resolve conflicts

This commit is contained in:
shueybubbles
2019-05-14 14:35:24 -04:00
25 changed files with 1152 additions and 910 deletions
@@ -3,7 +3,7 @@
-- bigger - so you can see more impactful
-- Intelligent QP demonstrations (aka.ms/iqp)
--
-- Script last updated 10/02/2018
-- Script last updated 05/03/2019
--
-- Database backup source: aka.ms/wwibak
--
@@ -100,4 +100,4 @@ GO
UPDATE Fact.OrderHistoryExtended
SET [WWI Order ID] = [Order Key];
GO
GO
@@ -9,7 +9,17 @@
-- Email IntelligentQP@microsoft.com for questions\feedback
-- ******************************************************** --
USE WideWorldImportersDW;
USE [master];
GO
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 150;
GO
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE [WideWorldImportersDW];
GO
-- Compare execution time and distinct counts
@@ -0,0 +1,54 @@
-- ******************************************************** --
-- Batch mode Adaptive Join
-- See https://aka.ms/IQP for more background
-- Demo scripts: https://aka.ms/IQPDemos
-- This demo is on SQL Server 2017 and Azure SQL DB
-- Email IntelligentQP@microsoft.com for questions\feedback
-- ******************************************************** --
USE [master];
GO
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 140;
GO
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE [WideWorldImportersDW];
GO
-- Show with Live Query Stats
SELECT [fo].[Order Key], [si].[Lead Time Days], [fo].[Quantity]
FROM [Fact].[Order] AS [fo]
INNER JOIN [Dimension].[Stock Item] AS [si]
ON [fo].[Stock Item Key] = [si].[Stock Item Key]
WHERE [fo].[Quantity] = 360;
GO
-- Inserting quantity row that doesn't exist in the table yet
DELETE [Fact].[Order]
WHERE Quantity = 361;
INSERT [Fact].[Order]
([City Key], [Customer Key], [Stock Item Key], [Order Date Key], [Picked Date Key], [Salesperson Key], [Picker Key], [WWI Order ID], [WWI Backorder ID], Description, Package, Quantity, [Unit Price], [Tax Rate], [Total Excluding Tax], [Tax Amount], [Total Including Tax], [Lineage Key])
SELECT TOP 5 [City Key], [Customer Key], [Stock Item Key],
[Order Date Key], [Picked Date Key], [Salesperson Key],
[Picker Key], [WWI Order ID], [WWI Backorder ID],
Description, Package, 361, [Unit Price], [Tax Rate],
[Total Excluding Tax], [Tax Amount], [Total Including Tax],
[Lineage Key]
FROM [Fact].[Order];
GO
-- Show with Live Query Stats
SELECT [fo].[Order Key], [si].[Lead Time Days], [fo].[Quantity]
FROM [Fact].[Order] AS [fo]
INNER JOIN [Dimension].[Stock Item] AS [si]
ON [fo].[Stock Item Key] = [si].[Stock Item Key]
WHERE [fo].[Quantity] = 361;
GO
@@ -0,0 +1,46 @@
-- ******************************************************** --
-- Batch mode Memory Grant Feedback
-- See https://aka.ms/IQP for more background
-- Demo scripts: https://aka.ms/IQPDemos
-- This demo is on SQL Server 2017 and Azure SQL DB
-- Email IntelligentQP@microsoft.com for questions\feedback
-- ******************************************************** --
USE [master];
GO
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 140;
GO
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE [WideWorldImportersDW];
GO
-- Intentionally forcing a row underestimate
CREATE OR ALTER PROCEDURE [FactOrderByLineageKey]
@LineageKey INT
AS
SELECT [fo].[Order Key], [fo].[Description]
