Adding upstream version 14.2.21.upstream/14.2.21upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

40 files changed, 1195 insertions, 0 deletions

diff --git a/qa/suites/rados/singleton/all/.qa b/qa/suites/rados/singleton/all/.qa
new file mode 120000
index 00000000..a602a035
--- /dev/null
+++ b/qa/suites/rados/singleton/all/.qa
@@ -0,0 +1 @@
+../.qa/
\ No newline at end of file
diff --git a/qa/suites/rados/singleton/all/admin-socket.yaml b/qa/suites/rados/singleton/all/admin-socket.yaml
new file mode 100644
index 00000000..13af8131
--- /dev/null
+++ b/qa/suites/rados/singleton/all/admin-socket.yaml
@@ -0,0 +1,26 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - client.a
+openstack:
+  - volumes: # attached to each instance
+      count: 2
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+- admin_socket:
+    osd.0:
+      version:
+      git_version:
+      help:
+      config show:
+      config help:
+      config set filestore_dump_file /tmp/foo:
+      perf dump:
+      perf schema:
+      get_heap_property tcmalloc.max_total_thread_cache_byte:
+      set_heap_property tcmalloc.max_total_thread_cache_bytes 67108864:
+      set_heap_property tcmalloc.max_total_thread_cache_bytes 33554432:
diff --git a/qa/suites/rados/singleton/all/deduptool.yaml b/qa/suites/rados/singleton/all/deduptool.yaml
new file mode 100644
index 00000000..f2c54f1a
--- /dev/null
+++ b/qa/suites/rados/singleton/all/deduptool.yaml
@@ -0,0 +1,26 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 2
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+    - but it is still running
+    - had wrong client addr
+    - had wrong cluster addr
+    - reached quota
+    - overall HEALTH_
+    - \(POOL_FULL\)
+    - \(POOL_APP_NOT_ENABLED\)
+- workunit:
+    clients:
+      all:
+        - rados/test_dedup_tool.sh
diff --git a/qa/suites/rados/singleton/all/divergent_priors.yaml b/qa/suites/rados/singleton/all/divergent_priors.yaml
new file mode 100644
index 00000000..743d73d4
--- /dev/null
+++ b/qa/suites/rados/singleton/all/divergent_priors.yaml
@@ -0,0 +1,26 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+
+overrides:
+  ceph:
+    log-whitelist:
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_
+      - \(POOL_APP_NOT_ENABLED\)
+
+tasks:
+- install:
+- ceph:
+- divergent_priors:
diff --git a/qa/suites/rados/singleton/all/divergent_priors2.yaml b/qa/suites/rados/singleton/all/divergent_priors2.yaml
new file mode 100644
index 00000000..2da2c466
--- /dev/null
+++ b/qa/suites/rados/singleton/all/divergent_priors2.yaml
@@ -0,0 +1,26 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+
+overrides:
+  ceph:
+    log-whitelist:
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_
+      - \(POOL_APP_NOT_ENABLED\)
+
+tasks:
+- install:
+- ceph:
+- divergent_priors2:
diff --git a/qa/suites/rados/singleton/all/dump-stuck.yaml b/qa/suites/rados/singleton/all/dump-stuck.yaml
new file mode 100644
index 00000000..59085ffa
--- /dev/null
+++ b/qa/suites/rados/singleton/all/dump-stuck.yaml
@@ -0,0 +1,19 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+openstack:
+  - volumes: # attached to each instance
+      count: 2
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - but it is still running
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+- dump_stuck:
diff --git a/qa/suites/rados/singleton/all/ec-lost-unfound.yaml b/qa/suites/rados/singleton/all/ec-lost-unfound.yaml
new file mode 100644
index 00000000..aeb4b278
--- /dev/null
+++ b/qa/suites/rados/singleton/all/ec-lost-unfound.yaml
@@ -0,0 +1,26 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - osd.3
+openstack:
