DistOS 2015W Session 7 - Revision history

Jasons: /* Key Features */

2015-04-20T10:12:24Z

Key Features

← Older revision		Revision as of 10:12, 20 April 2015
Line 35:		Line 35:
	== Key Features ==		== Key Features ==
	* Decoupled data and metadata		* Decoupled data and metadata
			** good for scalability of various file size, from small to large

	* Dynamic Distributed Metadata Management		* Dynamic Distributed Metadata Management

Jasons: /* Ceph */

2015-04-20T10:07:40Z

Ceph

← Older revision		Revision as of 10:07, 20 April 2015
Line 1:		Line 1:
	= Ceph =		= Ceph =
	Unlike GFS that was talked about previously, this is a general purpose distributed file system. It follows the same general model of distribution as GFS and Amoeba.		Unlike GFS that was talked about previously, this is a general purpose distributed file system (for various file size, from small to large). It follows the same general model of distribution as GFS and Amoeba.

	HOW IT WORKS		HOW IT WORKS

Veenarose: /* Chubby */

2015-04-12T18:27:47Z

Chubby

← Older revision		Revision as of 18:27, 12 April 2015
Line 54:		Line 54:
	It is a coarse grained lock service, made and used internally by Google, that serves multiple clients with small number of servers (chubby cell).		It is a coarse grained lock service, made and used internally by Google, that serves multiple clients with small number of servers (chubby cell).

			Chubby was designed to be a lock service, a distributed system that clients could connect to and share access to small files. The servers providing the system are partitioned into a variety of cells and access for a particular file is managed through one elected master node in one cell. This master makes all decisions and informs the rest of the cell nodes of that decision. If the master fails, the other nodes elect a new master. The problem of asynchronous consensus is solved through the use of timeouts as a failure detector. To avoid the scaling problem of a single bottleneck, the number of cells can be increased with the cost of making some cells smaller.

	== System Components ==		== System Components ==

Veenarose: /* Ceph */

2015-04-11T19:25:31Z

Ceph

← Older revision		Revision as of 19:25, 11 April 2015
Line 11:		Line 11:
	Applications that use file systems can use Ceph FS with POSIX semantics. No integration or customization required!		Applications that use file systems can use Ceph FS with POSIX semantics. No integration or customization required!
	Ceph automatically balances the file system to deliver maximum performance.		Ceph automatically balances the file system to deliver maximum performance.


			== Advantages of using File systems ==
			* It supports heterogeneous operating systems including all flavors of the unix operating system as well as Linux and windows
			* Multiple client machines can access a single resource simultaneously.
			enables sharing common application binaries and read only information instead of putting them on each single machine. This results in reduced overall disk storage cost and administration overhead.
			*Gives access to uniform data to groups of users.
			*Useful when many users exists on many systems with each user's home directory located on every single machine. Network file systems allows you to all users home directories on a single machine under /home

Veenarose: /* Ceph */

2015-04-11T19:23:48Z

Ceph

← Older revision		Revision as of 19:23, 11 April 2015
Line 1:		Line 1:
	= Ceph =		= Ceph =
	Unlike GFS that was talked about previously, this is a general purpose distributed file system. It follows the same general model of distribution as GFS and Amoeba.		Unlike GFS that was talked about previously, this is a general purpose distributed file system. It follows the same general model of distribution as GFS and Amoeba.

			HOW IT WORKS
			Ceph file system runs on top of the same object storage system that provides object storage and block device interfaces. The Ceph metadata server cluster provides a service that maps the directories and filenames of the file system to objects stored within RADOS clusters. The metadata server cluster can expand or contract, and it can rebalance the file system dynamically to distribute data evenly among cluster hosts. This ensures high performance and prevents heavy loads on specific hosts within the cluster.

			BENEFITS
			The Ceph file system provides numerous benefits:
			It provides stronger data safety for mission-critical applications.
			It provides virtually unlimited storage to file systems.
			Applications that use file systems can use Ceph FS with POSIX semantics. No integration or customization required!
			Ceph automatically balances the file system to deliver maximum performance.

Abeinges: /* Issues */

2015-04-06T05:04:30Z

Issues

← Older revision		Revision as of 05:04, 6 April 2015
Line 67:		Line 67:
	* Since it has a file-system client interface, many programmers tend to abuse the system and need education (even inside Google)		* Since it has a file-system client interface, many programmers tend to abuse the system and need education (even inside Google)
	* Clients need to constantly ping Chubby to verify that they still exist. This is to ensure that a server disappearing while holding a lock does not indefinitely hold that lock.		* Clients need to constantly ping Chubby to verify that they still exist. This is to ensure that a server disappearing while holding a lock does not indefinitely hold that lock.
			* Clients must also consequently re-verify that they hold a lock that they think they hold because Chubby may have timed them out.

