Update vanilla plugin to the latest version

New vanilla supports following features:

 * Oozie of 4.2.0 version
 * YARN, MapReduce, HDFS of latest 2.7.1 version.

Also required templates for testing were added.

Implements blueprint: support-vanilla-2-7-1

Change-Id: Iae884d9f044ba1fe64b6d4ff23fa6ebabdbb41d9
This commit is contained in:
Vitaly Gridnev 2015-08-03 17:22:35 +03:00
parent c1348a40ae
commit d5cee43cea
13 changed files with 12768 additions and 0 deletions

View File

@ -34,6 +34,7 @@ include sahara/plugins/vanilla/v1_2_1/resources/*.sh
include sahara/plugins/vanilla/v1_2_1/resources/*.sql include sahara/plugins/vanilla/v1_2_1/resources/*.sql
include sahara/plugins/vanilla/v1_2_1/resources/*.xml include sahara/plugins/vanilla/v1_2_1/resources/*.xml
include sahara/plugins/vanilla/v2_6_0/resources/*.xml include sahara/plugins/vanilla/v2_6_0/resources/*.xml
include sahara/plugins/vanilla/v2_7_1/resources/*.xml
include sahara/plugins/hdp/versions/version_1_3_2/resources/*.template include sahara/plugins/hdp/versions/version_1_3_2/resources/*.template
include sahara/plugins/hdp/versions/version_1_3_2/resources/*.json include sahara/plugins/hdp/versions/version_1_3_2/resources/*.json
include sahara/plugins/hdp/versions/version_1_3_2/resources/*.sh include sahara/plugins/hdp/versions/version_1_3_2/resources/*.sh

View File

@ -0,0 +1,71 @@
clusters:
- plugin_name: vanilla
plugin_version: 2.7.1
image: ${vanilla_two_seven_one_image}
node_group_templates:
- name: worker-dn-nm
flavor: ${ci_flavor_id}
node_processes:
- datanode
- nodemanager
volumes_per_node: 2
volumes_size: 2
auto_security_group: true
- name: worker-nm
flavor: ${ci_flavor_id}
node_processes:
- nodemanager
auto_security_group: true
- name: worker-dn
flavor: ${ci_flavor_id}
node_processes:
- datanode
volumes_per_node: 2
volumes_size: 2
auto_security_group: true
- name: master-rm-nn-hvs
flavor: ${ci_flavor_id}
node_processes:
- namenode
- resourcemanager
- hiveserver
- nodemanager
auto_security_group: true
- name: master-oo-hs-sn
flavor: ${ci_flavor_id}
node_processes:
- oozie
- historyserver
- secondarynamenode
- nodemanager
auto_security_group: true
cluster_template:
name: vanilla271
node_group_templates:
master-rm-nn-hvs: 1
master-oo-hs-sn: 1
worker-dn-nm: 2
worker-dn: 1
worker-nm: 1
cluster_configs:
HDFS:
dfs.replication: 1
cluster:
name: ${cluster_name}
scaling:
- operation: resize
node_group: worker-dn-nm
size: 1
- operation: resize
node_group: worker-dn
size: 0
- operation: resize
node_group: worker-nm
size: 0
- operation: add
node_group: worker-dn
size: 1
- operation: add
node_group: worker-nm
size: 2
edp_jobs_flow: hadoop_2