+  - volumes: # attached to each instance
+      count: 4
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - objects unfound and apparently lost
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_
+      - \(SLOW_OPS\)
+      - slow request
+- ec_lost_unfound:
diff --git a/qa/suites/rados/singleton/all/erasure-code-nonregression.yaml b/qa/suites/rados/singleton/all/erasure-code-nonregression.yaml
new file mode 100644
index 00000000..e8201ee0
--- /dev/null
+++ b/qa/suites/rados/singleton/all/erasure-code-nonregression.yaml
@@ -0,0 +1,17 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- workunit:
+    clients:
+      all:
+        - erasure-code/encode-decode-non-regression.sh
diff --git a/qa/suites/rados/singleton/all/lost-unfound-delete.yaml b/qa/suites/rados/singleton/all/lost-unfound-delete.yaml
new file mode 100644
index 00000000..636cb944
--- /dev/null
+++ b/qa/suites/rados/singleton/all/lost-unfound-delete.yaml
@@ -0,0 +1,25 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - objects unfound and apparently lost
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_
+      - \(SLOW_OPS\)
+      - slow request
+- rep_lost_unfound_delete:
diff --git a/qa/suites/rados/singleton/all/lost-unfound.yaml b/qa/suites/rados/singleton/all/lost-unfound.yaml
new file mode 100644
index 00000000..2f60db16
--- /dev/null
+++ b/qa/suites/rados/singleton/all/lost-unfound.yaml
@@ -0,0 +1,25 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - objects unfound and apparently lost
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_
+      - \(SLOW_OPS\)
+      - slow request
+- lost_unfound:
diff --git a/qa/suites/rados/singleton/all/max-pg-per-osd.from-mon.yaml b/qa/suites/rados/singleton/all/max-pg-per-osd.from-mon.yaml
new file mode 100644
index 00000000..b8a7feae
--- /dev/null
+++ b/qa/suites/rados/singleton/all/max-pg-per-osd.from-mon.yaml
@@ -0,0 +1,27 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+openstack:
+  - volumes: # attached to each instance
+      count: 2
+      size: 10 # GB
+overrides:
+  ceph:
+    create_rbd_pool: False
+    conf:
+      mon:
+        osd pool default size: 2
+      osd:
+        mon max pg per osd : 2
+        osd max pg per osd hard ratio : 1
+    log-whitelist:
+      - \(TOO_FEW_PGS\)
+      - \(PENDING_CREATING_PGS\)
+tasks:
+- install:
+- ceph:
+- osd_max_pg_per_osd:
+    test_create_from_mon: True
+    pg_num: 2
diff --git a/qa/suites/rados/singleton/all/max-pg-per-osd.from-primary.yaml b/qa/suites/rados/singleton/all/max-pg-per-osd.from-primary.yaml
new file mode 100644
index 00000000..8ffc9a31
--- /dev/null
+++ b/qa/suites/rados/singleton/all/max-pg-per-osd.from-primary.yaml
@@ -0,0 +1,32 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - osd.3
+openstack:
+  - volumes: # attached to each instance
+      count: 4
+      size: 10 # GB
+overrides:
+  ceph:
+    create_rbd_pool: False
+    conf:
+      mon:
+        osd pool default size: 2
+      osd:
+        mon max pg per osd : 1
+        osd max pg per osd hard ratio : 1
+    log-whitelist:
+      - \(TOO_FEW_PGS\)
+      - \(PG_
+      - \(PENDING_CREATING_PGS\)
+tasks:
+- install:
+- ceph:
+- osd_max_pg_per_osd:
+    test_create_from_mon: False
+    pg_num: 1
+    pool_size: 2
+    from_primary: True
diff --git a/qa/suites/rados/singleton/all/max-pg-per-osd.from-replica.yaml b/qa/suites/rados/singleton/all/max-pg-per-osd.from-replica.yaml
new file mode 100644
index 00000000..8da365dd
--- /dev/null
+++ b/qa/suites/rados/singleton/all/max-pg-per-osd.from-replica.yaml
@@ -0,0 +1,32 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - osd.3
+openstack:
