Coder Legion - Recent posts tagged filesystem

AuriStor rebuilt the Andrew File System to fix decades of technical debt and performance issues.

Thu, 09 Oct 2025 23:57:38 +0000

AuriStor Tackles Distributed File System Performance With Protocol-Level Improvements

Most developers don't think much about distributed file systems until they hit a wall. You're moving files across continents, dealing with spotty connections, or trying to sync data for thousands of compute nodes. That's when you realize the infrastructure matters.

AuriStor spent the past decade rebuilding the Andrew File System. They forked from OpenAFS in 2012 and focused on what they call "paying off technical debt." The result is AuriStorFS, a commercial product that prioritizes performance and security over backward compatibility.

The company's approach is technical, not trendy. They identified bottlenecks in the RX remote procedure call protocol and systematically addressed them. Senior engineer Simon Wilkinson presented results showing a 10x performance improvement—the time to transfer 10GB of data dropped from 437,500 milliseconds to under 50,000 milliseconds using multiple threads.

Protocol improvements that matter

RX is a UDP-based RPC protocol. It's not new or exciting, but it works. AuriStor's team analyzed every aspect of how packets move through the system and found ways to optimize.

They increased the default window size from 32 packets to 8,192 packets. A larger window means more data in flight at once. On a 1ms round-trip link, this bumps theoretical throughput from 362 Mbit/sec to 92 Gbit/sec.

Window size alone doesn't solve everything. The team implemented RFC-compliant congestion control algorithms, including New Reno and SACK-based loss recovery. They added RACK-TLP for better tail loss detection. These aren't radical ideas—they're proven TCP techniques adapted for RX.

Path MTU discovery now works properly. The system starts with a conservative 1,200-byte MTU and probes upward. If your network supports jumbo frames, AuriStor uses them. This cuts packet overhead significantly.

Real-world performance gains

One government research organization moved its AFS deployment to the cloud and measured the results. Copying a 1GB file from local disk to AFS took 3 minutes and 11 seconds with OpenAFS servers. With AuriStor's 2021 release, it dropped to 1 minute. The latest release with path MTU discovery and proportional rate reduction cut it to 30 seconds.

These improvements scale. Production AuriStor file servers handle over 500,000 simultaneous connections from 40,000 cache managers. One deployment manages 1.7 million volumes, with shutdown times reduced from 30 minutes to 4 seconds.

A large financial institution (operating under NDA) runs 80 cells with 300 servers serving 175,000 clients. They deploy software updates continuously—new releases push out every few minutes. The infrastructure handles 1.5 million volumes across 180 to 200 regional cells globally, distributed across multiple cloud providers.

Security without the theater

The security model is straightforward. AuriStorFS uses GSS-API with Kerberos v5 for authentication and AES-256 for encryption. The YFS-RxGK security class supports combined identity authentication—both user and machine identities are verified together.

This matters for organizations that need to control where data gets accessed. You're not just "you"—you're "you on your phone," "you on your company laptop," "you on your personal laptop." You can grant permissions to a user only when they're on a specific machine.

Volume-level security policies let administrators enforce encryption requirements. Volumes can only move to servers with equal or stronger security policies. File servers can require specific authentication levels before serving data. Maximum access control lists prevent users from accidentally exposing data, even if they set overly permissive permissions on individual files.

The perpetual license model

AuriStor's pricing is unusual. Base cost is $21,000 per year per cell, covering up to 4 servers and 1,000 user or machine IDs. Additional servers cost $1,000 to $2,500 each. There's no charge based on storage capacity or data volume. As Jeffrey Altman, Founder and CEO
put it during the presentation to the 64th IT Press Tour, "We give you the first 100 exabytes for free."

The license is perpetual. Stop paying and you keep using the version you licensed. You just don't get updates or support. Security patches continue for at least two years after each release.

For developers working on large-scale deployments, this model is predictable. Your costs don't explode when you add storage.

Container integration happening now

AuriStor built a CSI driver for Kubernetes that works with Red Hat OpenShift. Their large financial customer is using it to transition 180,000 systems to containers without losing the benefits of AFS.

The challenge: container images for machine learning applications start at 40 gigabytes. You don't need all that data to run the application—only a fraction gets executed. Copying 40 gigabytes to expensive compute instances wastes time and money.

AuriStorFS caches only the regions of files that applications actually access. The CSI driver lets containers mount AFS volumes directly. Applications execute binaries from the AFS namespace instead of packaging them into container images.

One customer has software distribution trees that are hundreds of gigabytes. With updates every few minutes, pushing new container images to 50,000 clients is impossible. AuriStorFS replicates only the incremental changes.

The Linux kernel's built-in AFS client (kafs) supports AuriStorFS protocols. It's distributed in Fedora, Ubuntu, Debian, and RHEL 9.2 and later. Last night, the team successfully booted a Linux system from AFS for the first time using mainline kernel tools.

Technical trade-offs

AuriStorFS doesn't support server-side byte range locks yet. This means it's not suitable for databases or virtual machine images. That's on the roadmap but won't arrive before 2026.

The system works best for read-heavy workloads with occasional writes. Think software distribution, research data, and home directories. It handles files up to 16 exabytes, though real-world deployments use files in the 5TB to 50TB range regularly.

Mixed deployments with OpenAFS work but lose some features. You can run both, but you're limited to the lowest common denominator.

Small team, focused mission

AuriStor has a core team of five developers, the same people who worked on OpenAFS before the fork. They're augmented by about five part-time contractors with specialized skills.

The company is sub-$2 million in annual revenue but profitable. Altman didn't take a salary from 2007 to 2016. The company received SBIR grants from the Department of Energy, sponsored by SLAC and Fermilab.

