You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@ignite.apache.org by percent620 <pe...@163.com> on 2016/08/24 14:28:49 UTC
Yarn deployment for memory capacity make a bigger than before:
Urgent!!!
Here is my detailed steps
1)root@sparkup1 config]# cat default-config.xml
<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:util="http://www.springframework.org/schema/util"
xsi:schemaLocation="http://www.springframework.org/schema/beans
http://www.springframework.org/schema/beans/spring-beans-4.1.xsd">
<bean class="org.apache.ignite.configuration.IgniteConfiguration">
<property name="discoverySpi">
<bean
class="org.apache.ignite.spi.discovery.tcp.TcpDiscoverySpi">
<property name="ipFinder">
<bean
class="org.apache.ignite.spi.discovery.tcp.ipfinder.vm.TcpDiscoveryVmIpFinder">
<property name="addresses">
<list>
<value>172.16.186.200:47500..47509</value>
<value>172.16.186.201:47500..47509</value>
<value>172.16.186.202:47500..47509</value>
</list>
</property>
</bean>
</property>
</bean>
</property>
</bean>
</beans>
[root@sparkup1 config]#
2)yarn contains log as below
i started 3 ignite node and for every is 1024G
$cat cluster.properties
# The number of nodes in the cluster.
IGNITE_NODE_COUNT=3
# The number of CPU Cores for each Apache Ignite node.
IGNITE_RUN_CPU_PER_NODE=1
# The number of Megabytes of RAM for each Apache Ignite node.
IGNITE_MEMORY_PER_NODE=1024
# The version ignite which will be run on nodes.
IGNITE_VERSION=1.0.6
IGNITE_WORK_DIR=/u01/yueyi/apache-ignite-hadoop-1.6.0-bin
IGNITE_XML_CONFIG=/ignite/releases/apache-ignite-hadoop-1.6.0-bin/config/default-config.xml
IGNITE_RELEASES_DIR=/ignite/releases/
IGNITE_USERS_LIBS=/ignite/releases/apache-ignite-hadoop-1.6.0-bin/libs/
#IGNITE_HOSTNAME_CONSTRAINT=vmsecdomain010194070026.cm10
IGNITE_PATH=/ignite/releases/
[root@sparkup3 config]# tail -f
/usr/hadoop-2.4.1/logs/userlogs/application_1472047995043_0001/container_1472047995043_0001_01_000003/stdout
[07:13:45] Configured plugins:
[07:13:45] ^-- None
[07:13:45]
[07:13:46] Security status [authentication=off, tls/ssl=off]
[07:13:47] To start Console Management & Monitoring run
ignitevisorcmd.{sh|bat}
[07:13:47]
[07:13:47] Ignite node started OK (id=20fb73be)
[07:13:47] Topology snapshot [ver=1, servers=1, clients=0, CPUs=1,
heap=1.0GB]
[07:13:48] Topology snapshot [ver=2, servers=2, clients=0, CPUs=2,
heap=2.0GB]
[07:13:50] Topology snapshot [ver=3, servers=3, clients=0, CPUs=3,
heap=3.0GB]
==========================================
Thanks is ok for above steps
3)
spark-submit *--driver-memory 4G* --class com.ignite.testIgniteSharedRDD
--master yarn --executor-cores 2 --executor-memory 1000m --num-executors 2
--conf spark.rdd.compress=false --conf spark.shuffle.compress=false --conf
spark.broadcast.compress=false
/root/limu/ignite/spark-project-jar-with-dependencies.jar
4)Yarn logs become is
[07:13:46] Security status [authentication=off, tls/ssl=off]
[07:13:47] To start Console Management & Monitoring run
ignitevisorcmd.{sh|bat}
[07:13:47]
[07:13:47] Ignite node started OK (id=20fb73be)
[07:13:47] Topology snapshot [ver=1, servers=1, clients=0, CPUs=1,
heap=1.0GB]
[07:13:48] Topology snapshot [ver=2, servers=2, clients=0, CPUs=2,
heap=2.0GB]
[07:13:50] Topology snapshot [ver=3, servers=3, clients=0, CPUs=3,
heap=3.0GB]
*[07:16:54] Topology snapshot [ver=4, servers=3, clients=1, CPUs=3,
heap=7.0GB] correct
*
/[07:17:06] Topology snapshot [ver=5, servers=4, clients=1, CPUs=3,
heap=8.0GB]
[07:17:07] Topology snapshot [ver=6, servers=5, clients=1, CPUs=3,
heap=9.0GB]/
is not correct, why become 5 servers and 9GB memory
details log
nohup: ignoring input
16/08/24 07:16:17 INFO spark.SparkContext: Running Spark version 1.6.1
16/08/24 07:16:18 WARN util.NativeCodeLoader: Unable to load native-hadoop
library for your platform... using builtin-java classes where applicable
16/08/24 07:16:18 INFO spark.SecurityManager: Changing view acls to: root
16/08/24 07:16:18 INFO spark.SecurityManager: Changing modify acls to: root
16/08/24 07:16:18 INFO spark.SecurityManager: SecurityManager:
authentication disabled; ui acls disabled; users with view permissions:
Set(root); users with modify permissions: Set(root)
16/08/24 07:16:19 INFO util.Utils: Successfully started service
'sparkDriver' on port 56368.
16/08/24 07:16:20 INFO slf4j.Slf4jLogger: Slf4jLogger started
16/08/24 07:16:20 INFO Remoting: Starting remoting
16/08/24 07:16:20 INFO Remoting: Remoting started; listening on addresses
:[akka.tcp://sparkDriverActorSystem@172.16.186.200:45375]
16/08/24 07:16:20 INFO util.Utils: Successfully started service
'sparkDriverActorSystem' on port 45375.
16/08/24 07:16:20 INFO spark.SparkEnv: Registering MapOutputTracker
16/08/24 07:16:20 INFO spark.SparkEnv: Registering BlockManagerMaster
16/08/24 07:16:20 INFO storage.DiskBlockManager: Created local directory at
/tmp/blockmgr-8739bc15-9e06-4496-91fc-beea794a57d7
16/08/24 07:16:20 INFO storage.MemoryStore: MemoryStore started with
capacity 2.7 GB
16/08/24 07:16:21 INFO spark.SparkEnv: Registering OutputCommitCoordinator
16/08/24 07:16:21 INFO server.Server: jetty-8.y.z-SNAPSHOT
16/08/24 07:16:21 INFO server.AbstractConnector: Started
SelectChannelConnector@0.0.0.0:4040
16/08/24 07:16:21 INFO util.Utils: Successfully started service 'SparkUI' on
port 4040.
16/08/24 07:16:21 INFO ui.SparkUI: Started SparkUI at
http://172.16.186.200:4040
16/08/24 07:16:21 INFO spark.HttpFileServer: HTTP File server directory is
/tmp/spark-07a3f373-5d80-42b0-8544-33583e9fff7d/httpd-4d4119d2-ac26-4f49-90a9-03b88e24f9d9
16/08/24 07:16:21 INFO spark.HttpServer: Starting HTTP Server
16/08/24 07:16:21 INFO server.Server: jetty-8.y.z-SNAPSHOT
16/08/24 07:16:21 INFO server.AbstractConnector: Started
SocketConnector@0.0.0.0:38541
16/08/24 07:16:21 INFO util.Utils: Successfully started service 'HTTP file
server' on port 38541.