+  - volumes: # attached to each instance
+      count: 4
+      size: 10 # GB
+overrides:
+  ceph:
+    create_rbd_pool: False
+    conf:
+      mon:
+        osd pool default size: 2
+      osd:
+        mon max pg per osd : 1
+        osd max pg per osd hard ratio : 1
+    log-whitelist:
+      - \(TOO_FEW_PGS\)
+      - \(PG_
+      - \(PENDING_CREATING_PGS\)
+tasks:
+- install:
+- ceph:
+- osd_max_pg_per_osd:
+    test_create_from_mon: False
+    pg_num: 1
+    pool_size: 2
+    from_primary: False
diff --git a/qa/suites/rados/singleton/all/mon-auth-caps.yaml b/qa/suites/rados/singleton/all/mon-auth-caps.yaml
new file mode 100644
index 00000000..ae4a5d2e
--- /dev/null
+++ b/qa/suites/rados/singleton/all/mon-auth-caps.yaml
@@ -0,0 +1,17 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+    - overall HEALTH_
+    - \(AUTH_BAD_CAPS\)
+- workunit:
+    clients:
+      all:
+        - mon/auth_caps.sh
diff --git a/qa/suites/rados/singleton/all/mon-config-key-caps.yaml b/qa/suites/rados/singleton/all/mon-config-key-caps.yaml
new file mode 100644
index 00000000..0b0b95c5
--- /dev/null
+++ b/qa/suites/rados/singleton/all/mon-config-key-caps.yaml
@@ -0,0 +1,17 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+    - overall HEALTH_
+    - \(AUTH_BAD_CAPS\)
+- workunit:
+    clients:
+      all:
+        - mon/test_config_key_caps.sh
diff --git a/qa/suites/rados/singleton/all/mon-config-keys.yaml b/qa/suites/rados/singleton/all/mon-config-keys.yaml
new file mode 100644
index 00000000..7bb4f650
--- /dev/null
+++ b/qa/suites/rados/singleton/all/mon-config-keys.yaml
@@ -0,0 +1,20 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+- workunit:
+    clients:
+      all:
+        - mon/test_mon_config_key.py
diff --git a/qa/suites/rados/singleton/all/mon-config.yaml b/qa/suites/rados/singleton/all/mon-config.yaml
new file mode 100644
index 00000000..2d9de8bb
--- /dev/null
+++ b/qa/suites/rados/singleton/all/mon-config.yaml
@@ -0,0 +1,20 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+- workunit:
+    clients:
+      all:
+        - mon/config.sh
diff --git a/qa/suites/rados/singleton/all/mon-memory-target-compliance.yaml.disabled b/qa/suites/rados/singleton/all/mon-memory-target-compliance.yaml.disabled
new file mode 100644
index 00000000..7f9dd495
--- /dev/null
+++ b/qa/suites/rados/singleton/all/mon-memory-target-compliance.yaml.disabled
@@ -0,0 +1,152 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - osd.3
+  - osd.4
+  - osd.5
+  - osd.6
+  - osd.7
+  - osd.8
+  - osd.9
+  - osd.10
+  - osd.11
+  - osd.12
+  - osd.13
+  - osd.14
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 4
+      size: 1 # GB
+overrides:
+  ceph:
+    conf:
+      mon:
+        mon memory target: 134217728 # reduced to 128_M
+        rocksdb cache size: 67108864 # reduced to 64_M
+        mon osd cache size: 100000
+        mon osd cache size min: 134217728
+      osd:
+        osd memory target: 1610612736 # reduced to 1.5_G
+        osd objectstore: bluestore
+        debug bluestore: 20
+        osd scrub min interval: 60
+        osd scrub max interval: 120
+        osd max backfills: 9
+
+tasks:
+- install:
+    branch: wip-sseshasa2-testing-2019-07-30-1825 # change as appropriate
+- ceph:
+    create_rbd_pool: false
+    log-whitelist:
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(POOL_
+      - \(CACHE_POOL_
+      - \(OBJECT_
+      - \(SLOW_OPS\)
+      - \(REQUEST_SLOW\)
+      - \(TOO_FEW_PGS\)
+      - slow request
+- interactive:
+- parallel:
+    - log-mon-rss
+    - stress-tasks
+    - benchload
+- exec:
+    client.0:
+      - "ceph_test_mon_memory_target 134217728" # mon memory target
