Merge branch 'master' into kjacque/control-cart-fabric

Features: control

src/tests/ftest/container/per_server_fault_domain.yaml

@@ -6,6 +6,7 @@ timeout: 300
 server_config:
  name: daos_server
  engines_per_host: 2
+ crt_timeout: 10
  engines:
  0:
  pinned_numa_node: 0

src/tests/ftest/erasurecode/cell_size_property.yaml

@@ -5,6 +5,7 @@ timeout: 900
 server_config:
  name: daos_server
  engines_per_host: 2
+ crt_timeout: 10
  engines:
  0:
  pinned_numa_node: 0

src/tests/ftest/erasurecode/offline_rebuild.yaml

@@ -15,6 +15,7 @@ setup:
 server_config:
  name: daos_server
  engines_per_host: 2
+ crt_timeout: 10
  engines:
  0:
  pinned_numa_node: 0

src/tests/ftest/erasurecode/rebuild_disabled_single.yaml

@@ -36,7 +36,7 @@ pool:
  pool_query_timeout: 30
 container:
  type: POSIX
- control_method: API
+ control_method: daos
  single_data_set:
  # [object_qty, record_qty, dkey, akey, data_size]
  - [1, 1, 1, 1, 4194304]

src/tests/ftest/rebuild/container_create_race.yaml

@@ -7,6 +7,7 @@ timeout: 360
 server_config:
  name: daos_server
  engines_per_host: 2
+ crt_timeout: 10
  engines:
  0:
  targets: 2

src/tests/ftest/soak/faults.yaml

@@ -120,7 +120,7 @@ ior_faults:
  dfs_oclass:
  - ["EC_2P1GX", "RP_2GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/ior/"
+ mount_dir: "/tmp/soak_dfuse_ior/"
  disable_caching: true
 hdf5_vol:
  plugin_path: "/usr/lib64/mpich/lib"

src/tests/ftest/soak/harassers.yaml

@@ -8,8 +8,7 @@ hosts:
 orterun:
  allow_run_as_root: true
 # This timeout must be longer than the test_timeout param (+15minutes)
-# 12 hour test
-timeout: 12H15M
+timeout: 24H30M
 setup:
  start_servers: true
  start_agents: true
@@ -56,7 +55,7 @@ container:
  daos_timeout: 30
 container_reserved:
  type: POSIX
- properties: cksum:crc16,cksum_size:16384,srv_cksum:on,rd_fac:1
+ properties: cksum:crc16,cksum_size:16384,srv_cksum:on
  file_oclass: SX
  dir_oclass: SX
  control_method: daos
@@ -78,8 +77,8 @@ soak_harassers:
  # harasser test timeout in hours
  single_test_pool: false
  test_timeout:
- test_soak_online_harassers: 12
- test_soak_offline_harassers: 12
+ test_soak_online_harassers: 24
+ test_soak_offline_harassers: 24
  # maximum timeout for a single job in test in minutes
  joblist:
  - ior_harasser
@@ -93,12 +92,14 @@ soak_harassers:
  - server-stop_server-reintegrate-offline
  - extend-pool-offline
  # - vmd-identify-check-offline
+ - reboot_reboot-reintegrate-offline
  test_soak_online_harassers:
  - exclude_reintegrate
  - server-stop_server-start
  - server-stop_server-reintegrate
  - extend-pool
  # - vmd-identify-check
+ - reboot_reboot-reintegrate
  harasser_to: 1200
  # drain rank from all pools before stopping server
  enable_drain: true
@@ -140,7 +141,7 @@ ior_harasser:
  - ["EC_2P1GX", "RP_2GX"]
  - ["EC_4P2GX", "RP_3GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/ior"
+ mount_dir: "/tmp/soak_dfuse_ior"
  disable_caching: true
 fio_harasser:
  api:
@@ -150,7 +151,7 @@ fio_harasser:
  - global
  - test
  global:
- directory: "/tmp/daos_dfuse/fio/"
+ directory: "/tmp/soak_dfuse_fio/"
  ioengine: 'libaio'
  thread: 1
  group_reporting: 1
@@ -172,7 +173,7 @@ fio_harasser:
  - ["EC_2P1GX", "RP_2GX"]
  - ["EC_4P2GX", "RP_3GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/fio/"
+ mount_dir: "/tmp/soak_dfuse_fio/"
  disable_caching: true
 mdtest_harasser:
  # maximum timeout for a single job in test in minutes
@@ -204,7 +205,7 @@ mdtest_harasser:
  - ["EC_4P2G1", "RP_3G1"]
  dfs_destroy: false
  dfuse:
- mount_dir: "/tmp/daos_dfuse/mdtest/"
+ mount_dir: "/tmp/soak_dfuse_mdtest/"
  disable_caching: true
 hdf5_vol:
  plugin_path: "/usr/lib64/mpich/lib"

