How to benchmark MongoDB

run.benchmark.bash

#!/bin/bash

# remember the directory we are starting from
#   the script expects the MongoDB configuration files here
export homeDirectory=$PWD

# directory where MongoDB/TokuMX tarballs are located
export tarDirectory=/home/tcallaghan/big-dir/backups/mongodb

# directory used for MongoDB server binaries and data folder
export MONGO_DIR=~/temp

# perform some sanity checks

# check that $MONGO_DIR is defined
if [ -z "$MONGO_DIR" ]; then
    echo "Need to set MONGO_DIR"
    exit 1
fi

# check that $MONGO_DIR exists
if [ ! -d "$MONGO_DIR" ]; then
    echo "Need to create directory $MONGO_DIR"
    exit 1
fi

# check that $MONGO_DIR is empty
#   force manual cleanup before starting
if [ "$(ls -A ${MONGO_DIR})" ]; then
    echo "Directory $MONGO_DIR must be empty before starting"
    exit 1
fi

# decide which tarballs and configurations we want to benchmark
#   use semi-colon list of "tarball;id;config;mongo_type"
#     tarball     : MongoDB or TokuMX tarball
#     id          : Short hand description of this particular benchmark run, ends up in the log file and the summary log
#     config      : YAML configuration file to use for the this benchmark run
#     mongo_type  : Identifies which "type" of MongoDB, tokumx|mxse|wt|mongo
export benchmarkList=""
export benchmarkList="${benchmarkList} mongodb-linux-x86_64-tokumxse-1.0.0-rc.2.tgz;mxse_100rc2_none;tokumxse-uncompressed.conf;mxse"
export benchmarkList="${benchmarkList} mongodb-linux-x86_64-tokumxse-1.0.0-rc.2.tgz;mxse_100rc2_quicklz;tokumxse-quicklz.conf;mxse"
export benchmarkList="${benchmarkList} mongodb-linux-x86_64-tokumxse-1.0.0-rc.2.tgz;mxse_100rc2_zlib;tokumxse-zlib.conf;mxse"
export benchmarkList="${benchmarkList} mongodb-linux-x86_64-tokumxse-1.0.0-rc.2.tgz;mxse_100rc2_lzma;tokumxse-lzma.conf;mxse"
export benchmarkList="${benchmarkList} mongodb-linux-x86_64-3.0.0-rc8.tgz;mmapv1_300rc8;mmapv1.conf;mongo"
export benchmarkList="${benchmarkList} mongodb-linux-x86_64-3.0.0-rc8.tgz;wt_300rc8_none;wiredtiger-uncompressed.conf;wt"
export benchmarkList="${benchmarkList} mongodb-linux-x86_64-3.0.0-rc8.tgz;wt_300rc8_snappy;wiredtiger-snappy.conf;wt"
export benchmarkList="${benchmarkList} mongodb-linux-x86_64-3.0.0-rc8.tgz;wt_300rc8_zlib;wiredtiger-zlib.conf;wt"

# make sure we have valid tarballs and config scripts for this benchmark run
echo "checking that all needed tarballs exist."
for thisBenchmark in ${benchmarkList}; do
    TARBALL=$(echo "${thisBenchmark}" | cut -d';' -f1)
    MONGOD_CONFIG=$(echo "${thisBenchmark}" | cut -d';' -f3)

    if [ -e ${tarDirectory}/${TARBALL} ]; then
        echo "  located ${tarDirectory}/${TARBALL}"
    else
        echo "  unable to locate ${tarDirectory}/${TARBALL}, exiting."
        exit 1
    fi

    if [ -e ${MONGOD_CONFIG} ]; then
        echo "  located ${MONGOD_CONFIG}"
    else
        echo "  unable to locate ${MONGOD_CONFIG}, exiting."
        exit 1
    fi
done

export DB_NAME=test
export NUM_CLIENTS=2
export DOCS_PER_CLIENT=$((512 * 80000))
export NUM_INSERTS=$((NUM_CLIENTS * DOCS_PER_CLIENT))
export SUMMARY_LOG_NAME=summary.log
rm -f ${SUMMARY_LOG_NAME}

for thisBenchmark in ${benchmarkList}; do
    export TARBALL=$(echo "${thisBenchmark}" | cut -d';' -f1)
    export MINI_BENCH_ID=$(echo "${thisBenchmark}" | cut -d';' -f2)
    export MONGOD_CONFIG=$(echo "${thisBenchmark}" | cut -d';' -f3)
    export MONGO_TYPE=$(echo "${thisBenchmark}" | cut -d';' -f4)

    echo "benchmarking tarball = ${TARBALL}"