+      - "ceph_test_mon_rss_usage 134217728"
+log-mon-rss:
+- background_exec:
+    client.0:
+      - while true
+      - do /usr/bin/ceph_test_log_rss_usage ceph-mon >> /var/log/ceph/ceph-mon-rss-usage.log
+      - sleep 300 # log rss usage every 5 mins. May be modified accordingly
+      - done
+- exec:
+    client.0:
+      - sleep 37860 # sum total of the radosbench test times below plus 60 secs
+benchload: # The total radosbench test below translates to 10.5 hrs
+- full_sequential:
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+  - radosbench:
+      clients: [client.0]
+      time: 1800
+stress-tasks:
+- thrashosds:
+    op_delay: 1
+    bdev_inject_crash: 1
+    bdev_inject_crash_probability: .8
+    chance_down: 80
+    chance_pgnum_grow: 3
+    chance_pgpnum_fix: 1
+    chance_thrash_cluster_full: 0
+    chance_thrash_pg_upmap: 3
+    chance_thrash_pg_upmap_items: 3
+    min_in: 2
diff --git a/qa/suites/rados/singleton/all/osd-backfill.yaml b/qa/suites/rados/singleton/all/osd-backfill.yaml
new file mode 100644
index 00000000..5b374071
--- /dev/null
+++ b/qa/suites/rados/singleton/all/osd-backfill.yaml
@@ -0,0 +1,26 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - but it is still running
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_
+    conf:
+      osd:
+        osd min pg log entries: 5
+- osd_backfill:
diff --git a/qa/suites/rados/singleton/all/osd-recovery-incomplete.yaml b/qa/suites/rados/singleton/all/osd-recovery-incomplete.yaml
new file mode 100644
index 00000000..ed5b216b
--- /dev/null
+++ b/qa/suites/rados/singleton/all/osd-recovery-incomplete.yaml
@@ -0,0 +1,28 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - osd.3
+openstack:
+  - volumes: # attached to each instance
+      count: 4
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - but it is still running
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_
+    conf:
+      osd:
+        osd min pg log entries: 5
+        osd_fast_fail_on_connection_refused: false
+- osd_recovery.test_incomplete_pgs:
diff --git a/qa/suites/rados/singleton/all/osd-recovery.yaml b/qa/suites/rados/singleton/all/osd-recovery.yaml
new file mode 100644
index 00000000..d937a8db
--- /dev/null
+++ b/qa/suites/rados/singleton/all/osd-recovery.yaml
@@ -0,0 +1,30 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - but it is still running
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_DEGRADED\)
+      - \(SLOW_OPS\)
+      - slow request
+    conf:
+      osd:
+        osd min pg log entries: 5
+        osd pg log trim min: 0
+        osd_fast_fail_on_connection_refused: false
+- osd_recovery:
diff --git a/qa/suites/rados/singleton/all/peer.yaml b/qa/suites/rados/singleton/all/peer.yaml
new file mode 100644
index 00000000..645034a4
--- /dev/null
+++ b/qa/suites/rados/singleton/all/peer.yaml
@@ -0,0 +1,25 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    config:
+      global:
+        osd pool default min size : 1
+    log-whitelist:
+      - objects unfound and apparently lost
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+- peer:
diff --git a/qa/suites/rados/singleton/all/pg-autoscaler-progress-off.yaml b/qa/suites/rados/singleton/all/pg-autoscaler-progress-off.yaml
new file mode 100644
index 00000000..2784b7e3
--- /dev/null
+++ b/qa/suites/rados/singleton/all/pg-autoscaler-progress-off.yaml
@@ -0,0 +1,42 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - osd.3
+  - client.0
+- - mon.b
+  - mon.c
+  - osd.4
+  - osd.5
+  - osd.6
+  - osd.7
+openstack:
+  - volumes: # attached to each instance
+      count: 4
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    create_rbd_pool: false
