summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--docs/requirements/02-use_cases.rst2
-rw-r--r--docs/requirements/07-annex.rst157
-rwxr-xr-xtests/run.sh30
3 files changed, 95 insertions, 94 deletions
diff --git a/docs/requirements/02-use_cases.rst b/docs/requirements/02-use_cases.rst
index df041e9f..424a3c6e 100644
--- a/docs/requirements/02-use_cases.rst
+++ b/docs/requirements/02-use_cases.rst
@@ -59,7 +59,7 @@ represented as different virtual resources marked by different colors. Consumers
resources (VMs in this example) shown with the same colors.
The first requirement in this use case is that the Controller needs to detect
-faults in the NVFI ("1. Fault Notification" in :numref:`figure1`) affecting
+faults in the NFVI ("1. Fault Notification" in :numref:`figure1`) affecting
the proper functioning of the virtual resources (labelled as VM-x) running on
top of it. It should be possible to configure which relevant fault items should
be detected. The VIM (e.g. OpenStack) itself could be extended to detect such
diff --git a/docs/requirements/07-annex.rst b/docs/requirements/07-annex.rst
index bf65ff7c..8cb19612 100644
--- a/docs/requirements/07-annex.rst
+++ b/docs/requirements/07-annex.rst
@@ -26,99 +26,100 @@ Administrator should be notified. The following tables provide a list of high
level faults that are considered within the scope of the Doctor project
requiring immediate action by the Consumer.
-**Compute Hardware**
+**Compute/Storage**
-+-------------------+----------+------------+-----------------+----------------+
-| Fault | Severity | How to | Comment | Action to |
-| | | detect? | | recover |
-+===================+==========+============+=================+================+
-| Processor/CPU | Critical | Zabbix | | Switch to |
-| failure, CPU | | | | hot standby |
-| condition not ok | | | | |
-+-------------------+----------+------------+-----------------+----------------+
-| Memory failure/ | Critical | Zabbix | | Switch to |
-| Memory condition | | (IPMI) | | hot standby |
-| not ok | | | | |
-+-------------------+----------+------------+-----------------+----------------+
-| Network card | Critical | Zabbix/ | | Switch to |
-| failure, e.g. | | Ceilometer | | hot standby |
-| network adapter | | | | |
-| connectivity lost | | | | |
-+-------------------+----------+------------+-----------------+----------------+
-| Disk crash | Info | RAID | Network storage | Inform OAM |
-| | | monitoring | is very | |
-| | | | redundant (e.g. | |
-| | | | RAID system) | |
-| | | | and can | |
-| | | | guarantee high | |
-| | | | availability | |
-+-------------------+----------+------------+-----------------+----------------+
-| Storage | Critical | Zabbix | | Live migration |
-| controller | | (IPMI) | | if storage |
-| | | | | is still |
-| | | | | accessible; |
-| | | | | otherwise hot |
-| | | | | standby |
-+-------------------+----------+------------+-----------------+----------------+
-| PDU/power | Critical | Zabbix/ | | Switch to |
-| failure, power | | Ceilometer | | hot standby |
-| off, server reset | | | | |
-+-------------------+----------+------------+-----------------+----------------+
-| Power | Warning | SNMP | | Live migration |
-| degration, power | | | | |
-| redundancy lost, | | | | |
-| power threshold | | | | |
-| exceeded | | | | |
-+-------------------+----------+------------+-----------------+----------------+
-| Chassis problem | Warning | SNMP | | Live migration |
-| (e.g. fan | | | | |
-| degraded/failed, | | | | |
-| chassis power | | | | |
-| degraded), CPU | | | | |
-| fan problem, | | | | |
-| temperature/ | | | | |
-| thermal condition | | | | |
-| not ok | | | | |
-+-------------------+----------+------------+-----------------+----------------+
-| Mainboard failure | Critical | Zabbix | | Switch to |
-| | | (IPMI) | | hot standby |
-+-------------------+----------+------------+-----------------+----------------+
-| OS crash (e.g. | Critical | Zabbix | | Switch to |
