LizardFS

LizardFS
Developer(s)	Distributed FS Sp. z o.o.
Stable release	3.12.0 / 21 December 2017;4 years ago
Repository	github.com/lizardfs/lizardfs ;
Operating system	Linux, FreeBSD, Mac OS X, Solaris
Type	Distributed file system
License	GPLv3
Website	LizardFS.com

Last updated April 29, 2022

LizardFS is an open source distributed file system that is POSIX-compliant and licensed under GPLv3.^[3]^[4] It was released in 2013 as fork of MooseFS.^[5] LizardFS is also offering a paid Technical Support (Standard, Enterprise and Enterprise Plus) with possibility of configurating and setting up the cluster and active cluster monitoring.

Description

LizardFS makes files secure by keeping all the data in multiple replicas spread over the available servers. This storage is presented to the end-user as a single logical namespace. It can also be used to build space-efficient storage because it is designed to run on commodity hardware. It has applications in multiple fields and is used by institutions in finance, telecommunications, medicine, education, post-production, game development, cloud hosting services, and others.

Hardware

LizardFS is fully hardware agnostic. Commodity hardware can be utilized for cost efficiency. The minimum requirements are two dedicated nodes with a number of disks, but to obtain a high available installation at least 3 nodes are needed. This will also enable the use of erasure coding.

Architecture

LizardFS keeps metadata (e.g. file names, modification timestamps, directory trees) and the data separately. Metadata are kept on metadata servers, while data is kept on chunkservers.

A typical installation consists of:

At least two metadata servers, which work in the master-slave mode for failure recovery. Their role is to manage the whole installation, so the active metadata server is often called the master server. The role of other metadata servers is to keep in sync with the active master server, so they are often called shadow master servers. Any shadow master server is ready to take the role of the master server at any time. A suggested configuration of a metadata server is a machine with fast CPU, at least 32 GB of RAM and at least one drive (preferably SSD) to store several GB of metadata.

A set of chunkservers which store the data. Each file is divided into blocks called chunks (each up to 64 MB) which are stored on the chunkservers. A suggested configuration of a chunkserver is a machine with large disk space available either in a JBOD or RAID configuration. CPU and RAM are not very important. You can have as little as 2 chunkservers or as many as hundreds of them.

Clients who use the data stored on LizardFS. These machines use LizardFS mount to access files in the installation and process them just like those on their local hard drives. Files stored on LizardFS can be seen and accessed by as many clients as needed.

Features

Snapshots - When creating a snapshot, only the metadata of a target file is copied, speeding up the operation. Chunks of the original and the duplicated file are shared until one of them is modified.

QoS - LizardFS offers mechanisms that allow administrators to set read/write bandwidth limits for all the traffic generated by a given mount point, as well as for a specific group of processes spread over multiple client machines and mountpoints.

Data replication - Files stored in LizardFS are divided into blocks called chunks, each up to 64 MB in size. Each chunk is kept on chunkservers and administrators can choose how many copies of each file are maintained. For example, choosing to keep 3 copies (configuration goal=3), all of the data will survive a failure of any two disks or chunkservers, because LizardFS will never keep 2 copies of the same chunk on the same node.

Geo-replication - With Geo-replication you can decide where the chunks are stored. The topology feature allows for suggesting which copy should be read by a client in the case when more than one copy is available. For example, when LizardFS is deployed across two data centers, e.g. one located in London and one in Paris, it is possible to assign the label “london” to each server in the London location and “paris” to each server in the Paris location.

Metadata replication - Metadata is stored on metadata servers. At any time, one of the metadata servers also manages the whole installation and is called the master server. Other metadata servers remain in sync with it and are shadow master servers

High availability - Shadow master servers provide LizardFS with High Availability. If there is at least one shadow master server running and the active master server is lost, one of the shadow master servers takes over

Quotas - LizardFS support disk quota mechanism known from other POSIX le systems. It offers an option to set soft and hard limits for a number of files and their total size for a specific user or a group of users. A user whose hard limit is exceeded cannot write new data to LizardFS.

Trash - Another feature of LizardFS is a transparent and fully automatic trash bin. After removing any file, it is moved to a trash bin, which is visible only to the administrator. Any file in the trash bin can be restored or deleted permanently.

Native Windows™ client - LizardFS Windows Client can be installed on both workstations and servers. It provides access to files stored on LizardFS via a virtual drive. The Windows client is a licensed feature to be obtained by contacting the creators of LizardFS - Distributed FS Sp. z o.o.

Monitoring LizardFS offers two monitoring interfaces. First of all, there is a command-line tool useful for systems like Nagios, Zabbix, Icinga, which are typically used for proactive monitoring. Moreover, there is a graphical web-based monitoring interface available for administrators, which allows tracking almost all aspects of a system.