+    log-whitelist:
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(POOL_
+      - \(CACHE_POOL_
+      - \(OBJECT_
+      - \(SLOW_OPS\)
+      - \(REQUEST_SLOW\)
+      - \(TOO_FEW_PGS\)
+      - slow request
+- exec:
+    client.0:
+    - ceph progress off
+
+- workunit:
+    clients:
+      all:
+        - mon/pg_autoscaler.sh
diff --git a/qa/suites/rados/singleton/all/pg-autoscaler.yaml b/qa/suites/rados/singleton/all/pg-autoscaler.yaml
new file mode 100644
index 00000000..72e18d52
--- /dev/null
+++ b/qa/suites/rados/singleton/all/pg-autoscaler.yaml
@@ -0,0 +1,38 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - osd.3
+  - client.0
+- - mon.b
+  - mon.c
+  - osd.4
+  - osd.5
+  - osd.6
+  - osd.7
+openstack:
+  - volumes: # attached to each instance
+      count: 4
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    create_rbd_pool: false
+    log-whitelist:
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(POOL_
+      - \(CACHE_POOL_
+      - \(OBJECT_
+      - \(SLOW_OPS\)
+      - \(REQUEST_SLOW\)
+      - \(TOO_FEW_PGS\)
+      - slow request
+- workunit:
+    clients:
+      all:
+        - mon/pg_autoscaler.sh
diff --git a/qa/suites/rados/singleton/all/pg-removal-interruption.yaml b/qa/suites/rados/singleton/all/pg-removal-interruption.yaml
new file mode 100644
index 00000000..3ada5518
--- /dev/null
+++ b/qa/suites/rados/singleton/all/pg-removal-interruption.yaml
@@ -0,0 +1,34 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - but it is still running
+      - slow request
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+- exec:
+    client.0:
+      - sudo ceph osd pool create foo 128 128
+      - sudo ceph osd pool application enable foo rados
+      - sleep 5
+      - sudo ceph tell osd.0 injectargs -- --osd-inject-failure-on-pg-removal
+      - sudo ceph osd pool delete foo foo --yes-i-really-really-mean-it
+- ceph.wait_for_failure: [osd.0]
+- exec:
+    client.0:
+      - sudo ceph osd down 0
+- ceph.restart: [osd.0]
+- ceph.healthy:
diff --git a/qa/suites/rados/singleton/all/radostool.yaml b/qa/suites/rados/singleton/all/radostool.yaml
new file mode 100644
index 00000000..18277953
--- /dev/null
+++ b/qa/suites/rados/singleton/all/radostool.yaml
@@ -0,0 +1,26 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 2
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+    - but it is still running
+    - had wrong client addr
+    - had wrong cluster addr
+    - reached quota
+    - overall HEALTH_
+    - \(POOL_FULL\)
+    - \(POOL_APP_NOT_ENABLED\)
+- workunit:
+    clients:
+      all:
+        - rados/test_rados_tool.sh
diff --git a/qa/suites/rados/singleton/all/random-eio.yaml b/qa/suites/rados/singleton/all/random-eio.yaml
new file mode 100644
index 00000000..5df910b8
--- /dev/null
+++ b/qa/suites/rados/singleton/all/random-eio.yaml
@@ -0,0 +1,44 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+- - osd.3
+  - osd.4
+  - osd.5
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+    - missing primary copy of
+    - objects unfound and apparently lost
+    - had a read error
+    - overall HEALTH_
+    - \(POOL_APP_NOT_ENABLED\)
+    - \(PG_DEGRADED\)
+    - \(OSD_TOO_MANY_REPAIRS\)
+- full_sequential:
+  - exec:
+      client.0:
+        - sudo ceph tell osd.1 injectargs -- --filestore_debug_random_read_err=0.33
+        - sudo ceph tell osd.1 injectargs -- --bluestore_debug_random_read_err=0.33
+        - sudo ceph osd pool create test 16 16
+        - sudo ceph osd pool set test size 3
+        - sudo ceph pg  dump pgs --format=json-pretty
+  - radosbench:
+      clients: [client.0]
