You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@drill.apache.org by ts...@apache.org on 2015/05/17 08:51:40 UTC
[20/26] drill git commit: last-min features
last-min features
Project: http://git-wip-us.apache.org/repos/asf/drill/repo
Commit: http://git-wip-us.apache.org/repos/asf/drill/commit/6ea0c7a8
Tree: http://git-wip-us.apache.org/repos/asf/drill/tree/6ea0c7a8
Diff: http://git-wip-us.apache.org/repos/asf/drill/diff/6ea0c7a8
Branch: refs/heads/gh-pages
Commit: 6ea0c7a88a8f1852c9fd9f363f21944a578d5998
Parents: d8c9599
Author: Kristine Hahn <kh...@maprtech.com>
Authored: Sat May 16 19:17:13 2015 -0700
Committer: Kristine Hahn <kh...@maprtech.com>
Committed: Sat May 16 19:17:13 2015 -0700
----------------------------------------------------------------------
_data/docs.json | 97 ++++++-
_docs/074-query-audit-logging.md | 5 +
_docs/075-getting-query-information.md | 55 ++++
.../020-configuring-drill-memory.md | 4 +-
.../010-configuration-options-introduction.md | 2 +-
.../020-start-up-options.md | 3 +-
.../030-planning-and-exececution-options.md | 5 -
.../035-plugin-configuration-introduction.md | 2 +-
_docs/img/drill-bin.png | Bin 85005 -> 51164 bytes
_docs/img/drill-directory.png | Bin 87661 -> 46151 bytes
_docs/img/sqlline1.png | Bin 23074 -> 6633 bytes
_docs/install/010-install-drill-introduction.md | 10 +-
.../install/045-embedded-mode-prerequisites.md | 10 +-
.../047-installing-drill-on-the-cluster.md | 7 +-
.../050-starting-drill-in-distributed mode.md | 83 +++---
.../010-embedded-mode-prerequisites.md | 9 +-
...20-installing-drill-on-linux-and-mac-os-x.md | 8 +-
.../030-starting-drill-on-linux-and-mac-os-x.md | 25 +-
.../040-installing-drill-on-windows.md | 6 +-
.../050-starting-drill-on-windows.md | 8 +-
.../010-interfaces-introduction.md | 2 +-
_docs/tutorials/020-drill-in-10-minutes.md | 137 +++++----
.../030-analyzing-the-yelp-academic-dataset.md | 284 ++++++++++---------
.../050-analyzing-highly-dynamic-datasets.md | 53 ++--
24 files changed, 477 insertions(+), 338 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_data/docs.json
----------------------------------------------------------------------
diff --git a/_data/docs.json b/_data/docs.json
index c34dc8f..2bf92ef 100644
--- a/_data/docs.json
+++ b/_data/docs.json
@@ -2937,6 +2937,23 @@
"title": "Functions for Handling Nulls",
"url": "/docs/functions-for-handling-nulls/"
},
+ "Getting Query Information": {
+ "breadcrumbs": [
+ {
+ "title": "Query Audit Logging",
+ "url": "/docs/query-audit-logging/"
+ }
+ ],
+ "children": [],
+ "next_title": "SQL Reference",
+ "next_url": "/docs/sql-reference/",
+ "parent": "Query Audit Logging",
+ "previous_title": "Query Audit Logging",
+ "previous_url": "/docs/query-audit-logging/",
+ "relative_path": "_docs/075-getting-query-information.md",
+ "title": "Getting Query Information",
+ "url": "/docs/getting-query-information/"
+ },
"Getting Started": {
"breadcrumbs": [],
"children": [
@@ -4067,8 +4084,8 @@
}
],
"children": [],
- "next_title": "SQL Reference",
- "next_url": "/docs/sql-reference/",
+ "next_title": "Query Audit Logging",
+ "next_url": "/docs/query-audit-logging/",
"parent": "Query Data",
"previous_title": "Querying System Tables",
"previous_url": "/docs/querying-system-tables/",
@@ -4876,6 +4893,36 @@
"title": "Project Bylaws",
"url": "/docs/project-bylaws/"
},
+ "Query Audit Logging": {
+ "breadcrumbs": [],
+ "children": [
+ {
+ "breadcrumbs": [
+ {
+ "title": "Query Audit Logging",
+ "url": "/docs/query-audit-logging/"
+ }
+ ],
+ "children": [],
+ "next_title": "SQL Reference",
+ "next_url": "/docs/sql-reference/",
+ "parent": "Query Audit Logging",
+ "previous_title": "Query Audit Logging",
+ "previous_url": "/docs/query-audit-logging/",
+ "relative_path": "_docs/075-getting-query-information.md",
+ "title": "Getting Query Information",
+ "url": "/docs/getting-query-information/"
+ }
+ ],
+ "next_title": "Getting Query Information",
+ "next_url": "/docs/getting-query-information/",
+ "parent": "",
+ "previous_title": "Monitoring and Canceling Queries in the Drill Web UI",
+ "previous_url": "/docs/monitoring-and-canceling-queries-in-the-drill-web-ui/",
+ "relative_path": "_docs/074-query-audit-logging.md",
+ "title": "Query Audit Logging",
+ "url": "/docs/query-audit-logging/"
+ },
"Query Data": {
"breadcrumbs": [],
"children": [
@@ -5239,8 +5286,8 @@
}
],
"children": [],
- "next_title": "SQL Reference",
- "next_url": "/docs/sql-reference/",
+ "next_title": "Query Audit Logging",
+ "next_url": "/docs/query-audit-logging/",
"parent": "Query Data",
"previous_title": "Querying System Tables",
"previous_url": "/docs/querying-system-tables/",
@@ -7365,8 +7412,8 @@
"next_title": "SQL Reference Introduction",
"next_url": "/docs/sql-reference-introduction/",
"parent": "",
- "previous_title": "Monitoring and Canceling Queries in the Drill Web UI",
- "previous_url": "/docs/monitoring-and-canceling-queries-in-the-drill-web-ui/",
+ "previous_title": "Getting Query Information",
+ "previous_url": "/docs/getting-query-information/",
"relative_path": "_docs/080-sql-reference.md",
"title": "SQL Reference",
"url": "/docs/sql-reference/"
@@ -10776,8 +10823,8 @@
}
],
"children": [],
- "next_title": "SQL Reference",
- "next_url": "/docs/sql-reference/",
+ "next_title": "Query Audit Logging",
+ "next_url": "/docs/query-audit-logging/",
"parent": "Query Data",
"previous_title": "Querying System Tables",
"previous_url": "/docs/querying-system-tables/",
@@ -10801,6 +10848,36 @@
{
"breadcrumbs": [
{
+ "title": "Query Audit Logging",
+ "url": "/docs/query-audit-logging/"
+ }
+ ],
+ "children": [],
+ "next_title": "SQL Reference",
+ "next_url": "/docs/sql-reference/",
+ "parent": "Query Audit Logging",
+ "previous_title": "Query Audit Logging",
+ "previous_url": "/docs/query-audit-logging/",
+ "relative_path": "_docs/075-getting-query-information.md",
+ "title": "Getting Query Information",
+ "url": "/docs/getting-query-information/"
+ }
+ ],
+ "next_title": "Getting Query Information",
+ "next_url": "/docs/getting-query-information/",
+ "parent": "",
+ "previous_title": "Monitoring and Canceling Queries in the Drill Web UI",