View File

@ -0,0 +1,98 @@
# Copyright (c) 2015 Mirantis Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
# implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from oslo_config import cfg
from oslo_log import log as logging
from sahara.plugins.vanilla.hadoop2 import config_helper as c_helper
from sahara.utils import xmlutils as x
CONF = cfg.CONF
CONF.import_opt("enable_data_locality", "sahara.topology.topology_helper")
LOG = logging.getLogger(__name__)
CORE_DEFAULT = x.load_hadoop_xml_defaults(
'plugins/vanilla/v2_7_1/resources/core-default.xml')
HDFS_DEFAULT = x.load_hadoop_xml_defaults(
'plugins/vanilla/v2_7_1/resources/hdfs-default.xml')
MAPRED_DEFAULT = x.load_hadoop_xml_defaults(
'plugins/vanilla/v2_7_1/resources/mapred-default.xml')
YARN_DEFAULT = x.load_hadoop_xml_defaults(
'plugins/vanilla/v2_7_1/resources/yarn-default.xml')
OOZIE_DEFAULT = x.load_hadoop_xml_defaults(
'plugins/vanilla/v2_7_1/resources/oozie-default.xml')
HIVE_DEFAULT = x.load_hadoop_xml_defaults(
'plugins/vanilla/v2_7_1/resources/hive-default.xml')
XML_CONFS = {
"Hadoop": [CORE_DEFAULT],
"HDFS": [HDFS_DEFAULT],
"YARN": [YARN_DEFAULT],
"MapReduce": [MAPRED_DEFAULT],
"JobFlow": [OOZIE_DEFAULT],
"Hive": [HIVE_DEFAULT]
}
ENV_CONFS = {
"YARN": {
'ResourceManager Heap Size': 1024,
'NodeManager Heap Size': 1024
},
"HDFS": {
'NameNode Heap Size': 1024,
'SecondaryNameNode Heap Size': 1024,
'DataNode Heap Size': 1024
},
"MapReduce": {
'JobHistoryServer Heap Size': 1024
},
"JobFlow": {
'Oozie Heap Size': 1024
}
}
# Initialise plugin Hadoop configurations
PLUGIN_XML_CONFIGS = c_helper.init_xml_configs(XML_CONFS)
PLUGIN_ENV_CONFIGS = c_helper.init_env_configs(ENV_CONFS)
def _init_all_configs():
configs = []
configs.extend(PLUGIN_XML_CONFIGS)
configs.extend(PLUGIN_ENV_CONFIGS)
configs.extend(c_helper.PLUGIN_GENERAL_CONFIGS)
return configs
PLUGIN_CONFIGS = _init_all_configs()
def get_plugin_configs():
return PLUGIN_CONFIGS
def get_xml_configs():
return PLUGIN_XML_CONFIGS
def get_env_configs():
return ENV_CONFS

View File

@ -0,0 +1,35 @@
# Copyright (c) 2015 Red Hat, Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
# implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from sahara.plugins.vanilla import confighints_helper as ch_helper
from sahara.plugins.vanilla.hadoop2 import edp_engine
from sahara.utils import edp
class EdpOozieEngine(edp_engine.EdpOozieEngine):
@staticmethod
def get_possible_job_config(job_type):
if edp.compare_job_type(job_type, edp.JOB_TYPE_HIVE):
return {'job_config': ch_helper.get_possible_hive_config_from(
'plugins/vanilla/v2_7_1/resources/hive-default.xml')}
if edp.compare_job_type(job_type,
edp.JOB_TYPE_MAPREDUCE,
edp.JOB_TYPE_MAPREDUCE_STREAMING):
return {'job_config': ch_helper.get_possible_mapreduce_config_from(
'plugins/vanilla/v2_7_1/resources/mapred-default.xml')}
if edp.compare_job_type(job_type, edp.JOB_TYPE_PIG):
return {'job_config': ch_helper.get_possible_pig_config_from(
'plugins/vanilla/v2_7_1/resources/mapred-default.xml')}
return edp_engine.EdpOozieEngine.get_possible_job_config(job_type)

View File

@ -0,0 +1,28 @@
Apache Hadoop Configurations for Sahara
=======================================
This directory contains default XML configuration files:
* core-default.xml
* hdfs-default.xml
* mapred-default.xml
* yarn-default.xml
* oozie-default.xml
* hive-default.xml
These files are applied for Sahara's plugin of Apache Hadoop version 2.7.1
Files were taken from here:
* `core-default.xml <https://github.com/apache/hadoop/blob/release-2.7.1/hadoop-common-project/hadoop-common/src/main/resources/core-default.xml>`_
* `hdfs-default.xml <https://github.com/apache/hadoop/blob/release-2.7.1/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml>`_
* `yarn-default.xml <https://github.com/apache/hadoop/blob/release-2.7.1/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/main/resources/yarn-default.xml>`_
* `mapred-default.xml <https://github.com/apache/hadoop/blob/release-2.7.1/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/resources/mapred-default.xml>`_
* `oozie-default.xml <https://github.com/apache/oozie/blob/release-4.2.0/core/src/main/resources/oozie-default.xml>`_
* `hive-default.xml <https://github.com/apache/hive/blob/release-0.11.0/conf/hive-default.xml.template>`_
XML configs are used to expose default Hadoop configurations to the users
through Sahara's REST API. It allows users to override some config values which
will be pushed to the provisioned VMs running Hadoop services as part of
appropriate xml config.