+      time: 360
+      type: rand
+      objectsize: 1048576
+      pool: test
+      create_pool: false
+  - exec:
+      client.0:
+        - sudo ceph tell osd.1 injectargs -- --filestore_debug_random_read_err=0.0
+        - sudo ceph tell osd.1 injectargs -- --bluestore_debug_random_read_err=0.0
diff --git a/qa/suites/rados/singleton/all/rebuild-mondb.yaml b/qa/suites/rados/singleton/all/rebuild-mondb.yaml
new file mode 100644
index 00000000..cc1c6809
--- /dev/null
+++ b/qa/suites/rados/singleton/all/rebuild-mondb.yaml
@@ -0,0 +1,32 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - no reply from
+      - overall HEALTH_
+      - \(MON_DOWN\)
+      - \(MGR_DOWN\)
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+- full_sequential:
+  - radosbench:
+      clients: [client.0]
+      time: 30
+  - rebuild_mondb:
+  - radosbench:
+      clients: [client.0]
+      time: 30
diff --git a/qa/suites/rados/singleton/all/recovery-preemption.yaml b/qa/suites/rados/singleton/all/recovery-preemption.yaml
new file mode 100644
index 00000000..fbf1772c
--- /dev/null
+++ b/qa/suites/rados/singleton/all/recovery-preemption.yaml
@@ -0,0 +1,57 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - osd.3
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 20 # GB
+tasks:
+- install:
+- ceph:
+    conf:
+      osd:
+        osd recovery sleep: .1
+        osd min pg log entries: 10
+        osd max pg log entries: 1000
+        osd pg log trim min: 10
+    log-whitelist:
+      - \(POOL_APP_NOT_ENABLED\)
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(OBJECT_
+      - \(PG_
+      - \(SLOW_OPS\)
+      - overall HEALTH
+      - slow request
+- exec:
+    osd.0:
+      - ceph osd pool create foo 128
+      - ceph osd pool application enable foo foo
+      - sleep 5
+- ceph.healthy:
+- exec:
+    osd.0:
+      - rados -p foo bench 30 write -b 4096 --no-cleanup
+      - ceph osd out 0
+      - sleep 5
+      - ceph osd set noup
+- ceph.restart:
+    daemons: [osd.1]
+    wait-for-up: false
+    wait-for-healthy: false
+- exec:
+    osd.0:
+      - rados -p foo bench 3 write -b 4096 --no-cleanup
+      - ceph osd unset noup
+      - sleep 10
+      - for f in 0 1 2 3 ; do sudo ceph daemon osd.$f config set osd_recovery_sleep 0 ; sudo ceph daemon osd.$f config set osd_recovery_max_active 20 ; done
+- ceph.healthy:
+- exec:
+    osd.0:
+      - egrep '(defer backfill|defer recovery)' /var/log/ceph/ceph-osd.*.log
diff --git a/qa/suites/rados/singleton/all/resolve_stuck_peering.yaml b/qa/suites/rados/singleton/all/resolve_stuck_peering.yaml
new file mode 100644
index 00000000..3eddce82
--- /dev/null
+++ b/qa/suites/rados/singleton/all/resolve_stuck_peering.yaml
@@ -0,0 +1,17 @@
+roles:
+- [mon.a, mgr.x]
+- [osd.0, osd.1, osd.2, client.0]
+
+tasks:
+- install:
+- ceph:
+    fs: xfs
+    log-whitelist:
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_DEGRADED\)
+      - \(POOL_APP_NOT_ENABLED\)
+- resolve_stuck_peering:
+
diff --git a/qa/suites/rados/singleton/all/test-crash.yaml b/qa/suites/rados/singleton/all/test-crash.yaml
new file mode 100644
index 00000000..8002deaa
--- /dev/null
+++ b/qa/suites/rados/singleton/all/test-crash.yaml
@@ -0,0 +1,15 @@
+roles:
+  - [client.0, mon.a, mgr.x, osd.0, osd.1, osd.2]
+
+tasks:
+  - install:
+  - ceph:
+      log-whitelist:
+        - Reduced data availability
+        - OSD_.*DOWN
+        - \(RECENT_CRASH\)
+  - workunit:
+      clients:
+         client.0:
+           - rados/test_crash.sh
+  - ceph.restart: [osd.*]
diff --git a/qa/suites/rados/singleton/all/test_envlibrados_for_rocksdb.yaml b/qa/suites/rados/singleton/all/test_envlibrados_for_rocksdb.yaml
