<html><head><meta http-equiv="Content-Type" content="text/html charset=windows-1252"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div><div>In addition I like to point out that:</div><div><br></div><div>- Glusterfs can leave your files in a whole piece. Call me old fashion, but for "normal" workload I like that</div><div>- ceph also needs an underlying filesystem too, so you will be left with fsck questions etc. too</div><div>- cephfs is, as of now, still not production ready and following the news this isn't the main focus right now.</div><div>So you either have to use rbd's (and what filesystem inside?) or you make you applications using RADOSGW.</div><div>So for my actual scenario (small amount of server, n sided replication as VM-image storage backend) </div><div>glusterfs seems the better approach to me (less administration effort, keep my files in one piece)</div><div>hth</div><div><br></div><div>Bernhard</div><div></div><div><br></div><div>On Dec 29, 2013, at 1:50 AM, Peter B. <<a href="mailto:pb@das-werkstatt.com">pb@das-werkstatt.com</a>> wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite">On 12/28/2013 08:06 PM, Knut Moe wrote:<br><blockquote type="cite">Are there benefits in configuration, scaling, management etc?<br></blockquote><br>Hi,<br>One year ago I was also in the situation where I had to compare these 3 cluster <br>file systems. I'm not the greatest expert on this topic, but here's a rough summary of what I know and why we chose GlusterFS over Hadoop or Ceph.<br><br>There are great differences between Hadoop/Ceph and GlusterFS.<br>First of all being that GlusterFS distributes files and works on top of<br>existing filesystems. It is completely transparent to the system and<br>applications.<br>This adds overhead (at costs of speed), but increases your options in<br>case of errors and long-term preservation.<br><br>Most other storage cluster systems on the other hand, split each file<br>into a certain number of blocks and distribute those.<br><br>Hadoop is not just some filesystem you can mount (as I understood from<br>reading Apache's docs): You have to talk to it using the Hadoop API. As<br>I understood it, you'd have to write your applications to use Hadoop,<br>instead of just having it as transparent filesystem beneath. Please<br>correct me if I'm wrong.<br><br>This makes a great difference regarding effort and use-cases.<br><br><br>What's also special about GlusterFS is that it's really (really) easy<br>and quick to set up a basic constellation, and it ships out-of-the-box<br>with most distro repositories. There are things you can tweak, but you<br>don't have to. It's understandable very quickly by any regular Linux admin.<br>Just yesterday, I've setup gluster on my raspberry pi home fileserver :)<br><br>There are many many more details about how Hadoop and Ceph "tick",<br>compared to GlusterFS (e.g. "NameNode"), but I think there are others<br>here who can explain that way better than me.<br><br><br><blockquote type="cite">I know Hadoop is used by the likes of Yahoo and Facebook. I would be<br>interested in information on any large (known) users of GlusterFS.<br></blockquote><br>When I was looking for systems for large storage clusters for long-term media <br>archiving, I initially thought I'd go for Hadoop, because "the big ones are <br>using it". I also listened to a presentation about Ceph, so I could compare them.<br><br>In the end, we chose GlusterFS, because for digital archiving, we needed a scalable storage cluster with the highest chance of maintaining it over the years, rather than minimizing our downtime to seconds. We are currently building up a storage for the national A/V archive with 2x >300 TiB.<br><br>I've already done initial tests with GlusterFS on one node, but it's too soon to really speak of "experience" on our side.<br>We've also only used gluster in "distribute" mode, so I have no experience with gluster-replication at all.<br><br><br>Regards,<br>Peter B.