist on that subvolume, the same must be done to all the subvolumes. If the file is found, a link file is made on the expected dht subvolume pointing to the place we found the file. This will make finding it faster the next time. Once the file is found and is determined to be clean, the file system can move on to the next file operation. PHP applications, specifically, normally have a lot of small files that are opened for every page query so per-page, that overhead adds up. PHP also queries a lot of files that just don't exist. Your single page might query 200 files that just aren't there. They're in a different portion of the search path, or they're a plugin that's not used, etc. NFS mitigates that affect by using FScache in the kernel. It stores directories and stats, preventing the call to the actual filesystem. This also means, of course, that the image that was just uploaded through a different server isn't going to exist on this one until the cache times out. Stale data in a multi-client system is going to have to be expected in a cached client. Jeff Darcy created a test translator that caches negative lookups which he said also mitigated the PHP problem pretty nicely. If you have control over your app, things like absolute pathing for PHP or leaving file descriptors open can also avoid overhead. Also, optimizing the number of times you open a file or the number of files to open can help. So small files refers to the percent of total file op time that's spent on overhead vs actual data retrieval. Chandan Kumar chandank.ku...@gmail.com wrote: Hello All, I am new to gluster and evaluating it for my production environment. After reading some blogs and googling I learned that NFS mount at clients give better read performance for small files and the glusterfs/FUSE mount gives better for large write operations. Now my questions are 1) What do we mean by small files? 1KB/1MB/1GB? 2) If I am using NFS mount at the client I am most likely loosing the high availability feature of gluster. unlike fuse mount where if primary goes down I don't need to worry about availability. Basically my production environment will mostly have read operations of files ranging from 400KB to 5MB and they will be concurrently read by different threads. Thanks, Chandan ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] infiniband bonding
Hi folks, Reading this post: http://community.gluster.org/q/port-bonding-link-aggregation-transport-rdma-ib-verbs/ It says that gluster 3.2 does not support bonding of infiniband ports. Does anyone knows whether 3.3 has changed this limitation? Is there any other place where to find information about this subject? Thanks in advance! Samuel. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] infiniband bonding
Well, it actually says it is a limitation of the Infiniband driver so nothing with Gluster I guess. If the driver allow then in theory should not be a problem for Gluster. Fernando From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of samuel Sent: 21 September 2012 10:56 To: gluster-users@gluster.org Subject: [Gluster-users] infiniband bonding Hi folks, Reading this post: http://community.gluster.org/q/port-bonding-link-aggregation-transport-rdma-ib-verbs/ It says that gluster 3.2 does not support bonding of infiniband ports. Does anyone knows whether 3.3 has changed this limitation? Is there any other place where to find information about this subject? Thanks in advance! Samuel. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] gluster 3.2x and 3.3 compatible?
Hi, I test gluster on two debian (3.2.7) and one ubuntu machine (3.2.5). So long it work. Then I try to upgrade on the debian machines to 3.3.0 from experimental. With this, I can't use the ubuntu one as peer. Isn't that compatible? Bye Gregor -- ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] gluster 3.2x and 3.3 compatible?
Sorry, no. That was a design goal, but it wasn't possible. On 09/21/2012 03:44 AM, Gregor Burck wrote: Hi, I test gluster on two debian (3.2.7) and one ubuntu machine (3.2.5). So long it work. Then I try to upgrade on the debian machines to 3.3.0 from experimental. With this, I can't use the ubuntu one as peer. Isn't that compatible? Bye Gregor ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] cannot create a new volume with a brick that used to be part of a deleted volume?
Yes, I think an option (--force maybe) that says I know I'm about to lose data, that's what I want sounds like a reasonable compromise. And the given examples have clarified the current behavior in my mind. Thank you for the replies everyone. I'm better informed now. Sent from my Google Nexus 7 On Sep 21, 2012 2:11 AM, Joe Julian j...@julianfamily.org wrote: Adding a --yes-i-know-what-im-doing type option is something I would get behind (and have suggested, myself). File a bug report as an enhancement request. Dr. Jörg Petersen joerg.h.peter...@googlemail.com wrote: Hello, what I regularly do: 1) Create a snapshot (btrfs) of Brick 2) reassemble the snapshots into an new (Snapshot-) Gluster-Volume When Reassembling the snapshots I have to remove all xattr's and .gluster-Directory. Since btrfs is painfully slow in deleting, I would prefer an option to reuse the Content, wich should be valid for the new (Snapshot-) Gluster-Volume... Greetings, Jörg Am 20.09.2012 20:56, schrieb Doug Hunley: On Thu, Sep 20, 2012 at 2:47 PM, Joe Julian j...@julianfamily.org wrote: Because it's a vastly higher priority to preserve data. Just because I delete a volume doesn't mean I want the data deleted. In fact, more often than not, it's quite the opposite. The barrier to data loss is high, and it should remain high. OK, again I'll ask: what is a typical scenario for me as a gluster admin to delete a volume and want to add one (or more) of its former bricks to another volume and keep that data in tact? I can't think of a real world example. But I assume they exist as this is the model taken by gluster.. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Performance optimization tips Gluster 3.3? (small files / directory listings)
Hi Brian, I'm just wondering if you had any luck with figuring out performance limitations of your setup. I'm testing a similar configuration, so any tips or recommendations would be much appreciated. Thanks, --Alex ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users