A few weeks ago, we received a call familiar to many cloud architects—a customer with a massive GlusterFS deployment impacted by Red Hat’s end-of-support deadline (December 2024) wondering: “What now?”. With hundreds of terabytes across their infrastructure serving both internal teams and external customers, moving away from GlusterFS became a business continuity imperative.  

Having worked with numerous storage migrations over the years, I could already see the late nights ahead for their team if they simply tried to recreate their existing architecture in the cloud. So, we rolled up our sleeves and dug into their environment to find a better way forward.

The GlusterFS challenge  

GlusterFS emerged in 2005 as a groundbreaking open-source distributed file system that solved horizontal scaling problems when enterprise storage had to work around mechanical device limitations. Storage administrators traditionally created pools of drives limited to single systems and difficult to expand without major downtime. GlusterFS addressed this by allowing distributed storage across physical servers, each maintaining its own redundant storage.  

Red Hat’s acquisition of GlusterFS (Red Hat to Acquire Gluster) in 2011 brought enterprise legitimacy, but its architecture reflected a pre-cloud world with significant limitations:  

• Costly local/geo replication due to limited site/WAN bandwidth  

• Upgrades requiring outages and extensive planning  

• Overhead from OS patching and maintaining compliance standards  

• Constant “backup babysitting” for offsite tape rotation  

• 24/7 on-call staffing for potential “brick” failures  

Indeed, during our initial discussions, customer’s storage team lead half-jokingly mentioned having a special ringtone for middle-of-the-night “brick” failure alerts. We also noticed that they were running the share exports on SMB 3.0 and NFS 3.0, something which is considered “slightly” deprecated today. 

Note: In GlusterFS, a “brick” is the basic storage unit—a directory on a disk contributing to the overall volume that enables scalable, distributed storage.

Why Azure Files made perfect sense 

With the challenges our customer faced with maintaining redundancies & administration efforts, they required a turnkey solution to manage their data. Azure Files provided them a fully managed file share service in the Cloud, offering SMB, NFS, and REST-based shares, with on-demand scaling, integrated backups & automated failover. 

GlusterFS was designed for large scale distributed storage systems. With Azure Files, GlusterFS customers can take advantage of up to 100TiB of Premium file or 256TiB of Provisioned V2 HDD, 10 GBPs of throughput and up to 10K IOPS for demanding workloads. 

The advantages of Azure Files don’t just end at performance.  As customers migrate from GlusterFS to Azure files, these are the additional benefits out of the box: 

• Azure Backup integration  

• One-click redundancy configuration upgrades  

• Built-in monitoring via Azure Monitor  

• HIPAA, PCI DSS, and GDPR compliance  

• Enterprise security through granular access control and encryption (in transit and at Rest)

The financial reality  

At a high level, we found that migrating to Azure files was 3X cheaper than migrating to an equivalent VM based setup running GlusterFS.   

We compared a self-managed 3-node GlusterFS cluster (running SMB 3.0) on Azure VMs via Provisioned v2 disks with Azure Files – Premium tier (SMB 3.11).  

Note: All disks on VM are using Provisioned V2 for best cost saving. Region – East US2. 

 
As the table illustrates, even before we factor in the administration cost, Azure Files already has a compelling financial advantage. We also recently released “Provisioned v2” billing model for Azure files – HDD tier which provides fine grained cost management and can scale up to 256TiB!!   
 
With GlusterFS running on-premises, customers must take in account the various administrative overheads, which will be taken away with Azure Files.  

The migration journey

We developed a phased approach tailored to the customer’s risk tolerance, starting with lower-priority workloads as a pilot:  

Phase 1: Assessment (2-3 weeks) 

• Inventory GlusterFS environments and analyse workloads 

• Define requirements and select appropriate Azure Files tier 

• Develop migration strategy 

Phase 2: Pilot Migration (1-2 weeks) 

• Set up Azure Files and test connectivity 

• Migrate test workloads and refine process 

Phase 3: Production Migration (variable) 

• Execute transfers using appropriate tools (AzCopy, Robocopy, rsync // fpsync) 

• Implement incremental sync and validate data integrity 

Phase 4: Optimization (1-2 weeks) 

• Fine-tune performance and implement monitoring 

• Decommission legacy infrastructure

Results that matter 

Working with Tata Consultancy Services (TCS) as our migration partner, the customer did a POC migrating from a three-node RHEL 8 environment with a 1TB SMB (GlusterFS) share, to Azure Storage Account- Premium files.  The source share was limited to ~1500 IOPS, and had 20+ subfolders, each being reserved for application access which made administrative tasks challenging. The application sub-folder structure was modified to individual Azure Files shares as part of the migration planning process. In addition, each share was secured using on-premises Active directory – Domain controller-based share authentication. Migration was done using Robocopy with SMB shares mounted on Windows clients and data copy being done in a mirror mode. 

The migration delivered significant benefits:  

• Dramatically improved general-purpose performance due to migration of HDD based shares to SSD (1500 IOPS shared at source vs 3000 IOPS // 200MBPS base performance per share) 

• Meeting and exceeding current RTO and RPO requirements (15 min) set by customer 

• Customer mentioned noticeable performance gains for SQL Server workloads 

• Flexibility to resize each share to Azure files maximum limit, independent of noise neighbours as previously configured 

• Significant reduced TCO (at 33% of cost compared to equivalent VM based deployment) with higher base performance 

What this means for your GlusterFS environment 

If you’re facing the GlusterFS support deadline, this is an opportunity to modernize your file storage approach. Azure Files offers a chance to eliminate infrastructure headaches through simplified management, robust security, seamless scalability, and compelling economics.  

Looking to begin your own migration? Reach out to us at azurefiles@microsoft.com, contact your Microsoft representatives, or explore our Azure Files documentation  to learn more about capabilities and migration paths.