+ "previous_url": "/docs/monitoring-and-canceling-queries-in-the-drill-web-ui/",
+ "relative_path": "_docs/074-query-audit-logging.md",
+ "title": "Query Audit Logging",
+ "url": "/docs/query-audit-logging/"
+ },
+ {
+ "breadcrumbs": [],
+ "children": [
+ {
+ "breadcrumbs": [
+ {
"title": "SQL Reference",
"url": "/docs/sql-reference/"
}
@@ -11582,8 +11659,8 @@
"next_title": "SQL Reference Introduction",
"next_url": "/docs/sql-reference-introduction/",
"parent": "",
- "previous_title": "Monitoring and Canceling Queries in the Drill Web UI",
- "previous_url": "/docs/monitoring-and-canceling-queries-in-the-drill-web-ui/",
+ "previous_title": "Getting Query Information",
+ "previous_url": "/docs/getting-query-information/",
"relative_path": "_docs/080-sql-reference.md",
"title": "SQL Reference",
"url": "/docs/sql-reference/"
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/074-query-audit-logging.md
----------------------------------------------------------------------
diff --git a/_docs/074-query-audit-logging.md b/_docs/074-query-audit-logging.md
new file mode 100644
index 0000000..f305725
--- /dev/null
+++ b/_docs/074-query-audit-logging.md
@@ -0,0 +1,5 @@
+---
+title: "Query Audit Logging"
+---
+
+
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/075-getting-query-information.md
----------------------------------------------------------------------
diff --git a/_docs/075-getting-query-information.md b/_docs/075-getting-query-information.md
new file mode 100644
index 0000000..51c7fe4
--- /dev/null
+++ b/_docs/075-getting-query-information.md
@@ -0,0 +1,55 @@
+---
+title: "Getting Query Information"
+parent: "Query Audit Logging"
+---
+The query log provides audit log functionality for the queries executed by various drillbits in the cluster. To access the query log, go to `sqlline_queries.json` file in the `log` directory of the Drill installation. The log records important information about queries executed on the Drillbit where Drill runs. The log includes query text, start time, end time, user, status, schema, and the query id.
+
+You can query the `sqlline_queries.json` using Drill to get audit logging information.
+
+## Checking the Most Recent Queries
+
+For example, to check the most recent queries, query the log using this command:
+
+ SELECT * FROM dfs.`default`.`/Users/drill-user/apache-drill-1.0.0/log/sqlline_queries.json` t ORDER BY `start` LIMIT 5;
+
+ +----------------+------------+---------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+---------+----------------+------------+
+ | finish | outcome | queryId | queryText | schema | start | username |
+ +----------------+------------+---------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+---------+----------------+------------+
+ | 1431752662216 | FAILED | 2aa9302b-bf6f-a378-d66e-151834e87b16 | select * from dfs.`default`.`/Users/nrentachintala/Downloads/testgoogle.json` t limit 1 | | 1431752660376 | anonymous |
+ | 1431752769079 | COMPLETED | 2aa92fc1-b722-c27a-10f7-57a1cf0dd366 | SELECT KVGEN(checkin_info) checkins FROM dfs.`/users/nrentachintala/Downloads/yelp/yelp_academic_dataset_checkin.json` LIMIT 2 | | 1431752765303 | anonymous |
+ | 1431752786341 | COMPLETED | 2aa92faf-2103-047b-9761-32eedefba1e6 | SELECT FLATTEN(KVGEN(checkin_info)) checkins FROM dfs.`/users/nrentachintala/Downloads/yelp/yelp_academic_dataset_checkin.json` LIMIT 20 | | 1431752784532 | anonymous |
+ | 1431752809084 | FAILED | 2aa92f97-61d3-1e9a-97b0-c754f5b568d5 | SELECT SUM(checkintbl.checkins.`value`) AS TotalCheckins FROM (SELECT FLATTEN(KVGEN(checkin_info)) checkins FROM dfs.`/users/nrentachintala/Downloads/yelp/yelp_academic_dataset_checkin.json` ) checkintbl | | 1431752808923 | anonymous |
+ | 1431752853992 | COMPLETED | 2aa92f87-0250-c6ac-3700-9ae1f98435b8 | SELECT SUM(checkintbl.checkins.`value`) AS TotalCheckins FROM (SELECT FLATTEN(KVGEN(checkin_info)) checkins FROM dfs.`/users/nrentachintala/Downloads/yelp/yelp_academic_dataset_checkin.json` ) checkintbl | | 1431752824947 | anonymous |
+ +----------------+------------+---------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+---------+----------------+------------+
+ 5 rows selected (0.532 seconds)
+
+{% include startnote.html %}This document aligns Drill output for example purposes. Drill output is not aligned in this case.{% include endnote.html %}
+
+## Checking Drillbit Traffic
+
+To check the total number of queries executed since the session started on the Drillbit, use the following command:
+
+ SELECT COUNT(*) FROM dfs.`default`.`/Users/drill-user/apache-drill-1.0.0/log/sqlline_queries.json`;
+
+ +---------+
+ | EXPR$0 |
+ +---------+
+ | 32 |
+ +---------+
+ 1 row selected (0.144 seconds)
+
+## Getting Query Success Statistics
+
+To get the total number of successful and failed executions, run the following command:
+
+ SELECT outcome, COUNT(*) FROM dfs.`default`.`/Users/drill-user/apache-drill-1.0.0/log/sqlline_queries.json` GROUP BY outcome;
+
+ +------------+---------+
+ | outcome | EXPR$1 |
+ +------------+---------+
+ | COMPLETED | 18 |
+ | FAILED | 14 |
+ +------------+---------+
+ 2 rows selected (0.219 seconds)
+
+Note the queryid column in the audit can be correlated with the profiles of the queries for troubleshooting/diagnostics purposes.
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/configure-drill/020-configuring-drill-memory.md
----------------------------------------------------------------------
diff --git a/_docs/configure-drill/020-configuring-drill-memory.md b/_docs/configure-drill/020-configuring-drill-memory.md
index 81487d1..5948bcc 100644
--- a/_docs/configure-drill/020-configuring-drill-memory.md
+++ b/_docs/configure-drill/020-configuring-drill-memory.md
@@ -3,7 +3,7 @@ title: "Configuring Drill Memory"
parent: "Configure Drill"
---
-This section describes how to configure the amount of direct memory allocated to a Drillbit for query processing in any Drill cluster, multitenant or not. The default memory for a Drillbit is 8G, but Drill prefers 16G or more depending on the workload. The total amount of direct memory that a Drillbit allocates to query operations cannot exceed the limit set.