<br><br>_______________________________________________<br>Gluster-users mailing list<br><a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>http://supercolony.gluster.org/mailman/listinfo/gluster-users<br></blockquote><br></div><div><br></div><div><div><div style="background-color: rgb(255, 255, 255); "><table border="0" cellpadding="0" cellspacing="5"><tbody><tr><td colspan="2" valign="center" align="center" style="vertical-align: middle; text-align: center; color: rgb(255, 255, 255); "><hr style="height: 2px; background-color: rgb(111, 112, 114); color: rgb(111, 112, 114); border-width: 0px; "></td></tr><tr><td align="center" style="text-align: center; color: rgb(24, 41, 131); "><img alt="*Ecologic Institute*" height="120" width="129" id="43f18b92-f7f7-4b7d-a585-77f572ebf958" apple-width="yes" apple-height="yes" src="cid:2112670B-2A78-40B7-9211-559A695F9B4D"></td><td align="left" style="text-align: left; padding-right: 10px; white-space: nowrap; "><font face="sans-serif" color="black"><small><b>Bernhard Glomm</b><br>IT Administration<br><br></small><small><small><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td style="white-space: nowrap; "><small><small>Phone:</small></small></td><td style="padding-left: 5px; white-space: nowrap; "><small><small>+49 (30) 86880 134</small></small></td></tr><tr><td style="white-space: nowrap; "><small><small>Fax:</small></small></td><td style="padding-left: 5px; white-space: nowrap; "><small><small>+49 (30) 86880 100</small></small></td></tr><tr><td style="white-space: nowrap; "><small><small>Skype:</small></small></td><td style="padding-left: 5px; white-space: nowrap; "><small><small>bernhard.glomm.ecologic</small></small></td></tr></tbody></table></small></small></font></td></tr><tr><td colspan="2" valign="center" align="center" style="vertical-align: middle; text-align: center; background-color: rgb(111, 112, 114); color: rgb(255, 255, 255); white-space: nowrap; "><a href="http://ecologic.eu"><img title="Visit our website" alt="Website:" height="36" width="36" id="423b40a0-7480-4751-bf49-e821acf99263" apple-width="yes" apple-height="yes" src="cid:568BC185-D81B-4061-8D84-8A3538311CE8"></a> <a href="http://www.youtube.com/v/hZtiK04A9Yo"><img title="Watch our video" alt="| Video:" height="36" width="36" id="a008d4da-da3f-421c-aeb3-d48d3c41a0c0" apple-width="yes" apple-height="yes" src="cid:54CE698C-9A22-41E3-892D-F169CAC5D5F3"></a> <a href="http://ecologic.eu/newsletter/subscribe"><img title="Subscribe to our newsletter" alt="| Newsletter:" height="36" width="36" id="5c5e1c00-356e-4a71-91f4-0374543543a0" apple-width="yes" apple-height="yes" src="cid:F14F2E42-EB92-46BC-817D-A8341AA7F6E2"></a> <a href="http://www.facebook.com/Ecologic.Institute"><img title="Visit us on Facebook" alt="| Facebook:" height="36" width="36" id="1f3cc323-3ebc-4299-9ef2-d4e05b796a50" apple-width="yes" apple-height="yes" src="cid:4657EB15-BE30-44E1-A2C1-853B0AD40091"></a> <a href="http://www.linkedin.com/company/ecologic-institute-berlin-germany"><img title="Visit us on Linkedin" alt="| Linkedin:" height="36" width="36" id="3faa2eaf-de39-43fd-8dff-85c7ff45406c" apple-width="yes" apple-height="yes" src="cid:968B24BD-87D8-4FE5-AC20-C0BF7EA70E00"></a> <a href="http://twitter.com/EcologicBerlin"><img title="Visit us on Twitter" alt="| Twitter:" height="36" width="36" id="c3750de9-4afc-46a3-9c5a-1a03f61ab3be" apple-width="yes" apple-height="yes" src="cid:88DB4548-EF3C-49BB-8D87-C3EF48BF0194"></a> <a href="http://www.youtube.com/user/EcologicInstitute"><img title="Visit us on YouTube" alt="| YouTube:" height="36" width="36" id="aadd5ce9-5f59-4e89-8721-f869a0254ce5" apple-width="yes" apple-height="yes" src="cid:5F78BC3D-BEBC-4EE3-A8FC-3D31F52D525C"></a> <a href="http://plus.google.com/113756356645020994482"><img title="Visit us on Google+" alt="| Google+:" height="36" width="36" id="89189781-3982-4c5f-8262-fa67e5424432" apple-width="yes" apple-height="yes" src="cid:84394AB1-8072-4ACB-A6DF-9391AD159B1B"></a></td></tr><tr><td colspan="2" valign="center" align="left" style="vertical-align: middle; text-align: left; padding-left: 5px; padding-right: 5px; white-space: nowrap; "><small><small>Ecologic Institut gemeinnützige GmbH | Pfalzburger Str. 43/44 | 10717 Berlin | Germany<br>GF: R. Andreas Kraemer | AG: Charlottenburg HRB 57947 | USt/VAT-IdNr.: DE811963464<br>Ecologic™ is a Trade Mark (TM) of Ecologic Institut gemeinnützige GmbH</small></small></td></tr><tr><td colspan="2" valign="center" align="center" style="vertical-align: middle; text-align: center; color: rgb(255, 255, 255); "><hr style="height: 2px; background-color: rgb(111, 112, 114); color: rgb(111, 112, 114); border-width: 0px; "></td></tr></tbody></table></div></div><br><div></div></div><br></body></html>