-| kernel panic) | | | | hot standby |
-+-------------------+----------+------------+-----------------+----------------+
++-------------------+----------+------------+-----------------+------------------+
+| Fault | Severity | How to | Comment | Immediate action |
+| | | detect? | | to recover |
++===================+==========+============+=================+==================+
+| Processor/CPU | Critical | Zabbix | | Switch to hot |
+| failure, CPU | | | | standby |
+| condition not ok | | | | |
++-------------------+----------+------------+-----------------+------------------+
+| Memory failure/ | Critical | Zabbix | | Switch to |
+| Memory condition | | (IPMI) | | hot standby |
+| not ok | | | | |
++-------------------+----------+------------+-----------------+------------------+
+| Network card | Critical | Zabbix/ | | Switch to |
+| failure, e.g. | | Ceilometer | | hot standby |
+| network adapter | | | | |
+| connectivity lost | | | | |
++-------------------+----------+------------+-----------------+------------------+
+| Disk crash | Info | RAID | Network storage | Inform OAM |
+| | | monitoring | is very | |
+| | | | redundant (e.g. | |
+| | | | RAID system) | |
+| | | | and can | |
+| | | | guarantee high | |
+| | | | availability | |
++-------------------+----------+------------+-----------------+------------------+
+| Storage | Critical | Zabbix | | Live migration |
+| controller | | (IPMI) | | if storage |
+| | | | | is still |
+| | | | | accessible; |
+| | | | | otherwise hot |
+| | | | | standby |
++-------------------+----------+------------+-----------------+------------------+
+| PDU/power | Critical | Zabbix/ | | Switch to |
+| failure, power | | Ceilometer | | hot standby |
+| off, server reset | | | | |
++-------------------+----------+------------+-----------------+------------------+
+| Power | Warning | SNMP | | Live migration |
+| degration, power | | | | |
+| redundancy lost, | | | | |
+| power threshold | | | | |
+| exceeded | | | | |
++-------------------+----------+------------+-----------------+------------------+
+| Chassis problem | Warning | SNMP | | Live migration |
+| (e.g. fan | | | | |
+| degraded/failed, | | | | |
+| chassis power | | | | |
+| degraded), CPU | | | | |
+| fan problem, | | | | |
+| temperature/ | | | | |
+| thermal condition | | | | |
+| not ok | | | | |
++-------------------+----------+------------+-----------------+------------------+
+| Mainboard failure | Critical | Zabbix | e.g. PCIe, SAS | Switch to |
+| | | (IPMI) | link failure | hot standby |
++-------------------+----------+------------+-----------------+------------------+
+| OS crash (e.g. | Critical | Zabbix | | Switch to |
+| kernel panic) | | | | hot standby |
++-------------------+----------+------------+-----------------+------------------+
**Hypervisor**
-+----------------+----------+------------+---------+-------------------+
-| Fault | Severity | How to | Comment | Action to |
-| | | detect? | | recover |
-+================+==========+============+=========+===================+
-| System has | Critical | Zabbix | | Switch to |
-| restarted | | | | hot standby |
-+----------------+----------+------------+---------+-------------------+
-| Hypervisor | Warning/ | Zabbix/ | | Evacuation/switch |
-| failure | Critical | Ceilometer | | to hot standby |
-+----------------+----------+------------+---------+-------------------+
-| Zabbix/ | Warning | ? | | Live migration |
-| Ceilometer | | | | |
-| is unreachable | | | | |
-+----------------+----------+------------+---------+-------------------+
++----------------+----------+------------+-------------+-------------------+
+| Fault | Severity | How to | Comment | Immediate action |
+| | | detect? | | to recover |
++================+==========+============+=============+===================+
+| System has | Critical | Zabbix | | Switch to |
+| restarted | | | | hot standby |
++----------------+----------+------------+-------------+-------------------+