+You can configure the amount of direct memory allocated to a Drillbit for query processing in any Drill cluster, multitenant or not. The default memory for a Drillbit is 8G, but Drill prefers 16G or more depending on the workload. The total amount of direct memory that a Drillbit allocates to query operations cannot exceed the limit set.
Drill uses Java direct memory and performs well when executing
operations in memory instead of storing the operations on disk. Drill does not
@@ -26,7 +26,7 @@ After you edit `<drill_installation_directory>/conf/drill-env.sh`, [restart the
## About the Drillbit startup script
-The drill-env.sh file contains the following options:
+The `drill-env.sh` file contains the following options:
DRILL_MAX_DIRECT_MEMORY="8G"
DRILL_MAX_HEAP="4G"
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/configure-drill/configuration-options/010-configuration-options-introduction.md
----------------------------------------------------------------------
diff --git a/_docs/configure-drill/configuration-options/010-configuration-options-introduction.md b/_docs/configure-drill/configuration-options/010-configuration-options-introduction.md
index 4fd7948..ee2ff9e 100644
--- a/_docs/configure-drill/configuration-options/010-configuration-options-introduction.md
+++ b/_docs/configure-drill/configuration-options/010-configuration-options-introduction.md
@@ -9,7 +9,7 @@ env.sh` and `drill-override.conf` files in the
`/conf` directory. Drill sources` /etc/drill/conf` if it exists. Otherwise,
Drill sources the local `<drill_installation_directory>/conf` directory.
-The sys.options table contains information about boot (start-up), system, and session options. The section, ["Start-up Options"]({{site.baseurl}}/docs/start-up-options), covers how to configure and view key boot options. The following table lists the options in alphabetical order and provides a brief description of supported options:
+The sys.options table contains information about system and session options. The sys.boot table contains information about Drill start-up options. The section, ["Start-up Options"]({{site.baseurl}}/docs/start-up-options), covers how to configure and view key boot options. The following table lists the system options in alphabetical order and provides a brief description of supported options:
## System Options
The sys.options table lists the following options that you can set as a system or session option as described in the section, ["Planning and Execution Options"]({{site.baseurl}}/docs/planning-and-execution-options).
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/configure-drill/configuration-options/020-start-up-options.md
----------------------------------------------------------------------
diff --git a/_docs/configure-drill/configuration-options/020-start-up-options.md b/_docs/configure-drill/configuration-options/020-start-up-options.md
index e525608..2f1ee5d 100644
--- a/_docs/configure-drill/configuration-options/020-start-up-options.md
+++ b/_docs/configure-drill/configuration-options/020-start-up-options.md
@@ -36,7 +36,7 @@ file tells Drill to scan that JAR file or associated object and include it.
You can run the following query to see a list of Drill’s startup options:
- SELECT * FROM sys.options WHERE type='BOOT';
+ SELECT * FROM sys.boot;
## Configuring Start-Up Options
@@ -57,7 +57,6 @@ The summary of start-up options, also known as boot options, lists default value
Tells Drill which directory to use when spooling. Drill uses a spool and sort operation for beyond memory operations. The sorting operation is designed to spool to a Hadoop file system. The default Hadoop file system is a local file system in the /tmp directory. Spooling performance (both writing and reading back from it) is constrained by the file system. For MapR clusters, use MapReduce volumes or set up local volumes to use for spooling purposes. Volumes improve performance and stripe data across as many disks as possible.
-
* drill.exec.zk.connect
Provides Drill with the ZooKeeper quorum to use to connect to data sources. Change this setting to point to the ZooKeeper quorum that you want Drill to use. You must configure this option on each Drillbit node.
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/configure-drill/configuration-options/030-planning-and-exececution-options.md
----------------------------------------------------------------------
diff --git a/_docs/configure-drill/configuration-options/030-planning-and-exececution-options.md b/_docs/configure-drill/configuration-options/030-planning-and-exececution-options.md
index f7d3442..2608538 100644
--- a/_docs/configure-drill/configuration-options/030-planning-and-exececution-options.md
+++ b/_docs/configure-drill/configuration-options/030-planning-and-exececution-options.md
@@ -8,11 +8,6 @@ queries that you run during the current Drill connection. Options set at the
system level affect the entire system and persist between restarts. Session
level settings override system level settings.
-You can run the following query to see a list of the system and session
-planning and execution options:
-
- SELECT name FROM sys.options WHERE type in (SYSTEM, SESSION);
-
## Configuring Planning and Execution Options
Use the ALTER SYSTEM or ALTER SESSION commands to set options. Typically,
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/connect-a-data-source/035-plugin-configuration-introduction.md
----------------------------------------------------------------------
diff --git a/_docs/connect-a-data-source/035-plugin-configuration-introduction.md b/_docs/connect-a-data-source/035-plugin-configuration-introduction.md
index 7744310..332966c 100644
--- a/_docs/connect-a-data-source/035-plugin-configuration-introduction.md
+++ b/_docs/connect-a-data-source/035-plugin-configuration-introduction.md
@@ -7,7 +7,7 @@ cluster, Drill broadcasts the information to all of the other Drill nodes
to have identical storage plugin configurations. You do not need to
restart any of the Drillbits when you add or update a storage plugin instance.
-Use the Drill Web UI to update or add a new storage plugin. Launch a web browser, go to: `http://<IP address of the sandbox>:8047`, and then go to the Storage tab.
+Use the Drill Web UI to update or add a new storage plugin. Launch a web browser, go to: `http://<IP address or host name>:8047`, and then go to the Storage tab.
To create and configure a new storage plugin:
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/img/drill-bin.png
----------------------------------------------------------------------
diff --git a/_docs/img/drill-bin.png b/_docs/img/drill-bin.png
old mode 100644
new mode 100755
index 6cbf7b8..a4c21d8
Binary files a/_docs/img/drill-bin.png and b/_docs/img/drill-bin.png differ
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/img/drill-directory.png
----------------------------------------------------------------------
diff --git a/_docs/img/drill-directory.png b/_docs/img/drill-directory.png
old mode 100644
new mode 100755
index f15e898..ab38a33
Binary files a/_docs/img/drill-directory.png and b/_docs/img/drill-directory.png differ
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/img/sqlline1.png
----------------------------------------------------------------------
diff --git a/_docs/img/sqlline1.png b/_docs/img/sqlline1.png
old mode 100644
new mode 100755
index 2588d91..5ea6b30
Binary files a/_docs/img/sqlline1.png and b/_docs/img/sqlline1.png differ
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/010-install-drill-introduction.md
----------------------------------------------------------------------
diff --git a/_docs/install/010-install-drill-introduction.md b/_docs/install/010-install-drill-introduction.md
index 09df476..0ca6fe5 100644
--- a/_docs/install/010-install-drill-introduction.md
+++ b/_docs/install/010-install-drill-introduction.md
@@ -4,9 +4,7 @@ parent: "Install Drill"
---
-You can install Drill in embedded mode or in distributed mode. Installing
-Drill in embedded mode does not require any configuration. If you want to use Drill in a
-clustered Hadoop environment, you can install Drill in distributed mode.