16/08/24 07:16:22 INFO spark.SparkContext: Added JAR
file:/root/limu/ignite/spark-project-jar-with-dependencies.jar at
http://172.16.186.200:38541/jars/spark-project-jar-with-dependencies.jar
with timestamp 1472048182938
16/08/24 07:16:23 INFO client.RMProxy: Connecting to ResourceManager at
sparkup1/172.16.186.200:8032
16/08/24 07:16:23 INFO yarn.Client: Requesting a new application from
cluster with 3 NodeManagers
16/08/24 07:16:23 INFO yarn.Client: Verifying our application has not
requested more than the maximum memory capability of the cluster (8192 MB
per container)
16/08/24 07:16:23 INFO yarn.Client: Will allocate AM container, with 896 MB
memory including 384 MB overhead
16/08/24 07:16:23 INFO yarn.Client: Setting up container launch context for
our AM
16/08/24 07:16:23 INFO yarn.Client: Setting up the launch environment for
our AM container
16/08/24 07:16:23 INFO yarn.Client: Preparing resources for our AM container
16/08/24 07:16:24 INFO yarn.Client: Uploading resource
file:/usr/spark-1.6.1-bin-hadoop2.6/lib/spark-assembly-1.6.1-hadoop2.6.0.jar
->
hdfs://sparkup1:9000/user/root/.sparkStaging/application_1472047995043_0002/spark-assembly-1.6.1-hadoop2.6.0.jar
16/08/24 07:16:31 INFO yarn.Client: Uploading resource
file:/tmp/spark-07a3f373-5d80-42b0-8544-33583e9fff7d/__spark_conf__9140885938827716798.zip
->
hdfs://sparkup1:9000/user/root/.sparkStaging/application_1472047995043_0002/__spark_conf__9140885938827716798.zip
16/08/24 07:16:31 INFO spark.SecurityManager: Changing view acls to: root
16/08/24 07:16:31 INFO spark.SecurityManager: Changing modify acls to: root
16/08/24 07:16:31 INFO spark.SecurityManager: SecurityManager:
authentication disabled; ui acls disabled; users with view permissions:
Set(root); users with modify permissions: Set(root)
16/08/24 07:16:31 INFO yarn.Client: Submitting application 2 to
ResourceManager
16/08/24 07:16:31 INFO impl.YarnClientImpl: Submitted application
application_1472047995043_0002
16/08/24 07:16:32 INFO yarn.Client: Application report for
application_1472047995043_0002 (state: ACCEPTED)
16/08/24 07:16:32 INFO yarn.Client:
client token: N/A
diagnostics: N/A
ApplicationMaster host: N/A
ApplicationMaster RPC port: -1
queue: default
start time: 1472048191273
final status: UNDEFINED
tracking URL:
http://sparkup1:8088/proxy/application_1472047995043_0002/
user: root
16/08/24 07:16:33 INFO yarn.Client: Application report for
application_1472047995043_0002 (state: ACCEPTED)
16/08/24 07:16:34 INFO yarn.Client: Application report for
application_1472047995043_0002 (state: ACCEPTED)
16/08/24 07:16:35 INFO yarn.Client: Application report for
application_1472047995043_0002 (state: ACCEPTED)
16/08/24 07:16:36 INFO yarn.Client: Application report for
application_1472047995043_0002 (state: ACCEPTED)
16/08/24 07:16:37 INFO yarn.Client: Application report for
application_1472047995043_0002 (state: ACCEPTED)
16/08/24 07:16:38 INFO cluster.YarnSchedulerBackend$YarnSchedulerEndpoint:
ApplicationMaster registered as NettyRpcEndpointRef(null)
16/08/24 07:16:38 INFO cluster.YarnClientSchedulerBackend: Add WebUI Filter.
org.apache.hadoop.yarn.server.webproxy.amfilter.AmIpFilter, Map(PROXY_HOSTS
-> sparkup1, PROXY_URI_BASES ->
http://sparkup1:8088/proxy/application_1472047995043_0002),
/proxy/application_1472047995043_0002
16/08/24 07:16:38 INFO ui.JettyUtils: Adding filter:
org.apache.hadoop.yarn.server.webproxy.amfilter.AmIpFilter
16/08/24 07:16:38 INFO yarn.Client: Application report for
application_1472047995043_0002 (state: RUNNING)
16/08/24 07:16:38 INFO yarn.Client:
client token: N/A
diagnostics: N/A
ApplicationMaster host: 172.16.186.201
ApplicationMaster RPC port: 0
queue: default
start time: 1472048191273
final status: UNDEFINED
tracking URL:
http://sparkup1:8088/proxy/application_1472047995043_0002/
user: root
16/08/24 07:16:38 INFO cluster.YarnClientSchedulerBackend: Application
application_1472047995043_0002 has started running.
16/08/24 07:16:38 INFO util.Utils: Successfully started service
'org.apache.spark.network.netty.NettyBlockTransferService' on port 41610.
