Project

General

Profile

Actions
Copy link

Feature #3760

closed

osd: maintain checksum on collection contents

Added by Samuel Just over 11 years ago. Updated almost 8 years ago.

Status:
Rejected
Priority:
Normal
Assignee:
-
Category:
-
Target version:
-
% Done:

0%

Source:
Tags:
Backport:
Reviewed:
Affected Versions:
Pull request ID:

Description

Currently, there is no way for an OSD to detect erroneously missing objects in a pg collection. A scrub, therefore, if it detects an object present on the primary and missing on the replica does not have a way of knowing which filesystem is in error. One approach would be for the HashIndex mechanism to maintain some form of hash of each subdirectory's contents.

Actions
Copy link
 #1

Updated by Samuel Just over 11 years ago

  • Translation missing: en.field_position set to 38
Actions
Copy link
 #2

Updated by Greg Farnum over 11 years ago

It wasn't clear to me from the description, but we are of course talking about maintaining in the HashIndex a checksum and then comparing that checksum to what we get on some or all collection IO operations to make sure we don't lose anything.

Actions
Copy link
 #3

Updated by Sage Weil almost 8 years ago

  • Status changed from New to Rejected
Actions
Copy link

Also available in: Atom PDF