killerwhile

diff --git a/pom.xml b/pom.xml
index 1e29c4d..30aef6a 100644
--- a/pom.xml
+++ b/pom.xml
@@ -1048,6 +1048,27 @@
         </plugins>
       </build>
     </profile>
+    <profile>
+      <id>cdh5.2</id>

killerwhile

diff --git a/tez-mapreduce/src/main/java/org/apache/tez/mapreduce/hadoop/mapreduce/JobContextImpl.java b/tez-mapreduce/src/main/java/org/apache/tez/mapreduce/hadoop/mapreduce/JobContextImpl.java
index 12491ed..b4ca24c 100644
--- a/tez-mapreduce/src/main/java/org/apache/tez/mapreduce/hadoop/mapreduce/JobContextImpl.java
+++ b/tez-mapreduce/src/main/java/org/apache/tez/mapreduce/hadoop/mapreduce/JobContextImpl.java
@@ -475,5 +475,16 @@ public class JobContextImpl implements JobContext {
   public Progressable getProgressible() {
     return progress;
   }
+
+  /**

killerwhile

ls -1 /var/run/cloudera-scm-agent/process/ | while read line; do id=$(echo $line | cut -d "-" -f1); process=$(echo $line | sed -e "s/^[0-9]*-//"); echo "$process $id"; done | sort -k1,1r -k2,2nr | while read key value; do if [ "$cur_key" = "$key" ]; then echo -n ",$value"; else if [ "" != "$cur_key" ]; then echo; fi; echo -n "$key:$value"; cur_key=$key; fi; done | grep "." | while read line; do process=$(echo $line | cut -d ":" -f1); ids=$(echo $line | cut -d ":" -f2 | sed -e "s/,/ /g"); first=0; for i in $ids; do if [ "0" = "$first" ]; then first=1; else echo "Deleting /var/run/cloudera-scm-agent/process/${i}-${process}"; rm -fr "/var/run/cloudera-scm-agent/process/${i}-${process}"; fi; done; done

killerwhile

This is a "one liner" shell command to list all partitions with not in-synch replicas (i.e. with a list of in-synch replicas not matching the list of replicas).

Please set ZK variable accordingly.

/usr/hdp/current/kafka-broker/bin/kafka-topics.sh --zookeeper $ZK --describe | grep "Isr: " | while read line; 
do 
    replicas=$(echo $line | sed -e "s/.*Replicas: \([^ ]*\).*/\1/" -e "s/,/\n/g" | sort -n | paste -sd ",");
 isr=$(echo $line | sed -e "s/.*Isr: \([^ ]*\).*/\1/" -e "s/,/\n/g" | sort -n | paste -sd ","); 

killerwhile

# hadoop classpath prior to 2.6 returns wildcarded path (starting hadoop 2.6, hadoop classpath --glob is doing the trick by itself)
# It's sometimes convenient to have a nicely printed list of jars that that part of the classpath when running hadoop jar.

for i in $(hadoop classpath | sed -e "s/:/ /g"); 
do 
    echo $i | egrep "\.jar$" >/dev/null && python -c "import os,sys; print os.path.realpath(sys.argv[1])" $i
done | sort | uniq


# If you want to generate the list of ArtifactIds to exclude from your packaging, use this version

killerwhile

If you're as lazy as I am for your cloud based pet projects, use this simple ansible play to setup a DNS-ready infrastructure :)

- lineinfile: dest=/etc/hosts regexp=".*{{ item }}.*" line="{{ hostvars[item].ansible_default_ipv4.address }} {{ item }}" state=present
  sudo: yes
  with_items: hostvars | list

killerwhile

Server 1 (external ip: 188.165.250.161)

sudo tcptraceroute 140.211.11.121 443
Selected device eth0, address 188.165.250.161, port 38659 for outgoing packets
Tracing the path to 140.211.11.121 on TCP port 443 (https), 30 hops max
 1  vss-4-6k.fr.eu (188.165.250.253)  121.387 ms  1.456 ms *
 2  rbx-g1-a9.fr.eu (94.23.122.161)  0.609 ms  0.601 ms  0.545 ms
 3  th2-g1-a9.fr.eu (91.121.131.210)  4.539 ms  4.293 ms  4.071 ms
 4  * * *