More than 50% of their engineering effort goes into network performance. As Altman said, "If we can't make the network fast, it doesn't matter what anything else does."

Source code is walled

AuriStor keeps source code private. Customers can license access to repositories, test infrastructure, and participate in development. If AuriStor goes out of business, source licensees gain the right to create public forks.

This is a deliberate choice after years of watching OpenAFS struggle with the free rider problem. Organizations would use the software, but not fund development. The trade-off is commercial sustainability versus open collaboration. AuriStor chose sustainability.

For shops considering distributed file systems, AuriStorFS offers measurable improvements over OpenAFS. The question is whether the licensing model and closed source approach fit your organization. If you need global data access with predictable costs and don't want storage-based pricing, it's worth evaluating.

Discover how Panzura's cloud-native file system eliminates collaboration headaches for developers in distributed teams.

Sat, 10 May 2025 23:54:27 +0000

How Panzura Makes Developers' Lives Easier in Multi-Cloud Environments

In today's distributed development world, collaborating on projects across multiple locations can be a nightmare of file conflicts, version control issues, and performance bottlenecks. Panzura, a leader in cloud-native file services, has developed solutions that directly address these pain points for developers, engineers, and architects working in complex multi-cloud environments.

The Developer's File Collaboration Problem

If you've ever worked on a large-scale project with team members spread across different locations, you've likely encountered the "file collaboration problem." Traditional network-attached storage (NAS) systems weren't designed for global teams, and cloud storage often introduces latency, file locking issues, and versioning conflicts that can destroy productivity.

These challenges become even more pronounced when working with large binary files, ML models, or resource-intensive development environments that don't work well with traditional version control systems like Git.

How Panzura Solves Developer Headaches

Panzura's CloudFS platform transforms how distributed development teams work together by solving several critical issues that plague modern software development workflows.

1. Real-Time File Collaboration Without Conflicts

Panzura's most powerful feature for developers is its distributed file locking and byte-range locking capabilities. This enables multiple team members to work on different parts of the same file simultaneously without conflicts.

For example, engineers working on CAD designs, large datasets, or complex simulations can collaborate in real-time without the "last save wins" problem that often results in lost work. The system implements file locking at a granular level, similar to how Google Docs allows multiple editors, but for enterprise file systems and specialized development files.

2. Eliminating the "Pre-Warming Cache" Problem

In traditional distributed systems, teams often must "pre-warm" caches to ensure everyone has access to the files they need. This means administrators must predict which files teams will need and prepare them in advance.

With Panzura's CloudFS 8.5 Adapt's new Regional Store feature, this problem disappears. The platform automatically synchronizes data across cloud regions, ensuring that files are always available with minimal latency, regardless of where team members are located. This is especially valuable for development teams working with large datasets for AI/ML projects or media files, where access speeds directly impact productivity.

3. Immutability and Versioning Built Into the File System

For developers, accidental deletions or corruptions can be catastrophic. Panzura implements immutability at the file system level, meaning data is never overwritten. Instead, the system creates pointers to new blocks, preserving previous versions automatically.

This built-in versioning provides an extra layer of protection beyond Git or other VCS systems, especially for binary files and large assets. Developers can roll back to previous file versions with just a few clicks, without lengthy restores from backups.

4. Accelerating Build and Test Pipelines

With development pipelines increasingly distributed across environments, build and test processes can be slowed by file access latency. Panzura's architecture speeds up these workflows by:

Caching active files locally for fast access
Deduplicating data to reduce transfer volumes
Providing consistent, immediate file access across all locations
Enabling high-performance data access for CI/CD pipelines

This acceleration is particularly valuable for organizations running complex microservices architectures or containerized applications where components are developed and tested across multiple environments.

5. Seamless Cloud Development Environment Integration

Modern development increasingly involves shifting workloads between on-premises and cloud environments. Panzura's platform creates a consistent file system experience regardless of where computation happens.

For instance, a developer might work locally but need to run intensive computations in AWS, Azure, or GCP. With Panzura, the file system layer remains consistent across these environments, eliminating the need for complex file synchronization or transfer processes.

Real-World Example: How Regional Store Changes the Game

The upcoming CloudFS 8.5 Adapt release (February 2025) includes a powerful feature called Regional Store that dramatically improves performance for geographically distributed teams.

Consider a development team with members in San Francisco, London, and Singapore. Without Regional Store, engineers in Singapore might face significant latency when accessing files stored in a US-based object store. With Regional Store, organizations can configure up to four synchronized object storage buckets across their preferred cloud provider's regions.

This means every developer, regardless of location, experiences local-like performance when accessing uncached files. The buckets are synchronized by the cloud provider, ensuring data consistency while eliminating performance penalties for remote team members.

Security That Doesn't Get in Developers' Way

Security requirements often create friction for developers. Panzura's approach minimizes this tension by:

Implementing FIPS 140-3 certified encryption transparently
Providing role-based access control with Okta SSO integration
Including ransomware detection and interdiction that doesn't disrupt legitimate work
Allowing secure remote access without cumbersome VPNs

These security capabilities are particularly valuable for teams working on sensitive projects or in regulated industries where compliance is non-negotiable.

The Future of Development Infrastructure

As development continues to evolve toward more distributed, multi-cloud models, infrastructure that can provide seamless data access, collaboration, and security will become increasingly essential.

Panzura's vision for "autonomic" infrastructure—systems that self-heal, self-optimize, and self-protect—aligns with the needs of modern development teams. For architects and engineering leaders planning their infrastructure strategy, platforms like Panzura represent a pathway to development environments that enhance productivity rather than hindering it.

By tackling the fundamental challenges of file collaboration in distributed environments, Panzura helps development teams focus on creating great software rather than wrestling with infrastructure limitations.