src/tests/ftest/soak/smoke.yaml

@@ -120,7 +120,7 @@ ior_smoke:
  dfs_oclass:
  - ["EC_2P1GX", "RP_2GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/ior/"
+ mount_dir: "/tmp/soak_dfuse_ior/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -134,7 +134,7 @@ fio_smoke:
  - global
  - test
  global:
- directory: "/tmp/daos_dfuse/fio/"
+ directory: "/tmp/soak_dfuse_fio/"
  ioengine: 'libaio'
  thread: 1
  group_reporting: 1
@@ -155,7 +155,7 @@ fio_smoke:
  oclass:
  - ["EC_2P1GX", "RP_2GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/fio/"
+ mount_dir: "/tmp/soak_dfuse_fio/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -172,9 +172,9 @@ vpic_smoke:
  - POSIX
  - POSIX-LIBIOIL
  - POSIX-LIBPIL4DFS
- workdir: "/tmp/daos_dfuse/vpic/"
+ workdir: "/tmp/soak_dfuse_vpic/"
  dfuse:
- mount_dir: "/tmp/daos_dfuse/vpic/"
+ mount_dir: "/tmp/soak_dfuse_vpic/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -191,9 +191,9 @@ lammps_smoke:
  - POSIX
  - POSIX-LIBIOIL
  - POSIX-LIBPIL4DFS
- workdir: "/tmp/daos_dfuse/lammps/"
+ workdir: "/tmp/soak_dfuse_lammps/"
  dfuse:
- mount_dir: "/tmp/daos_dfuse/lammps/"
+ mount_dir: "/tmp/soak_dfuse_lammps/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -226,7 +226,7 @@ mdtest_smoke:
  - ["EC_2P1G1", "RP_2G1"]
  dfs_destroy: false
  dfuse:
- mount_dir: "/tmp/daos_dfuse/mdtest/"
+ mount_dir: "/tmp/soak_dfuse_mdtest/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -250,7 +250,7 @@ macsio_smoke:
  oclass:
  - ["EC_2P1GX", "RP_2GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/macsio/"
+ mount_dir: "/tmp/soak_dfuse_macsio/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'

src/tests/ftest/soak/stress.yaml

@@ -134,7 +134,7 @@ ior_stress:
  # - ["EC_8P2G1", "RP_3GX"]
  # - ["EC_16P2GX", "RP_3GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/ior/"
+ mount_dir: "/tmp/soak_dfuse_ior/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -149,7 +149,7 @@ fio_stress:
  - test
  global:
  create_serialize: 0
- directory: "/tmp/daos_dfuse/fio/"
+ directory: "/tmp/soak_dfuse_fio/"
  ioengine: 'libaio'
  thread: 1
  group_reporting: 1
@@ -176,7 +176,7 @@ fio_stress:
  # - ["EC_8P2G1", "RP_3GX"]
  # - ["EC_16P2GX", "RP_3GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/fio/"
+ mount_dir: "/tmp/soak_dfuse_fio/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -194,9 +194,9 @@ vpic_stress:
  - POSIX
  - POSIX-LIBIOIL
  - POSIX-LIBPIL4DFS
- workdir: "/tmp/daos_dfuse/vpic/"
+ workdir: "/tmp/soak_dfuse_vpic/"
  dfuse:
- mount_dir: "/tmp/daos_dfuse/vpic/"
+ mount_dir: "/tmp/soak_dfuse_vpic/"
  disable_caching: true
  oclass:
  - ["EC_2P1GX", "RP_2GX"]
@@ -211,9 +211,9 @@ lammps_stress:
  - POSIX
  - POSIX-LIBIOIL
  - POSIX-LIBPIL4DFS
- workdir: "/tmp/daos_dfuse/lammps/"
+ workdir: "/tmp/soak_dfuse_lammps/"
  dfuse:
- mount_dir: "/tmp/daos_dfuse/lammps/"
+ mount_dir: "/tmp/soak_dfuse_lammps/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -254,7 +254,7 @@ mdtest_stress:
  # - ["EC_16P2G1", "RP_3G1"]
  dfs_destroy: false
  dfuse:
- mount_dir: "/tmp/daos_dfuse/mdtest/"
+ mount_dir: "/tmp/soak_dfuse_mdtest/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
@@ -285,18 +285,15 @@ macsio_stress:
  # - ["EC_8P2G1", "RP_3GX"]
  # - ["EC_16P2GX", "RP_3GX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/macsio/"
+ mount_dir: "/tmp/soak_dfuse_macsio/"
  disable_caching: true
  thread_count: 8
  cores: '0-7'
 datamover_stress:
  job_timeout: 10
  nodesperjob:
- - 1
- - 4
  - 8
  taskspernode:
- - 16
  - 32
  oclass:
  - ["SX","SX"]