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,140 @@
# Copyright (c) 2015 Mirantis Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
# implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from oslo_config import cfg
from oslo_log import log as logging
from sahara import conductor
from sahara import context
from sahara.plugins import utils
from sahara.plugins.vanilla import abstractversionhandler as avm
from sahara.plugins.vanilla.hadoop2 import config as c
from sahara.plugins.vanilla.hadoop2 import recommendations_utils as ru
from sahara.plugins.vanilla.hadoop2 import run_scripts as run
from sahara.plugins.vanilla.hadoop2 import scaling as sc
from sahara.plugins.vanilla.hadoop2 import starting_scripts as s_scripts
from sahara.plugins.vanilla.hadoop2 import validation as vl
from sahara.plugins.vanilla import utils as vu
from sahara.plugins.vanilla.v2_7_1 import config_helper as c_helper
from sahara.plugins.vanilla.v2_7_1 import edp_engine
conductor = conductor.API
LOG = logging.getLogger(__name__)
CONF = cfg.CONF
class VersionHandler(avm.AbstractVersionHandler):
def __init__(self):
self.pctx = {
'env_confs': c_helper.get_env_configs(),
'all_confs': c_helper.get_plugin_configs()
}
def get_plugin_configs(self):
return self.pctx['all_confs']
def get_node_processes(self):
return {
"Hadoop": [],
"MapReduce": ["historyserver"],
"HDFS": ["namenode", "datanode", "secondarynamenode"],
"YARN": ["resourcemanager", "nodemanager"],
"JobFlow": ["oozie"],
"Hive": ["hiveserver"]
}
def validate(self, cluster):
vl.validate_cluster_creating(self.pctx, cluster)
def update_infra(self, cluster):
pass
def configure_cluster(self, cluster):
c.configure_cluster(self.pctx, cluster)
def start_cluster(self, cluster):
s_scripts.start_namenode(cluster)
s_scripts.start_secondarynamenode(cluster)
s_scripts.start_resourcemanager(cluster)
run.start_dn_nm_processes(utils.get_instances(cluster))
run.await_datanodes(cluster)
s_scripts.start_historyserver(cluster)
s_scripts.start_oozie(self.pctx, cluster)
s_scripts.start_hiveserver(self.pctx, cluster)
self._set_cluster_info(cluster)
def decommission_nodes(self, cluster, instances):
sc.decommission_nodes(self.pctx, cluster, instances)
def validate_scaling(self, cluster, existing, additional):
vl.validate_additional_ng_scaling(cluster, additional)
vl.validate_existing_ng_scaling(self.pctx, cluster, existing)
def scale_cluster(self, cluster, instances):
sc.scale_cluster(self.pctx, cluster, instances)
def _set_cluster_info(self, cluster):
nn = vu.get_namenode(cluster)
rm = vu.get_resourcemanager(cluster)
hs = vu.get_historyserver(cluster)
oo = vu.get_oozie(cluster)
info = {}
if rm:
info['YARN'] = {
'Web UI': 'http://%s:%s' % (rm.management_ip, '8088'),
'ResourceManager': 'http://%s:%s' % (rm.management_ip, '8032')
}
if nn:
info['HDFS'] = {
'Web UI': 'http://%s:%s' % (nn.management_ip, '50070'),
'NameNode': 'hdfs://%s:%s' % (nn.hostname(), '9000')
}
if oo:
info['JobFlow'] = {
'Oozie': 'http://%s:%s' % (oo.management_ip, '11000')
}
if hs:
info['MapReduce JobHistory Server'] = {
'Web UI': 'http://%s:%s' % (hs.management_ip, '19888')
}
ctx = context.ctx()
conductor.cluster_update(ctx, cluster, {'info': info})
def get_edp_engine(self, cluster, job_type):
if job_type in edp_engine.EdpOozieEngine.get_supported_job_types():
return edp_engine.EdpOozieEngine(cluster)
return None
def get_edp_job_types(self):
return edp_engine.EdpOozieEngine.get_supported_job_types()
def get_edp_config_hints(self, job_type):
return edp_engine.EdpOozieEngine.get_possible_job_config(job_type)
def get_open_ports(self, node_group):
return c.get_open_ports(node_group)
def recommend_configs(self, cluster):
ru.recommend_configs(cluster, self.get_plugin_configs())