+| Hypervisor | Warning/ | Zabbix/ | | Evacuation/switch |
+| failure | Critical | Ceilometer | | to hot standby |
++----------------+----------+------------+-------------+-------------------+
+| Hypervisor | Warning | Alarming | Zabbix/ | Rebuild VM |
+| status not | | service | Ceilometer | |
+| retrievable | | | unreachable | |
+| after certain | | | | |
+| period | | | | |
++----------------+----------+------------+-------------+-------------------+
**Network**
-
+------------------+----------+---------+----------------+---------------------+
-| Fault | Severity | How to | Comment | Action to |
+| Fault | Severity | How to | Comment | Immediate action to |
| | | detect? | | recover |
+==================+==========+=========+================+=====================+
-| SDN/OpenFlow | Critical | ? | | Switch to |
-| switch, | | | | hot standby |
+| SDN/OpenFlow | Critical | Ceilo- | | Switch to |
+| switch, | | meter | | hot standby |
| controller | | | | or reconfigure |
| degraded/failed | | | | virtual network |
| | | | | topology |
+------------------+----------+---------+----------------+---------------------+
| Hardware failure | Warning | SNMP | Redundancy of | Live migration if |
-| of physical | | | physical | possible otherwise |
+| of physical | | | physical | possible otherwise |
| switch/router | | | infrastructure | evacuation |
| | | | is reduced or | |
| | | | no longer | |
diff --git a/tests/run.sh b/tests/run.sh
index 241d6898..56bacca7 100755
--- a/tests/run.sh
+++ b/tests/run.sh
@@ -21,7 +21,7 @@ INSPECTOR_PORT=12345
CONSUMER_PORT=12346
TEST_USER=demo
TEST_PW=demo
-TEST_TENANT=demo
+TEST_PROJECT=demo
TEST_ROLE=_member_
SUPPORTED_INSTALLER_TYPES="apex local"
@@ -89,16 +89,16 @@ register_image() {
}
create_test_user() {
- keystone user-list | grep -q "$TEST_USER" || {
- keystone user-create --name "$TEST_USER" --pass "$TEST_PW"
+ openstack user list | grep -q "$TEST_USER" || {
+ openstack user create "$TEST_USER" --password "$TEST_PW"
}
- keystone tenant-list | grep -q "$TEST_TENANT" || {
- keystone tenant-create --name "$TEST_TENANT"
+ openstack project list | grep -q "$TEST_PROJECT" || {
+ openstack project create "$TEST_PROJECT"
}
- keystone user-role-list --user "$TEST_USER" --tenant "$TEST_TENANT" \
+ openstack user role list "$TEST_USER" --project "$TEST_PROJECT" \
| grep -q "$TEST_ROLE" || {
- keystone user-role-add --user "$TEST_USER" --role "$TEST_ROLE" \
- --tenant "$TEST_TENANT"
+ openstack role add "$TEST_ROLE" --user "$TEST_USER" \
+ --project "$TEST_PROJECT"
}
}
@@ -108,7 +108,7 @@ boot_vm() {
# test VM done with test user, so can test non-admin
export OS_USERNAME="$TEST_USER"
export OS_PASSWORD="$TEST_PW"
- export OS_TENANT_NAME="$TEST_TENANT"
+ export OS_TENANT_NAME="$TEST_PROJECT"
nova boot --flavor "$VM_FLAVOR" \
--image "$IMAGE_NAME" \
"$VM_NAME"
@@ -202,7 +202,7 @@ check_host_status_down() {
# Switching to test user
export OS_USERNAME="$TEST_USER"
export OS_PASSWORD="$TEST_PW"
- export OS_TENANT_NAME="$TEST_TENANT"
+ export OS_TENANT_NAME="$TEST_PROJECT"
host_status_line=$(nova show $VM_NAME | grep "host_status")
[[ $? -ne 0 ]] && {
@@ -226,7 +226,7 @@ cleanup() {
python ./nova_force_down.py "$COMPUTE_HOST" --unset
sleep 1
- nova delete "$VM_NAME"
+ nova list | grep -q " $VM_NAME " && nova delete "$VM_NAME"
sleep 1
alarm_id=$(ceilometer alarm-list | grep " $ALARM_NAME " | awk '{print $2}')
sleep 1
@@ -235,10 +235,10 @@ cleanup() {
image_id=$(glance image-list | grep " $IMAGE_NAME " | awk '{print $2}')
sleep 1
[ -n "$image_id" ] && glance image-delete "$image_id"
- keystone user-role-remove --user "$TEST_USER" --role "$TEST_ROLE" \
- --tenant "$TEST_TENANT"
- keystone tenant-remove --name "$TEST_TENANT"
- keystone user-delete "$TEST_USER"
+ openstack role remove "$TEST_ROLE" --user "$TEST_USER" \
+ --project "$TEST_PROJECT"
+ openstack project delete "$TEST_PROJECT"
+ openstack user delete "$TEST_USER"
#TODO: add host status check via nova admin api
echo "waiting disabled compute host back to be enabled..."