Abeinges: /* Issues */

2015-04-06T05:03:56Z

Issues

← Older revision		Revision as of 05:03, 6 April 2015
Line 66:		Line 66:
	* Due to the use of Paxos (the only algorithm for this problem), the chubby cell is limited to only 5 servers. While this limits fault-tolerance, in practice this is more than enough.		* Due to the use of Paxos (the only algorithm for this problem), the chubby cell is limited to only 5 servers. While this limits fault-tolerance, in practice this is more than enough.
	* Since it has a file-system client interface, many programmers tend to abuse the system and need education (even inside Google)		* Since it has a file-system client interface, many programmers tend to abuse the system and need education (even inside Google)
			* Clients need to constantly ping Chubby to verify that they still exist. This is to ensure that a server disappearing while holding a lock does not indefinitely hold that lock.

Abeinges: /* Main Features */

2015-04-06T05:02:07Z

Main Features

← Older revision		Revision as of 05:02, 6 April 2015
Line 52:		Line 52:
	** Trivial to use by programs; just use the standard ''fopen()'' family of calls		** Trivial to use by programs; just use the standard ''fopen()'' family of calls

	* Uses consensus algorithm among a set of servers to agree on who is the master that is in charge of the metadata		* Uses consensus algorithm (paxos) among a set of servers to agree on who is the master that is in charge of the metadata

	* Meant for locks that last hours or days, not seconds (thus, "coarse grained")		* Meant for locks that last hours or days, not seconds (thus, "coarse grained")
Line 62:		Line 62:

	* Also used by Google as a nameserver		* Also used by Google as a nameserver


	== Issues ==		== Issues ==
	* Due to the use of Paxos (the only algorithm for this problem), the chubby cell is limited to only 5 servers. While this limits fault-tolerance, in practice this is more than enough.		* Due to the use of Paxos (the only algorithm for this problem), the chubby cell is limited to only 5 servers. While this limits fault-tolerance, in practice this is more than enough.
	* Since it has a file-system client interface, many programmers tend to abuse the system and need education (even inside Google)		* Since it has a file-system client interface, many programmers tend to abuse the system and need education (even inside Google)

Abeinges: /* Ceph */

2015-04-06T05:01:06Z

Ceph

← Older revision		Revision as of 05:01, 6 April 2015
Line 27:		Line 27:
	* CRUSH (Controlled, Replicated, Under Scalable, Hashing)		* CRUSH (Controlled, Replicated, Under Scalable, Hashing)
	** The hashing algorithm used to calculate the location of object instead of looking for them		** The hashing algorithm used to calculate the location of object instead of looking for them
	** This significantly reduces the load on the MDSs		** This significantly reduces the load on the MDSs because each client has enough information to independently determine where things should be located.
	** Responsible for automatically moving data when ODSs are added or removed (can be simplified as ''location = CRUSH(filename) % num_servers'')		** Responsible for automatically moving data when ODSs are added or removed (can be simplified as ''location = CRUSH(filename) % num_servers'')
	** The CRUSH paper on Ceph’s website can be [http://ceph.com/papers/weil-crush-sc06.pdf viewed here]		** The CRUSH paper on Ceph’s website can be [http://ceph.com/papers/weil-crush-sc06.pdf viewed here]

	* RADOS (Reliable Autonomic Distributed Object-Store) is the object store for Ceph		* RADOS (Reliable Autonomic Distributed Object-Store) is the object store for Ceph


	= Chubby =		= Chubby =

Aimbot: Formatting, updates and additions to both sections.

2015-02-28T16:59:14Z

Formatting, updates and additions to both sections.

@@ Line 1: / Line 1: @@
 = Ceph =
-* Key advantage is that it is a general purpose distributed file system.
+Unlike GFS that was talked about previously, this is a general purpose distributed file system. It follows the same general model of distribution as GFS and Amoeba.
-* System is composed of three units:
-	*Client,
-	*Cluster of Object Storage device (OSDs): It is basically stores data and metadata and clients communicate directly with it to perform IO operations.
+== Main Components ==
-	*MetaData Server (MDS): It is used to manage the file and directories.Client basically interacts with it to perform metadata operations like open, rename. It manages the capabilities of a client.
+* Client
-* system has three key features:
-     * decoupled data and metadata:
+* Cluster of Object Storage Devices (OSD)
-     * Dynamic Distributed Metadata Management: It distribute the metadata among multiple metadata servers using dynamic subtree partitioning to increase the performance and avoid metadata access hot spots.
+** It basically stores data and metadata and clients communicate directly with it to perform IO operations
-     * Object based storage: Using cluster of OSDs to form a Reliable Autonomic Distributed Object-Store(RADOS) for ceph failure detection and recovery.
+** Data is stored in objects (variable size chunks)
 = Chubby =
-It is basically a coarse grained lock service that serves multiple clients with small number of servers (chubby cell).
+It is a coarse grained lock service, made and used internally by Google, that serves multiple clients with small number of servers (chubby cell).
-* Is a consensus algorithm among a set of servers to agree on who is the master that is in charge of the metadata.
+== Issues ==
-* Can be considered a distributed file system for small size files only “256 KB” with very low scalability “5 servers”.
+* Due to the use of Paxos (the only algorithm for this problem), the chubby cell is limited to only 5 servers. While this limits fault-tolerance, in practice this is more than enough.
-* Is defined in the paper as “A lock service used within a loosely-coupled distributed system consisting of moderately large number of small machines connected by a high speed network”.
+* Since it has a file-system client interface, many programmers tend to abuse the system and need education (even inside Google)