Gluster Blog

By GFS do you mean GlusterFS[0]? I never ended up using it because it was seemingly bad for databases -- it is probably nuseful but in comparison it wasn't that great. [0]: https://www.gluster.org/

What filesystem did you end up using? Ever looked at GlusterFS (http://www.gluster.org/)? From an (admittedly unscientific) comparison of the various free/open-source distributed filesystems, it seems the best to me. Ceph is still in beta, and the fact that Lustre only supports a single Metadata Server is really scary to me.

Doing some light googling aside from Ceph being listed, there's one called Gluster as well. Hypes itself as "using common off-the-shelf hardware you can create large, distributed storage solutions for media streaming, data analysis, and other data- and bandwidth-intensive tasks." It's open source / free to boot. I have no direct experience with it myself however. https://www.gluster.org/

Heyas, Ex-GlusterFS person here (used to work at Red Hat on the project side, leaving mid last year). "Small file access", and "lots of files in a directory" have been a pain point with GlusterFS for ages. The 3.7.0 release had some important improvements in it, specificially designed to help fix that: https://www.gluster.org/community/documentation/index.php/Features/Fea… The latest Gluster release is 3.7.8 (the same series as 3.7.0), and is worth looking at if you're needing a good distributed file system. If you have something like 1Mill files in a single directory though... hrmmm... NFS or other technologies might still be a better idea. ;)

Persistence for AWS can be relatively simple if you use a distributed filesystem, such as GlusterFS (http://gluster.org) or our ObjectiveFS (https://objectivefs.com). You get a shared namespace for all your instances and persisting your data becomes as simple as writing files.

How is this better than Gluster[1] or MogileFS[2]? Haystack is pretty neat but it seems like it loses quite a bit when simplified. [1]: http://www.gluster.org/ [2]: http://danga.com/mogilefs/

The book mentions a number of distributed file systems but omits one that I think deserves mention: http://www.gluster.org/ Glusterfs is an interesting take on the DFS concept and it is open source.

GlusterFS is a FUSE based distributed filesystem. You can mirror the files on as many servers as you like, aggregate storage from different servers. It has no central metadata server either. It doesn't serve via HTTP directly, but it's easy to point a web server at the filesystem (it has an Apache module to provide direct access without going through FUSE if you want higher performance). http://www.gluster.org

I recommend to look at GlusterFS. It fast, modularized, layered clustering file system. It is not tied to Linux kernel because it built for (patched) Fuse. With Infiniband hardware, it is fastest clustered system available for free. See http://www.gluster.org/docs/index.php/GlusterFS_1.3.pre2-VERGACION_vs_… for example.

Do people perceive this to be more cost effective than backing up data? What is the total cost in terms of down-time, failing audits, disclosing to customers and employees that control of their data has been lost? Would that loss be greater than a backup solution? Has it become taboo in 2020 to do backups that can't be tainted by attackers or dodgy automation? It was not a problem 20 years ago. What changed? If it's cost, even a low end gluster cluster [0] or Ceph with an archive read-only share that has rsnapshot [1] diffs for 5 days would mitigate this, assuming you know within 2 or 3 days to sound the alarm. Rsnapshot would run on the server. People would just see multiple folders with the last 5 days of changes. The snapshots would not be writable by employees or malware. To further reduce cost, perhaps de-duplicate data with ZFS or VDO [2]. Everything mentioned here is open source and has multiple enterprise supported options that your engineering and IT staff are likely already aware of. If not, there are plenty of documents on integrating gluster into active directory. [0] - https://www.gluster.org/community/ [1] - https://github.com/rsnapshot/rsnapshot [2] - https://blog.delouw.ch/2018/12/17/using-data-deduplication-and-compres…

I was going to agree but decided to load up web site to be sure: https://www.gluster.org/ I don't see a list of features at all here or an obvious link to them. Most sites have something like this (see "Why Sector/Sphere?"): http://sector.sourceforge.net/ Or this: http://lustre.org/about/ Wait, that one almost sucks as much as GlusterFS site. It could also use a page detailing exactly what it can and can't do with obvious link on front-page. At least it had obvious link and basic description, though. So, hard to judge writer of recent post on what features were in GlusterFS, etc if their page doesn't go through the trouble to list them without us having to dig. I'd have to point two fingers. Fortunately, Wikipedia to rescue doing what site didn't do: https://en.wikipedia.org/wiki/GlusterFS Note: Oh shit, it still doesn't mention encryption. Not in the comparison or list of distributed filesystems either. Still undocumented for casual researcher.

