skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: FileScale: Fast and Elastic Metadata Management for Distributed File Systems
File systems that store metadata on a single machine or via a shared-disk abstraction face scalability challenges, especially in contexts demanding the management of billions of files. Recent work has shown that employing shared-nothing, distributed database system (DDBMS) for metadata storage can alleviate these scalability challenges without compromising on high availability guarantees. However, for low-scale deployments -- where metadata can fit in memory on a single machine -- these DDBMS-based systems typically perform an order of magnitude worse than systems that store metadata in memory on a single machine. This has limited the impact of these distributed database approaches, since they are only currently applicable to file systems of extreme scale. This paper describes FileScale, a three-tier architecture that incorporates a DDBMS as part of a comprehensive approach to file system metadata management. In contrast to previous approaches, FileScale performs comparably to the single-machine architecture at a small scale, while enabling linear scalability as the file system metadata increases.  more » « less
Award ID(s):
1910613
PAR ID:
10498402
Author(s) / Creator(s):
;
Publisher / Repository:
ACM
Date Published:
Journal Name:
SoCC '23: Proceedings of the 2023 ACM Symposium on Cloud Computing
ISBN:
9798400703874
Page Range / eLocation ID:
459 to 474
Format(s):
Medium: X
Location:
Santa Cruz CA USA
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, 2020 International Symposium on Networks, Computers and Communications (ISNCC))
    null (Ed.)
    As IoT services scale up from single homes to smart cities, directories and mapping services are needed to manage potentially millions of devices. However, directory service providers will likely struggle to accommodate the increasing number of IoT devices, made more challenging by their heterogeneous metadata and the large volume of queries. One of the critical challenges, the high heterogeneity of IoT, is being addressed by a working standard of W3C, which formalizes a physical or virtual device as a formatted Thing Description (TD).We propose a local directory service architecture with a series of design requirements. With a focus on query performance, we build a proof-of-concept system to store metadata of IoT devices as TDs in terms of the working standard. A Raspberry Pi is configured to investigate the query performance of relational database and non-relational database as the classic choices for internal directories. Evaluation results demonstrate that compared with relational database, non-relational database can achieve 2.9 times higher resilience on property query and 2.35 times faster processing on spatial query, with mild loss on aggregation query. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, ACM)
    In recent years, deep learning models have revolutionized computer vision, enabling diverse applications. However, these models are computationally expensive, and leveraging them for video analyt- ics involves low-level imperative programming. To address these efficiency and usability challenges, the database community has de- veloped video database management systems (VDBMSs). However, existing VDBMSs lack extensibility and composability and do not support holistic system optimizations, limiting their practical appli- cation. In response to these issues, we present our vision for EVA, a VDBMS that allows for extensible support of user-defined functions and employs a Cascades-style query optimizer. Additionally, we leverage RAY’s distributed execution to enhance scalability and performance and explore hardware-specific optimizations to facilitate runtime optimizations. We discuss the architecture and design of EVA, our achievements thus far, and our research roadmap. 
    more » « less
  3. (, Vault)
    Ceph is an open source distributed storage system that is object-based and massively scalable. Ceph provides developers with the capability to create data interfaces that can take advantage of local CPU and memory on the storage nodes (Ceph Object Storage Devices). These interfaces are powerful for application developers and can be created in C, C++, and Lua. Skyhook is an open source storage and database project in the Center for Research in Open Source Software at UC Santa Cruz. Skyhook uses these capabilities in Ceph to create specialized read/write interfaces that leverage IO and CPU within the storage layer toward database processing and management. Specifically, we develop methods to apply predicates locally as well as additional metadata and indexing capabilities using Ceph's internal indexing mechanism built on top of RocksDB. Skyhook's approach helps to enable scale-out of a single node database system by scaling out the storage layer. Our results show the performance benefits for some queries indeed scale well as the storage layer scales out. 
    more » « less
  4. ; ; ; ; (, Advances in Databases and Information Systems)
    Darmont, J; Novikov, B.; Wrembel, R. (Ed.)
    Bitcoin [12] is a successful and interesting example of a global scale peer-to-peer cryptocurrency that integrates many techniques and protocols from cryptography, distributed systems, and databases. The main underlying data structure is blockchain, a scalable fully replicated structure that is shared among all participants and guarantees a consistent view of all user transactions by all participants in the system. In a blockchain, nodes agree on their shared states across a large network of untrusted participants. Although originally devised for cryptocurrencies, recent systems exploit its many unique features such as transparency, provenance, fault tolerance, and authenticity to support a wide range of distributed applications. Bitcoin and other cryptocurrencies use permissionless blockchains. In a permissionless blockchain, the network is public, and anyone can participate without a specific identity. Many other distributed applications, such as supply chain management and healthcare, are deployed on permissioned blockchains consisting of a set of known, identified nodes that still might not fully trust each other. This paper illustrates some of the main challenges and opportunities from a database perspective in the many novel and interesting application domains of blockchains. These opportunities are illustrated using various examples from recent research in both permissionless and permissioned blockchains. Two main themes unite the various examples: (1) the important role of distribution and consensus in managing large scale systems and (2) the need to tolerate malicious failures. The advent of cloud computing and large data centers shifted large scale data management infrastructures from centralized databases to distributed systems. One of the main challenges in designing distributed systems is the need for fault-tolerance. Cloud-based systems typically assume trusted infrastructures, since data centers are owned by the enterprises managing the data, and hence the design typically only assumes and tolerates crash failures. The advent of blockchain and the underlying premise that copies of the blockchain are distributed among untrusted entities has shifted the focus of fault-tolerance from tolerating crash failures to tolerating malicious failures. These interesting and challenging settings pose great opportunities for database researchers. 
    more » « less
  5. ; ; ; ; ; ; (, Proceedings of 21st USENIX Conference on File and Storage Technologies (FAST ’23))
    Persistent memory (PM) can be accessed directly from userspace without kernel involvement, but most PM filesystems still perform metadata operations in the kernel for secuity and rely on the kernel for cross-process synchronization. We present per-file virtualization, where a virtualization layer implements a complete set of file functionalities, including metadata management, crash consistency, and concurrency control, in userspace. We observe that not all file metadata need to be maintained by the kernel and propose embedding insensitive metadata into the file for userspace management. For crash consistency, copy-on-write (CoW) benefits from the embedding of the block mapping since the mapping can be efficiently updated without kernel involvement. For cross-process synchronization, we introduce lockfree optimistic concurrency control (OCC) at user level, which tolerates process crashes and provides better scalability. Based on per-file virtualization, we implement MadFS, a library PM filesystem that maintains the embedded metadata as a compact log. Experimental results show that on concurrent workloads, MadFS achieves up to 3.6× the throughput of ext4-DAX. For real-world applications, MadFS provides up to 48% speedup for YCSB on LevelDB and 85% for TPC-C on SQLite compared to NOVA. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email