FROM [Fact].[Order] AS [fo]
INNER HASH JOIN [Dimension].[Stock Item] AS [si]
ON [fo].[Stock Item Key] = [si].[Stock Item Key]
WHERE [fo].[Lineage Key] = @LineageKey
AND [si].[Lead Time Days] > 0
ORDER BY [fo].[Stock Item Key], [fo].[Order Date Key] DESC
OPTION (MAXDOP 1);
GO
-- Compiled and executed using a lineage key that doesn't have rows
EXEC [FactOrderByLineageKey] 8;
GO
-- Execute this query a few times - each time looking at
-- the plan to see impact on spills, memory grant size, and run time
EXEC [FactOrderByLineageKey] 9;
GO
@@ -10,12 +10,18 @@
-- Email IntelligentQP@microsoft.com for questions\feedback
-- ******************************************************** --
USE [master];
GO
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 150;
GO
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE [WideWorldImportersDW];
GO
-- Row mode due to hint
SELECT [Tax Rate],
[Lineage Key],
@@ -0,0 +1,173 @@
-- ******************************************************** --
-- Interleaved Execution
-- See https://aka.ms/IQP for more background
-- Demo scripts: https://aka.ms/IQPDemos
-- This demo is on SQL Server 2017 and Azure SQL DB
-- Email IntelligentQP@microsoft.com for questions\feedback
-- ******************************************************** --
/*
Create MSTVF
*/
USE [WideWorldImportersDW];
GO
CREATE FUNCTION [Fact].[WhatIfOutlierEventQuantity](@event VARCHAR(15), @beginOrderDateKey DATE, @endOrderDateKey DATE)
RETURNS @OutlierEventQuantity TABLE (
[Order Key] [bigint],
[City Key] [int] NOT NULL,
[Customer Key] [int] NOT NULL,
[Stock Item Key] [int] NOT NULL,
[Order Date Key] [date] NOT NULL,
[Picked Date Key] [date] NULL,
[Salesperson Key] [int] NOT NULL,
[Picker Key] [int] NULL,
[OutlierEventQuantity] [int] NOT NULL)
AS
BEGIN
-- Valid @event values
-- 'Mild Recession'
-- 'Hurricane - South Atlantic'
-- 'Hurricane - East South Central'
-- 'Hurricane - West South Central'
IF @event = 'Mild Recession'
INSERT @OutlierEventQuantity
SELECT [o].[Order Key], [o].[City Key], [o].[Customer Key],
[o].[Stock Item Key], [o].[Order Date Key], [o].[Picked Date Key],
[o].[Salesperson Key], [o].[Picker Key],
CASE
WHEN [o].[Quantity] > 2 THEN [o].[Quantity] * .5
ELSE [o].[Quantity]
END
FROM [Fact].[Order] AS [o]
INNER JOIN [Dimension].[City] AS [c]
ON [c].[City Key] = [o].[City Key]
IF @event = 'Hurricane - South Atlantic'
INSERT @OutlierEventQuantity
SELECT [o].[Order Key], [o].[City Key], [o].[Customer Key],
[o].[Stock Item Key], [o].[Order Date Key], [o].[Picked Date Key],
[o].[Salesperson Key], [o].[Picker Key],
CASE
WHEN [o].[Quantity] > 10 THEN [o].[Quantity] * .5
ELSE [o].[Quantity]
END
FROM [Fact].[Order] AS [o]
INNER JOIN [Dimension].[City] AS [c]
ON [c].[City Key] = [o].[City Key]
WHERE [c].[State Province] IN
('Florida', 'Georgia', 'Maryland', 'North Carolina',
'South Carolina', 'Virginia', 'West Virginia',
'Delaware')
AND [o].[Order Date Key] BETWEEN @beginOrderDateKey AND @endOrderDateKey
IF @event = 'Hurricane - East South Central'
INSERT @OutlierEventQuantity
SELECT [o].[Order Key], [o].[City Key], [o].[Customer Key],
[o].[Stock Item Key], [o].[Order Date Key], [o].[Picked Date Key],
[o].[Salesperson Key], [o].[Picker Key],
CASE
WHEN [o].[Quantity] > 50 THEN [o].[Quantity] * .5
ELSE [o].[Quantity]
END
FROM [Fact].[Order] AS [o]
