Qualification Tool - Jar Usage#

The Qualification tool can be run as a Java cmd in three different ways if you are not using the CLI tool:

  1. A standalone tool on the Spark event logs after the application(s) have run,

  2. Inside a running Spark application using explicit API calls, and

  3. Using a Spark listener, which can output results per SQL query.

Setting Up Environment#

Prerequisites#

  • Java 8+

  • Spark event log(s) from Spark 2.0 or above version. Supports both rolled and compressed event logs with .lz4, .lzf, .snappy and .zstd suffixes as well as Databricks-specific rolled and compressed(.gz) event logs.

  • The tool requires the Spark 3.x+ jars to be able to run but it does not need an Apache Spark runtime. If you do not already have Spark 3.x+ installed, you can download the Apache Spark Distribution to any machine and include the jars in the classpath.

  • This tool parses the Spark CPU event log(s) and creates an output report. Acceptable inputs are either individual or multiple event logs files or directories containing spark event logs in the local filesystem, HDFS, S3, ABFS, GCS or mixed. If you want to point to the local filesystem be sure to include prefix file: in the path. If any input is a remote file path or directory path, then you need to the connector dependencies to be on the classpath

    Include $HADOOP_CONF_DIR in classpath

    Sample showing Java’s classpath#
    -cp ~/rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/*:$HADOOP_CONF_DIR/

    Download the gcs-connector-hadoop3-<version>-shaded.jar and follow the instructions to configure Hadoop/Spark.

    Download the matched jars based on the Hadoop version

    • hadoop-aws-<version>.jar

    • aws-java-sdk-<version>.jar

    In $SPARK_HOME/conf, create hdfs-site.xml with below AWS S3 keys inside:

     1<?xml version="1.0"?>
 2<configuration>
 3   <property>
 4      <name>fs.s3a.access.key</name>
 5      <value>xxx</value>
 6   </property>
 7   <property>
 8      <name>fs.s3a.secret.key</name>
 9      <value>xxx</value>
10   </property>
11</configuration>

    You can test your configuration by including the above jars in the -jars option to spark-shell or spark-submit

    Please refer to the Hadoop-AWS doc on more options about integrating Hadoop-AWS module with S3.

    • Download the matched jar based on the Hadoop version hadoop-azure-<version>.jar.

    • The simplest authentication mechanism is to use account-name and account-key. Please refer to the Hadoop-ABFS support doc on more options about integrating Hadoop-ABFS module with ABFS.

Getting the Tools Jar#

  • Checkout the code repository

    git clone git@github.com:NVIDIA/spark-rapids-tools.git
cd spark-rapids-tools/core

  • Build using MVN. After a successful build, the jar of rapids-4-spark-tools_2.12-<version>-SNAPSHOT.jar will be in target/ directory. Refer to build doc for more information on build options (i.e., Spark version)

    mvn clean package

Deploying Tools Jar#

Running the Qualification Tool Standalone on Spark Event Logs#

  1. The tool reads the log files and processes them in memory. So, the heap memory should be increased when processing a large volume of events. It is recommended to pass VM options -Xmx10g and adjust according to the number-of-apps / size-of-logs being processed.

    export JVM_HEAP=-Xmx10g

  2. Examples running the tool on the following environments

    • Extract the Spark distribution into a local directory if necessary.

    • Either set SPARK_HOME to point to that directory or just put the path inside of the classpath java -cp toolsJar:$SPARK_HOME/jars/*:... when you run the Qualification tool.

    1java ${JVM_HEAP} \
2     -cp rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/* \
3     com.nvidia.spark.rapids.tool.qualification.QualificationMain [options] \
4     <eventlogs | eventlog directories ...>

    1java ${JVM_HEAP} \
2     -cp rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/* \
3     com.nvidia.spark.rapids.tool.qualification.QualificationMain \
4     /usr/logs/app-name1

    Example running on files in HDFS: (include $HADOOP_CONF_DIR in classpath). Note, on an HDFS cluster, the default filesystem is likely HDFS for both the input and output, so if you want to point to the local filesystem, be sure to include file: in the path.