-Installing in distributed mode requires some configuration, however once you
-install you can connect Drill to your Hive, HBase, or distributed file system
-data sources and run queries on them.
\ No newline at end of file
+You can install Drill in either embedded mode or distributed mode. Installing
+Drill in embedded mode does not require any configuration. To use Drill in a
+clustered Hadoop environment, install Drill in distributed mode. You need to perform some configuration after installing Drill in distributed mode. After you complete these tasks, connect Drill to your Hive, HBase, or distributed file system
+data sources, and run queries on them.
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/045-embedded-mode-prerequisites.md
----------------------------------------------------------------------
diff --git a/_docs/install/045-embedded-mode-prerequisites.md b/_docs/install/045-embedded-mode-prerequisites.md
index e0289d2..73f4ab0 100644
--- a/_docs/install/045-embedded-mode-prerequisites.md
+++ b/_docs/install/045-embedded-mode-prerequisites.md
@@ -14,10 +14,10 @@ To install Apache Drill in distributed mode, complete the following steps:
**Prerequisites**
-Before you install Apache Drill on nodes in your cluster, you must have the
-following software and services installed:
+Before you install Apache Drill on nodes in your cluster, install and configure the
+following software and services:
- * [Oracle JDK version 7](http://www.oracle.com/technetwork/java/javase/downloads/jdk7-downloads-1880260.html)
- * Configured and running ZooKeeper quorum
- * Configured and running Hadoop cluster (Recommended)
+ * [Oracle JDK version 7](http://www.oracle.com/technetwork/java/javase/downloads/jdk7-downloads-1880260.html) (Required)
+ * Configured and running a ZooKeeper quorum (Required)
+ * Configured and running a Hadoop cluster (Recommended)
* DNS (Recommended)
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/047-installing-drill-on-the-cluster.md
----------------------------------------------------------------------
diff --git a/_docs/install/047-installing-drill-on-the-cluster.md b/_docs/install/047-installing-drill-on-the-cluster.md
index eeef763..ac224b5 100644
--- a/_docs/install/047-installing-drill-on-the-cluster.md
+++ b/_docs/install/047-installing-drill-on-the-cluster.md
@@ -6,8 +6,8 @@ Complete the following steps to install Drill on designated nodes:
1. Download the Drill tarball.
- curl http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz
- 2. Explode the tarball to the directory of your choice. For example, to install Drill in `/opt`:
+ curl http://getdrill.org/drill/download/apache-drill-1.0.0.tar.gz
+ 2. Explode the tarball to the directory of your choice, such as `/opt`:
tar -xzvf apache-drill-0.9.0.tar.gz -C /opt
3. In `drill-override.conf,` create a unique Drill `cluster ID`, and provide Zookeeper host names and port numbers to configure a connection to your Zookeeper quorum.
@@ -21,6 +21,5 @@ Complete the following steps to install Drill on designated nodes:
zk.connect: "<zkhostname1>:<port>,<zkhostname2>:<port>,<zkhostname3>:<port>"
}
-You can connect Drill to various types of data sources. Refer to [Connect
-Apache Drill to Data Sources]({{ site.baseurl }}/docs/connect-a-data-source-introduction) to get configuration instructions for the
+You can connect Drill to various types of data sources. Refer to [Connect Apache Drill to Data Sources]({{ site.baseurl }}/docs/connect-a-data-source-introduction) to get configuration instructions for the
particular type of data source that you want to connect to Drill.
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/050-starting-drill-in-distributed mode.md
----------------------------------------------------------------------
diff --git a/_docs/install/050-starting-drill-in-distributed mode.md b/_docs/install/050-starting-drill-in-distributed mode.md
index ac730c7..4a66447 100644
--- a/_docs/install/050-starting-drill-in-distributed mode.md
+++ b/_docs/install/050-starting-drill-in-distributed mode.md
@@ -17,12 +17,44 @@ For example, to restart a Drillbit, navigate to the Drill installation directory
bin/drillbit.sh restart
-## Invoking SQLLine
-SQLLine is used as the Drill shell. SQLLine connects to relational databases and executes SQL commands. You invoke SQLLine for Drill in embedded or distributed mode. If you want to use a particular storage plugin, you specify the plugin as a schema when you invoke SQLLine.
+## Starting the Drill Shell
+Using the Drill shell, you can connect to relational databases and execute SQL commands. To start the Drill shell, run one of the following scripts, which are located in the bin directory of the Drill installation:
-### SQLLine Command Syntax on Linux and Mac OS X
-To start SQLLine, use the following **sqlline command** syntax:
+* `drill-conf`
+ Opens the shell using the connection string to ZooKeeper nodes specified in the drill-conf script.
+* `drill-localhost`
+ Opens the Drill shell using a connection to the ZooKeeper running on the local host.
+Complete the following steps to start the Drill shell on the local node:
+
+ 1. Navigate to the Drill installation directory, and issue the following command to start the Drillbit if necessary:
+
+ bin/drillbit.sh restart
+ 2. Issue the following command to start the Drill shell if ZooKeeper is running on the same node as the shell:
+
+ bin/drill-localhost
+
+ Alternatively, issue the following command to start the Drill shell using the connection string in `drill-conf`:
+
+ bin/drill-conf
+
+ 3. Issue the following query to check the Drillbits running in the cluster:
+
+ 0: jdbc:drill:zk=<zk1host>:<port> select * from sys.drillbits;
+
+Drill provides a list of Drillbits that are running.
+
+ +----------------+--------------+--------------+--------------------+
+ | host | user_port | control_port | data_port |
+ +----------------+--------------+--------------+--------------------+
+ | <host address> | <port number>| <port number>| <port number> |
+ +----------------+--------------+--------------+--------------------+
+
+Now you can run queries. The Drill installation includes sample data
+that you can query. Refer to [Querying Parquet Files]({{ site.baseurl }}/docs/querying-parquet-files/).
+
+### Using an Ad-Hoc Connection to Drill
+To use a custom connection to Drill, but not alter the connection string in `drill-conf` that you normally use, start the Drill shell on an ad-hoc basis using `sqlline`. For example, to start the Drill shell using a particular storage plugin as a schema, use the following command syntax:
sqlline –u jdbc:drill:[schema=<storage plugin>;]zk=<zk name>[:<port>][,<zk name2>[:<port>]... ]
@@ -31,51 +63,20 @@ To start SQLLine, use the following **sqlline command** syntax:
* `-u` is the option that precedes a connection string. Required.
* `jdbc` is the connection protocol. Required.
* `schema` is the name of a [storage plugin]({{site.baseurl}}/docs/storage-plugin-registration) to use for queries. Optional.
-* `Zk=zkname` is one or more ZooKeeper host names or IP addresses. Optional if you are running SQLLine and ZooKeeper on the local node.
+* `Zk=zkname` is one or more ZooKeeper host names or IP addresses.
* `port` is the ZooKeeper port number. Optional. Port 2181 is the default.