16/08/24 07:16:38 INFO netty.NettyBlockTransferService: Server created on
41610
16/08/24 07:16:38 INFO storage.BlockManagerMaster: Trying to register
BlockManager
16/08/24 07:16:38 INFO storage.BlockManagerMasterEndpoint: Registering block
manager 172.16.186.200:41610 with 2.7 GB RAM, BlockManagerId(driver,
172.16.186.200, 41610)
16/08/24 07:16:38 INFO storage.BlockManagerMaster: Registered BlockManager
16/08/24 07:16:46 INFO cluster.YarnClientSchedulerBackend: Registered
executor NettyRpcEndpointRef(null) (sparkup2:56516) with ID 1
16/08/24 07:16:46 INFO storage.BlockManagerMasterEndpoint: Registering block
manager sparkup2:43778 with 500.0 MB RAM, BlockManagerId(1, sparkup2, 43778)
16/08/24 07:16:47 INFO cluster.YarnClientSchedulerBackend: Registered
executor NettyRpcEndpointRef(null) (sparkup1:46131) with ID 2
16/08/24 07:16:47 INFO cluster.YarnClientSchedulerBackend: SchedulerBackend
is ready for scheduling beginning after reached minRegisteredResourcesRatio:
0.8
16/08/24 07:16:47 INFO storage.BlockManagerMasterEndpoint: Registering block
manager sparkup1:35739 with 500.0 MB RAM, BlockManagerId(2, sparkup1, 35739)
16/08/24 07:16:48 INFO xml.XmlBeanDefinitionReader: Loading XML bean
definitions from URL
[file:/usr/apache-ignite-fabric-1.6.0-bin/config/default-config.xml]
16/08/24 07:16:52 INFO support.GenericApplicationContext: Refreshing
org.springframework.context.support.GenericApplicationContext@467048e:
startup date [Wed Aug 24 07:16:52 PDT 2016]; root of context hierarchy
16/08/24 07:16:53 INFO internal.IgniteKernal:
>>> __________ ________________
>>> / _/ ___/ |/ / _/_ __/ __/
>>> _/ // (7 7 // / / / / _/
>>> /___/\___/_/|_/___/ /_/ /___/
>>>
>>> ver. 1.6.0#20160518-sha1:0b22c45b
>>> 2016 Copyright(C) Apache Software Foundation
>>>
>>> Ignite documentation: http://ignite.apache.org
16/08/24 07:16:53 INFO internal.IgniteKernal: Config URL: n/a
16/08/24 07:16:53 INFO internal.IgniteKernal: Daemon mode: off
16/08/24 07:16:53 INFO internal.IgniteKernal: OS: Linux
2.6.32-431.el6.x86_64 amd64
16/08/24 07:16:53 INFO internal.IgniteKernal: OS user: root
16/08/24 07:16:53 INFO internal.IgniteKernal: Language runtime: Java
Platform API Specification ver. 1.7
16/08/24 07:16:53 INFO internal.IgniteKernal: VM information: Java(TM) SE
Runtime Environment 1.7.0_71-b14 Oracle Corporation Java HotSpot(TM) 64-Bit
Server VM 24.71-b01
16/08/24 07:16:53 INFO internal.IgniteKernal: VM total memory: 3.9GB
16/08/24 07:16:53 INFO internal.IgniteKernal: Remote Management [restart:
off, REST: on, JMX (remote: off)]
16/08/24 07:16:53 INFO internal.IgniteKernal:
IGNITE_HOME=/usr/apache-ignite-fabric-1.6.0-bin
16/08/24 07:16:53 INFO internal.IgniteKernal: VM arguments: [-Xms4G, -Xmx4G,
-XX:MaxPermSize=256m]
16/08/24 07:16:53 INFO internal.IgniteKernal: Configured caches
['ignite-marshaller-sys-cache', 'ignite-sys-cache',
'ignite-atomics-sys-cache']
16/08/24 07:16:53 INFO internal.IgniteKernal: 3-rd party licenses can be
found at: /usr/apache-ignite-fabric-1.6.0-bin/libs/licenses
16/08/24 07:16:53 INFO internal.IgniteKernal: Non-loopback local IPs:
172.16.186.200, fe80:0:0:0:20c:29ff:fecd:2f25%2
16/08/24 07:16:53 INFO internal.IgniteKernal: Enabled local MACs:
000C29CD2F25
16/08/24 07:16:53 INFO plugin.IgnitePluginProcessor: Configured plugins:
16/08/24 07:16:53 INFO plugin.IgnitePluginProcessor: ^-- None
16/08/24 07:16:53 INFO plugin.IgnitePluginProcessor:
16/08/24 07:16:53 INFO tcp.TcpCommunicationSpi: IPC shared memory server
endpoint started [port=48101,
tokDir=/usr/apache-ignite-fabric-1.6.0-bin/work/ipc/shmem/529a5fe1-5f95-4aeb-a0dc-a8f814f63369-25100]
16/08/24 07:16:53 INFO tcp.TcpCommunicationSpi: Successfully bound shared
memory communication to TCP port [port=48101, locHost=0.0.0.0/0.0.0.0]
16/08/24 07:16:53 INFO tcp.TcpCommunicationSpi: Successfully bound to TCP
port [port=47101, locHost=0.0.0.0/0.0.0.0]
16/08/24 07:16:53 WARN noop.NoopCheckpointSpi: Checkpoints are disabled (to
enable configure any GridCheckpointSpi implementation)
16/08/24 07:16:53 WARN collision.GridCollisionManager: Collision resolution
is disabled (all jobs will be activated upon arrival).
16/08/24 07:16:53 WARN noop.NoopSwapSpaceSpi: Swap space is disabled. To
enable use FileSwapSpaceSpi.
16/08/24 07:16:53 INFO internal.IgniteKernal: Security status
[authentication=off, tls/ssl=off]
16/08/24 07:16:54 INFO tcp.GridTcpRestProtocol: Command protocol
successfully started [name=TCP binary, host=0.0.0.0/0.0.0.0, port=11212]
16/08/24 07:16:54 WARN internal.IgniteKernal: Attempting to start more nodes
than physical RAM available on current host (this can cause significant
slowdown)
16/08/24 07:16:54 INFO cache.GridCacheProcessor: Started cache
[name=ignite-marshaller-sys-cache, mode=REPLICATED]
16/08/24 07:16:54 INFO cache.GridCacheProcessor: Started cache
[name=ignite-atomics-sys-cache, mode=PARTITIONED]
16/08/24 07:16:54 INFO cache.GridCacheProcessor: Started cache
[name=ignite-sys-cache, mode=REPLICATED]
16/08/24 07:16:55 INFO internal.IgniteKernal: To start Console Management &
Monitoring run ignitevisorcmd.{sh|bat}
16/08/24 07:16:55 INFO internal.IgniteKernal:
16/08/24 07:16:55 INFO internal.IgniteKernal:
>>> +----------------------------------------------------------------------+
>>> Ignite ver. 1.6.0#20160518-sha1:0b22c45bb9b97692208fd0705ddf8045ff34a031
>>> +----------------------------------------------------------------------+
>>> OS name: Linux 2.6.32-431.el6.x86_64 amd64
>>> CPU(s): 1
>>> Heap: 4.0GB
>>> VM name: 25100@sparkup1
>>> Local node [ID=529A5FE1-5F95-4AEB-A0DC-A8F814F63369, order=4,
>>> clientMode=true]
>>> Local node addresses: [sparkup1/0:0:0:0:0:0:0:1%1, /127.0.0.1,
>>> /172.16.186.200]
>>> Local ports: TCP:11212 TCP:47101 TCP:48101
16/08/24 07:16:55 INFO discovery.GridDiscoveryManager: Topology snapshot
[ver=4, servers=3, clients=1, CPUs=3, heap=7.0GB]
16/08/24 07:16:56 INFO cache.GridCacheProcessor: Started cache
[name=sharedIgniteRDD-ling-sha111o, mode=PARTITIONED]