    1java ${JVM_HEAP} \
2     -cp rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/*:$HADOOP_CONF_DIR/ \
3     com.nvidia.spark.rapids.tool.qualification.QualificationMain  /eventlogDir

Qualification tool options

  1java -cp ~/rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/*:$HADOOP_CONF_DIR/ \
  2 com.nvidia.spark.rapids.tool.qualification.QualificationMain --help
  3
  4RAPIDS Accelerator Qualification tool for Apache Spark
  5
  6Usage: java -cp rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/*
  7       com.nvidia.spark.rapids.tool.qualification.QualificationMain [options]
  8       <eventlogs | eventlog directories ...>
  9
 10      --all                          Apply multiple event log filtering criteria
 11                                     and process only logs for which all
 12                                     conditions are satisfied.Example: <Filter1>
 13                                     <Filter2> <Filter3> --all -> result is
 14                                     <Filter1> AND <Filter2> AND <Filter3>.
 15                                     Default is all=true
 16      --any                          Apply multiple event log filtering criteria
 17                                     and process only logs for which any condition
 18                                     is satisfied.Example: <Filter1> <Filter2>
 19                                     <Filter3> --any -> result is <Filter1> OR
 20                                     <Filter2> OR <Filter3>
 21  -a, --application-name  <arg>      Filter event logs by application name. The
 22                                     string specified can be a regular expression,
 23                                     substring, or exact match. For filtering
 24                                     based on complement of application name, use
 25                                     ~APPLICATION_NAME. i.e Select all event logs
 26                                     except the ones which have application name
 27                                     as the input string.
 28      --auto-tuner                   Toggle AutoTuner module.
 29  -f, --filter-criteria  <arg>       Filter newest or oldest N eventlogs based on
 30                                     application start timestamp, unique
 31                                     application name or filesystem timestamp.
 32                                     Filesystem based filtering happens before any
 33                                     application based filtering.For application
 34                                     based filtering, the order in which filters
 35                                     areapplied is: application-name,
 36                                     start-app-time, filter-criteria.Application
 37                                     based filter-criteria are:100-newest (for
 38                                     processing newest 100 event logs based on
 39                                     timestamp insidethe eventlog) i.e application
 40                                     start time)  100-oldest (for processing
 41                                     oldest 100 event logs based on timestamp
 42                                     insidethe eventlog) i.e application start
 43                                     time)  100-newest-per-app-name (select at
 44                                     most 100 newest log files for each unique
 45                                     application name) 100-oldest-per-app-name
 46                                     (select at most 100 oldest log files for each
 47                                     unique application name)Filesystem based
 48                                     filter criteria are:100-newest-filesystem
 49                                     (for processing newest 100 event logs based
 50                                     on filesystem timestamp).
 51                                     100-oldest-filesystem (for processing oldest
 52                                     100 event logsbased on filesystem timestamp).
 53  -h, --html-report                  Default is to generate an HTML report.
 54      --no-html-report               Disables generating the HTML report.
 55  -m, --match-event-logs  <arg>      Filter event logs whose filenames contain the
 56                                     input string. Filesystem based filtering
 57                                     happens before any application based
 58                                     filtering.
 59      --max-sql-desc-length  <arg>   Maximum length of the SQL description
 60                                     string output with the per sql output.
 61                                     Default is 100.
 62      --ml-functions                 Report if there are any SparkML or Spark XGBoost
 63                                     functions in the eventlog.
 64  -n, --num-output-rows  <arg>       Number of output rows in the summary report.
 65                                     Default is 1000.
 66      --num-threads  <arg>           Number of thread to use for parallel
 67                                     processing. The default is the number of
 68                                     cores on host divided by 4.
 69      --order  <arg>                 Specify the sort order of the report. desc or
 70                                     asc, desc is the default. desc (descending)
 71                                     would report applications most likely to be
 72                                     accelerated at the top and asc (ascending)
 73                                     would show the least likely to be accelerated
 74                                     at the top.
 75  -o, --output-directory  <arg>      Base output directory. Default is current
 76                                     directory for the default filesystem. The
 77                                     final output will go into a subdirectory
 78                                     called rapids_4_spark_qualification_output.
 79                                     It will overwrite any existing directory with
 80                                     the same name.
 81  -p, --per-sql                      Report at the individual SQL query level.
 82      --platform  <arg>              Cluster platform where Spark CPU workloads were
 83                                     executed. Options include onprem, dataproc-t4,
 84                                     dataproc-l4, emr, databricks-aws, and
 85                                     databricks-azure.
 86                                     Default is onprem.
 87  -r, --report-read-schema           Whether to output the read formats and
 88                                     datatypes to the CSV file. This can be very
 89                                     long. Default is false.
 90      --spark-property  <arg>...     Filter applications based on certain Spark
 91                                     properties that were set during launch of the
 92                                     application. It can filter based on key:value
 93                                     pair or just based on keys. Multiple configs
 94                                     can be provided where the filtering is done
 95                                     if any of theconfig is present in the
 96                                     eventlog. filter on specific configuration:
 97                                     --spark-property=spark.eventLog.enabled:truefilter
 98                                     all eventlogs which has config:
 99                                     --spark-property=spark.driver.portMultiple
100                                     configs:
101                                     --spark-property=spark.eventLog.enabled:true
102                                     --spark-property=spark.driver.port
103  -s, --start-app-time  <arg>        Filter event logs whose application start
104                                     occurred within the past specified time
105                                     period. Valid time periods are
106                                     min(minute),h(hours),d(days),w(weeks),m(months).
107                                     If a period is not specified it defaults to
108                                     days.
109  -t, --timeout  <arg>               Maximum time in seconds to wait for the event
110                                     logs to be processed. Default is 24 hours
111                                     (86400 seconds) and must be greater than 3
112                                     seconds. If it times out, it will report what
113                                     it was able to process up until the timeout.
114  -u, --user-name  <arg>             Applications which a particular user has
115                                     submitted.
116  -w, --worker-info  <arg>           File path containing the system information
117                                     of a worker node. It is assumed that all
118                                     workers are homogenous. It requires the
119                                     AutoTuner to be enabled. Default is
120                                     ./worker_info.yaml
121      --help                         Show help message
122
123 trailing arguments:
124  eventlog (required)   Event log filenames(space separated) or directories
125                        containing event logs. eg: s3a://<BUCKET>/eventlog1
126                        /path/to/eventlog2