src/tests/ftest/soak/stress_2h.yaml

@@ -97,7 +97,7 @@ ior_stress:
  dfs_oclass:
  - ["SX","SX"]
  dfuse:
- mount_dir: "/tmp/daos_dfuse/ior/"
+ mount_dir: "/tmp/soak_dfuse_ior/"
  disable_caching: true
 mdtest_stress:
  # maximum timeout for a single job in test in minutes
@@ -124,7 +124,7 @@ mdtest_stress:
  - ["S1","S1"]
  dfs_destroy: false
  dfuse:
- mount_dir: "/tmp/daos_dfuse/mdtest/"
+ mount_dir: "/tmp/soak_dfuse_mdtest/"
  disable_caching: true
 vpic_stress:
  job_timeout: 20
@@ -134,9 +134,9 @@ vpic_stress:
  - 16
  cmdline: "/var/hit/daos/builds/vpic-install/bin/harris.Linux"
  posix: true
- workdir: "/tmp/daos_dfuse/vpic/"
+ workdir: "/tmp/soak_dfuse_vpic/"
  dfuse:
- mount_dir: "/tmp/daos_dfuse/vpic/"
+ mount_dir: "/tmp/soak_dfuse_vpic/"
  disable_caching: true
  oclass:
  - ["SX","SX"]
@@ -148,9 +148,9 @@ lammps_stress:
  - 16
  cmdline: "/var/hit/daos/builds/lammps/src/lmp_mpi -i /var/hit/daos/builds/lammps/bench/in.lj"
  posix: true
- workdir: "/tmp/daos_dfuse/lammps/"
+ workdir: "/tmp/soak_dfuse_lammps/"
  dfuse:
- mount_dir: "/tmp/daos_dfuse/lammps/"
+ mount_dir: "/tmp/soak_dfuse_lammps/"
  disable_caching: true
  oclass:
  - ["SX","SX"]

src/tests/ftest/util/ec_utils.py

@@ -1,5 +1,5 @@
 """
- (C) Copyright 2020-2023 Intel Corporation.
+ (C) Copyright 2020-2024 Intel Corporation.
 
  SPDX-License-Identifier: BSD-2-Clause-Patent
 """
@@ -280,6 +280,10 @@ def ec_container_create(self, oclass):
  oclass (str): object class for creating the container.
  """
  self.container.append(self.get_container(self.pool, create=False, oclass=oclass))
+ if self.container[-1].control_method.value == \
+ self.container[-1].USE_DAOS and self.container[-1].oclass.value:
+ self.container[-1].oclass.update(self.container[-1].oclass.value.replace("OC_", ""),
+ "container.oclass")
 
  # Get the Parity count for setting the container RF property.
  ec_object = get_data_parity_number(self.log, oclass)

src/tests/ftest/util/server_utils.py

@@ -477,7 +477,7 @@ def display_memory_info(self):
  """Display server hosts memory info."""
  self.log.debug("#" * 80)
  self.log.debug("<SERVER> Collection debug memory info")
- run_remote(self.log, self._hosts, "free -m")
+ run_remote(self.log, self._hosts, "free -m && df -h --type=tmpfs")
  run_remote(self.log, self._hosts, "ps -eo size,pid,user,command --sort -size | head -n 6")
  self.log.debug("#" * 80)
 
@@ -720,6 +720,9 @@ def stop(self):
  # Make sure the mount directory belongs to non-root user
  self.set_scm_mount_ownership()
 
+ # Collective memory usage after stop.
+ self.display_memory_info()
+
  # Report any errors after all stop actions have been attempted
  if messages:
  raise ServerFailed("Failed to stop servers:\n {}".format("\n ".join(messages)))