16/08/24 07:16:57 INFO spark.SparkContext: Starting job: count at
testIgniteSharedRDD.scala:19
16/08/24 07:16:57 INFO scheduler.DAGScheduler: Got job 0 (count at
testIgniteSharedRDD.scala:19) with 1024 output partitions
16/08/24 07:16:57 INFO scheduler.DAGScheduler: Final stage: ResultStage 0
(count at testIgniteSharedRDD.scala:19)
16/08/24 07:16:57 INFO scheduler.DAGScheduler: Parents of final stage:
List()
16/08/24 07:16:57 INFO scheduler.DAGScheduler: Missing parents: List()
16/08/24 07:16:57 INFO scheduler.DAGScheduler: Submitting ResultStage 0
(IgniteRDD[0] at RDD at IgniteAbstractRDD.scala:31), which has no missing
parents
16/08/24 07:16:57 INFO storage.MemoryStore: Block broadcast_0 stored as
values in memory (estimated size 1872.0 B, free 1872.0 B)
16/08/24 07:16:57 INFO storage.MemoryStore: Block broadcast_0_piece0 stored
as bytes in memory (estimated size 1853.0 B, free 3.6 KB)
16/08/24 07:16:57 INFO storage.BlockManagerInfo: Added broadcast_0_piece0 in
memory on 172.16.186.200:41610 (size: 1853.0 B, free: 2.7 GB)
16/08/24 07:16:57 INFO spark.SparkContext: Created broadcast 0 from
broadcast at DAGScheduler.scala:1006
16/08/24 07:16:57 INFO scheduler.DAGScheduler: Submitting 1024 missing tasks
from ResultStage 0 (IgniteRDD[0] at RDD at IgniteAbstractRDD.scala:31)
16/08/24 07:16:57 INFO cluster.YarnScheduler: Adding task set 0.0 with 1024
tasks
16/08/24 07:16:57 INFO scheduler.TaskSetManager: Starting task 7.0 in stage
0.0 (TID 0, sparkup2, partition 7,NODE_LOCAL, 1967 bytes)
16/08/24 07:16:57 INFO scheduler.TaskSetManager: Starting task 1.0 in stage
0.0 (TID 1, sparkup1, partition 1,NODE_LOCAL, 1967 bytes)
16/08/24 07:16:57 INFO scheduler.TaskSetManager: Starting task 8.0 in stage
0.0 (TID 2, sparkup2, partition 8,NODE_LOCAL, 1967 bytes)
16/08/24 07:16:57 INFO scheduler.TaskSetManager: Starting task 3.0 in stage
0.0 (TID 3, sparkup1, partition 3,NODE_LOCAL, 1967 bytes)
16/08/24 07:17:00 INFO storage.BlockManagerInfo: Added broadcast_0_piece0 in
memory on sparkup1:35739 (size: 1853.0 B, free: 500.0 MB)
16/08/24 07:17:01 INFO storage.BlockManagerInfo: Added broadcast_0_piece0 in
memory on sparkup2:43778 (size: 1853.0 B, free: 500.0 MB)
[07:17:04] New version is available at ignite.apache.org: 1.7.0
16/08/24 07:17:04 WARN cluster.GridUpdateNotifier: New version is available
at ignite.apache.org: 1.7.0
*16/08/24 07:17:06 INFO discovery.GridDiscoveryManager: Added new node to
topology: TcpDiscoveryNode [id=18575d1b-d764-43ca-9fcb-2f130b159557,
addrs=[0:0:0:0:0:0:0:1%1, 127.0.0.1, 172.16.186.201],
sockAddrs=[sparkup2/172.16.186.201:47501, /0:0:0:0:0:0:0:1%1:47501,
/127.0.0.1:47501, /172.16.186.201:47501], discPort=47501, order=5,
intOrder=5, lastExchangeTime=1472048225977, loc=false,
ver=1.6.0#20160518-sha1:0b22c45b, isClient=false]
16/08/24 07:17:06 INFO discovery.GridDiscoveryManager: Topology snapshot
[ver=5, servers=4, clients=1, CPUs=3, heap=8.0GB]
16/08/24 07:17:07 INFO discovery.GridDiscoveryManager: Added new node to
topology: TcpDiscoveryNode [id=a8fbf4cd-7fe3-40d6-ad64-b1c53479785f,
addrs=[0:0:0:0:0:0:0:1%1, 127.0.0.1, 172.16.186.200],
sockAddrs=[sparkup1/172.16.186.200:47501, /0:0:0:0:0:0:0:1%1:47501,
/127.0.0.1:47501, /172.16.186.200:47501], discPort=47501, order=6,
intOrder=6, lastExchangeTime=1472048226549, loc=false,
ver=1.6.0#20160518-sha1:0b22c45b, isClient=false]
16/08/24 07:17:07 INFO discovery.GridDiscoveryManager: Topology snapshot
[ver=6, servers=5, clients=1, CPUs=3, heap=9.0GB]*
*why local port 127.0.0.1 join yarn ignite topology, is this correct? I
think that this is not correct.
*
16/08/24 07:17:11 INFO scheduler.TaskSetManager: Starting task 17.0 in stage
0.0 (TID 4, sparkup2, partition 17,NODE_LOCAL, 1967 bytes)
16/08/24 07:17:11 INFO scheduler.TaskSetManager: Starting task 18.0 in stage
0.0 (TID 5, sparkup2, partition 18,NODE_LOCAL, 1967 bytes)
16/08/24 07:17:11 INFO scheduler.TaskSetManager: Finished task 8.0 in stage
0.0 (TID 2) in 13294 ms on sparkup2 (1/1024)
16/08/24 07:17:11 INFO scheduler.TaskSetManager: Finished task 7.0 in stage
0.0 (TID 0) in 13364 ms on sparkup2 (2/1024)
16/08/24 07:17:11 INFO scheduler.TaskSetManager: Starting task 4.0 in stage
0.0 (TID 6, sparkup1, partition 4,NODE_LOCAL, 1967 bytes)
16/08/24 07:17:11 INFO scheduler.TaskSetManager: Starting task 6.0 in stage
0.0 (TID 7, sparkup1, partition 6,NODE_LOCAL, 1967 bytes)
16/08/24 07:17:11 INFO scheduler.TaskSetManager: Finished task 1.0 in stage
0.0 (TID 1) in 13763 ms on sparkup1 (3/1024)
16/08/24 07:17:11 INFO scheduler.TaskSetManager: Finished task 3.0 in stage
0.0 (TID 3) in 13759 ms on sparkup1 (4/1024)
16/08/24 07:17:12 INFO scheduler.TaskSetManager: Starting task 20.0 in stage
0.0 (TID 8, sparkup2, partition 20,NODE_LOCAL,
--
View this message in context: http://apache-ignite-users.70518.x6.nabble.com/Yarn-deployment-for-memory-capacity-make-a-bigger-than-before-Urgent-tp7275.html
Sent from the Apache Ignite Users mailing list archive at Nabble.com.
Re: Yarn deployment for memory capacity make a bigger than before:
Urgent!!!
Posted by percent620 <pe...@163.com>.
Thanks Nikolai Tikhonov-2,
2 questions
1)How to configure -Xmx and -Xms jvm options for client nodes? I have
submitted this job via spark-sub, you mean change this memory.
2)You can't explain the reason? Can you please double check this?
**why local port 127.0.0.1 join yarn ignite topology, is this correct?
Ithink that this is not correct.*
--
View this message in context: http://apache-ignite-users.70518.x6.nabble.com/Yarn-deployment-for-memory-capacity-make-a-bigger-than-before-Urgent-tp7275p7282.html
Sent from the Apache Ignite Users mailing list archive at Nabble.com.
Re: Yarn deployment for memory capacity make a bigger than before: Urgent!!!
Posted by Nikolai Tikhonov <nt...@apache.org>.
Hi,
How I see from your logs, server node (which probably deployed by YARN)
consumes 1Gb memory (per node). But client node consumes more memory how I
see 4Gb. You can decrease memory consumption using -Xmx and -Xms jvm
options for client nodes.