-#### Examples of Starting Drill
-This example also starts SQLLine using the `dfs` storage plugin. Specifying the storage plugin when you start up eliminates the need to specify the storage plugin in the query:
-
+For example, start the Drill shell using the `dfs` storage plugin. Specifying the storage plugin when you start up eliminates the need to specify the storage plugin in the query:
bin/sqlline –u jdbc:drill:schema=dfs;zk=centos26
-This command starts SQLLine in a cluster configured to run ZooKeeper on three nodes:
+This command starts the Drill shell in a cluster configured to run ZooKeeper on three nodes:
bin/sqlline –u jdbc:drill:zk=cento23,zk=centos24,zk=centos26:5181
-## Procedure for Starting Drill in Distributed Mode
-
-Complete the following steps to start Drill:
-
- 1. Navigate to the Drill installation directory, and issue the following command to start a Drillbit:
-
- bin/drillbit.sh restart
- 2. Issue the following command to invoke SQLLine and start Drill if ZooKeeper is running on the same node as SQLLine:
-
- bin/sqlline -u jdbc:drill:
-
- If you cannot connect to Drill, invoke SQLLine with the ZooKeeper quorum:
-
- bin/sqlline -u jdbc:drill:zk=<zk1host>:<port>,<zk2host>:<port>,<zk3host>:<port>
- 3. Issue the following query to Drill to verify that all Drillbits have joined the cluster:
-
- 0: jdbc:drill:zk=<zk1host>:<port> select * from sys.drillbits;
-
-Drill provides a list of Drillbits that have joined.
-
- +------------+------------+--------------+--------------------+
- | host | user_port | control_port | data_port |
- +------------+------------+--------------+--------------------+
- | <host address> | <port number>| <port number>| <port number>|
- +------------+------------+--------------+--------------------+
-
-Now you can run queries. The Drill installation includes sample data
-that you can query. Refer to [Querying Parquet Files]({{ site.baseurl }}/docs/querying-parquet-files/).
-
-## Exiting SQLLine
+## Exiting the Drill Shell
-To exit SQLLine, issue the following command:
+To exit the Drill shell, issue the following command:
!quit
@@ -83,4 +84,4 @@ To exit SQLLine, issue the following command:
In some cases, such as stopping while a query is in progress, the `!quit` command does not stop Drill running in embedded mode. In distributed mode, you stop the Drillbit service. Navigate to the Drill installation directory, and issue the following command to stop a Drillbit:
- bin/drillbit.sh stop
+ bin/drillbit.sh stop
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/installing-drill-in-embedded-mode/010-embedded-mode-prerequisites.md
----------------------------------------------------------------------
diff --git a/_docs/install/installing-drill-in-embedded-mode/010-embedded-mode-prerequisites.md b/_docs/install/installing-drill-in-embedded-mode/010-embedded-mode-prerequisites.md
index 87113c3..f0cd33f 100644
--- a/_docs/install/installing-drill-in-embedded-mode/010-embedded-mode-prerequisites.md
+++ b/_docs/install/installing-drill-in-embedded-mode/010-embedded-mode-prerequisites.md
@@ -3,16 +3,13 @@ title: "Embedded Mode Prerequisites"
parent: "Installing Drill in Embedded Mode"
---
Installing Drill in embedded mode installs Drill locally on your machine.
-Embedded mode is a quick, easy way to install and try Drill without having to
-perform any configuration tasks. When you install Drill in embedded mode, the
-Drillbit service is installed locally and starts automatically when you invoke
-SQLLine, the Drill shell. You can install Drill in embedded mode on a machine
+Embedded mode is a quick way to install and try Drill without having to
+perform any configuration tasks. Installing Drill in embedded mode configures the
+local Drillbit service to start automatically when you launch the Drill shell. You can install Drill in embedded mode on a machine
running Linux, Mac OS X, or Windows.
**Prerequisite:**
-You must have the following software installed on your machine to run Drill:
-
You need to meet the following prerequisites to run Drill:
* Linux, Mac OS X, and Windows: [Oracle Java SE Development (JDK) Kit 7](http://www.oracle.com/technetwork/java/javase/downloads/jdk7-downloads-1880260.html) installation
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/installing-drill-in-embedded-mode/020-installing-drill-on-linux-and-mac-os-x.md
----------------------------------------------------------------------
diff --git a/_docs/install/installing-drill-in-embedded-mode/020-installing-drill-on-linux-and-mac-os-x.md b/_docs/install/installing-drill-in-embedded-mode/020-installing-drill-on-linux-and-mac-os-x.md
index 2720fe7..51c80fe 100755
--- a/_docs/install/installing-drill-in-embedded-mode/020-installing-drill-on-linux-and-mac-os-x.md
+++ b/_docs/install/installing-drill-in-embedded-mode/020-installing-drill-on-linux-and-mac-os-x.md
@@ -6,16 +6,16 @@ First, check that you [meet the prerequisites]({{site.baseurl}}/docs/embedded-mo
Complete the following steps to install Drill:
-1. Issue the following command in a terminal to download the latest, stable version of Apache Drill to a directory on your machine, or download Drill from the [Drill web site](http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz):
+1. Issue the following command in a terminal to download the latest, stable version of Apache Drill to a directory on your machine, or download Drill from the [Drill web site](http://getdrill.org/drill/download/apache-drill-1.0.0.tar.gz):
- wget http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz
+ wget http://getdrill.org/drill/download/apache-drill-1.0.0.tar.gz
2. Copy the downloaded file to the directory where you want to install Drill.
3. Extract the contents of the Drill tar.gz file. Use sudo if necessary:
- sudo tar -xvzf apache-drill-0.9.0..tar.gz
+ sudo tar -xvzf apache-drill-1.0.0.tar.gz
-The extraction process creates the installation directory named apache-drill-0.9.0 containing the Drill software.
+The extraction process creates the installation directory named apache-drill-1.0.0 containing the Drill software.
At this point, you can [start Drill]({{site.baseurl}}/docs/starting-drill-on-linux-and-mac-os-x).
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/installing-drill-in-embedded-mode/030-starting-drill-on-linux-and-mac-os-x.md
----------------------------------------------------------------------
diff --git a/_docs/install/installing-drill-in-embedded-mode/030-starting-drill-on-linux-and-mac-os-x.md b/_docs/install/installing-drill-in-embedded-mode/030-starting-drill-on-linux-and-mac-os-x.md
index ae72664..2bbfede 100644
--- a/_docs/install/installing-drill-in-embedded-mode/030-starting-drill-on-linux-and-mac-os-x.md
+++ b/_docs/install/installing-drill-in-embedded-mode/030-starting-drill-on-linux-and-mac-os-x.md
@@ -2,38 +2,27 @@
title: "Starting Drill on Linux and Mac OS X"
parent: "Installing Drill in Embedded Mode"
---
-Launch SQLLine using the sqlline command to start to Drill in embedded mode. The command directs SQLLine to connect to Drill using jdbc. The zk=local means the local node is the ZooKeeper node. Complete the following steps to launch SQLLine and start Drill:
+Start the Drill shell using the `drill-embedded` command. The command uses a jdbc connection string and identifies the local node as the ZooKeeper node. Complete the following steps to start the Drill shell:
1. Navigate to the Drill installation directory. For example:
- cd apache-drill-0.9.0
+ cd apache-drill-1.0.0
2. Issue the following command to launch SQLLine:
- bin/sqlline -u jdbc:drill:zk=local
+ bin/drill-embedded
The `0: jdbc:drill:zk=local>` prompt appears.