INNER JOIN [Dimension].[City] AS [c]
ON [c].[City Key] = [o].[City Key]
INNER JOIN [Dimension].[Stock Item] AS [si]
ON [si].[Stock Item Key] = [o].[Stock Item Key]
WHERE [c].[State Province] IN
('Alabama', 'Kentucky', 'Mississippi', 'Tennessee')
AND [si].[Buying Package] = 'Carton'
AND [o].[Order Date Key] BETWEEN @beginOrderDateKey AND @endOrderDateKey
IF @event = 'Hurricane - West South Central'
INSERT @OutlierEventQuantity
SELECT [o].[Order Key], [o].[City Key], [o].[Customer Key],
[o].[Stock Item Key], [o].[Order Date Key], [o].[Picked Date Key],
[o].[Salesperson Key], [o].[Picker Key],
CASE
WHEN [cu].[Customer] = 'Unknown' THEN 0
WHEN [cu].[Customer] <> 'Unknown' AND
[o].[Quantity] > 10 THEN [o].[Quantity] * .5
ELSE [o].[Quantity]
END
FROM [Fact].[Order] AS [o]
INNER JOIN [Dimension].[City] AS [c]
ON [c].[City Key] = [o].[City Key]
INNER JOIN [Dimension].[Customer] AS [cu]
ON [cu].[Customer Key] = [o].[Customer Key]
WHERE [c].[State Province] IN
('Arkansas', 'Louisiana', 'Oklahoma', 'Texas')
AND [o].[Order Date Key] BETWEEN @beginOrderDateKey AND @endOrderDateKey
RETURN
END
GO
USE [master];
GO
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 130;
GO
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE [WideWorldImportersDW];
GO
SELECT [fo].[Order Key], [fo].[Description], [fo].[Package],
[fo].[Quantity], [foo].[OutlierEventQuantity]
FROM [Fact].[Order] AS [fo]
INNER JOIN [Fact].[WhatIfOutlierEventQuantity]('Mild Recession',
'1-01-2013',
'10-15-2014') AS [foo] ON [fo].[Order Key] = [foo].[Order Key]
AND [fo].[City Key] = [foo].[City Key]
AND [fo].[Customer Key] = [foo].[Customer Key]
AND [fo].[Stock Item Key] = [foo].[Stock Item Key]
AND [fo].[Order Date Key] = [foo].[Order Date Key]
AND [fo].[Picked Date Key] = [foo].[Picked Date Key]
AND [fo].[Salesperson Key] = [foo].[Salesperson Key]
AND [fo].[Picker Key] = [foo].[Picker Key]
INNER JOIN [Dimension].[Stock Item] AS [si]
ON [fo].[Stock Item Key] = [si].[Stock Item Key]
WHERE [si].[Lead Time Days] > 0
AND [fo].[Quantity] > 50;
GO
USE [master];
GO
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 140;
GO
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE [WideWorldImportersDW];
GO
SELECT [fo].[Order Key], [fo].[Description], [fo].[Package],
[fo].[Quantity], [foo].[OutlierEventQuantity]
FROM [Fact].[Order] AS [fo]
INNER JOIN [Fact].[WhatIfOutlierEventQuantity]('Mild Recession',
'1-01-2013',
'10-15-2014') AS [foo] ON [fo].[Order Key] = [foo].[Order Key]
AND [fo].[City Key] = [foo].[City Key]
AND [fo].[Customer Key] = [foo].[Customer Key]
AND [fo].[Stock Item Key] = [foo].[Stock Item Key]
AND [fo].[Order Date Key] = [foo].[Order Date Key]
AND [fo].[Picked Date Key] = [foo].[Picked Date Key]
AND [fo].[Salesperson Key] = [foo].[Salesperson Key]
AND [fo].[Picker Key] = [foo].[Picker Key]
INNER JOIN [Dimension].[Stock Item] AS [si]
ON [fo].[Stock Item Key] = [si].[Stock Item Key]
WHERE [si].[Lead Time Days] > 0
AND [fo].[Quantity] > 50;
GO
@@ -10,13 +10,16 @@
-- Email IntelligentQP@microsoft.com for questions\feedback
-- ******************************************************** --
ALTER DATABASE WideWorldImportersDW SET COMPATIBILITY_LEVEL = 150;
USE [master];
GO
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 150;
GO
