Bug 2208600

Summary:	Update the mClock documentation to reflect the new mclock profile information and other important changes.
Product:	[Red Hat Storage] Red Hat Ceph Storage	Reporter:	Sridhar Seshasayee <sseshasa>
Component:	Documentation	Assignee:	Akash Raj <akraj>
Documentation sub component:	Administration Guide	QA Contact:	skanta
Status:	CLOSED CURRENTRELEASE	Docs Contact:	Rivka Pollack <rpollack>
Severity:	medium
Priority:	unspecified	CC:	akraj, asriram, cephqe-warriors, msaini, rmandyam, rpollack, skanta, vereddy, vumrao
Version:	6.1
Target Milestone:	---
Target Release:	6.1
Hardware:	Unspecified
OS:	Unspecified
Whiteboard:
Fixed In Version:		Doc Type:	Enhancement
Doc Text:	.Usability and design improvements are implemented to the mClock scheduler With this release, significant usability and design improvements are implemented to the mClock scheduler to address the slow backfill issues. - The `balanced` profile is set as the default mClock profile because it represents a compromise between prioritizing client IO or recovery IO. Users can then choose either the `high_client_ops` profile to prioritize client IO or the `high_recovery_ops` profile to prioritize recovery IO. - QoS parameters like _reservation_ and _limit_ are now specified in terms of a fraction (`range`: `0.0` to `1.0`) of the OSD's IOPS capacity. - The cost parameters - `osd_mclock_cost_per_io_usec_` and `osd_mclock_cost_per_byte_usec_` have been removed. The cost of an operation is now determined using the random IOPS and maximum sequential bandwidth capability of the OSD's underlying device. - Degraded object recovery is given higher priority when compared to misplaced object recovery because degraded objects present a data safety issue not present with objects that are merely misplaced. Therefore, backfilling operations with the `balanced` and `high_client_ops` mClock profiles may progress slower than what was seen with the `WeightedPriorityQueue` (WPQ) scheduler. - The QoS allocations in all the mClock profiles are optimized based on the above fixes and enhancements.	Story Points:	---
Clone Of:		Environment:
Last Closed:	2023-06-21 06:59:51 UTC	Type:	Bug
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:
Bug Depends On:
Bug Blocks:	2192813

Description Sridhar Seshasayee 2023-05-19 17:28:10 UTC

Describe the issue:

With the recent changes to mClock scheduler and recovery specific changes to address
the slow backfill issue (see https://bugzilla.redhat.com/show_bug.cgi?id=2163473),
the following significant changes were introduced:

1. Change the way QoS parameters are specified in mclock profiles.
2. The allocations for different ops within profiles are changed
3. The default mclock profile is now changed.
4. The earlier cost related config parameters are removed and new ones are
   introduced.
5. The recovery and backfill limits are changed.
6. Miscellaneous changes to a few subsections.

All the above changes are already present in the upstream documentation, the link
for which is mentioned below under the "Document URL" section.


Document URL:
https://docs.ceph.com/en/quincy/rados/configuration/mclock-config-ref/

Additional information:
The upstream documentation can be used as reference to modify the affected sections in the downstream documentation. I can provide additional inputs when necessary.

Comment 1 RHEL Program Management 2023-05-19 17:28:22 UTC

Please specify the severity of this bug. Severity is defined here:
https://bugzilla.redhat.com/page.cgi?id=fields.html#bug_severity.

Comment 10 Manisha Saini 2023-06-05 18:55:30 UTC

Thanks Akash for fixing this.

Clearing the needinfo on my name as Sridhar will be verifying this BZ