- At this point, you can [submit queries]({{site.baseurl}}/docs/drill-in-10-minutes#query-sample-data) to Drill.
+ At this point, you can [run queries]({{site.baseurl}}/docs/drill-in-10-minutes#query-sample-data).
-## Example of Starting Drill
-
-The simplest example of how to start SQLLine is to identify the protocol, JDBC, and ZooKeeper node or nodes in the **sqlline** command. This example starts SQLLine on a node in an embedded, single-node cluster:
-
- sqlline -u jdbc:drill:zk=local
-
-This example also starts SQLLine using the `dfs` storage plugin. Specifying the storage plugin when you start up eliminates the need to specify the storage plugin in the query:
-
-
- bin/sqlline –u jdbc:drill:schema=dfs;zk=centos26
-
-You can use the schema option in the **sqlline** command to specify a storage plugin. Specifying the storage plugin when you start up eliminates the need to specify the storage plugin in the query: For example, this command specifies the `dfs` storage plugin.
+You can also use the **sqlline** command to start Drill using a custom connection string, as described in ["Using an Ad-Hoc Connection to Drill"](docs/starting-drill-in-distributed-mode/#using-an-ad-hoc-connection-to-drill). For example, you can specify the storage plugin when you start the shell. Doing so eliminates the need to specify the storage plugin in the query: For example, this command specifies the `dfs` storage plugin.
bin/sqlline –u jdbc:drill:schema=dfs;zk=local
-## Exiting SQLLine
+## Exiting the Drill Shell
-To exit SQLLine, issue the following command:
+To exit the Drill shell, issue the following command:
!quit
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/installing-drill-in-embedded-mode/040-installing-drill-on-windows.md
----------------------------------------------------------------------
diff --git a/_docs/install/installing-drill-in-embedded-mode/040-installing-drill-on-windows.md b/_docs/install/installing-drill-in-embedded-mode/040-installing-drill-on-windows.md
index f12e175..05328c7 100755
--- a/_docs/install/installing-drill-in-embedded-mode/040-installing-drill-on-windows.md
+++ b/_docs/install/installing-drill-in-embedded-mode/040-installing-drill-on-windows.md
@@ -4,9 +4,9 @@ parent: "Installing Drill in Embedded Mode"
---
You can install Drill on Windows 7 or 8. First, check that you [meet the prerequisites]({{site.baseurl}}/docs/embedded-mode-prerequisites), including setting the JAVA_HOME environment variable, and then install Drill. Complete the following steps to install Drill:
-1. Click the following link to download the latest, stable version of Apache Drill: [http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz](http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz)
-2. Move the `apache-drill-0.9.0.tar.gz` file to a directory where you want to install Drill.
-3. Unzip the `TAR.GZ` file using a third-party tool. If the tool you use does not unzip the TAR file as well as the `TAR.GZ` file, unzip the `apache-drill-0.9.0.tar` to extract the Drill software. The extraction process creates the installation directory named apache-drill-0.9.0 containing the Drill software. For example:
+1. Click the following link to download the latest, stable version of Apache Drill: [http://getdrill.org/drill/download/apache-drill-0.1.0.tar.gz](http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz)
+2. Move the `apache-drill-0.1.0.tar.gz` file to a directory where you want to install Drill.
+3. Unzip the `TAR.GZ` file using a third-party tool. If the tool you use does not unzip the TAR file as well as the `TAR.GZ` file, unzip the `apache-drill-0.1.0.tar` to extract the Drill software. The extraction process creates the installation directory named apache-drill-0.1.0 containing the Drill software. For example:
At this point, you can [start Drill]({{site.baseurl}}/docs/starting-drill-on-windows).
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/install/installing-drill-in-embedded-mode/050-starting-drill-on-windows.md
----------------------------------------------------------------------
diff --git a/_docs/install/installing-drill-in-embedded-mode/050-starting-drill-on-windows.md b/_docs/install/installing-drill-in-embedded-mode/050-starting-drill-on-windows.md
index ba95059..e8ef3e4 100644
--- a/_docs/install/installing-drill-in-embedded-mode/050-starting-drill-on-windows.md
+++ b/_docs/install/installing-drill-in-embedded-mode/050-starting-drill-on-windows.md
@@ -2,9 +2,9 @@
title: "Starting Drill on Windows"
parent: "Installing Drill in Embedded Mode"
---
-Launch SQLLine using the **sqlline command** to start to Drill in embedded mode. The command directs SQLLine to connect to Drill. The `zk=local` means the local node is the ZooKeeper node. Complete the following steps to launch SQLLine and start Drill:
+Start the Drill shell using the **sqlline command**. The `zk=local` means the local node is the ZooKeeper node. Complete the following steps to launch the Drill shell:
-1. Open the apache-drill-0.9.0 folder.
+1. Open the apache-drill-0.1.0 folder.
2. Open the bin folder, and double-click the `sqlline.bat` file:
The Windows command prompt opens.
@@ -18,9 +18,9 @@ You can use the schema option in the **sqlline** command to specify a storage pl
bin/sqlline –u jdbc:drill:schema=dfs;zk=local
-## Exiting SQLLine
+## Exiting the Drill Shell
-To exit SQLLine, issue the following command:
+To exit the Drill shell, issue the following command:
!quit
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/odbc-jdbc-interfaces/010-interfaces-introduction.md
----------------------------------------------------------------------
diff --git a/_docs/odbc-jdbc-interfaces/010-interfaces-introduction.md b/_docs/odbc-jdbc-interfaces/010-interfaces-introduction.md
index d7bba62..a427590 100644
--- a/_docs/odbc-jdbc-interfaces/010-interfaces-introduction.md
+++ b/_docs/odbc-jdbc-interfaces/010-interfaces-introduction.md
@@ -4,7 +4,7 @@ parent: "ODBC/JDBC Interfaces"
---
You can connect to Apache Drill through the following interfaces:
- * Drill shell (SQLLine)
+ * Drill shell
* Drill Web UI
* [ODBC]({{ site.baseurl }}/docs/odbc-jdbc-interfaces#using-odbc-to-access-apache-drill-from-bi-tools)*
* [JDBC]({{ site.baseurl }}/docs/using-jdbc/)
http://git-wip-us.apache.org/repos/asf/drill/blob/6ea0c7a8/_docs/tutorials/020-drill-in-10-minutes.md
----------------------------------------------------------------------
diff --git a/_docs/tutorials/020-drill-in-10-minutes.md b/_docs/tutorials/020-drill-in-10-minutes.md
index 9f16044..98f5758 100755
--- a/_docs/tutorials/020-drill-in-10-minutes.md
+++ b/_docs/tutorials/020-drill-in-10-minutes.md
@@ -43,32 +43,32 @@ The output looks something like this:
Complete the following steps to install Drill:
-1. Issue the following command in a terminal to download the latest, stable version of Apache Drill to a directory on your machine, or download Drill from the [Drill web site](http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz):
+1. Issue the following command in a terminal to download the latest version of Apache Drill to a directory on your machine, or download Drill from the [Drill web site](http://getdrill.org/drill/download/apache-drill-1.0.0.tar.gz):