Note

  • --help should be before the trailing event logs.

  • The “regular expression” used by -a option is based on java.util.regex.Pattern.

Please refer to Java CMD Samples for more examples and sample commands.

Tuning Spark Properties For GPU Clusters#

Currently, the Auto-Tuner calculates a set of configurations that impact the performance of Apache Spark apps executing on GPU. Those calculations can leverage cluster information (e.g. memory, cores, Spark default configurations) as well as information processed in the application event logs. Note that the tool also will recommend settings for the application assuming that the job will be able to use all the cluster resources (CPU and GPU) when it is running. The values loaded from the app logs have higher precedence than the default configs.

Note

Auto-Tuner limitations:

  • It is assumed that all the worker nodes on the cluster are homogenous.

To run the Auto-Tuner, enable the auto-tuner flag and optionally pass a valid --worker-info <FILE_PATH>. The Auto-Tuner needs to learn the system properties of the worker nodes that run application code in the cluster. The argument FILE_PATH can either be local or remote file (i.e., HDFS).

If the --worker-info argument is not supplied, then the Auto-Tuner will only recommend tuned settings based on the job event log and not on any cluster or worker information since that is not available.

Template of the worker information file in “yaml” format#
 1system:
 2  numCores: 32
 3  memory: 212992MiB
 4  numWorkers: 5
 5gpu:
 6  memory: 15109MiB
 7  count: 4
 8  name: T4
 9softwareProperties:
10  spark.driver.maxResultSize: 7680m
11  spark.driver.memory: 15360m
12  spark.executor.cores: '8'
13  spark.executor.instances: '2'
14  spark.executor.memory: 47222m
15  spark.executorEnv.OPENBLAS_NUM_THREADS: '1'
16  spark.scheduler.mode: FAIR
17  spark.sql.cbo.enabled: 'true'
18  spark.ui.port: '0'
19  spark.yarn.am.memory: 640m

Property

Optional

If Missing

system.numCores

No

Auto-Tuner does not calculate recommendations

system.memory

No

Auto-Tuner does not calculate any recommendations

system.numWorkers

Yes

Default: 1

gpu.name

Yes

Default: T4 (Nvidia Tesla T4)

gpu.memory

Yes

Default: 16G

softwareProperties

Yes

This section is optional. The Auto-Tuner reads the configs within the logs of the Apache Spark apps with higher precedence

Running Using a Spark Listener#

We provide a Spark Listener that can be installed at the application start that will produce output for each SQL query in the running application and indicate if that query is a good fit to try with the Rapids Accelerator for Spark.

Configuration#

  • Add the following class to the spark listeners configuration:

    1spark.extraListeners=org.apache.spark.sql.rapids.tool.qualification.RunningQualificationEventProcessor

  • The user should specify the output directory (spark.rapids.qualification.outputDir) if they want the output to go to separate files. Otherwise, it will go to the Spark driver log. If the output directory is specified, it outputs two files, one CSV, and one pretty printed log file. The output directory can be a local directory or point to a distributed file system or blobstore like S3.

  • By default, this will output results for 10 SQL queries per file and keep 100 files. This behavior is because many blob stores don’t show files until they are fully written so you wouldn’t be able to see the results for a running application until it finishes the number of SQL queries per file. This behavior can be configured with the following configs.

    • spark.rapids.qualification.output.numSQLQueriesPerFile: default 10

    • spark.rapids.qualification.output.maxNumFiles: default 100

Run the Spark Application#

Run the application and include the tools jar, spark.extraListeners config, and optionally the other configs to control the tool’s behavior.