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE WideWorldImportersDW;
USE [WideWorldImportersDW];
GO
-- Simulate out-of-date stats
@@ -30,10 +33,10 @@ GO
SELECT
fo.[Order Key], fo.Description,
si.[Lead Time Days]
FROM Fact.OrderHistory AS fo
FROM Fact.OrderHistory AS fo
INNER HASH JOIN Dimension.[Stock Item] AS si
ON fo.[Stock Item Key] = si.[Stock Item Key]
WHERE fo.[Lineage Key] = 9
WHERE fo.[Lineage Key] = 9
AND si.[Lead Time Days] > 19;
-- Cleanup
@@ -9,19 +9,21 @@
-- Email IntelligentQP@microsoft.com for questions\feedback
-- ******************************************************** --
USE WideWorldImportersDW;
USE [master];
GO
ALTER DATABASE WideWorldImportersDW
SET COMPATIBILITY_LEVEL = 150;
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 150;
GO
ALTER DATABASE SCOPED CONFIGURATION
CLEAR PROCEDURE_CACHE;
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE [WideWorldImportersDW];
GO
/*
Adapted from SQL Server Books Online
https://docs.microsoft.com/en-us/sql/relational-databases/user-defined-functions/scalar-udf-inlining?view=sqlallproducts-allversions
https://docs.microsoft.com/sql/relational-databases/user-defined-functions/scalar-udf-inlining?view=sqlallproducts-allversions
*/
CREATE OR ALTER FUNCTION
dbo.customer_category(@CustomerKey INT)
@@ -13,7 +13,10 @@
USE [master];
GO
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 140;
ALTER DATABASE [WideWorldImportersDW] SET COMPATIBILITY_LEVEL = 150;
GO
ALTER DATABASE SCOPED CONFIGURATION CLEAR PROCEDURE_CACHE;
GO
USE [WideWorldImportersDW];
@@ -8,6 +8,9 @@ Here are the instructions to prepare for demonstrating Intelligent QP's latest r
Demos (with more on the way!):
- [Batch Mode Adaptive Join](Intelligent%20QP%20Demos%20WideWorldImportersDW%20Public%20Preview%20-%20Batch%20Mode%20Adaptive%20Join.sql)
- [Interleaved Execution](Intelligent%20QP%20Demos%20WideWorldImportersDW%20Public%20Preview%20-%20Interleaved%20Execution.sql)
- [Batch mode memory grant feedback](Intelligent%20QP%20Demos%20WideWorldImportersDW%20Public%20Preview%20-%20Batch%20Mode%20MGF.sql)
- [Row mode memory grant feedback](Intelligent%20QP%20Demos%20WideWorldImportersDW%20Public%20Preview%20-%20Row%20Mode%20MGF.sql)
- [Batch mode on rowstore](Intelligent%20QP%20Demos%20WideWorldImportersDW%20Public%20Preview%20-%20Batch%20Mode%20on%20Rowstore.sql)
- [APPROX_COUNT_DISTINCT](Intelligent%20QP%20Demos%20WideWorldImportersDW%20Public%20Preview%20-%20APPROX_COUNT_DISTINCT.sql)
@@ -46,7 +46,7 @@ if /i "%CTP_VERSION%" EQU "CTP2.4" (set MASTER_POD_NAME=mssql-master-pool-0) els
REM Copy the backup file, restore the database, create necessary objects and data file
echo Copying sales database backup file to SQL Master instance...
%DEBUG% kubectl cp tpcxbb_1gb.bak %CLUSTER_NAMESPACE%/%MASTER_POD_NAME%:/var/opt/mssql/data -c mssql-server || goto exit
%DEBUG% kubectl cp tpcxbb_1gb.bak %CLUSTER_NAMESPACE%/%MASTER_POD_NAME%:var/opt/mssql/data -c mssql-server || goto exit
REM Download and copy the sample backup files
if /i "%AW_WWI_SAMPLES%" EQU "--install-extra-samples" (
@@ -57,7 +57,7 @@ if /i "%AW_WWI_SAMPLES%" EQU "--install-extra-samples" (
%DEBUG% curl -L -G "https://github.com/Microsoft/sql-server-samples/releases/download/adventureworks/%%f" -o %%f
)
echo Copying %%f database backup file to SQL Master instance...
