Template:SetupStep Warning Before Creating OSDs Journals - Revision history

Qadmin: /* Note Before Creating OSDs and Ceph Journals */

2020-02-12T18:35:39Z

Note Before Creating OSDs and Ceph Journals

← Older revision		Revision as of 18:35, 12 February 2020
Line 5:		Line 5:
	* Each system should have 5x HDDs (or SSDs) for data devices to satisfy minimum Placement Group redundancy requirements		* Each system should have 5x HDDs (or SSDs) for data devices to satisfy minimum Placement Group redundancy requirements
	* Each system should have 1x or more journal devices (NVMe/Optane preferred)		* Each system should have 1x or more journal devices (NVMe/Optane preferred)

			<br><br>

Qadmin: /* Note Before Creating OSDs and Ceph Journals */

2019-06-04T17:43:22Z

Note Before Creating OSDs and Ceph Journals

← Older revision		Revision as of 17:43, 4 June 2019
Line 3:		Line 3:
	The Object Storage Daemons (OSDs) store data, while the Journals accelerate write performance as all writes flow to the journal and are complete from the client perspective once the journal write is complete. A quick review of OSD and Journal requirements in a QuantaStor/Ceph Scale-out Block and Object configuration:		The Object Storage Daemons (OSDs) store data, while the Journals accelerate write performance as all writes flow to the journal and are complete from the client perspective once the journal write is complete. A quick review of OSD and Journal requirements in a QuantaStor/Ceph Scale-out Block and Object configuration:

	* QuanaStor maps OSDs to XFS Storage Pools on a one-to-one basis		* Each system should have 5x HDDs (or SSDs) for data devices to satisfy minimum Placement Group redundancy requirements
	* Journals map to a partition on a ''Physical Device'' like a SSD or [http://www.nvmexpress.org/ NVMe] device		* Each system should have 1x or more journal devices (NVMe/Optane preferred)
	* Each system should have ~~at least 3 Storage Pools/OSDs~~ to satisfy minimum Placement Group redundancy requirements~~, with between 3x to 25x OSD per system (15x to 125x disks in RAID5 units)~~
	* 1x ~~SSD Journal device is needed for every 8x OSDs~~ (~~with 4x OSDs per Journal the optimal maximum~~)

	~~[[File:qs4_ceph_osd_journal_map.png\|800px]]~~

	While stand-alone SSD devices can be used as Journal Devices, in practice it's better to use hardware RAID to protect and accelerate the journal device. Using RAID1 with two SSDs will make it easy to maintain with no downtime for the node. Going further, using RAID5 will boost performance and provide fault tolerance for a relatively small increase in hardware cost for a large boost in write performance.

	~~[[File:qs4_ceph_journal_types.png\|600px]]~~

Qadmin: /* Note Before Creating OSDs and Ceph Journals */

2019-05-03T16:01:16Z

Note Before Creating OSDs and Ceph Journals

← Older revision		Revision as of 16:01, 3 May 2019
Line 5:		Line 5:
	* QuanaStor maps OSDs to XFS Storage Pools on a one-to-one basis		* QuanaStor maps OSDs to XFS Storage Pools on a one-to-one basis
	* Journals map to a partition on a ''Physical Device'' like a SSD or [http://www.nvmexpress.org/ NVMe] device		* Journals map to a partition on a ''Physical Device'' like a SSD or [http://www.nvmexpress.org/ NVMe] device
	* Each ~~appliance~~ should have at least 3 Storage Pools/OSDs to satisfy minimum Placement Group redundancy requirements, with between 3x to 25x OSD per ~~Appliance~~ (15x to 125x disks in RAID5 units)		* Each system should have at least 3 Storage Pools/OSDs to satisfy minimum Placement Group redundancy requirements, with between 3x to 25x OSD per system (15x to 125x disks in RAID5 units)
	* 1x SSD Journal device is needed for every 8x OSDs (with 4x OSDs per Journal the optimal maximum)		* 1x SSD Journal device is needed for every 8x OSDs (with 4x OSDs per Journal the optimal maximum)

Qadmin: /* Note before Creating the OSDs and Journals */

2016-03-19T00:01:16Z

Note before Creating the OSDs and Journals

← Older revision		Revision as of 00:01, 19 March 2016
Line 1:		Line 1:
	== Note ~~before~~ Creating ~~the~~ OSDs and Journals ==		== Note Before Creating OSDs and Ceph Journals ==

	The Object Storage Daemons (OSDs) store data, while the Journals accelerate write performance as all writes flow to the journal and are complete from the client perspective once the journal write is complete. A quick review of OSD and Journal requirements in a QuantaStor/Ceph Scale-out Block and Object configuration:		The Object Storage Daemons (OSDs) store data, while the Journals accelerate write performance as all writes flow to the journal and are complete from the client perspective once the journal write is complete. A quick review of OSD and Journal requirements in a QuantaStor/Ceph Scale-out Block and Object configuration:

Qadmin: Created page with "== Note before Creating the OSDs and Journals == The Object Storage Daemons (OSDs) store data, while the Journals accelerate write performance as all writes flow to the journ..."

2016-03-17T22:10:14Z

Created page with "== Note before Creating the OSDs and Journals == The Object Storage Daemons (OSDs) store data, while the Journals accelerate write performance as all writes flow to the journ..."

New page

== Note before Creating the OSDs and Journals ==

The Object Storage Daemons (OSDs) store data, while the Journals accelerate write performance as all writes flow to the journal and are complete from the client perspective once the journal write is complete. A quick review of OSD and Journal requirements in a QuantaStor/Ceph Scale-out Block and Object configuration:

* QuanaStor maps OSDs to XFS Storage Pools on a one-to-one basis
* Journals map to a partition on a ''Physical Device'' like a SSD or [http://www.nvmexpress.org/ NVMe] device
* Each appliance should have at least 3 Storage Pools/OSDs to satisfy minimum Placement Group redundancy requirements, with between 3x to 25x OSD per Appliance (15x to 125x disks in RAID5 units)
* 1x SSD Journal device is needed for every 8x OSDs (with 4x OSDs per Journal the optimal maximum)

[[File:qs4_ceph_osd_journal_map.png|800px]]

While stand-alone SSD devices can be used as Journal Devices, in practice it's better to use hardware RAID to protect and accelerate the journal device. Using RAID1 with two SSDs will make it easy to maintain with no downtime for the node. Going further, using RAID5 will boost performance and provide fault tolerance for a relatively small increase in hardware cost for a large boost in write performance.

[[File:qs4_ceph_journal_types.png|600px]]