On Wed, Aug 24, 2016 at 5:28 PM, percent620 <pe...@163.com> wrote:
> Here is my detailed steps
> 1)root@sparkup1 config]# cat default-config.xml
> <?xml version="1.0" encoding="UTF-8"?>
> <beans xmlns="http://www.springframework.org/schema/beans"
> xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
> xmlns:util="http://www.springframework.org/schema/util"
> xsi:schemaLocation="http://www.springframework.org/schema/beans
> http://www.springframework.org/schema/beans/spring-beans-4.1.xsd">
> <bean class="org.apache.ignite.configuration.IgniteConfiguration">
> <property name="discoverySpi">
> <bean
> class="org.apache.ignite.spi.discovery.tcp.TcpDiscoverySpi">
> <property name="ipFinder">
> <bean
> class="org.apache.ignite.spi.discovery.tcp.ipfinder.vm.
> TcpDiscoveryVmIpFinder">
> <property name="addresses">
> <list>
>
> <value>172.16.186.200:47500..47509</value>
>
> <value>172.16.186.201:47500..47509</value>
>
> <value>172.16.186.202:47500..47509</value>
> </list>
> </property>
> </bean>
> </property>
> </bean>
> </property>
> </bean>
> </beans>
> [root@sparkup1 config]#
>
> 2)yarn contains log as below
>
> i started 3 ignite node and for every is 1024G
>
>
> $cat cluster.properties
> # The number of nodes in the cluster.
> IGNITE_NODE_COUNT=3
> # The number of CPU Cores for each Apache Ignite node.
> IGNITE_RUN_CPU_PER_NODE=1
> # The number of Megabytes of RAM for each Apache Ignite node.
> IGNITE_MEMORY_PER_NODE=1024
> # The version ignite which will be run on nodes.
> IGNITE_VERSION=1.0.6
> IGNITE_WORK_DIR=/u01/yueyi/apache-ignite-hadoop-1.6.0-bin
> IGNITE_XML_CONFIG=/ignite/releases/apache-ignite-hadoop-
> 1.6.0-bin/config/default-config.xml
> IGNITE_RELEASES_DIR=/ignite/releases/
> IGNITE_USERS_LIBS=/ignite/releases/apache-ignite-hadoop-1.6.0-bin/libs/
> #IGNITE_HOSTNAME_CONSTRAINT=vmsecdomain010194070026.cm10
> IGNITE_PATH=/ignite/releases/
>
>
> [root@sparkup3 config]# tail -f
> /usr/hadoop-2.4.1/logs/userlogs/application_1472047995043_0001/container_
> 1472047995043_0001_01_000003/stdout
> [07:13:45] Configured plugins:
> [07:13:45] ^-- None
> [07:13:45]
> [07:13:46] Security status [authentication=off, tls/ssl=off]
> [07:13:47] To start Console Management & Monitoring run
> ignitevisorcmd.{sh|bat}
> [07:13:47]
> [07:13:47] Ignite node started OK (id=20fb73be)
> [07:13:47] Topology snapshot [ver=1, servers=1, clients=0, CPUs=1,
> heap=1.0GB]
> [07:13:48] Topology snapshot [ver=2, servers=2, clients=0, CPUs=2,
> heap=2.0GB]
> [07:13:50] Topology snapshot [ver=3, servers=3, clients=0, CPUs=3,
> heap=3.0GB]
> ==========================================
> Thanks is ok for above steps
>
>
>
> 3)
> spark-submit *--driver-memory 4G* --class com.ignite.testIgniteSharedRDD
> --master yarn --executor-cores 2 --executor-memory 1000m --num-executors 2
> --conf spark.rdd.compress=false --conf spark.shuffle.compress=false --conf
> spark.broadcast.compress=false
> /root/limu/ignite/spark-project-jar-with-dependencies.jar
>
>
> 4)Yarn logs become is
> [07:13:46] Security status [authentication=off, tls/ssl=off]
> [07:13:47] To start Console Management & Monitoring run
> ignitevisorcmd.{sh|bat}
> [07:13:47]
> [07:13:47] Ignite node started OK (id=20fb73be)
> [07:13:47] Topology snapshot [ver=1, servers=1, clients=0, CPUs=1,
> heap=1.0GB]
> [07:13:48] Topology snapshot [ver=2, servers=2, clients=0, CPUs=2,
> heap=2.0GB]
> [07:13:50] Topology snapshot [ver=3, servers=3, clients=0, CPUs=3,
> heap=3.0GB]
> *[07:16:54] Topology snapshot [ver=4, servers=3, clients=1, CPUs=3,
> heap=7.0GB] correct
>
> *
> /[07:17:06] Topology snapshot [ver=5, servers=4, clients=1, CPUs=3,
> heap=8.0GB]
> [07:17:07] Topology snapshot [ver=6, servers=5, clients=1, CPUs=3,
> heap=9.0GB]/
>
> is not correct, why become 5 servers and 9GB memory
>
>
>
> details log
> nohup: ignoring input
> 16/08/24 07:16:17 INFO spark.SparkContext: Running Spark version 1.6.1
> 16/08/24 07:16:18 WARN util.NativeCodeLoader: Unable to load native-hadoop
> library for your platform... using builtin-java classes where applicable
> 16/08/24 07:16:18 INFO spark.SecurityManager: Changing view acls to: root
> 16/08/24 07:16:18 INFO spark.SecurityManager: Changing modify acls to: root
> 16/08/24 07:16:18 INFO spark.SecurityManager: SecurityManager:
> authentication disabled; ui acls disabled; users with view permissions:
> Set(root); users with modify permissions: Set(root)
> 16/08/24 07:16:19 INFO util.Utils: Successfully started service
> 'sparkDriver' on port 56368.
> 16/08/24 07:16:20 INFO slf4j.Slf4jLogger: Slf4jLogger started
> 16/08/24 07:16:20 INFO Remoting: Starting remoting
> 16/08/24 07:16:20 INFO Remoting: Remoting started; listening on addresses
> :[akka.tcp://sparkDriverActorSystem@172.16.186.200:45375]
> 16/08/24 07:16:20 INFO util.Utils: Successfully started service
> 'sparkDriverActorSystem' on port 45375.
> 16/08/24 07:16:20 INFO spark.SparkEnv: Registering MapOutputTracker
> 16/08/24 07:16:20 INFO spark.SparkEnv: Registering BlockManagerMaster
> 16/08/24 07:16:20 INFO storage.DiskBlockManager: Created local directory at
> /tmp/blockmgr-8739bc15-9e06-4496-91fc-beea794a57d7
> 16/08/24 07:16:20 INFO storage.MemoryStore: MemoryStore started with
> capacity 2.7 GB
> 16/08/24 07:16:21 INFO spark.SparkEnv: Registering OutputCommitCoordinator
> 16/08/24 07:16:21 INFO server.Server: jetty-8.y.z-SNAPSHOT
> 16/08/24 07:16:21 INFO server.AbstractConnector: Started
> SelectChannelConnector@0.0.0.0:4040
> 16/08/24 07:16:21 INFO util.Utils: Successfully started service 'SparkUI'
> on
> port 4040.