%DEBUG% kubectl cp %%f %CLUSTER_NAMESPACE%/%MASTER_POD_NAME%:/var/opt/mssql/data -c mssql-server || goto exit
%DEBUG% kubectl cp %%f %CLUSTER_NAMESPACE%/%MASTER_POD_NAME%:var/opt/mssql/data -c mssql-server || goto exit
)
set FILES=WideWorldImporters-Full.bak WideWorldImportersDW-Full.bak
@@ -67,7 +67,7 @@ if /i "%AW_WWI_SAMPLES%" EQU "--install-extra-samples" (
%DEBUG% curl -L -G "https://github.com/Microsoft/sql-server-samples/releases/download/wide-world-importers-v1.0/%%f" -o %%f
)
echo Copying %%f database backup file to SQL Master instance...
%DEBUG% kubectl cp %%f %CLUSTER_NAMESPACE%/%MASTER_POD_NAME%:/var/opt/mssql/data -c mssql-server || goto exit
%DEBUG% kubectl cp %%f %CLUSTER_NAMESPACE%/%MASTER_POD_NAME%:var/opt/mssql/data -c mssql-server || goto exit
)
)
@@ -60,8 +60,8 @@ else
MASTER_POD_NAME=master-0
fi
echo Copying database backup file...
$DEBUG kubectl cp tpcxbb_1gb.bak $CLUSTER_NAMESPACE/$MASTER_POD_NAME:/var/opt/mssql/data -c mssql-server || (echo $ERROR_MESSAGE && exit 1)
echo Copying sales database backup file...
$DEBUG kubectl cp tpcxbb_1gb.bak $CLUSTER_NAMESPACE/$MASTER_POD_NAME:var/opt/mssql/data -c mssql-server || (echo $ERROR_MESSAGE && exit 1)
# $DEBUG rm tpcxbb_1gb.bak
if [ "$AW_WWI_SAMPLES" == "--install-extra-samples" ]
@@ -74,7 +74,7 @@ then
$DEBUG curl -L -G "https://github.com/Microsoft/sql-server-samples/releases/download/adventureworks/$file" -o $file
fi
echo Copying $file database backup file to SQL Master instance...
$DEBUG kubectl cp $file $CLUSTER_NAMESPACE/$MASTER_POD_NAME:/var/opt/mssql/data -c mssql-server || (echo $ERROR_MESSAGE && exit 1)
$DEBUG kubectl cp $file $CLUSTER_NAMESPACE/$MASTER_POD_NAME:var/opt/mssql/data -c mssql-server || (echo $ERROR_MESSAGE && exit 1)
done
@@ -86,7 +86,7 @@ then
$DEBUG curl -L -G "https://github.com/Microsoft/sql-server-samples/releases/download/wide-world-importers-v1.0/$file" -o $file
fi
echo Copying $file database backup file to SQL Master instance...
$DEBUG kubectl cp $file $CLUSTER_NAMESPACE/$MASTER_POD_NAME:/var/opt/mssql/data -c mssql-server || (echo $ERROR_MESSAGE && exit 1)
$DEBUG kubectl cp $file $CLUSTER_NAMESPACE/$MASTER_POD_NAME:var/opt/mssql/data -c mssql-server || (echo $ERROR_MESSAGE && exit 1)
done
fi
@@ -97,7 +97,7 @@ $DEBUG sqlcmd -S $SQL_MASTER_INSTANCE -Usa -P$SQL_MASTER_SA_PASSWORD -I -b < "$S
# remove files copied into the pod:
echo Removing database backup files...
