Securing High-Performance Async Storage: Programmable io_uring Policy Enforcement with BPF in Linux 7.0
Abstract
Modern Linux storage infrastructure is rapidly evolving toward fully asynchronous I/O models driven by io_uring, NVMe, and highly parallel storage architectures. By minimizing syscall overhead, reducing context switches, and enabling efficient submission/completion queue processing, io_uring has become a foundational technology for next-generation databases, AI infrastructure, object storage systems, and cloud-native storage platforms. However, this shift toward asynchronous execution introduces a significant architectural challenge for security, governance, and multi-tenant isolation.
Traditional Linux security mechanisms such as seccomp were designed around a syscall-centric execution model, where syscall arguments can be inspected and filtered at syscall entry points. io_uring changes this assumption fundamentally. Instead of embedding operation metadata directly in syscalls, requests are encoded inside Submission Queue Entries (SQEs) that are processed asynchronously by the kernel. This creates visibility and enforcement gaps for container runtimes, orchestration systems, and storage platforms attempting to apply fine-grained policy controls to async I/O operations. As a result, some production environments have restricted or disabled io_uring usage entirely due to concerns around security boundaries, tenant isolation, and operational governance.
Linux 7.0 introduces a new cBPF-based filtering framework for io_uring that enables programmable inspection and enforcement of asynchronous operations before execution. This capability represents a major step toward restoring fine-grained control and observability for modern Linux storage stacks while preserving the performance advantages of asynchronous I/O. By attaching programmable filters to io_uring operations, administrators and platform operators can selectively permit, reject, or constrain async requests based on operation type, flags, and workload-specific policies.
This session examines the architectural evolution that led to the need for programmable async I/O filtering and explains how Linux 7.0 implements io_uring BPF enforcement internally. We will analyze how async submission semantics differ from traditional syscall execution paths, why existing seccomp approaches are insufficient for modern async storage systems, and how the new filtering model integrates with containerized and multi-tenant infrastructure.
The presentation will include practical examples of filtering policies for operations such as OPENAT2, socket creation, and storage-related asynchronous requests, along with demonstrations of policy inheritance and runtime enforcement behavior. We will also evaluate the performance implications of programmable filtering under high-throughput storage workloads using NVMe and io_uring-based applications, including measurements of latency overhead, scalability impact, and operational trade-offs.
Attendees will gain a deeper understanding of how programmable filtering can help organizations safely deploy io_uring in production storage environments while maintaining strong isolation, governance, and operational visibility. The session will also explore future opportunities for combining eBPF observability with async I/O policy enforcement to build adaptive and security-aware storage infrastructure for cloud-native and AI-scale systems.
Related Sessions
Why S3FS Fails in AI/ML — and How to Achieve Scalable POSIX Access Anyway
Mounting S3-compatible storage via S3FS seems like an easy way to enable POSIX-like access in Kubernetes. But in real AI/ML workloads—e.g., training with PyTorch or TensorFlow—we hit major issues: crashes from incomplete writes, vanished checkpoints, inconsistent metadata, and unpredictable I/O latency.
In this session, we’ll share how we overcame these challenges by designing a scalable, POSIX-compliant distributed file system that still leverages the cost-effectiveness of object storage. Instead of abandoning object storage, we rebuilt the access layer for better consistency, performance, and observability in large-scale environments.
Attendees will gain insight into architectural trade-offs, POSIX compliance in user space, Kubernetes integration via CSI and Operators, and observability benchmarks collected from real production AI training clusters.
Ideal for platform engineers, MLOps, and K8s architects seeking reliable, scalable storage for data-heavy workloads.
This is an intermediate session; attendees should be comfortable with object storage, file storage, and the basic concepts of the Kubernetes CSI driver.