> 16/08/24 07:16:21 INFO ui.SparkUI: Started SparkUI at
> http://172.16.186.200:4040
> 16/08/24 07:16:21 INFO spark.HttpFileServer: HTTP File server directory is
> /tmp/spark-07a3f373-5d80-42b0-8544-33583e9fff7d/httpd-
> 4d4119d2-ac26-4f49-90a9-03b88e24f9d9
> 16/08/24 07:16:21 INFO spark.HttpServer: Starting HTTP Server
> 16/08/24 07:16:21 INFO server.Server: jetty-8.y.z-SNAPSHOT
> 16/08/24 07:16:21 INFO server.AbstractConnector: Started
> SocketConnector@0.0.0.0:38541
> 16/08/24 07:16:21 INFO util.Utils: Successfully started service 'HTTP file
> server' on port 38541.
> 16/08/24 07:16:22 INFO spark.SparkContext: Added JAR
> file:/root/limu/ignite/spark-project-jar-with-dependencies.jar at
> http://172.16.186.200:38541/jars/spark-project-jar-with-dependencies.jar
> with timestamp 1472048182938
> 16/08/24 07:16:23 INFO client.RMProxy: Connecting to ResourceManager at
> sparkup1/172.16.186.200:8032
> 16/08/24 07:16:23 INFO yarn.Client: Requesting a new application from
> cluster with 3 NodeManagers
> 16/08/24 07:16:23 INFO yarn.Client: Verifying our application has not
> requested more than the maximum memory capability of the cluster (8192 MB
> per container)
> 16/08/24 07:16:23 INFO yarn.Client: Will allocate AM container, with 896 MB
> memory including 384 MB overhead
> 16/08/24 07:16:23 INFO yarn.Client: Setting up container launch context for
> our AM
> 16/08/24 07:16:23 INFO yarn.Client: Setting up the launch environment for
> our AM container
> 16/08/24 07:16:23 INFO yarn.Client: Preparing resources for our AM
> container
> 16/08/24 07:16:24 INFO yarn.Client: Uploading resource
> file:/usr/spark-1.6.1-bin-hadoop2.6/lib/spark-assembly-
> 1.6.1-hadoop2.6.0.jar
> ->
> hdfs://sparkup1:9000/user/root/.sparkStaging/application_1472047995043_
> 0002/spark-assembly-1.6.1-hadoop2.6.0.jar
> 16/08/24 07:16:31 INFO yarn.Client: Uploading resource
> file:/tmp/spark-07a3f373-5d80-42b0-8544-33583e9fff7d/__spark_conf__
> 9140885938827716798.zip
> ->
> hdfs://sparkup1:9000/user/root/.sparkStaging/application_1472047995043_
> 0002/__spark_conf__9140885938827716798.zip
> 16/08/24 07:16:31 INFO spark.SecurityManager: Changing view acls to: root
> 16/08/24 07:16:31 INFO spark.SecurityManager: Changing modify acls to: root
> 16/08/24 07:16:31 INFO spark.SecurityManager: SecurityManager:
> authentication disabled; ui acls disabled; users with view permissions:
> Set(root); users with modify permissions: Set(root)
> 16/08/24 07:16:31 INFO yarn.Client: Submitting application 2 to
> ResourceManager
> 16/08/24 07:16:31 INFO impl.YarnClientImpl: Submitted application
> application_1472047995043_0002
> 16/08/24 07:16:32 INFO yarn.Client: Application report for
> application_1472047995043_0002 (state: ACCEPTED)
> 16/08/24 07:16:32 INFO yarn.Client:
> client token: N/A
> diagnostics: N/A
> ApplicationMaster host: N/A
> ApplicationMaster RPC port: -1
> queue: default
> start time: 1472048191273
> final status: UNDEFINED
> tracking URL:
> http://sparkup1:8088/proxy/application_1472047995043_0002/
> user: root
> 16/08/24 07:16:33 INFO yarn.Client: Application report for
> application_1472047995043_0002 (state: ACCEPTED)
> 16/08/24 07:16:34 INFO yarn.Client: Application report for
> application_1472047995043_0002 (state: ACCEPTED)
> 16/08/24 07:16:35 INFO yarn.Client: Application report for
> application_1472047995043_0002 (state: ACCEPTED)
> 16/08/24 07:16:36 INFO yarn.Client: Application report for
> application_1472047995043_0002 (state: ACCEPTED)
> 16/08/24 07:16:37 INFO yarn.Client: Application report for
> application_1472047995043_0002 (state: ACCEPTED)
> 16/08/24 07:16:38 INFO cluster.YarnSchedulerBackend$YarnSchedulerEndpoint:
> ApplicationMaster registered as NettyRpcEndpointRef(null)
> 16/08/24 07:16:38 INFO cluster.YarnClientSchedulerBackend: Add WebUI
> Filter.
> org.apache.hadoop.yarn.server.webproxy.amfilter.AmIpFilter,
> Map(PROXY_HOSTS
> -> sparkup1, PROXY_URI_BASES ->
> http://sparkup1:8088/proxy/application_1472047995043_0002),
> /proxy/application_1472047995043_0002
> 16/08/24 07:16:38 INFO ui.JettyUtils: Adding filter:
> org.apache.hadoop.yarn.server.webproxy.amfilter.AmIpFilter
> 16/08/24 07:16:38 INFO yarn.Client: Application report for
> application_1472047995043_0002 (state: RUNNING)
> 16/08/24 07:16:38 INFO yarn.Client:
> client token: N/A
> diagnostics: N/A
> ApplicationMaster host: 172.16.186.201
> ApplicationMaster RPC port: 0
> queue: default
> start time: 1472048191273
> final status: UNDEFINED
> tracking URL:
> http://sparkup1:8088/proxy/application_1472047995043_0002/
> user: root
> 16/08/24 07:16:38 INFO cluster.YarnClientSchedulerBackend: Application
> application_1472047995043_0002 has started running.
> 16/08/24 07:16:38 INFO util.Utils: Successfully started service
> 'org.apache.spark.network.netty.NettyBlockTransferService' on port 41610.
