From 2681156ce210f310d90d537519b1db40b3aa2a0b Mon Sep 17 00:00:00 2001
From: Andrea Dell'Amico <adellam@isti.cnr.it>
Date: Sat, 14 Apr 2018 18:25:10 +0200
Subject: [PATCH] Add haproxy support for some services.

---
 hadoop/CDH/defaults/main.yml                  |  1 +
 hadoop/CDH/tasks/main.yml                     |  2 +
 hadoop/CDH/tasks/services-haproxy.yml         |  7 ++
 .../CDH/templates/hue-hive-impala_haproxy.cfg | 84 +++++++++++++++++++
 4 files changed, 94 insertions(+)
 create mode 100644 hadoop/CDH/tasks/services-haproxy.yml
 create mode 100644 hadoop/CDH/templates/hue-hive-impala_haproxy.cfg

diff --git a/hadoop/CDH/defaults/main.yml b/hadoop/CDH/defaults/main.yml
index c3d6b8e3..47b09700 100644
--- a/hadoop/CDH/defaults/main.yml
+++ b/hadoop/CDH/defaults/main.yml
@@ -48,3 +48,4 @@ cdh_zeppelin_work_dirs:
 cdh_zeppelin_ldap_auth: True
 cdh_zeppelin_dedicated_node: False 
 
+cdh_impala_load_balancer: False
\ No newline at end of file
diff --git a/hadoop/CDH/tasks/main.yml b/hadoop/CDH/tasks/main.yml
index edfdd39d..ec27c482 100644
--- a/hadoop/CDH/tasks/main.yml
+++ b/hadoop/CDH/tasks/main.yml
@@ -7,4 +7,6 @@
   when: cdh_oozie_server
 - import_tasks: zeppelin.yml
   when: cdh_zeppelin_node
+- import_tasks: services-haproxy.yml
+  when: cdh_impala_load_balancer
 
diff --git a/hadoop/CDH/tasks/services-haproxy.yml b/hadoop/CDH/tasks/services-haproxy.yml
new file mode 100644
index 00000000..3a9fbfe2
--- /dev/null
+++ b/hadoop/CDH/tasks/services-haproxy.yml
@@ -0,0 +1,7 @@
+---
+- block:
+  - name: Install the haproxy configuration
+    template: src=hue-hive-impala_haproxy.cfg dest=/etc/haproxy/haproxy.cfg owner=root group=root
+    notify: Reload haproxy
+
+  tags: [ 'cdh', 'haproxy', 'impala', 'hue', 'hive' ]
\ No newline at end of file
diff --git a/hadoop/CDH/templates/hue-hive-impala_haproxy.cfg b/hadoop/CDH/templates/hue-hive-impala_haproxy.cfg
new file mode 100644
index 00000000..bdf72ea0
--- /dev/null
+++ b/hadoop/CDH/templates/hue-hive-impala_haproxy.cfg
@@ -0,0 +1,84 @@
+global
+    # References:
+    # https://www.cloudera.com/documentation/enterprise/5-13-x/topics/impala_proxy.html
+    # https://www.cloudera.com/documentation/enterprise/5-13-x/topics/hue_sec_ha.html#concept_ef1_1pf_51b
+    #
+    # To have these messages end up in /var/log/haproxy.log you will
+    # need to:
+    #
+    # 1) configure syslog to accept network log events.  This is done
+    #    by adding the '-r' option to the SYSLOGD_OPTIONS in
+    #    /etc/sysconfig/syslog
+    #
+    # 2) configure local2 events to go to the /var/log/haproxy.log
+    #   file. A line like the following can be added to
+    #   /etc/sysconfig/syslog
+    #
+    #    local2.*                       /var/log/haproxy.log
+    #
+    log         127.0.0.1 local0
+    log         127.0.0.1 local1 notice
+    chroot      /var/lib/haproxy
+    pidfile     /run/haproxy.pid
+    maxconn     4000
+    user        haproxy
+    group       haproxy
+    daemon
+
+    # turn on stats unix socket
+    stats socket /var/lib/haproxy/stats
+
+#---------------------------------------------------------------------
+# common defaults that all the 'listen' and 'backend' sections will
+# use if not designated in their block
+#
+# You might need to adjust timing values to prevent timeouts.
+#---------------------------------------------------------------------
+defaults
+    mode                    http
+    log                     global
+    option                  httplog
+    option                  dontlognull
+    option http-server-close
+    option forwardfor       except 127.0.0.0/8
+    option                  redispatch
+    retries                 3
+    maxconn                 3000
+    contimeout 5000
+    clitimeout 50000
+    srvtimeout 50000
+
+#
+# This sets up the admin page for HA Proxy at port 25002.
+#
+# listen stats :25002
+#     balance
+#     mode http
+#     stats enable
+#     stats auth username:password
+
+# This is the setup for Impala. Impala client connect to load_balancer_host:25003.
+# HAProxy will balance connections among the list of servers listed below.
+# The list of Impalad is listening at port 21000 for beeswax (impala-shell) or original ODBC driver.
+# For JDBC or ODBC version 2.x driver, use port 21050 instead of 21000.
+listen impala :25003
+    mode tcp
+    option tcplog
+    balance leastconn
+{% for host in groups['workers'] %}
+    server {{ host }} {{host }}:21000 check
+{% endfor %}
+
+# Setup for Hue or other JDBC-enabled applications.
+# In particular, Hue requires sticky sessions.
+# The application connects to load_balancer_host:21051, and HAProxy balances
+# connections to the associated hosts, where Impala listens for JDBC
+# requests on port 21050.
+listen impalajdbc :21051
+    mode tcp
+    option tcplog
+    balance source
+{% for host in groups['workers'] %}
+    server {{ host }} {{host }}:21050 check
+{% endfor %}
+