From 746abe816980fbaa562d954620ac0a4e2309a476 Mon Sep 17 00:00:00 2001
From: Marvin Blum <marvin.blum@emvi.com>
Date: Fri, 12 Nov 2021 14:26:27 +0100
Subject: [PATCH] Updated ClickHouse image and added custom user configuration.

---
 clickhouse/docker-compose.yml |   3 +-
 clickhouse/users.xml          | 123 ++++++++++++++++++++++++++++++++++
 2 files changed, 125 insertions(+), 1 deletion(-)
 create mode 100644 clickhouse/users.xml

diff --git a/clickhouse/docker-compose.yml b/clickhouse/docker-compose.yml
index e34c985..6b11f3f 100644
--- a/clickhouse/docker-compose.yml
+++ b/clickhouse/docker-compose.yml
@@ -2,7 +2,7 @@ version: '3'
 
 services:
   clickhouse:
-    image: yandex/clickhouse-server:21.7
+    image: clickhouse/clickhouse-server:21.11
     container_name: clickhouse
     restart: always
     ports:
@@ -11,3 +11,4 @@ services:
     volumes:
       - /home/marvin/docker/clickhouse/data:/var/lib/clickhouse
 #      - /home/marvin/docker/clickhouse/config.xml:/etc/clickhouse-server/config.xml
+      - /home/marvin/docker/clickhouse/users.xml:/etc/clickhouse-server/users.xml
diff --git a/clickhouse/users.xml b/clickhouse/users.xml
new file mode 100644
index 0000000..280af4d
--- /dev/null
+++ b/clickhouse/users.xml
@@ -0,0 +1,123 @@
+<?xml version="1.0"?>
+<clickhouse>
+    <!-- See also the files in users.d directory where the settings can be overridden. -->
+
+    <!-- Profiles of settings. -->
+    <profiles>
+        <!-- Default settings. -->
+        <default>
+            <!-- Maximum memory usage for processing single query, in bytes. -->
+            <max_memory_usage>10000000000</max_memory_usage>
+
+            <!-- How to choose between replicas during distributed query processing.
+                 random - choose random replica from set of replicas with minimum number of errors
+                 nearest_hostname - from set of replicas with minimum number of errors, choose replica
+                  with minimum number of different symbols between replica's hostname and local hostname
+                  (Hamming distance).
+                 in_order - first live replica is chosen in specified order.
+                 first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
+            -->
+            <load_balancing>random</load_balancing>
+        </default>
+
+        <!-- Profile that allows only read queries. -->
+        <readonly>
+            <readonly>2</readonly>
+        </readonly>
+    </profiles>
+
+    <!-- Users and ACL. -->
+    <users>
+        <!-- If user name was not specified, 'default' user is used. -->
+        <default>
+            <!-- See also the files in users.d directory where the password can be overridden.
+
+                 Password could be specified in plaintext or in SHA256 (in hex format).
+
+                 If you want to specify password in plaintext (not recommended), place it in 'password' element.
+                 Example: <password>qwerty</password>.
+                 Password could be empty.
+
+                 If you want to specify SHA256, place it in 'password_sha256_hex' element.
+                 Example: <password_sha256_hex>65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5</password_sha256_hex>
+                 Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).
+
+                 If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
+                 Example: <password_double_sha1_hex>e395796d6546b1b65db9d665cd43f0e858dd4303</password_double_sha1_hex>
+
+                 If you want to specify a previously defined LDAP server (see 'ldap_servers' in the main config) for authentication,
+                  place its name in 'server' element inside 'ldap' element.
+                 Example: <ldap><server>my_ldap_server</server></ldap>
+
+                 If you want to authenticate the user via Kerberos (assuming Kerberos is enabled, see 'kerberos' in the main config),
+                  place 'kerberos' element instead of 'password' (and similar) elements.
+                 The name part of the canonical principal name of the initiator must match the user name for authentication to succeed.
+                 You can also place 'realm' element inside 'kerberos' element to further restrict authentication to only those requests
+                  whose initiator's realm matches it.
+                 Example: <kerberos />
+                 Example: <kerberos><realm>EXAMPLE.COM</realm></kerberos>
+
+                 How to generate decent password:
+                 Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
+                 In first line will be password and in second - corresponding SHA256.
+
+                 How to generate double SHA1:
+                 Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha1sum | tr -d '-' | xxd -r -p | sha1sum | tr -d '-'
+                 In first line will be password and in second - corresponding double SHA1.
+            -->
+            <password></password>
+
+            <!-- List of networks with open access.
+
+                 To open access from everywhere, specify:
+                    <ip>::/0</ip>
+
+                 To open access only from localhost, specify:
+                    <ip>::1</ip>
+                    <ip>127.0.0.1</ip>
+
+                 Each element of list has one of the following forms:
+                 <ip> IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
+                     2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
+                 <host> Hostname. Example: server01.yandex.ru.
+                     To check access, DNS query is performed, and all received addresses compared to peer address.
+                 <host_regexp> Regular expression for host names. Example, ^server\d\d-\d\d-\d\.yandex\.ru$
+                     To check access, DNS PTR query is performed for peer address and then regexp is applied.
+                     Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
+                     Strongly recommended that regexp is ends with $
+                 All results of DNS requests are cached till server restart.
+            -->
+            <networks>
+                <ip>::/0</ip>
+            </networks>
+
+            <!-- Settings profile for user. -->
+            <profile>default</profile>
+
+            <!-- Quota for user. -->
+            <quota>default</quota>
+
+            <!-- User can create other users and grant rights to them. -->
+            <access_management>1</access_management>
+        </default>
+    </users>
+
+    <!-- Quotas. -->
+    <quotas>
+        <!-- Name of quota. -->
+        <default>
+            <!-- Limits for time interval. You could specify many intervals with different limits. -->
+            <interval>
+                <!-- Length of interval. -->
+                <duration>3600</duration>
+
+                <!-- No limits. Just calculate resource usage for time interval. -->
+                <queries>0</queries>
+                <errors>0</errors>
+                <result_rows>0</result_rows>
+                <read_rows>0</read_rows>
+                <execution_time>0</execution_time>
+            </interval>
+        </default>
+    </quotas>
+</clickhouse>