The demikernel datapath os architecture for microsecond-scale datacenter systems
Datacenter systems and I/O devices now run at single-digit microsecond latencies, requiring
ns-scale operating systems. Traditional kernel-based operating systems impose an …
ns-scale operating systems. Traditional kernel-based operating systems impose an …
{ODINFS}: Scaling {PM} performance with opportunistic delegation
Existing file systems for persistent memory (PM) exploit its byte-addressable non-volatile
access with low latency and high bandwidth. However, they do not utilize two unique PM …
access with low latency and high bandwidth. However, they do not utilize two unique PM …
Enabling high-performance and secure userspace nvm file systems with the trio architecture
Userspace library file systems (LibFSes) promise to unleash the performance potential of
non-volatile memory (NVM) by directly accessing it and enabling unprivileged applications …
non-volatile memory (NVM) by directly accessing it and enabling unprivileged applications …
Scale and performance in a filesystem semi-microkernel
We present uFS, a user-level filesystem semi-microkernel. uFS takes advantage of a high-
performance storage development kit to realize a fully-functional, crash-consistent, highly …
performance storage development kit to realize a fully-functional, crash-consistent, highly …
Simurgh: a fully decentralized and secure NVMM user space file system
The availability of non-volatile main memory (NVMM) has started a new era for storage
systems and NVMM specific file systems can support extremely high data and metadata …
systems and NVMM specific file systems can support extremely high data and metadata …
GPU-initiated on-demand high-throughput storage access in the BaM system architecture
Graphics Processing Units (GPUs) have traditionally relied on the host CPU to initiate
access to the data storage. This approach is well-suited for GPU applications with known …
access to the data storage. This approach is well-suited for GPU applications with known …
{MT^ 2}: Memory Bandwidth Regulation on Hybrid {NVM/DRAM} Platforms
Non-volatile memory (NVM) has emerged as a new memory media, resulting in a hybrid
NVM/DRAM configuration in typical servers. Memory-intensive applications competing for …
NVM/DRAM configuration in typical servers. Memory-intensive applications competing for …
{FusionFS}: Fusing {I/O} Operations using {CISCOps} in Firmware File Systems
We present FusionFS, a direct-access firmware-level in-storage filesystem that exploits the
near-storage computational capability for fast I/O and data processing, consequently …
near-storage computational capability for fast I/O and data processing, consequently …
{ScalaCache}: Scalable {User-Space} Page Cache Management with {Software-Hardware} Coordination
Due to the host-centric design principle, the existing page cache management suffers from
CPU consumption, communication costs, and garbage collection (GC) interference. To …
CPU consumption, communication costs, and garbage collection (GC) interference. To …
LabStor: A modular and extensible platform for developing high-performance, customized I/O stacks in userspace
Traditionally, I/O systems have been developed within the confines of a centralized OS
kernel. This led to monolithic and rigid storage systems that are limited by low development …
kernel. This led to monolithic and rigid storage systems that are limited by low development …