Performance and extension of user space file systems

Rajgarhia, Aditya; Gehani, Ashish

doi:10.1145/1774088.1774130

Cited by 65 publications

(36 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As for the overhead of FUSE framework compared to the native Ext4 file system on spinning disks we see FUSE only adds little overhead to read files at all block sizes as shown in Figure 8(a): for most block sizes FUSE achieves nearly 100% performance of the native Ext4. Similar results are also reported in a review of FUSE performance in [13]. This fact indicates that even when the SSD cache is intensive and some files need to be swapped between SSD and HDD, HyCache can still outperform Ext4 since the slower media of HyCache (HDD FUSE in Figure 7), are comparable to Ext4.…”

Section: B Micro-benchmarksupporting

confidence: 84%

HyCache: A User-Level Caching Middleware for Distributed File Systems

Zhao

Raicu

2013

2013 IEEE International Symposium on Parallel &Amp; Distributed Processing, Workshops and PHD Forum

View full text Add to dashboard Cite

Abstract-One of the bottlenecks of distributed file systems deals with mechanical hard drives (HDD). Although solid-state drives (SSD) have been around since the 1990's, HDDs are still dominant due to large capacity and relatively low cost. Hybrid hard drives with a small built-in SSD cache does not meet the need of a large variety of workloads. This paper proposes a middleware that manages the underlying heterogeneous storage devices in order to allow distributed file systems to leverage the SSD performance while leveraging the capacity of HDD. We design and implement a user-level filesystem, HyCache, that can offer SSD-like performance at a cost similar to a HDD. We show how HyCache can be used to improve performance in distributed file systems, such as the Hadoop HDFS. Experiments show that HyCache achieves up to 7X higher throughput and 76X higher IOPS than Linux Ext4 file system, and can accelerate HDFS by 28% at 32-node scales (compared to vanilla HDFS).Index Terms-distributed file systems, user level file systems, hybrid file systems, heterogeneous storage, SSD

show abstract

Section: B Micro-benchmarksupporting

confidence: 84%

HyCache: A User-Level Caching Middleware for Distributed File Systems

Zhao

Raicu

2013

2013 IEEE International Symposium on Parallel &Amp; Distributed Processing, Workshops and PHD Forum

View full text Add to dashboard Cite

show abstract

“…To collect provenance without modifying applications or the operating system, events from a user space filesystem [50] were fused with process-related information from /proc (on Linux). Unmodified applications could ensure that a file's provenance was transparently transferred across network connections.…”

Section: Introductionmentioning

confidence: 99%

SPADE: Support for Provenance Auditing in Distributed Environments

Gehani

Tariq

2012

Lecture Notes in Computer Science

Self Cite

177

138

View full text Add to dashboard Cite

Abstract. SPADE is an open source software infrastructure for data provenance collection and management. The underlying data model used throughout the system is graph-based, consisting of vertices and directed edges that are modeled after the node and relationship types described in the Open Provenance Model. The system has been designed to decouple the collection, storage, and querying of provenance metadata. At its core is a novel provenance kernel that mediates between the producers and consumers of provenance information, and handles the persistent storage of records. It operates as a service, peering with remote instances to enable distributed provenance queries. The provenance kernel on each host handles the buffering, filtering, and multiplexing of incoming metadata from multiple sources, including the operating system, applications, and manual curation. Provenance elements can be located locally with queries that use wildcard, fuzzy, proximity, range, and Boolean operators. Ancestor and descendant queries are transparently propagated across hosts until a terminating expression is satisfied, while distributed path queries are accelerated with provenance sketches.

show abstract

“…From the point of view of a user application, such information is passed through the errno variable and a predefined return code 16 . However, there is no special interface on the kernel side -an error is returned the same way as correct values.…”

Section: Syscall Error Handling (Errno)mentioning

confidence: 99%

“…Moreover, userspace filesystems do not require root capabilities to be mounted. This typically leads to easier interaction from the end-user point of view [16].…”

Section: Introductionmentioning

confidence: 99%

Portable Userspace Virtual Filesystem Switch

Faber

Boryczko

2013

csci

View full text Add to dashboard Cite

Multiple different filesystems -including disk-based, network, distributed, abstract -are an integral part of every operating system. They are usually written as kernel modules and abstracted to the user via a virtual filesystem switch.In this paper, we analyze the feasibility of reimplementing the virtual filesystem switch as a userspace daemon and applicability of this approach in real-life usage. Such reimplementation will require a way to virtualize processes behavior related to filesystem operations. The problem is non-trivial, as we assume limited capabilities of the VFS switch implemented in userspace. We present a layered architecture comprising of a monitoring process, the VFS abstraction and real filesystem implementations. All working in userspace. Then, we evaluate this solution in four areas: portability, feasibility, usability, and performance. Our results demonstrate possible gains in the use of a userspacebased approach with monolithic kernels, but also underline problems that are encountered in this approach.

show abstract

Performance and extension of user space file systems

Cited by 65 publications

References 21 publications

HyCache: A User-Level Caching Middleware for Distributed File Systems

HyCache: A User-Level Caching Middleware for Distributed File Systems

SPADE: Support for Provenance Auditing in Distributed Environments

Portable Userspace Virtual Filesystem Switch

Contact Info

Product

Resources

About