- wget http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz
+ wget http://getdrill.org/drill/download/apache-drill-1.0.0.tar.gz
2. Copy the downloaded file to the directory where you want to install Drill.
3. Extract the contents of the Drill tar.gz file. Use sudo if necessary:
- sudo tar -xvzf apache-drill-0.9.0..tar.gz
+ sudo tar -xvzf apache-drill-1.0.0.tar.gz
-The extraction process creates the installation directory named apache-drill-0.9.0 containing the Drill software.
+The extraction process creates the installation directory named apache-drill-1.0.0 containing the Drill software.
-At this point, you can [start Drill]({{site.baseurl}}/docs/drill-in-10-minutes/#start-drill).
+At this point, you can start Drill.
## Start Drill on Linux and Mac OS X
-Launch SQLLine using the sqlline command to start to Drill in embedded mode. The command directs SQLLine to connect to Drill. The zk=local means the local node is the ZooKeeper node. Complete the following steps to launch SQLLine and start Drill:
+Start Drill in embedded mode using the `drill-embedded` command:
1. Navigate to the Drill installation directory. For example:
- cd apache-drill-0.9.0
+ cd apache-drill-1.0.0
-2. Issue the following command to launch SQLLine:
+2. Issue the following command to launch Drill in embedded mode:
- bin/sqlline -u jdbc:drill:zk=local
+ bin/drill-embedded
- The `0: jdbc:drill:zk=local>` prompt appears.
+ The message of the day followed by the `0: jdbc:drill:zk=local>` prompt appears.
At this point, you can [submit queries]({{site.baseurl}}/docs/drill-in-10-minutes#query-sample-data) to Drill.
@@ -76,24 +76,25 @@ Launch SQLLine using the sqlline command to start to Drill in embedded mode. The
You can install Drill on Windows 7 or 8. First, set the JAVA_HOME environment variable, and then install Drill. Complete the following steps to install Drill:
-1. Click the following link to download the latest, stable version of Apache Drill: [http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz](http://getdrill.org/drill/download/apache-drill-0.9.0.tar.gz)
-2. Move the `apache-drill-0.9.0.tar.gz` file to a directory where you want to install Drill.
-3. Unzip the `TAR.GZ` file using a third-party tool. If the tool you use does not unzip the TAR file as well as the `TAR.GZ` file, unzip the `apache-drill-0.9.0.tar` to extract the Drill software. The extraction process creates the installation directory named apache-drill-0.9.0 containing the Drill software. For example:
+1. Click the following link to download the latest version of Apache Drill: [http://getdrill.org/drill/download/apache-drill-1.0.0.tar.gz](http://getdrill.org/drill/download/apache-drill-0.1.0.tar.gz)
+2. Move the `apache-drill-1.0.0.tar.gz` file to a directory where you want to install Drill.
+3. Unzip the `TAR.GZ` file using a third-party tool. If the tool you use does not unzip the TAR file as well as the `TAR.GZ` file, unzip the `apache-drill-1.0.0.tar` to extract the Drill software. The extraction process creates the installation directory named apache-drill-1.0.0 containing the Drill software. For example:
- At this point, you can start Drill.
+
+At this point, you can start Drill.
## Start Drill on Windows
-Launch SQLLine using the **sqlline command** to start to Drill in embedded mode. The command directs SQLLine to connect to Drill. The `zk=local` means the local node is the ZooKeeper node. Complete the following steps to launch SQLLine and start Drill:
+Start Drill by running the sqlline.bat file and typing a connection string, as shown in the following procedure. The `zk=local` in the connection string means the local node is the ZooKeeper node:
-1. Open the apache-drill-0.9.0 folder.
+1. Open the apache-drill-1.0.0 folder.
2. Open the bin folder, and double-click the `sqlline.bat` file:
The Windows command prompt opens.
3. At the sqlline> prompt, type `!connect jdbc:drill:zk=local` and then press Enter:
-4. Enter the username, `admin`, and password, also `admin` when prompted.
+4. Enter the username, `admin`, and password, also `admin` when prompted.
The `0: jdbc:drill:zk=local>` prompt appears.
-At this point, you can [submit queries]({{ site.baseurl }}/docs/drill-in-10-minutes#query-sample-data) to Drill.
+At this point, you can [run queries]({{ site.baseurl }}/docs/drill-in-10-minutes#query-sample-data).
## Stopping Drill
@@ -118,35 +119,18 @@ A sample JSON file, `employee.json`, contains fictitious employee data.
