Project

General

Profile

Actions

Bug #10004

closed

ceph osd find does not correctly report crush locations

Added by Christina Meno over 9 years ago. Updated about 9 years ago.

Status:
Can't reproduce
Priority:
Urgent
Assignee:
Category:
-
Target version:
-
% Done:

0%

Source:
other
Tags:
Backport:
Regression:
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

ubuntu@vpm061:~$ ceph osd find 0
{ "osd": 0,
  "ip": "10.214.138.176:6800\/31684",
  "crush_location": { "host": "vpm113ssd"}}ubuntu@vpm061:~$ 

I expected osd 0 to be found at hosts: vpm113 and vpm113ssd
as seen in the crushmap below.
ubuntu@vpm061:~$ ceph osd crush dump -f json-pretty

{ "devices": [
        { "id": 0,
          "name": "osd.0"},
        { "id": 1,
          "name": "osd.1"},
        { "id": 2,
          "name": "osd.2"}],
  "types": [
        { "type_id": 0,
          "name": "osd"},
        { "type_id": 1,
          "name": "host"},
        { "type_id": 2,
          "name": "chassis"},
        { "type_id": 3,
          "name": "rack"},
        { "type_id": 4,
          "name": "row"},
        { "type_id": 5,
          "name": "pdu"},
        { "type_id": 6,
          "name": "pod"},
        { "type_id": 7,
          "name": "room"},
        { "type_id": 8,
          "name": "datacenter"},
        { "type_id": 9,
          "name": "region"},
        { "type_id": 10,
          "name": "root"}],
  "buckets": [
        { "id": -1,
          "name": "default",
          "type_id": 10,
          "type_name": "root",
          "weight": 19659,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": -2,
                  "weight": 6553,
                  "pos": 0},
                { "id": -3,
                  "weight": 6553,
                  "pos": 1},
                { "id": -4,
                  "weight": 6553,
                  "pos": 2}]},
        { "id": -2,
          "name": "vpm061",
          "type_id": 1,
          "type_name": "host",
          "weight": 6553,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": 1,
                  "weight": 6553,
                  "pos": 0}]},
        { "id": -3,
          "name": "vpm113",
          "type_id": 1,
          "type_name": "host",
          "weight": 6553,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": 0,
                  "weight": 6553,
                  "pos": 0}]},
        { "id": -4,
          "name": "vpm145",
          "type_id": 1,
          "type_name": "host",
          "weight": 6553,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": 2,
                  "weight": 6553,
                  "pos": 0}]},
        { "id": -5,
          "name": "rackthing",
          "type_id": 3,
          "type_name": "rack",
          "weight": 19659,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": -2,
                  "weight": 6553,
                  "pos": 0},
                { "id": -3,
                  "weight": 6553,
                  "pos": 1},
                { "id": -4,
                  "weight": 6553,
                  "pos": 2}]},
        { "id": -10,
          "name": "defaultssd",
          "type_id": 10,
          "type_name": "root",
          "weight": 19659,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": -5,
                  "weight": 19659,
                  "pos": 0}]},
        { "id": -20,
          "name": "vpm061ssd",
          "type_id": 1,
          "type_name": "host",
          "weight": 6553,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": 1,
                  "weight": 6553,
                  "pos": 0}]},
        { "id": -30,
          "name": "vpm113ssd",
          "type_id": 1,
          "type_name": "host",
          "weight": 6553,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": 0,
                  "weight": 6553,
                  "pos": 0}]},
        { "id": -40,
          "name": "vpm145ssd",
          "type_id": 1,
          "type_name": "host",
          "weight": 6553,
          "alg": "straw",
          "hash": "rjenkins1",
          "items": [
                { "id": 2,
                  "weight": 6553,
                  "pos": 0}]}],
  "rules": [
        { "rule_id": 0,
          "rule_name": "replicated_ruleset",
          "ruleset": 0,
          "type": 1,
          "min_size": 1,
          "max_size": 10,
          "steps": [
                { "op": "take",
                  "item": -1,
                  "item_name": "default"},
                { "op": "chooseleaf_firstn",
                  "num": 0,
                  "type": "host"},
                { "op": "emit"}]}],
  "tunables": { "choose_local_tries": 0,
      "choose_local_fallback_tries": 0,
      "choose_total_tries": 50,
      "chooseleaf_descend_once": 1,
      "profile": "bobtail",
      "optimal_tunables": 0,
      "legacy_tunables": 0,
      "require_feature_tunables": 1,
      "require_feature_tunables2": 1}}
Actions #1

Updated by Dan Mick over 9 years ago

Moreover, it's no longer reporting the entire crush branch, but only the immediate parent; that's a change in behavior; although I don't know if it's intentional, it seems less helpful than it might.

regression from dumpling to firefly?

Actions #2

Updated by Samuel Just over 9 years ago

  • Priority changed from Normal to Urgent
Actions #3

Updated by Sage Weil over 9 years ago

What version is this? I can't reproduce it on giant.

Actions #4

Updated by Samuel Just over 9 years ago

  • Assignee set to Sage Weil
Actions #5

Updated by Dan Mick about 9 years ago

I see that current master reports the full location for a test cluster, as does firefly, but I don't have a dual-branch crushmap to test with.

Actions #6

Updated by Sage Weil about 9 years ago

  • Status changed from New to Can't reproduce
Actions

Also available in: Atom PDF