> 16/08/24 07:16:38 INFO netty.NettyBlockTransferService: Server created on
> 41610
> 16/08/24 07:16:38 INFO storage.BlockManagerMaster: Trying to register
> BlockManager
> 16/08/24 07:16:38 INFO storage.BlockManagerMasterEndpoint: Registering
> block
> manager 172.16.186.200:41610 with 2.7 GB RAM, BlockManagerId(driver,
> 172.16.186.200, 41610)
> 16/08/24 07:16:38 INFO storage.BlockManagerMaster: Registered BlockManager
> 16/08/24 07:16:46 INFO cluster.YarnClientSchedulerBackend: Registered
> executor NettyRpcEndpointRef(null) (sparkup2:56516) with ID 1
> 16/08/24 07:16:46 INFO storage.BlockManagerMasterEndpoint: Registering
> block
> manager sparkup2:43778 with 500.0 MB RAM, BlockManagerId(1, sparkup2,
> 43778)
> 16/08/24 07:16:47 INFO cluster.YarnClientSchedulerBackend: Registered
> executor NettyRpcEndpointRef(null) (sparkup1:46131) with ID 2
> 16/08/24 07:16:47 INFO cluster.YarnClientSchedulerBackend:
> SchedulerBackend
> is ready for scheduling beginning after reached
> minRegisteredResourcesRatio:
> 0.8
> 16/08/24 07:16:47 INFO storage.BlockManagerMasterEndpoint: Registering
> block
> manager sparkup1:35739 with 500.0 MB RAM, BlockManagerId(2, sparkup1,
> 35739)
> 16/08/24 07:16:48 INFO xml.XmlBeanDefinitionReader: Loading XML bean
> definitions from URL
> [file:/usr/apache-ignite-fabric-1.6.0-bin/config/default-config.xml]
> 16/08/24 07:16:52 INFO support.GenericApplicationContext: Refreshing
> org.springframework.context.support.GenericApplicationContext@467048e:
> startup date [Wed Aug 24 07:16:52 PDT 2016]; root of context hierarchy
> 16/08/24 07:16:53 INFO internal.IgniteKernal:
>
> >>> __________ ________________
> >>> / _/ ___/ |/ / _/_ __/ __/
> >>> _/ // (7 7 // / / / / _/
> >>> /___/\___/_/|_/___/ /_/ /___/
> >>>
> >>> ver. 1.6.0#20160518-sha1:0b22c45b
> >>> 2016 Copyright(C) Apache Software Foundation
> >>>
> >>> Ignite documentation: http://ignite.apache.org
>
> 16/08/24 07:16:53 INFO internal.IgniteKernal: Config URL: n/a
> 16/08/24 07:16:53 INFO internal.IgniteKernal: Daemon mode: off
> 16/08/24 07:16:53 INFO internal.IgniteKernal: OS: Linux
> 2.6.32-431.el6.x86_64 amd64
> 16/08/24 07:16:53 INFO internal.IgniteKernal: OS user: root
> 16/08/24 07:16:53 INFO internal.IgniteKernal: Language runtime: Java
> Platform API Specification ver. 1.7
> 16/08/24 07:16:53 INFO internal.IgniteKernal: VM information: Java(TM) SE
> Runtime Environment 1.7.0_71-b14 Oracle Corporation Java HotSpot(TM) 64-Bit
> Server VM 24.71-b01
> 16/08/24 07:16:53 INFO internal.IgniteKernal: VM total memory: 3.9GB
> 16/08/24 07:16:53 INFO internal.IgniteKernal: Remote Management [restart:
> off, REST: on, JMX (remote: off)]
> 16/08/24 07:16:53 INFO internal.IgniteKernal:
> IGNITE_HOME=/usr/apache-ignite-fabric-1.6.0-bin
> 16/08/24 07:16:53 INFO internal.IgniteKernal: VM arguments: [-Xms4G,
> -Xmx4G,
> -XX:MaxPermSize=256m]
> 16/08/24 07:16:53 INFO internal.IgniteKernal: Configured caches
> ['ignite-marshaller-sys-cache', 'ignite-sys-cache',
> 'ignite-atomics-sys-cache']
> 16/08/24 07:16:53 INFO internal.IgniteKernal: 3-rd party licenses can be
> found at: /usr/apache-ignite-fabric-1.6.0-bin/libs/licenses
> 16/08/24 07:16:53 INFO internal.IgniteKernal: Non-loopback local IPs:
> 172.16.186.200, fe80:0:0:0:20c:29ff:fecd:2f25%2
> 16/08/24 07:16:53 INFO internal.IgniteKernal: Enabled local MACs:
> 000C29CD2F25
> 16/08/24 07:16:53 INFO plugin.IgnitePluginProcessor: Configured plugins:
> 16/08/24 07:16:53 INFO plugin.IgnitePluginProcessor: ^-- None
> 16/08/24 07:16:53 INFO plugin.IgnitePluginProcessor:
> 16/08/24 07:16:53 INFO tcp.TcpCommunicationSpi: IPC shared memory server
> endpoint started [port=48101,
> tokDir=/usr/apache-ignite-fabric-1.6.0-bin/work/ipc/
> shmem/529a5fe1-5f95-4aeb-a0dc-a8f814f63369-25100]
> 16/08/24 07:16:53 INFO tcp.TcpCommunicationSpi: Successfully bound shared
> memory communication to TCP port [port=48101, locHost=0.0.0.0/0.0.0.0]
> 16/08/24 07:16:53 INFO tcp.TcpCommunicationSpi: Successfully bound to TCP
> port [port=47101, locHost=0.0.0.0/0.0.0.0]
> 16/08/24 07:16:53 WARN noop.NoopCheckpointSpi: Checkpoints are disabled (to
> enable configure any GridCheckpointSpi implementation)
> 16/08/24 07:16:53 WARN collision.GridCollisionManager: Collision
> resolution
> is disabled (all jobs will be activated upon arrival).
> 16/08/24 07:16:53 WARN noop.NoopSwapSpaceSpi: Swap space is disabled. To
> enable use FileSwapSpaceSpi.
> 16/08/24 07:16:53 INFO internal.IgniteKernal: Security status
> [authentication=off, tls/ssl=off]
> 16/08/24 07:16:54 INFO tcp.GridTcpRestProtocol: Command protocol
> successfully started [name=TCP binary, host=0.0.0.0/0.0.0.0, port=11212]
> 16/08/24 07:16:54 WARN internal.IgniteKernal: Attempting to start more
> nodes
> than physical RAM available on current host (this can cause significant
> slowdown)
> 16/08/24 07:16:54 INFO cache.GridCacheProcessor: Started cache
> [name=ignite-marshaller-sys-cache, mode=REPLICATED]
> 16/08/24 07:16:54 INFO cache.GridCacheProcessor: Started cache
> [name=ignite-atomics-sys-cache, mode=PARTITIONED]
> 16/08/24 07:16:54 INFO cache.GridCacheProcessor: Started cache
> [name=ignite-sys-cache, mode=REPLICATED]
> 16/08/24 07:16:55 INFO internal.IgniteKernal: To start Console Management &
> Monitoring run ignitevisorcmd.{sh|bat}
> 16/08/24 07:16:55 INFO internal.IgniteKernal:
> 16/08/24 07:16:55 INFO internal.IgniteKernal:
>
> >>> +-----------------------------------------------------------
> -----------+
> >>> Ignite ver. 1.6.0#20160518-sha1:0b22c45bb9b97692208fd0705ddf80
> 45ff34a031
> >>> +-----------------------------------------------------------
> -----------+
> >>> OS name: Linux 2.6.32-431.el6.x86_64 amd64