Hadoop - This is a java based solution allowing Hadoop to use LizardFS storage, implementing an HDFS interface to LizardFS. It functions as a kind of a File System Abstraction Layer. It enables you to use Hadoop jobs to directly access the data on a LizardFS cluster. The plugin translates LizardFS protocol and makes the metadata readable for Yarn and Map Reduce

NFS and pNFS - LizardFS uses NFS-ganesha server to create NFS shares, so technically NFS client connects not with the master server, but with a Ganesha file server that talks directly with LizardFS components. From the user point of view, it works just like an ordinary NFS server.

Related Research Articles

The Write Anywhere File Layout (WAFL) is a proprietary file system that supports large, high-performance RAID arrays, quick restarts without lengthy consistency checks in the event of a crash or power failure, and growing the filesystems size quickly. It was designed by NetApp for use in its storage appliances like NetApp FAS, AFF, Cloud Volumes ONTAP and ONTAP Select.

Google File System is a proprietary distributed file system developed by Google to provide efficient, reliable access to data using large clusters of commodity hardware. The last version of Google File System codenamed Colossus was released in 2010.

NIS+ is a directory service developed by Sun Microsystems to replace its older 'NIS'. It is designed to eliminate the need for duplication across many computers of configuration data such as user accounts, host names and addresses, printer information and NFS disk mounts on individual systems, instead using a central repository on a master server, simplifying system administration. NIS+ client software has been ported to other Unix and Unix-like platforms.

GPFS is a high-performance clustered file system software developed by IBM. It can be deployed in shared-disk or shared-nothing distributed parallel modes, or a combination of these. It is used by many of the world's largest commercial companies, as well as some of the supercomputers on the Top 500 List. For example, it is the filesystem of the Summit at Oak Ridge National Laboratory which was the #1 fastest supercomputer in the world in the November 2019 top500 list of supercomputers. Summit is a 200 Petaflops system composed of more than 9,000 POWER9 processors and 27,000 NVIDIA Volta GPUs. The storage filesystem called Alpine has 250 PB of storage using Spectrum Scale on IBM ESS storage hardware, capable of approximately 2.5TB/s of sequential I/O and 2.2TB/s of random I/O.

The Parallel Virtual File System (PVFS) is an open-source parallel file system. A parallel file system is a type of distributed file system that distributes file data across multiple servers and provides for concurrent access by multiple tasks of a parallel application. PVFS was designed for use in large scale cluster computing. PVFS focuses on high performance access to large data sets. It consists of a server process and a client library, both of which are written entirely of user-level code. A Linux kernel module and pvfs-client process allow the file system to be mounted and used with standard utilities. The client library provides for high performance access via the message passing interface (MPI). PVFS is being jointly developed between The Parallel Architecture Research Laboratory at Clemson University and the Mathematics and Computer Science Division at Argonne National Laboratory, and the Ohio Supercomputer Center. PVFS development has been funded by NASA Goddard Space Flight Center, The DOE Office of Science Advanced Scientific Computing Research program, NSF PACI and HECURA programs, and other government and private agencies. PVFS is now known as OrangeFS in its newest development branch.

Gluster Inc. was a software company that provided an open source platform for scale-out public and private cloud storage. The company was privately funded and headquartered in Sunnyvale, California, with an engineering center in Bangalore, India. Gluster was funded by Nexus Venture Partners and Index Ventures. Gluster was acquired by Red Hat on October 7, 2011.

Apache Hadoop is a collection of open-source software utilities that facilitates using a network of many computers to solve problems involving massive amounts of data and computation. It provides a software framework for distributed storage and processing of big data using the MapReduce programming model. Hadoop was originally designed for computer clusters built from commodity hardware, which is still the common use. It has since also found use on clusters of higher-end hardware. All the modules in Hadoop are designed with a fundamental assumption that hardware failures are common occurrences and should be automatically handled by the framework.

A clustered file system is a file system which is shared by being simultaneously mounted on multiple servers. There are several approaches to clustering, most of which do not employ a clustered file system. Clustered file systems can provide features like location-independent addressing and redundancy which improve reliability or reduce the complexity of the other parts of the cluster. Parallel file systems are a type of clustered file system that spread data across multiple storage nodes, usually for redundancy or performance.

Ceph is an open-source software-defined storage platform that implements object storage on a single distributed computer cluster and provides 3-in-1 interfaces for object-, block- and file-level storage. Ceph aims primarily for completely distributed operation without a single point of failure, scalability to the exabyte level, and to be freely available. Since version 12, Ceph does not rely on other filesystems and can directly manage HDDs and SSDs with its own storage backend BlueStore and can completely self reliantly expose a POSIX filesystem.

Moose File System (MooseFS) is an open-source, POSIX-compliant distributed file system developed by Core Technology. MooseFS aims to be fault-tolerant, highly available, highly performing, scalable general-purpose network distributed file system for data centers. Initially proprietary software, it was released to the public as open source on May 30, 2008.