    # clean up + start the new server
    
    pushd ${MONGO_DIR}
	  if [ "$?" -eq 1 ]; then
        echo "Unable to pushd $MONGO_DIR, exiting."
        exit 1
	  fi
    
	  # erase any files from the previous run
    rm -rf *
    
	  # untar server binaries to here
    tar xzvf ${tarDirectory}/${TARBALL} --strip 1
    
    # create the "data" directory
    mkdir data
    bin/mongod --config ${homeDirectory}/${MONGOD_CONFIG}
    popd

    # wait for mongo to start
    while [ 1 ]; do
        $MONGO_DIR/bin/mongostat -n 1 > /dev/null 2>&1
        if [ "$?" -eq 0 ]; then
            break
        fi    
        sleep 5
    done
    sleep 5

    # log for this run
    export LOG_NAME=${MINI_BENCH_ID}-${NUM_CLIENTS}-${NUM_INSERTS}.log
    rm -f ${LOG_NAME}

    # TODO : log server performance with mongostat

    # start the first inserter
    T="$(date +%s)"
    echo "`date` | starting insert client 1" | tee -a ${LOG_NAME}
    $MONGO_DIR/bin/mongo ${DB_NAME} --eval 'load("./compress_test.js")' &
    sleep 5

    # start the additional insert clients
    clientNumber=2
    while [ ${clientNumber} -le ${NUM_CLIENTS} ]; do
        echo "`date` | starting insert client ${clientNumber}" | tee -a ${LOG_NAME}
        $MONGO_DIR/bin/mongo ${DB_NAME} --eval 'load("./compress_test.js")' &
        let clientNumber=clientNumber+1
    done

    # wait for all of the client(s) to finish
    wait

    # report insert performance
    T="$(($(date +%s)-T))"
    printf "`date` | insert duration = %02d:%02d:%02d:%02d\n" "$((T/86400))" "$((T/3600%24))" "$((T/60%60))" "$((T%60))" | tee -a ${LOG_NAME}
    DOCS_PER_SEC=`echo "scale=0; ${NUM_INSERTS}/${T}" | bc `
    echo "`date` | inserts per second = ${DOCS_PER_SEC}" | tee -a ${LOG_NAME}

    # stop the server
    T="$(date +%s)"
    echo "`date` | shutting down the server" | tee -a ${LOG_NAME}
    $MONGO_DIR/bin/mongo admin --eval "db.shutdownServer({force: true})"
    
	  # wait for the MongoDB server to shutdown
    while [ 1 ]; do
        pgrep -U $USER mongod > /dev/null 2>&1
        if [ "$?" -eq 1 ]; then
            break
        fi    
        sleep 5
    done
    T="$(($(date +%s)-T))"
    printf "`date` | shutdown duration = %02d:%02d:%02d:%02d\n" "$((T/86400))" "$((T/3600%24))" "$((T/60%60))" "$((T%60))" | tee -a ${LOG_NAME}

    # report size on disk
    SIZE_BYTES=`du -c --block-size=1 ${MONGO_DIR}/data | tail -n 1 | cut -f1`
    SIZE_MB=`echo "scale=2; ${SIZE_BYTES}/(1024*1024)" | bc `
    echo "`date` | post-load sizing (SizeMB) = ${SIZE_MB}" | tee -a ${LOG_NAME}

    # put all the information into the summary log file
    echo "`date` | tech = ${MINI_BENCH_ID} | ips = ${DOCS_PER_SEC} | sizeMB = ${SIZE_MB}" | tee -a ${SUMMARY_LOG_NAME}
done