Project

General

Profile

Actions

Bug #20594

closed

mds: cache limits should be expressed in memory usage, not inode count

Added by Patrick Donnelly almost 7 years ago. Updated over 6 years ago.

Status:
Resolved
Priority:
Urgent
Category:
Performance/Resource Usage
Target version:
% Done:

0%

Source:
Development
Tags:
Backport:
luminous
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(FS):
MDS
Labels (FS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

Cached inode count (mds_cache_size) is an imperfect limit for what we really want. We frequently have to tell users/customers to tune this based on the amount of memory they want to consume for the MDS which is unacceptable.

Instead, use mempools with the cached objects to track memory usage and limit based on that.

BZ: https://bugzilla.redhat.com/show_bug.cgi?id=1464976


Related issues 5 (2 open3 closed)

Related to CephFS - Feature #4504: mds: trim based on total memory usageResolved03/19/2013

Actions
Related to CephFS - Feature #4502: mds: Make the MemoryModel usefulNew03/19/2013

Actions
Related to CephFS - Bug #21402: mds: move remaining containers in CDentry/CDir/CInode to mempoolResolvedPatrick Donnelly09/15/2017

Actions
Related to CephFS - Feature #36663: mds: adjust cache memory limit automatically via target that tracks RSSIn ProgressSidharth Anupkrishnan

Actions
Copied to CephFS - Backport #21384: luminous: mds: cache limits should be expressed in memory usage, not inode countResolvedPatrick DonnellyActions
Actions

Also available in: Atom PDF