kubectl exec $MASTER_POD_NAME -n $CLUSTER_NAMESPACE -c mssql-server -i -t -- bash -c "rm -rvf /var/opt/mssql/data/*.bak"
$DEBUG kubectl exec $MASTER_POD_NAME -n $CLUSTER_NAMESPACE -c mssql-server -i -t -- bash -c "rm -rvf /var/opt/mssql/data/*.bak"
for table in web_clickstreams inventory customer
do
@@ -70,8 +70,8 @@ GO
CREATE OR ALTER PROCEDURE #create_data_sources
AS
BEGIN
-- Create database master key (required for database scoped credentials used in the samples)
IF NOT EXISTS(SELECT * FROM sys.databases WHERE name = DB_NAME() and is_master_key_encrypted_by_server = 1)
-- Create database master key (required for database scoped credentials used in the samples)
IF NOT EXISTS(SELECT * FROM sys.symmetric_keys WHERE name = '##MS_DatabaseMasterKey##')
CREATE MASTER KEY ENCRYPTION BY PASSWORD = 'sql19bigdatacluster!';
-- Create default data sources for SQL Big Data Cluster
@@ -4,16 +4,15 @@
-- the Query menu, and "Specify Values for Template Parameters" option.
IF NOT EXISTS(SELECT * FROM sys.database_scoped_credentials WHERE name = 'MySQL80-user')
CREATE DATABASE SCOPED CREDENTIAL [MySQL80-user]
WITH IDENTITY = 'mssql-user'
, SECRET = 'sql19tw0mysql';
WITH IDENTITY = '<mysql_user,nvarchar(100),mssql-user>'
, SECRET = '<mysql_user_password,nvarchar(100),sql19tw0mysql>';
-- Create external data source that points to MySQL server
-- The tokens '%u' and '%p' is used to reference the credential information.
-- Create external data source that points to MySQL server.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'MySQL80')
CREATE EXTERNAL DATA SOURCE MySQL80
WITH (LOCATION = 'odbc://uc-win19-vm.redmond.corp.microsoft.com'
, CONNECTION_OPTIONS = 'Driver={MySQL ODBC 8.0 Unicode Driver};User name=%u;Passwword=%p;IGNORE_SPACE=1'
WITH (LOCATION = 'odbc://<mysql_server,nvarchar(100),mysql-server-name>'
, CONNECTION_OPTIONS = 'Driver={MySQL ODBC 8.0 Unicode Driver};IGNORE_SPACE=1'
, CREDENTIAL = [MySQL80-user]);
-- Create external table over inventory table on MySQL server
@@ -7,13 +7,12 @@ IF NOT EXISTS(SELECT * FROM sys.database_scoped_credentials WHERE name = 'Postgr
WITH IDENTITY = '<postgres_user,nvarchar(100),mssql-user>'
, SECRET = '<postgres_user_password,nvarchar(100),sql19tw0postgresql>';
-- Create external data source that points to PostgreSQL server
-- The tokens '%u' and '%p' is used to reference the credential information.
-- Create external data source that points to PostgreSQL server.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'PostgreSQL11')
CREATE EXTERNAL DATA SOURCE PostgreSQL11
WITH (LOCATION = 'odbc://<postgres_server,nvarchar(100),postgres-server-name>'
, CONNECTION_OPTIONS = 'Driver={PostgreSQL ODBC Driver(UNICODE)};User name=%u;Passwword=%p'
, CONNECTION_OPTIONS = 'Driver={PostgreSQL ODBC Driver(UNICODE)}'
, CREDENTIAL = [PostgreSQL11-user]);
-- Create external table over inventory table on PostgreSQL server
@@ -203,7 +203,7 @@
},
{
"cell_type": "markdown",
"source": "# Configuration settings for scaling to larger data\n\n## Number and size of nodes in our Kubernetes cluster\nWe can control the number and size of nodes in our Kubernetes cluster via the node-vm-size and node-count switches in our `aks create` command:\n\n`az aks create --name mycluster --resource-group myrg --generate-ssh-keys --node-vm-size Standard_DS14_v2 --node-count 3 --kubernetes-version 1.10.9`\n\nMore information is available [here](https://docs.microsoft.com/en-us/sql/big-data-cluster/deploy-on-aks?view=sqlallproducts-allversions#create-a-kubernetes-cluster).