Bug 1593868 - Best practices updates for bucket index to be on same nvme as journal
Summary: Best practices updates for bucket index to be on same nvme as journal
Keywords:
Status: CLOSED CURRENTRELEASE
Alias: None
Product: Red Hat Ceph Storage
Classification: Red Hat Storage
Component: Documentation
Version: 3.1
Hardware: Unspecified
OS: Unspecified
high
high
Target Milestone: rc
: 3.1
Assignee: John Wilkins
QA Contact: Vasu Kulkarni
URL:
Whiteboard:
Depends On:
Blocks: 1581350 1591074 1593418 1602919
TreeView+ depends on / blocked
 
Reported: 2018-06-21 17:43 UTC by Vasu Kulkarni
Modified: 2019-02-26 07:25 UTC (History)
8 users (show)

Fixed In Version:
Doc Type: If docs needed, set a value
Doc Text:
Clone Of:
Environment:
Last Closed: 2019-02-26 07:25:14 UTC
Embargoed:


Attachments (Terms of Use)


Links
System ID Private Priority Status Summary Last Updated
Red Hat Bugzilla 1591074 0 urgent CLOSED Support NVMe based bucket index pools 2021-02-22 00:41:40 UTC

Internal Links: 1591074

Description Vasu Kulkarni 2018-06-21 17:43:13 UTC
Description of problem:

The current GSS best practices guide recommends bucket index to be on separate nvm drive compared to journal,

During the DFG workload testing, John noticed too much traffic is on the filestore journals and there is not really advantageous to have bucket index on different nvme, the recommendation from the experiment is to split on same nvme probably using lvm, we need to update our best practices guide based on this testing.

Comment 3 Vasu Kulkarni 2018-06-27 17:47:02 UTC
So what John is recommending here is with LVM option that is equally split between journal and bucket index on same nvme.

Comment 5 Vasu Kulkarni 2018-09-04 17:28:26 UTC
One minor nit but looks good.


Note You need to log in before you can comment on or make changes to this bug.