Project

General

Profile

Bug #40159

mds: openfiletable prefetching large amounts of inodes lead to mds start failure

Added by Xuehan Xu about 2 years ago. Updated 5 months ago.

Status:
Fix Under Review
Priority:
Normal
Assignee:
Category:
Performance/Resource Usage
Target version:
% Done:

0%

Source:
Community (dev)
Tags:
Backport:
pacific,octopus,nautilus
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

Recently, we found that both mdses of one of our cluster can't boot to up:active

After debugging, we believe this is due to openfiletable's prefetch phase is forced to load large amounts of "opened" inodes even if their caps are dropped by clients when reconnecting.

History

#1 Updated by Patrick Donnelly about 2 years ago

  • Status changed from New to Fix Under Review
  • Assignee set to Xuehan Xu
  • Start date deleted (06/05/2019)
  • Backport set to nautilus,mimic
  • Pull request ID set to 28401
  • Component(FS) MDS added

#2 Updated by Patrick Donnelly over 1 year ago

  • Target version changed from v15.0.0 to v16.0.0

#3 Updated by Patrick Donnelly 5 months ago

  • Target version changed from v16.0.0 to v17.0.0
  • Backport changed from nautilus,mimic to pacific,octopus,nautilus

Also available in: Atom PDF