\n\n## Number of Spark pods\nWe can control the number of Spark pods via the CLUSTER_STORAGE_POOL_REPLICAS environment variable used by `mssqlctl create cluster`:\n\nSET CLUSTER_STORAGE_POOL_REPLICAS=2\n\n## YARN scheduler memory and cores\nWe can control the YARN scheduler memory and cores via the following environment variable used by `mssqlctl create cluster`:\n\n- YARN_SCHEDULER_MAX_MEMORY\n- YARN_SCHEDULER_MAX_VCORES\n- YARN_NODEMANAGER_RESOURCE_MEMORY\n- YARN_NODEMANAGER_RESOURCE_VCORES\n\nFurther information regarding mssqlctl environtment variables is available [here](https://docs.microsoft.com/en-us/sql/big-data-cluster/deployment-guidance?view=sqlallproducts-allversions#define-environment-variables).\n\n## Livy timeout\nThe Livy timeout sets a limit on the runtime of a cell in a PySpark3 Jupyter notebook. In SQL Server 2019 Big Data CTP 2.1, the Livy timeout defaults to 1 hour. In CTP 2.2, it defaults to 24 days. One can modify this as follows:\n\n- Log into the mssql-master-pool-0 pod using this command (requires permission to run kubectl):\n\n```\nkubectl exec -it mssql-master-pool-0 -n <your-cluster-name> -- /bin/bash\n```\n- To set the Livy timeout to 24 days, run the following command or edit /livy/conf/livy.conf accordingly:\n\n```\necho 'livy.server.session.timeout = 24d' | cat >> /livy/conf/livy.conf \n```\n- Then restart the Livy server by running the following command:\n\n```\nsupervisorctl restart livy\n```",
"source": "# Configuration settings for scaling to larger data\n\n## Number and size of nodes in our Kubernetes cluster\nWe can control the number and size of nodes in our Kubernetes cluster via the node-vm-size and node-count switches in our `aks create` command:\n\n`az aks create --name mycluster --resource-group myrg --generate-ssh-keys --node-vm-size Standard_DS14_v2 --node-count 3 --kubernetes-version 1.10.9`\n\nMore information is available [here](https://docs.microsoft.com/en-us/sql/big-data-cluster/deploy-on-aks?view=sqlallproducts-allversions#create-a-kubernetes-cluster).\n\n## Number of Spark pods\nWe can control the number of Spark pods via the CLUSTER_STORAGE_POOL_REPLICAS environment variable used by `mssqlctl create cluster`:\n\nSET CLUSTER_STORAGE_POOL_REPLICAS=2\n\n## YARN scheduler memory and cores\nWe can control the YARN scheduler memory and cores via the following environment variable used by `mssqlctl create cluster`:\n\n- YARN_SCHEDULER_MAX_MEMORY\n- YARN_SCHEDULER_MAX_VCORES\n- YARN_NODEMANAGER_RESOURCE_MEMORY\n- YARN_NODEMANAGER_RESOURCE_VCORES\n\nFurther information regarding mssqlctl environtment variables is available [here](https://docs.microsoft.com/en-us/sql/big-data-cluster/deployment-guidance?view=sqlallproducts-allversions#define-environment-variables).\n\nIn CTP 2.5 and later, these environment variables are replaced by similarly named properties in a JSON file. See [Custom configurations](https://docs.microsoft.com/en-us/sql/big-data-cluster/deployment-guidance?view=sqlallproducts-allversions#customconfig).\n\n## Livy timeout\nThe Livy timeout sets a limit on the runtime of a cell in a PySpark3 Jupyter notebook. In SQL Server 2019 Big Data CTP 2.1, the Livy timeout defaults to 1 hour. In CTP 2.2, it defaults to 24 days. One can modify this as follows:\n\n- Log into the mssql-master-pool-0 pod using this command (requires permission to run kubectl):\n\n```\nkubectl exec -it mssql-master-pool-0 -n <your-cluster-name> -- /bin/bash\n```\n- To set the Livy timeout to 24 days, run the following command or edit /livy/conf/livy.conf accordingly:\n\n```\necho 'livy.server.session.timeout = 24d' | cat >> /livy/conf/livy.conf \n```\n- Then restart the Livy server by running the following command:\n\n```\nsupervisorctl restart livy\n```",
"metadata": {}
},
{