For example:

1$SPARK_HOME/bin/spark-shell \
2--jars rapids-4-spark-tools_2.12-<version>.jar \
3--conf spark.extraListeners=org.apache.spark.sql.rapids.tool.qualification.RunningQualificationEventProcessor \
4--conf spark.rapids.qualification.outputDir=/tmp/qualPerSqlOutput \
5--conf spark.rapids.qualification.output.numSQLQueriesPerFile=5 \
6--conf spark.rapids.qualification.output.maxNumFiles=10

After running some SQL queries you can look in the output directory and see files like:

1rapids_4_spark_qualification_output_persql_0.csv
2rapids_4_spark_qualification_output_persql_0.log
3rapids_4_spark_qualification_output_persql_1.csv
4rapids_4_spark_qualification_output_persql_1.log
5rapids_4_spark_qualification_output_persql_2.csv
6rapids_4_spark_qualification_output_persql_2.log

See the Understanding the Qualification tool output section on the file contents details.

Running the Qualification Tool Inside a Running Spark Application Using the API#

Modify Your Application Code To Call the APIs#

Currently, only Scala APIs are supported. Note this does not support reporting at the per SQL level currently. This can be done manually by just wrapping and reporting around those queries instead of the entire application.

  1. Create the RunningQualicationApp:

    val qualApp = new com.nvidia.spark.rapids.tool.qualification.RunningQualificationApp()

  2. Get the event listener from it and install it as a Spark listener:

    1val listener = qualApp.getEventListener
2spark.sparkContext.addSparkListener(listener)

  3. Run your queries and get the summary or detailed output to see the results.

    • The summary output API:

      1/**
2* Get the summary report for qualification.
3* @param delimiter The delimiter separating fields of the summary report.
4* @param prettyPrint Whether to including the separate at start and end and
5*                    add spacing so the data rows align with column headings.
6* @return String of containing the summary report.
7*/
8getSummary(delimiter: String = "|", prettyPrint: Boolean = true): String

    • The detailed output api:

      1/**
2* Get the detailed report for qualification.
3* @param delimiter The delimiter separating fields of the summary report.
4* @param prettyPrint Whether to including the separate at start and end and
5*                    add spacing so the data rows align with column headings.
6* @return String of containing the detailed report.
7*/
8getDetailed(delimiter: String = "|", prettyPrint: Boolean = true, reportReadSchema: Boolean = false): String

Example:

 1// run your sql queries ...
 2
 3// To get the summary output:
 4val summaryOutput = qualApp.getSummary()
 5
 6// To get the detailed output:
 7val detailedOutput = qualApp.getDetailed()
 8
 9// print the output somewhere for user to see
10println(summaryOutput)
11println(detailedOutput)

If you need to specify the tools jar as a maven dependency to compile the Spark application:

1<dependency>
2   <groupId>com.nvidia</groupId>
3   <artifactId>rapids-4-spark-tools_2.12</artifactId>
4   <version>${version}</version>
5</dependency>

Run the Spark application#

Run your Spark application and include the tools jar you downloaded with the spark –jars options and view the output wherever you had it printed.

For example, if running the spark-shell:

$SPARK_HOME/bin/spark-shell --jars rapids-4-spark-tools_2.12-<version>.jar

Java CMD Samples#

  • Process the 10 newest logs, and only output the top 3 in the output:

    1java ${QUALIFICATION_HEAP} \
2  -cp ~/rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/*:$HADOOP_CONF_DIR/ \
3  com.nvidia.spark.rapids.tool.qualification.QualificationMain -f 10-newest -n 3 /eventlogDir

  • Process last 100 days’ logs:

    1java ${QUALIFICATION_HEAP} \
2  -cp ~/rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/*:$HADOOP_CONF_DIR/ \
3  com.nvidia.spark.rapids.tool.qualification.QualificationMain -s 100d /eventlogDir

  • Process only the newest log with the same application name:

    1java ${QUALIFICATION_HEAP} \
2  -cp ~/rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/*:$HADOOP_CONF_DIR/ \
3  com.nvidia.spark.rapids.tool.qualification.QualificationMain -f 1-newest-per-app-name /eventlogDir

  • Parse ML functions from the eventlog:

    1java ${QUALIFICATION_HEAP} \
2  -cp ~/rapids-4-spark-tools_2.12-<version>.jar:$SPARK_HOME/jars/*:$HADOOP_CONF_DIR/ \
3  com.nvidia.spark.rapids.tool.qualification.QualificationMain --ml-functions /eventlogDir
On this page