Project

General

Profile

Fix #7290

Increasing pg_num can hit mon_osd_max_split_count

Added by John Spray over 7 years ago. Updated over 7 years ago.

Status:
Resolved
Priority:
Normal
Assignee:
Category:
Backend (services)
Target version:
% Done:

0%

Source:
other
Tags:
Backport:
Reviewed:
Affected Versions:
ceph-qa-suite:
Crash signature (v1):
Crash signature (v2):

Description

The new calamari 2.0 pool expansion code doesn't take account of mon_osd_max_split_count (because it's a new thing in Firefly and was added after I wrote the code).

This limit (default 32 per OSD) will prevent growing the number of PGs in a pool by more than mon_osd_max_split_count*N_osds in one go: calamari would attempt it but the request would fail.

It would be nicer if Ceph would do some throttling here rather than just disallowing large increments, but it's probably equally easy to do the throttling in calamari as we're already tracking the PG creation process.

Associated revisions

Revision 30e26cab (diff)
Added by John Spray over 7 years ago

cthulhu: Issue multiple smaller PG create commands

This is in order to avoiding hitting the mon_osd_max_split_count
limit introduced in Firefly.

Fixes: #7290

History

#1 Updated by John Spray over 7 years ago

  • Tracker changed from Bug to Fix

#2 Updated by John Spray over 7 years ago

  • Target version changed from v1.2 Backlog to v1.2-dev4

#3 Updated by John Spray over 7 years ago

  • Assignee set to John Spray

#4 Updated by John Spray over 7 years ago

  • Status changed from New to In Progress

#5 Updated by John Spray over 7 years ago

  • Status changed from In Progress to Fix Under Review

#6 Updated by John Spray over 7 years ago

  • Status changed from Fix Under Review to Resolved

Merged at 0f5743308cd25c2198c3957b45d18fdc64fe4bb2

Also available in: Atom PDF