new file mode 100644
index 00000000..42c8ae39
--- /dev/null
+++ b/qa/suites/rados/singleton/all/test_envlibrados_for_rocksdb.yaml
@@ -0,0 +1,19 @@
+overrides:
+  ceph:
+    fs: ext4
+    conf:
+      global:
+        osd max object name len: 460
+        osd max object namespace len: 64
+roles:
+- [mon.a, mgr.x, osd.0, osd.1, osd.2, client.0]
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - overall HEALTH_
+      - \(POOL_APP_NOT_ENABLED\)
+- workunit:
+    clients:
+      all:
+        - rados/test_envlibrados_for_rocksdb.sh
diff --git a/qa/suites/rados/singleton/all/thrash-backfill-full.yaml b/qa/suites/rados/singleton/all/thrash-backfill-full.yaml
new file mode 100644
index 00000000..5cd32bd5
--- /dev/null
+++ b/qa/suites/rados/singleton/all/thrash-backfill-full.yaml
@@ -0,0 +1,50 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+- - osd.3
+  - osd.4
+  - osd.5
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+override:
+  ceph:
+    conf:
+      mon:
+        osd default pool size: 3
+        osd min pg log entries: 5
+        osd max pg log entries: 10
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+    - but it is still running
+    - missing primary copy of
+    - objects unfound and apparently lost
+    - overall HEALTH_
+    - \(OSDMAP_FLAGS\)
+    - \(SLOW_OPS\)
+    - \(PG_
+    - \(OBJECT_MISPLACED\)
+    - \(OSD_
+    - \(OBJECT_
+    - \(TOO_FEW_PGS\)
+    - \(POOL_BACKFILLFULL\)
+    - slow request
+- thrashosds:
+    op_delay: 30
+    clean_interval: 120
+    chance_down: .75
+    min_live: 5
+    min_in: 5
+    chance_test_backfill_full: .5
+- radosbench:
+    clients: [client.0]
+    time: 1800
+    type: rand
+    objectsize: 1048576
diff --git a/qa/suites/rados/singleton/all/thrash-eio.yaml b/qa/suites/rados/singleton/all/thrash-eio.yaml
new file mode 100644
index 00000000..0afb6c86
--- /dev/null
+++ b/qa/suites/rados/singleton/all/thrash-eio.yaml
@@ -0,0 +1,47 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+- - osd.3
+  - osd.4
+  - osd.5
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+override:
+  ceph:
+    conf:
+      mon:
+        osd default pool size: 3
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+    - but it is still running
+    - missing primary copy of
+    - objects unfound and apparently lost
+    - overall HEALTH_
+    - \(OSDMAP_FLAGS\)
+    - \(SLOW_OPS\)
+    - \(PG_
+    - \(OBJECT_MISPLACED\)
+    - \(OSD_
+    - \(OBJECT_
+    - \(TOO_FEW_PGS\)
+    - slow request
+- thrashosds:
+    op_delay: 30
+    clean_interval: 120
+    chance_down: .5
+    random_eio: .33
+    min_live: 5
+    min_in: 5
+- radosbench:
+    clients: [client.0]
+    time: 720
+    type: rand
+    objectsize: 1048576
diff --git a/qa/suites/rados/singleton/all/thrash-rados/+ b/qa/suites/rados/singleton/all/thrash-rados/+
new file mode 100644
index 00000000..e69de29b
--- /dev/null
+++ b/qa/suites/rados/singleton/all/thrash-rados/+
diff --git a/qa/suites/rados/singleton/all/thrash-rados/.qa b/qa/suites/rados/singleton/all/thrash-rados/.qa
new file mode 120000
index 00000000..a602a035
--- /dev/null
+++ b/qa/suites/rados/singleton/all/thrash-rados/.qa
@@ -0,0 +1 @@
+../.qa/
\ No newline at end of file
diff --git a/qa/suites/rados/singleton/all/thrash-rados/thrash-rados.yaml b/qa/suites/rados/singleton/all/thrash-rados/thrash-rados.yaml
new file mode 100644
index 00000000..37be8df9
--- /dev/null
+++ b/qa/suites/rados/singleton/all/thrash-rados/thrash-rados.yaml
@@ -0,0 +1,27 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+- - osd.3
+  - osd.4
+  - osd.5
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - but it is still running
