From 4ba36e9593b4d00fbd8130eaf87b86c9442ac23c Mon Sep 17 00:00:00 2001
From: =?utf8?q?S=C3=A9bastien=20Han?= <seb@redhat.com>
Date: Mon, 18 Dec 2017 16:43:37 +0100
Subject: [PATCH] osd: best effort if no device is found during activation
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

We have a scenario when we switch from non-container to containers. This
means we don't know anything about the ceph partitions associated to an
OSD. Normally in a containerized context we have files containing the
preparation sequence. From these files we can get the capabilities of
each OSD. As a last resort we use a ceph-disk call inside a dummy bash
container to discover the ceph journal on the current osd.

Closes: https://bugzilla.redhat.com/show_bug.cgi?id=1525612
Signed-off-by: Sébastien Han <seb@redhat.com>
(cherry picked from commit bbc79765f3e8b93b707b0f25f94e975c1bd85c66)
Signed-off-by: Sébastien Han <seb@redhat.com>
---
 roles/ceph-osd/templates/ceph-osd-run.sh.j2 | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/roles/ceph-osd/templates/ceph-osd-run.sh.j2 b/roles/ceph-osd/templates/ceph-osd-run.sh.j2
index 6651eb6b0..7778896eb 100644
--- a/roles/ceph-osd/templates/ceph-osd-run.sh.j2
+++ b/roles/ceph-osd/templates/ceph-osd-run.sh.j2
@@ -1,6 +1,7 @@
 #!/bin/bash
 # {{ ansible_managed }}
 
+DOCKER_ENV=""
 
 #############
 # FUNCTIONS #
@@ -27,11 +28,23 @@ function expose_partitions {
   fi
   if [[ -f {{ ceph_osd_docker_run_script_path }}/ceph-osd-prepare-{{ ansible_hostname }}-devdev${1}.log ]]; then
     part=$(grep "Journal is GPT partition" {{ ceph_osd_docker_run_script_path }}/ceph-osd-prepare-{{ ansible_hostname }}-devdev${1}.log | grep -Eo /dev/disk/by-partuuid/${REGEX} | uniq)
-    DOCKER_ENV="$DOCKER_ENV -e OSD_JOURNAL=$part"
+    DOCKER_ENV="-e OSD_JOURNAL=$part"
   fi
   if [[ -f {{ ceph_osd_docker_run_script_path }}/ceph-osd-prepare-{{ ansible_hostname }}-${1}.log ]]; then
     part=$(grep "Journal is GPT partition" {{ ceph_osd_docker_run_script_path }}/ceph-osd-prepare-{{ ansible_hostname }}-${1}.log | grep -Eo /dev/disk/by-partuuid/${REGEX} | uniq)
-    DOCKER_ENV="$DOCKER_ENV -e OSD_JOURNAL=$part"
+    DOCKER_ENV="-e OSD_JOURNAL=$part"
+  fi
+  if [[ -z $DOCKER_ENV ]]; then
+    # NOTE(leseb): if we arrive here this probably means we just switched from non-containers to containers.
+    # This is tricky as we don't have any info on the type of OSD, this is 'only' a problem for non-collocated scenarios
+    # We can't assume that the 'ceph' is still present so calling Docker exec instead
+    part=$(docker run --privileged=true -v /dev:/dev --entrypoint /usr/sbin/ceph-disk {{ ceph_docker_registry}}/{{ ceph_docker_image }}:{{ ceph_docker_image_tag }} list /dev/${1} | awk '/journal / {print $1}')
+    DOCKER_ENV="-e OSD_JOURNAL=$part"
+  fi
+  # if empty, the previous command didn't find anything so we fail
+  if [[ -z $DOCKER_ENV ]]; then
+    echo "ERROR: could not discover ceph partitions"
+    exit 1
   fi
 }
 {% endif -%}
-- 
2.39.5