Apache ZooKeeper is an open-source server for highly reliable distributed coordination of cloud applications. It is a project of the Apache Software Foundation.

BeeGFS is a parallel file system, developed and optimized for high-performance computing. BeeGFS includes a distributed metadata architecture for scalability and flexibility reasons. Its most used and widely known aspect is data throughput.

Apache Hive is a data warehouse software project built on top of Apache Hadoop for providing data query and analysis. Hive gives an SQL-like interface to query data stored in various databases and file systems that integrate with Hadoop. Traditional SQL queries must be implemented in the MapReduce Java API to execute SQL applications and queries over distributed data. Hive provides the necessary SQL abstraction to integrate SQL-like queries (HiveQL) into the underlying Java without the need to implement queries in the low-level Java API. Since most data warehousing applications work with SQL-based querying languages, Hive aids portability of SQL-based applications to Hadoop. While initially developed by Facebook, Apache Hive is used and developed by other companies such as Netflix and the Financial Industry Regulatory Authority (FINRA). Amazon maintains a software fork of Apache Hive included in Amazon Elastic MapReduce on Amazon Web Services.

RozoFS is a free software distributed file system. It comes as a free software, licensed under the GNU GPL v2. RozoFS uses erasure coding for redundancy.

In computing, a distributed file system (DFS) or network file system is any file system that allows access to files from multiple hosts sharing via a computer network. This makes it possible for multiple users on multiple machines to share files and storage resources.

Oracle NoSQL Database (ONDB) is a NoSQL-type distributed key-value database from Oracle Corporation. It provides transactional semantics for data manipulation, horizontal scalability, and simple administration and monitoring.

A distributed file system for cloud is a file system that allows many clients to have access to data and supports operations on that data. Each data file may be partitioned into several parts called chunks. Each chunk may be stored on different remote machines, facilitating the parallel execution of applications. Typically, data is stored in files in a hierarchical tree, where the nodes represent directories. There are several ways to share files in a distributed architecture: each solution must be suitable for a certain type of application, depending on how complex the application is. Meanwhile, the security of the system must be ensured. Confidentiality, availability and integrity are the main keys for a secure system.

The MapR File System is a clustered file system that supports both very large-scale and high-performance uses. MapR FS supports a variety of interfaces including conventional read/write file access via NFS and a FUSE interface, as well as via the HDFS interface used by many systems such as Apache Hadoop and Apache Spark. In addition to file-oriented access, MapR FS supports access to tables and message streams using the Apache HBase and Apache Kafka APIs as well as via a document database interface.

ONTAP or Data ONTAP or Clustered Data ONTAP (cDOT) or Data ONTAP 7-Mode is NetApp's proprietary operating system used in storage disk arrays such as NetApp FAS and AFF, ONTAP Select and Cloud Volumes ONTAP. With the release of version 9.0, NetApp decided to simplify the Data ONTAP name and removed word "Data" from it and remove 7-Mode image, therefore, ONTAP 9 is successor from Clustered Data ONTAP 8.

References

↑ "LizardFS".
↑ "Releases · lizardfs/lizardfs".
↑ "LizardFS: Software-defined storage, as it should be (original article in German)". www.golem.de. April 27, 2016. Retrieved 2016-05-06.
↑ "Mr. Blue Coat: (updated) Distributed File System benchmark" . Retrieved 2016-05-06.
↑ "ZFS + glusterfs on two or three nodes". permalink.gmane.org. Retrieved 2016-05-06.
↑ Korenkov, V. V.; Kutovskiy, N. A.; Balashov, N. A.; Baranov, A. V.; Semenov, R. N. (2015-01-01). "JINR Cloud Infrastructure". Procedia Computer Science. 4th International Young Scientist Conference on Computational Science. 66: 574–583. doi: 10.1016/j.procs.2015.11.065 .

External links

This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.

[1] "LizardFS".

[LizardFS_releases_on_GitHub-2] "Releases · lizardfs/lizardfs".

[3] "LizardFS: Software-defined storage, as it should be (original article in German)". www.golem.de. April 27, 2016. Retrieved 2016-05-06.

[4] "Mr. Blue Coat: (updated) Distributed File System benchmark" . Retrieved 2016-05-06.

[5] "ZFS + glusterfs on two or three nodes". permalink.gmane.org. Retrieved 2016-05-06.

[6] Korenkov, V. V.; Kutovskiy, N. A.; Balashov, N. A.; Baranov, A. V.; Semenov, R. N. (2015-01-01). "JINR Cloud Infrastructure". Procedia Computer Science. 4th International Young Scientist Conference on Computational Science. 66: 574–583. doi: 10.1016/j.procs.2015.11.065 .

[1]

[2]

[3]

[4]

[5]

[6]