+- thrashosds:
+    op_delay: 30
+    clean_interval: 120
+    chance_down: .5
+- workunit:
+    clients:
+      all:
+      - rados/load-gen-mix-small.sh
diff --git a/qa/suites/rados/singleton/all/thrash-rados/thrashosds-health.yaml b/qa/suites/rados/singleton/all/thrash-rados/thrashosds-health.yaml
new file mode 120000
index 00000000..9124eb1a
--- /dev/null
+++ b/qa/suites/rados/singleton/all/thrash-rados/thrashosds-health.yaml
@@ -0,0 +1 @@
+.qa/tasks/thrashosds-health.yaml
\ No newline at end of file
diff --git a/qa/suites/rados/singleton/all/thrash_cache_writeback_proxy_none.yaml b/qa/suites/rados/singleton/all/thrash_cache_writeback_proxy_none.yaml
new file mode 100644
index 00000000..c0b27075
--- /dev/null
+++ b/qa/suites/rados/singleton/all/thrash_cache_writeback_proxy_none.yaml
@@ -0,0 +1,70 @@
+roles:
+- - mon.a
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+- - osd.3
+  - osd.4
+  - osd.5
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 30 # GB
+tasks:
+- install:
+- ceph:
+    log-whitelist:
+      - but it is still running
+      - slow request
+      - overall HEALTH_
+      - \(CACHE_POOL_
+- exec:
+    client.0:
+      - sudo ceph osd pool create base 4
+      - sudo ceph osd pool application enable base rados
+      - sudo ceph osd pool create cache 4
+      - sudo ceph osd tier add base cache
+      - sudo ceph osd tier cache-mode cache writeback
+      - sudo ceph osd tier set-overlay base cache
+      - sudo ceph osd pool set cache hit_set_type bloom
+      - sudo ceph osd pool set cache hit_set_count 8
+      - sudo ceph osd pool set cache hit_set_period 60
+      - sudo ceph osd pool set cache target_max_objects 500
+- background_exec:
+    mon.a:
+      - while true
+      - do sleep 30
+      - echo proxy
+      - sudo ceph osd tier cache-mode cache proxy
+      - sleep 10
+      - sudo ceph osd pool set cache cache_target_full_ratio .001
+      - echo cache-try-flush-evict-all
+      - rados -p cache cache-try-flush-evict-all
+      - sleep 5
+      - echo cache-flush-evict-all
+      - rados -p cache cache-flush-evict-all
+      - sleep 5
+      - echo remove overlay
+      - sudo ceph osd tier remove-overlay base
+      - sleep 20
+      - echo add writeback overlay
+      - sudo ceph osd tier cache-mode cache writeback
+      - sudo ceph osd pool set cache cache_target_full_ratio .8
+      - sudo ceph osd tier set-overlay base cache
+      - sleep 30
+      - sudo ceph osd tier cache-mode cache readproxy
+      - done
+- rados:
+    clients: [client.0]
+    pools: [base]
+    max_seconds: 600
+    ops: 400000
+    objects: 10000
+    size: 1024
+    op_weights:
+      read: 100
+      write: 100
+      delete: 50
+      copy_from: 50
diff --git a/qa/suites/rados/singleton/all/watch-notify-same-primary.yaml b/qa/suites/rados/singleton/all/watch-notify-same-primary.yaml
new file mode 100644
index 00000000..48ef78ff
--- /dev/null
+++ b/qa/suites/rados/singleton/all/watch-notify-same-primary.yaml
@@ -0,0 +1,32 @@
+roles:
+- - mon.a
+  - mon.b
+  - mon.c
+  - mgr.x
+  - osd.0
+  - osd.1
+  - osd.2
+  - client.0
+openstack:
+  - volumes: # attached to each instance
+      count: 3
+      size: 10 # GB
+tasks:
+- install:
+- ceph:
+    config:
+      global:
+        osd pool default min size : 1
+      client:
+        debug ms: 1
+        debug objecter: 20
+        debug rados: 20
+    log-whitelist:
+      - objects unfound and apparently lost
+      - overall HEALTH_
+      - \(OSDMAP_FLAGS\)
+      - \(OSD_
+      - \(PG_
+      - \(OBJECT_DEGRADED\)
+- watch_notify_same_primary:
+    clients: [client.0]