start start-microservice raise MicroserviceError("failed to run seldon cli to create conf"+name)

[mullerhai]

when I command

start-microservice --type prediction --client test -i iris-xgboost seldonio/iris_xgboost:2.1 rest 1.0

raise Exception
maybe zookeeper can not normal work

Traceback (most recent call last):
File "/opt/conda/bin/seldon-cli", line 4, in
connecting to zookeeper-1:2181,zookeeper-2:2181,zookeeper-3:2181 [SUCCEEDED]
import('pkg_resources').run_script('seldon==2.2.6', 'seldon-cli')
File "/opt/conda/lib/python2.7/site-packages/setuptools-23.0.0-py2.7.egg/pkg_resources/init.py", line 719, in run_script
File "/opt/conda/lib/python2.7/site-packages/setuptools-23.0.0-py2.7.egg/pkg_resources/init.py", line 1504, in run_script
File "/opt/conda/lib/python2.7/site-packages/seldon-2.2.6-py2.7.egg/EGG-INFO/scripts/seldon-cli", line 5, in
seldon.cli.start_seldoncli()
File "/opt/conda/lib/python2.7/site-packages/seldon-2.2.6-py2.7.egg/seldon/cli/init.py", line 3, in start_seldoncli
cli_main.main()
File "/opt/conda/lib/python2.7/site-packages/seldon-2.2.6-py2.7.egg/seldon/cli/cli_main.py", line 373, in main
cmds[cmd](opts,command_data, command_args)
File "/opt/conda/lib/python2.7/site-packages/seldon-2.2.6-py2.7.egg/seldon/cli/cmd_pred.py", line 203, in cmd_pred
actions[action](command_data, opts)
File "/opt/conda/lib/python2.7/site-packages/seldon-2.2.6-py2.7.egg/seldon/cli/cmd_pred.py", line 158, in action_create
if not is_existing_client(zkroot, client_name):
File "/opt/conda/lib/python2.7/site-packages/seldon-2.2.6-py2.7.egg/seldon/cli/cmd_pred.py", line 64, in is_existing_client
client_names = os.listdir(zkroot + gdata["all_clients_node_path"])
OSError: [Errno 2] No such file or directory: '/seldon-data/conf/zkroot/all_clients'
command terminated with exit code 1
Traceback (most recent call last):
File "/home/muller/Documents/github/seldon-server/kubernetes/bin/start-microservice", line 313, in
runner.run(args.type,args.client,args.i + args.p)
File "/home/muller/Documents/github/seldon-server/kubernetes/bin/start-microservice", line 214, in run
self.predictCreate(client,services)
File "/home/muller/Documents/github/seldon-server/kubernetes/bin/start-microservice", line 203, in predictCreate
raise MicroserviceError("failed to run seldon cli to create conf"+name)
NameError: global name 'name' is not defined

NAME READY STATUS RESTARTS AGE
influxdb-grafana-65fd8f899-x6r2f 2/2 Running 0 21m
kafka-controller-94b9896d9-h8gzv 1/1 Running 0 17m
memcached1-5ccc54f47d-6s99q 1/1 Running 0 21m
memcached2-8d984bb95-52xlw 1/1 Running 0 21m
mysql-c74858654-mqq52 1/1 Running 0 21m
redis-74cf78b489-xlsfq 1/1 Running 0 21m
seldon-control-7594c78659-7pz78 1/1 Running 0 21m
spark-master-controller-7cfb76b44d-hdgvj 0/1 Pending 0 4m
td-agent-server-54bd8d4f58-9xvn5 1/1 Running 0 17m
zookeeper1-7769dc5c48-qvnsv 1/1 Running 0 21m
zookeeper2-6754ddb54b-4qhxc 1/1 Running 0 21m
zookeeper3-6749cd76d4-wd5sk 1/1 Running 0 21m

[root@localhost docker-compost]# kubectl get po
NAME READY STATUS RESTARTS AGE
influxdb-grafana-65fd8f899-x6r2f 2/2 Running 0 26m
iris-xgboost-6ff4567f58-krsnz 1/1 Running 0 5m
kafka-controller-94b9896d9-h8gzv 1/1 Running 0 22m
memcached1-5ccc54f47d-6s99q 1/1 Running 0 26m
memcached2-8d984bb95-52xlw 1/1 Running 0 26m
mysql-c74858654-mqq52 1/1 Running 0 26m
redis-74cf78b489-xlsfq 1/1 Running 0 26m
seldon-control-7594c78659-7pz78 1/1 Running 0 26m
spark-master-controller-7cfb76b44d-hdgvj 0/1 Pending 0 9m
td-agent-server-54bd8d4f58-9xvn5 1/1 Running 0 22m
zookeeper1-7769dc5c48-qvnsv 1/1 Running 0 26m
zookeeper2-6754ddb54b-4qhxc 1/1 Running 0 26m
zookeeper3-6749cd76d4-wd5sk 1/1 Running 0 26m

[root@localhost docker-compost]# kubectl get po
NAME READY STATUS RESTARTS AGE
influxdb-grafana-65fd8f899-x6r2f 2/2 Running 0 26m
iris-xgboost-6ff4567f58-krsnz 1/1 Running 0 5m
kafka-controller-94b9896d9-h8gzv 1/1 Running 0 22m
memcached1-5ccc54f47d-6s99q 1/1 Running 0 26m
memcached2-8d984bb95-52xlw 1/1 Running 0 26m
mysql-c74858654-mqq52 1/1 Running 0 26m
redis-74cf78b489-xlsfq 1/1 Running 0 26m
seldon-control-7594c78659-7pz78 1/1 Running 0 26m
spark-master-controller-7cfb76b44d-hdgvj 0/1 Pending 0 9m
td-agent-server-54bd8d4f58-9xvn5 1/1 Running 0 22m
zookeeper1-7769dc5c48-qvnsv 1/1 Running 0 26m
zookeeper2-6754ddb54b-4qhxc 1/1 Running 0 26m
zookeeper3-6749cd76d4-wd5sk 1/1 Running 0 26m

[ukclivecox]

Hi. It looks like the shared disk was not mounted. Are you running a cluster of multiple nodes? If so you would need a shared filesystem like glusterFS.
BTW: this project is dormant, you might want to look at https://github.com/SeldonIO/seldon-core and see if this fits your needs?