To view the data in the `employee.json` file, submit the following SQL query
to Drill:
- 0: jdbc:drill:zk=local> SELECT * FROM cp.`employee.json`;
+ 0: jdbc:drill:zk=local> SELECT * FROM cp.`employee.json` LIMIT 3;
-The query returns the following results:
+The query output is:
-**Example of partial output**
-
- +-------------+------------+------------+------------+-------------+-----------+
- | employee_id | full_name | first_name | last_name | position_id | position_ |
- +-------------+------------+------------+------------+-------------+-----------+
- | 1101 | Steve Eurich | Steve | Eurich | 16 | Store T |
- | 1102 | Mary Pierson | Mary | Pierson | 16 | Store T |
- | 1103 | Leo Jones | Leo | Jones | 16 | Store Tem |
- | 1104 | Nancy Beatty | Nancy | Beatty | 16 | Store T |
- | 1105 | Clara McNight | Clara | McNight | 16 | Store |
- | 1106 | Marcella Isaacs | Marcella | Isaacs | 17 | Stor |
- | 1107 | Charlotte Yonce | Charlotte | Yonce | 17 | Stor |
- | 1108 | Benjamin Foster | Benjamin | Foster | 17 | Stor |
- | 1109 | John Reed | John | Reed | 17 | Store Per |
- | 1110 | Lynn Kwiatkowski | Lynn | Kwiatkowski | 17 | St |
- | 1111 | Donald Vann | Donald | Vann | 17 | Store Pe |
- | 1112 | William Smith | William | Smith | 17 | Store |
- | 1113 | Amy Hensley | Amy | Hensley | 17 | Store Pe |
- | 1114 | Judy Owens | Judy | Owens | 17 | Store Per |
- | 1115 | Frederick Castillo | Frederick | Castillo | 17 | S |
- | 1116 | Phil Munoz | Phil | Munoz | 17 | Store Per |
- | 1117 | Lori Lightfoot | Lori | Lightfoot | 17 | Store |
- +-------------+------------+------------+------------+-------------+-----------+
- 1,155 rows selected (0.762 seconds)
- 0: jdbc:drill:zk=local>
+ +--------------+------------------+-------------+------------+--------------+---------------------+-----------+----------------+-------------+------------------------+----------+----------------+------------------+-----------------+---------+--------------------+
+ | employee_id | full_name | first_name | last_name | position_id | position_title | store_id | department_id | birth_date | hire_date | salary | supervisor_id | education_level | marital_status | gender | management_role |
+ +--------------+------------------+-------------+------------+--------------+---------------------+-----------+----------------+-------------+------------------------+----------+----------------+------------------+-----------------+---------+--------------------+
+ | 1 | Sheri Nowmer | Sheri | Nowmer | 1 | President | 0 | 1 | 1961-08-26 | 1994-12-01 00:00:00.0 | 80000.0 | 0 | Graduate Degree | S | F | Senior Management |
+ | 2 | Derrick Whelply | Derrick | Whelply | 2 | VP Country Manager | 0 | 1 | 1915-07-03 | 1994-12-01 00:00:00.0 | 40000.0 | 1 | Graduate Degree | M | M | Senior Management |
+ | 4 | Michael Spence | Michael | Spence | 2 | VP Country Manager | 0 | 1 | 1969-06-20 | 1998-01-01 00:00:00.0 | 40000.0 | 1 | Graduate Degree | S | M | Senior Management |
+ +--------------+------------------+-------------+------------+--------------+---------------------+-----------+----------------+-------------+------------------------+----------+----------------+------------------+-----------------+---------+--------------------+
+ 3 rows selected (0.827 seconds)
### Querying a Parquet File
@@ -176,17 +160,16 @@ your operating system:
The query returns the following results:
- +------------+------------+
- | EXPR$0 | EXPR$1 |
- +------------+------------+
- | AFRICA | lar deposits. blithely final packages cajole. regular waters ar |
- | AMERICA | hs use ironic, even requests. s |
- | ASIA | ges. thinly even pinto beans ca |
- | EUROPE | ly final courts cajole furiously final excuse |
- | MIDDLE EAST | uickly special accounts cajole carefully blithely close reques |
- +------------+------------+
- 5 rows selected (0.165 seconds)
- 0: jdbc:drill:zk=local>
+ +--------------+--------------+-----------------------+
+ | R_REGIONKEY | R_NAME | R_COMMENT |
+ +--------------+--------------+-----------------------+
+ | 0 | AFRICA | lar deposits. blithe |
+ | 1 | AMERICA | hs use ironic, even |
+ | 2 | ASIA | ges. thinly even pin |
+ | 3 | EUROPE | ly final courts cajo |
+ | 4 | MIDDLE EAST | uickly special accou |
+ +--------------+--------------+-----------------------+
+ 5 rows selected (0.409 seconds)
#### Nation File
@@ -194,7 +177,7 @@ If you followed the Apache Drill in 10 Minutes instructions to install Drill
in embedded mode, the path to the parquet file varies between operating
systems.
-**Note:** When you enter the query, include the version of Drill that you are currently running.
+{% include startnote.html %}When you enter the query, include the version of Drill that you are currently running.{% include endnote.html %}
To view the data in the `nation.parquet` file, issue the query appropriate for
your operating system:
@@ -212,14 +195,44 @@ your operating system:
The query returns the following results:
+ SELECT * FROM dfs.`Users/khahn/drill/apache-drill-1.0.0-SNAPSHOT/sample-data/nation.parquet`;
+ +--------------+-----------------+--------------+-----------------------+
+ | N_NATIONKEY | N_NAME | N_REGIONKEY | N_COMMENT |
+ +--------------+-----------------+--------------+-----------------------+
+ | 0 | ALGERIA | 0 | haggle. carefully f |
+ | 1 | ARGENTINA | 1 | al foxes promise sly |
+ | 2 | BRAZIL | 1 | y alongside of the p |
+ | 3 | CANADA | 1 | eas hang ironic, sil |
+ | 4 | EGYPT | 4 | y above the carefull |
+ | 5 | ETHIOPIA | 0 | ven packages wake qu |
+ | 6 | FRANCE | 3 | refully final reques |
+ | 7 | GERMANY | 3 | l platelets. regular |
+ | 8 | INDIA | 2 | ss excuses cajole sl |
+ | 9 | INDONESIA | 2 | slyly express asymp |
+ | 10 | IRAN | 4 | efully alongside of |
+ | 11 | IRAQ | 4 | nic deposits boost a |
+ | 12 | JAPAN | 2 | ously. final, expres |
+ | 13 | JORDAN | 4 | ic deposits are blit |
+ | 14 | KENYA | 0 | pending excuses hag |
+ | 15 | MOROCCO | 0 | rns. blithely bold c |
+ | 16 | MOZAMBIQUE | 0 | s. ironic, unusual a |
+ | 17 | PERU | 1 | platelets. blithely |
+ | 18 | CHINA | 2 | c dependencies. furi |
+ | 19 | ROMANIA | 3 | ular asymptotes are |
+ | 20 | SAUDI ARABIA | 4 | ts. silent requests |
+ | 21 | VIETNAM | 2 | hely enticingly expr |
+ | 22 | RUSSIA | 3 | requests against th |
+ | 23 | UNITED KINGDOM | 3 | eans boost carefully |
+ | 24 | UNITED STATES | 1 | y final packages. sl |
+ +--------------+-----------------+--------------+-----------------------+
+ 25 rows selected (0.101 seconds)
+
## Summary
-Now you know a bit about Apache Drill. To summarize, you have completed the
-following tasks:
+Now, you have been introduced to Apache Drill, which supports nested data, schema-less execution, and decentralized metadata. To summarize, you have completed the following tasks:
- * Learned that Apache Drill supports nested data, schema-less execution, and decentralized metadata.
* Downloaded and installed Apache Drill.
- * Invoked SQLLine with Drill in embedded mode.
+ * Started Drill in embedded mode.
* Queried the sample JSON file, `employee.json`, to view its data.
* Queried the sample `region.parquet` file to view its data.
* Queried the sample `nation.parquet` file to view its data.
@@ -228,7 +241,7 @@ following tasks:
Now that you have an idea about what Drill can do, you might want to:
- * [Deploy Drill in a clustered environment.]({{ site.baseurl }}/docs/deploying-drill-in-a-cluster)
+ * [Install Drill on a cluster.]({{ site.baseurl }}/docs/installing-drill-on-the-cluster)
* [Configure storage plugins to connect Drill to your data sources]({{ site.baseurl }}/docs/connect-a-data-source-introduction).
* Query [Hive]({{ site.baseurl }}/docs/querying-hive) and [HBase]({{ site.baseurl }}/docs/hbase-storage-plugin) data.
* [Query Complex Data]({{ site.baseurl }}/docs/querying-complex-data)