Highly Scalable, Masterless, Distributed Filesystem at Rubrik
Rubrik is a cybersecurity company protecting mission critical data for thousands of customers across the globe including banks, hospitals, and government agencies. SDFS is the filesystem that powers the data path and makes this possible. In this talk, we will discuss challenges in building a masterless distributed filesystem with support for data resilience, strong data integrity, and high performance which can run across a wide spectrum of hardware configurations including cloud platforms. We will discuss the high level architecture of our FUSE based filesystem, how we leverage erasure coding for maintaining data resilience and checksum schemes for maintaining strong data integrity with high performance. We will also cover the challenges in continuously monitoring and maintaining the health of the filesystem in terms of data resilience, data integrity and load balance. Further we will go over how we expand and shrink resources online from the filesystem. We will also discuss the need and challenge of providing priority natively in our filesystem to support a variety of workloads and background operations with varying SLA requirements. Finally, we will also touch on the benefits and challenges of supporting encryption, compression, and de-duplication natively in the filesystem.
Scalable Metadata in Distributed File Systems: Revisiting the GoogleFS Design for Exabyte-Scale Namespaces
GoogleFS introduced the architectural separation of metadata and data, but its reliance on a single active master imposed fundamental limitations on scalability, redundancy, and availability. This talk presents a modern metadata architecture, exemplified by SaunaFS, that eliminates the single-leader model by distributing metadata across multiple concurrent, multi-threaded servers. Metadata is stored in a sharded, ACID-compliant transactional database (e.g., FoundationDB), enabling horizontal scalability, fault tolerance through redundant metadata replicas, reduced memory footprint, and consistent performance under load. The result is a distributed file system architecture capable of exabyte-scale operation in a single namespace while preserving POSIX semantics and supporting workloads with billions of small files.
Open Flash Platform: An Initiative for Open, Highly Efficient AI Storage
Enterprise IT infrastructures face soaring AI and analytics demands, driving the need for storage that leverages existing networks, cuts power-hungry server counts, and frees CAPEX for AI. Yet current solutions create isolated silos: proprietary, server-based systems that waste power, lack cloud connectivity, and force large teams to manage multiple silo technologies—locking data behind vendor walls and hampering AI goals. Modeled on the Open Compute Project, the Open Flash Platform (OFP) liberates high-capacity flash through an open architecture built on standard pNFS which is included in every Linux distribution. Each OFP unit contains a DPU-based Linux instance and network port, so it connects directly as a peer—no additional servers. By removing surplus hardware and proprietary software, OFP lets enterprises use dense flash efficiently, halving TCO and increasing storage density 10×. Early configurations deliver up to 48 PB in 2U and scale to 1 EB per rack, yielding a 10× reduction in rack space, power, and OPEX and a 33 % longer service life. This session explains the vision and engineering that make OFP possible, showing how open, standards-based architecture can simplify, scale, and free enterprise data.
Choosing Your AI Storage Protocol: A Deep Dive into SMB and NFS Performance, Tuning, and Overhead
The performance of network file protocols is a critical factor in the efficiency of the AI and Machine Learning pipeline. This presentation provides a detailed comparative analysis of the two leading protocols, Server Message Block (SMB) and Network File System (NFS), specifically for demanding AI workloads. We evaluate the advanced capabilities of both protocols, comparing SMB3 with SMB Direct and Multichannel against NFS with RDMA and multistream TCP configurations. The industry-standard MLPerf Storage benchmark is used to simulate realistic AI data access patterns, providing a robust foundation for our comparison. The core of this research focuses on quantifying the performance differences and identifying the operational and configuration overhead associated with each technology.
New Transports in Samba: QUIC and SMB-Direct Support
The Samba file server is evolving beyond traditional TCP-based transport. This talk introduces the latest advancements in Samba's networking stack, including full support for SMB over QUIC, offering secure, firewall-friendly file sharing using modern internet protocols. We’ll also explore the ongoing development of SMB over SMB-Direct (RDMA), aimed at delivering low-latency, high-throughput file access for data center and high-performance environments. Join us for a deep dive into these transport innovations, their architecture, current status, and what's next for Samba’s high-performance networking roadmap.