> >>> CPU(s): 1
> >>> Heap: 4.0GB
> >>> VM name: 25100@sparkup1
> >>> Local node [ID=529A5FE1-5F95-4AEB-A0DC-A8F814F63369, order=4,
> >>> clientMode=true]
> >>> Local node addresses: [sparkup1/0:0:0:0:0:0:0:1%1, /127.0.0.1,
> >>> /172.16.186.200]
> >>> Local ports: TCP:11212 TCP:47101 TCP:48101
>
> 16/08/24 07:16:55 INFO discovery.GridDiscoveryManager: Topology snapshot
> [ver=4, servers=3, clients=1, CPUs=3, heap=7.0GB]
> 16/08/24 07:16:56 INFO cache.GridCacheProcessor: Started cache
> [name=sharedIgniteRDD-ling-sha111o, mode=PARTITIONED]
> 16/08/24 07:16:57 INFO spark.SparkContext: Starting job: count at
> testIgniteSharedRDD.scala:19
> 16/08/24 07:16:57 INFO scheduler.DAGScheduler: Got job 0 (count at
> testIgniteSharedRDD.scala:19) with 1024 output partitions
> 16/08/24 07:16:57 INFO scheduler.DAGScheduler: Final stage: ResultStage 0
> (count at testIgniteSharedRDD.scala:19)
> 16/08/24 07:16:57 INFO scheduler.DAGScheduler: Parents of final stage:
> List()
> 16/08/24 07:16:57 INFO scheduler.DAGScheduler: Missing parents: List()
> 16/08/24 07:16:57 INFO scheduler.DAGScheduler: Submitting ResultStage 0
> (IgniteRDD[0] at RDD at IgniteAbstractRDD.scala:31), which has no missing
> parents
> 16/08/24 07:16:57 INFO storage.MemoryStore: Block broadcast_0 stored as
> values in memory (estimated size 1872.0 B, free 1872.0 B)
> 16/08/24 07:16:57 INFO storage.MemoryStore: Block broadcast_0_piece0 stored
> as bytes in memory (estimated size 1853.0 B, free 3.6 KB)
> 16/08/24 07:16:57 INFO storage.BlockManagerInfo: Added broadcast_0_piece0
> in
> memory on 172.16.186.200:41610 (size: 1853.0 B, free: 2.7 GB)
> 16/08/24 07:16:57 INFO spark.SparkContext: Created broadcast 0 from
> broadcast at DAGScheduler.scala:1006
> 16/08/24 07:16:57 INFO scheduler.DAGScheduler: Submitting 1024 missing
> tasks
> from ResultStage 0 (IgniteRDD[0] at RDD at IgniteAbstractRDD.scala:31)
> 16/08/24 07:16:57 INFO cluster.YarnScheduler: Adding task set 0.0 with 1024
> tasks
> 16/08/24 07:16:57 INFO scheduler.TaskSetManager: Starting task 7.0 in stage
> 0.0 (TID 0, sparkup2, partition 7,NODE_LOCAL, 1967 bytes)
> 16/08/24 07:16:57 INFO scheduler.TaskSetManager: Starting task 1.0 in stage
> 0.0 (TID 1, sparkup1, partition 1,NODE_LOCAL, 1967 bytes)
> 16/08/24 07:16:57 INFO scheduler.TaskSetManager: Starting task 8.0 in stage
> 0.0 (TID 2, sparkup2, partition 8,NODE_LOCAL, 1967 bytes)
> 16/08/24 07:16:57 INFO scheduler.TaskSetManager: Starting task 3.0 in stage
> 0.0 (TID 3, sparkup1, partition 3,NODE_LOCAL, 1967 bytes)
> 16/08/24 07:17:00 INFO storage.BlockManagerInfo: Added broadcast_0_piece0
> in
> memory on sparkup1:35739 (size: 1853.0 B, free: 500.0 MB)
> 16/08/24 07:17:01 INFO storage.BlockManagerInfo: Added broadcast_0_piece0
> in
> memory on sparkup2:43778 (size: 1853.0 B, free: 500.0 MB)
> [07:17:04] New version is available at ignite.apache.org: 1.7.0
> 16/08/24 07:17:04 WARN cluster.GridUpdateNotifier: New version is available
> at ignite.apache.org: 1.7.0
> *16/08/24 07:17:06 INFO discovery.GridDiscoveryManager: Added new node to
> topology: TcpDiscoveryNode [id=18575d1b-d764-43ca-9fcb-2f130b159557,
> addrs=[0:0:0:0:0:0:0:1%1, 127.0.0.1, 172.16.186.201],
> sockAddrs=[sparkup2/172.16.186.201:47501, /0:0:0:0:0:0:0:1%1:47501,
> /127.0.0.1:47501, /172.16.186.201:47501], discPort=47501, order=5,
> intOrder=5, lastExchangeTime=1472048225977, loc=false,
> ver=1.6.0#20160518-sha1:0b22c45b, isClient=false]
> 16/08/24 07:17:06 INFO discovery.GridDiscoveryManager: Topology snapshot
> [ver=5, servers=4, clients=1, CPUs=3, heap=8.0GB]
> 16/08/24 07:17:07 INFO discovery.GridDiscoveryManager: Added new node to
> topology: TcpDiscoveryNode [id=a8fbf4cd-7fe3-40d6-ad64-b1c53479785f,
> addrs=[0:0:0:0:0:0:0:1%1, 127.0.0.1, 172.16.186.200],
> sockAddrs=[sparkup1/172.16.186.200:47501, /0:0:0:0:0:0:0:1%1:47501,
> /127.0.0.1:47501, /172.16.186.200:47501], discPort=47501, order=6,
> intOrder=6, lastExchangeTime=1472048226549, loc=false,
> ver=1.6.0#20160518-sha1:0b22c45b, isClient=false]
> 16/08/24 07:17:07 INFO discovery.GridDiscoveryManager: Topology snapshot
> [ver=6, servers=5, clients=1, CPUs=3, heap=9.0GB]*
>
> *why local port 127.0.0.1 join yarn ignite topology, is this correct? I
> think that this is not correct.
> *
> 16/08/24 07:17:11 INFO scheduler.TaskSetManager: Starting task 17.0 in
> stage
> 0.0 (TID 4, sparkup2, partition 17,NODE_LOCAL, 1967 bytes)
> 16/08/24 07:17:11 INFO scheduler.TaskSetManager: Starting task 18.0 in
> stage
> 0.0 (TID 5, sparkup2, partition 18,NODE_LOCAL, 1967 bytes)
> 16/08/24 07:17:11 INFO scheduler.TaskSetManager: Finished task 8.0 in stage
> 0.0 (TID 2) in 13294 ms on sparkup2 (1/1024)
> 16/08/24 07:17:11 INFO scheduler.TaskSetManager: Finished task 7.0 in stage
> 0.0 (TID 0) in 13364 ms on sparkup2 (2/1024)
> 16/08/24 07:17:11 INFO scheduler.TaskSetManager: Starting task 4.0 in stage
> 0.0 (TID 6, sparkup1, partition 4,NODE_LOCAL, 1967 bytes)
> 16/08/24 07:17:11 INFO scheduler.TaskSetManager: Starting task 6.0 in stage
> 0.0 (TID 7, sparkup1, partition 6,NODE_LOCAL, 1967 bytes)
> 16/08/24 07:17:11 INFO scheduler.TaskSetManager: Finished task 1.0 in stage
> 0.0 (TID 1) in 13763 ms on sparkup1 (3/1024)
> 16/08/24 07:17:11 INFO scheduler.TaskSetManager: Finished task 3.0 in stage
> 0.0 (TID 3) in 13759 ms on sparkup1 (4/1024)
> 16/08/24 07:17:12 INFO scheduler.TaskSetManager: Starting task 20.0 in
> stage
> 0.0 (TID 8, sparkup2, partition 20,NODE_LOCAL,
>
>
>
> --
> View this message in context: http://apache-ignite-users.
> 70518.x6.nabble.com/Yarn-deployment-for-memory-
> capacity-make-a-bigger-than-before-Urgent-tp7275.html
> Sent from the Apache Ignite Users mailing list archive at Nabble.com.
>