I have used AWS on 2 projects now. On the first project, we used 2 small instances as web servers, 1 small instance as a database master, and another as a slave. The slave machine handled backup of db and uploaded files by zipping everything up and throwing it onto s3. There was no EBS or RDS at this time. The main problem we had was sharing user uploaded files between instances. We used Gluster (http://www.gluster.org/) for this, but it was complicated and gave us problems. In general this setup worked fine and we could add webserver instances to handle traffic spikes. Even this limited setup took a bit of effort to maintain and I often wondered if we could have just handled the whole thing with one large or extra large instance. Does anyone know if there is some bottleneck that comes from vertically scaling like this? Sadly, on the second project we haven't really needed to scale at all, so we just use one small instance for everything and have our mysql files and user uploaded files in an EBS volume. I haven't really figured out backup and restore from snapshots yet, so I just zip up the contents of the EBS and transfer it to S3. We are using cloudfront to serve static files and it seems to work fine.

Check out GlusterFS: http://www.gluster.org/

Does Dar offer variable-block chunking file deduplication like Kopia and Duplicacy? https://www.gluster.org/deduplication-part-1-rabin-karp-for-variable-c…

If you are really good at Samba, join their commercial support providers list. Lots of big projects have similar things. https://www.samba.org/samba/support/ Edit: GlusterFS has one too: https://www.gluster.org/community/consultants/ Edit: unfortunately iFAX doesn't list other companies on the HylaFAX support page, but probably being active on their community support could get customers. https://www.hylafax.org/support/

Let me Google "GlusterFS encryption" for you. http://www.gluster.org/community/documentation/index.php/Features/disk… https://www.gluster.org/community/documentation/images/e/e2/GlusterFS_… ...and more. I think that still falls under "casual research" ... besides which, implementers and promoters should be doing more than casual research anyway. The fact that the Gluster documentation sucks doesn't change that. Plenty of others have implemented such end-to-end encryption as well, and the trend is already increasing. (I find that quite gratifying BTW since I felt like a lone voice in the wilderness when I was writing about the importance of keeping keys on the clients five-plus years ago.) What they present as a differentiator is very much a me-too nowadays so, again, it calls their other claims of originality or uniqueness into question.

> "Glfs has a severe problem with small writes, both with writing small files and small writes into large files. FhGFS does not have this bottleneck." GlusterFS has implemented many smallfile performance enhancements and with the latest release I am seeing a 20-50% improvement on smallfile performance. There are more improvements in the pipeline: http://www.gluster.org/community/documentation/index.php/Features/Feat… I would be curious to see these tests run on a properly tuned(readahead on bricks is important for spinning disks and read workloads, I didn't see any mention of brick tuning in the article) and on the latest version of glusterfs with the smallfile performance enhancements.

GIMP no longer distributes binaries on sourceforge because sourceforge's installer "bundles third-party offers with Free Software packages. We do not want to support this kind of behavior, and have thus decided to abandon SourceForge." http://www.gimp.org/ http://www.gluster.org/2013/08/how-far-the-once-mighty-sourceforge-has…

The link in the article sums up the "what happened to Sourceforge" pretty well: http://www.gluster.org/2013/08/how-far-the-once-mighty-sourceforge-has… The OSS project I maintained for several years was always in the top 10 downloaded lists on Sourceforge, but I got frustrated with how things were going and eventually moved the code to Github and hosted a simple website on my own. Honestly, I can't think of a reason why an OSS project would choose Sourceforge in this day and age.

There's a connector between Hadoop and the Gluster network file systems [1], giving a unified view of a large, distributed, POSIX compatible filesystem, which can be served up through Samba. We vastly prefer it to NFS, which we find to be far more flaky, slower, and when NFS fails it fails in really really painful ways. (Though looking again, I'm not sure if you meant NFS or NAS...) [1] http://gluster.org/community/documentation/index.php/Hadoop

Are the GlusterFS people mistaken? http://gluster.org/community/documentation/index.php/GlusterFS_General… "GlusterFS is fully POSIX compliant."