What our customers say

Given the exponential increases in human knowledge across a myriad of scientific disciplines, we found ourselves facing an unprecedented data explosion. Our lab uses a combination of recombinant DNA, DNA sequencing methods, and bioinformatics to analyze the structures and functions of genomes. As knowledge in field of genomics increases, our datasets and analysis result have increased exponentially. We found ourselves at a crossroad in terms of how to mitigate this data challenge. We sent out a request for proposals to many of the top vendors and they returned with some very interesting and cutting edge solutions that would stem the data flood, albeit with a six figures tag. However, I posed one simple question to the vendors, “How will this scale once we pass the inflexion point on our data growth?”. They returned with several upgrade paths that we could transition to over the years which would require us to migrate to newer software versions and hardware architectures. This was a bit of a sticking point for us. Software upgrades? Yes. Entirely new architectures? No.

I had looked at MooseFS several years ago and I liked the replication methods and trash retention system. However, at the time, our existing solution was tied to the hardware manufacture. When I looked at MooseFS this time, their new features such as Atomic Snapshots, Redundancy with Erasure Coding, Fast Disk Recovery, and Fault Tolerance, made me have to get them on the phone! They explained their solutions in detail and let me set up clusters in our own data center to see for ourselves just how powerful their solution could be. They had me sold and we have been using their products ever since. I can add on any hardware that I wish. Data on failed drives is automatically shuttled to other disks so I can hot swap disks from my multiple 90+ disk arrays almost at will. The Redundancy with Erasure Coding allows me to minimize space considerably. No vendor tie in. Use the disks and architectures that you want whether cutting edge and expensive or cheap and after-market.

Our research areas include Statistical Genetics, Genetic Epidemiology, Longevity Genetics, Cardiovascular Disease Genetics and we partner with numerous studies, academics institutions, and medical professionals around the world. During this period of COVID-19 pandemic, we have been tasked to double our research efforts. Our storage requirements have doubled in the span of a week. The MooseFS team reached out to us and asked if we were involved in COVID-19 research. When I confirmed this, they gave us additional tools and extended our license to enable us to face these data growth challenges, today. That is an experience that I never had with our other vendors.

I highly recommend MooseFS if you are looking for a new, dynamic, and cost-effective storage solution.

A top-10 US medical university runs MooseFS as the storage backbone for genomics research — statistical genetics, genetic epidemiology, longevity genetics and cardiovascular-disease genetics — absorbing exponential data growth without vendor lock-in. Atomic snapshots and erasure coding underpin the lab’s reproducibility and capacity strategy across 90+ disk arrays.

Our company got familiar with MooseFS at the time when company’s infrastructure started to grow in size exponentially. As more and more virtual servers were introduced the more public cloud limitations we faced. One of the most frustrating disadvantages was SAN storage failures and worse than expected I/O performance. We made a decision that we would better off by using Infrastructure as a Service solution where we would have self-support and decision-making possibilities. Our choice was a Hyperconvergent server solution combining computation, network and storage into a defined hardware units — something like a big-scale hyper modules. This enabled infrastructure to become hot-swappable set of elements with minimal downtime and highest fault tolerance and also greatly simplified scalability of the whole system.

In order to implement such vision, we had to choose a proper storage software which played a major role in this scenario, however most of the current modern solutions have one or more critical disadvantages in elements we took into consideration — they either lack in area of performance, high-availability, scalability or the cost. As an IT engineer I was really surprised that MooseFS was the best choice in the market after trying out and comparing multiple well-known enterprise-level solutions as it was certainly the easiest to implement, most flexible (especially for having ability to have different type of drives on each hardware unit), most tolerant to faults (f.e. unexpected power-offs), and self-recovering meaning that maintenance was a trouble-free process. I am also pleased that each new hardware unit brought into infrastructure increases the overall performance this way showing a great potential in scalability. Last but not least, I really enjoyed having great support on MooseFS and having every one of my question answered in a swift and detailed manner even before buying the actual product — a thing I never expected to find after many frustrating years dealing with corporate “premium” support lines.

So far, our choice for MooseFS seems a right decision as we have achieved the goal we desired — to have an infrastructure of high performance, redundancy and easy maintenance while keeping cost-efficiency in mind. I can honestly recommend MooseFS, especially from the perspective of IT engineer as it over-delivered my expectations and is an example of software done right.

Hotelston built their hyper-converged infrastructure around MooseFS after running into SAN failures and unpredictable I/O on public cloud. The key wins were easy implementation, mixed-drive flexibility per node, fault tolerance through unexpected power-offs, and a support experience that didn’t look like a “premium” support line.

Ipla is the Internet TV broadcaster streams on-demand content 24/7. It’s possible with the underlying MooseFS storage build with commodity hardware. We appreciated that the system is ready for unexpected peaks with its parallel, distributed design. The show must go on!

Ipla has streamed on-demand internet TV 24/7 on MooseFS since 2008. The parallel, distributed design absorbs unexpected traffic peaks without bottlenecking on any single node.

For data storage, Dedikam uses MooseFS, a robust, stable, redundant and high-performance file system. MooseFS is distributed under two types of license, open source GPL and a PRO version. Dedikam uses the Pro version, which makes it possible to have a system in high availability.

MooseFS checks the integrity of the files by a hashing algorithm and constantly checks the different nodes of the cluster to correct any type of anomalies. All Dedikam data is at least double replicated. If a hard disk or server fails, the data is automatically replicated to other servers and hard disks. Thus, user data is always available even in case of hardware failure. MooseFS makes it easy to add additional disk space (adding a server or hard drive) without any downtime.

The MooseFS team is very professional and responsive. In case of a technical problem, there is always a competent person to assist us or help us to find a solution quickly. We have been using this solution for 10 years so we can say that the system is reliable, robust and secure.

Integrity and security of data is fully assured with the MooseFS file system. We are very satisfied.

Dedikam has been on MooseFS Pro since 2008 for high-availability data storage. Built-in hashing keeps integrity verified across years of operation; failed disks and servers are repaired automatically without downtime.

As a researcher I need to deal with large sets of 3D points clouds. Hell of data. MooseFS helps me handle them, I can verify my ideas and algorithms efficiently. Atomic snapshots rocks! In addition I’m sure my work results are safe.

Mandala Robotics works with large 3D point-cloud datasets — the kind of data that grows quickly and is expensive to lose. Atomic snapshots make algorithm iteration cheap and reproducible.