#!/bin/sh
#/***************************************************************************
# *   Copyright (C) 2009 by Andy Pavlo, Brown University                    *
# *   http://www.cs.brown.edu/~pavlo/                                       *
# *                                                                         *
# *   Permission is hereby granted, free of charge, to any person obtaining *
# *   a copy of this software and associated documentation files (the       *
# *   "Software"), to deal in the Software without restriction, including   *
# *   without limitation the rights to use, copy, modify, merge, publish,   *
# *   distribute, sublicense, and/or sell copies of the Software, and to    *
# *   permit persons to whom the Software is furnished to do so, subject to *
# *   the following conditions:                                             *
# *                                                                         *
# *   The above copyright notice and this permission notice shall be        *
# *   included in all copies or substantial portions of the Software.       *
# *                                                                         *
# *   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,       *
# *   EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF    *
# *   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.*
# *   IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR     *
# *   OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, *
# *   ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR *
# *   OTHER DEALINGS IN THE SOFTWARE.                                       *
# ***************************************************************************/

## =====================================================
## DATA OPTIONS
## =====================================================

COMBINE_RESULTS=1    ## Combine Final Results into Single Output File
COMPRESS_DATA=0      ## Compress Input Data and Intermediate Results
TUPLE_DATA=0         ## Use TupleWritable for multi-column values
SEQUENCE_FILE=0      ## Use SequenceFile Input Formats
SPLIT_DATA=0         ## Split input files into separate, smaller subsets
INPUT_LIMIT=0        ## How many lines to limit for Input Files when loading

## =====================================================
## RUN TIME OPTIONS
## =====================================================

##
## Number of Trials Per Cluster Configuration
##
NUM_OF_TRIALS=3

##
## Debug Output
## This is flag is used in both the DataLoader and the Benchmarks
##
DEBUG=0

##
## Start the daemons for each new configuration
##
START_HDFS_MASTER=1
START_JOB_TRACKER=1

##
## Load/Unload Options
##
REFORMAT_HDFS=1         # Reformat HDFS before each run
LOAD_INPUT_DATA=1       # Load input data before executing
CLEANUP_INPUT_DATA=0    # Remove temporary files after loading input data (compression)
UNLOAD_INPUT_DATA=0     # Delete input data at shutdown
UNLOAD_OUTPUT_DATA=0    # Delete output data at shutdown

##
## Cache Control
##
FLUSH_CACHE_BEFORE_LOAD=1
FLUSH_CACHE_BEFORE_TRIAL=0
FLUSH_CACHE_BEFORE_BENCHMARK=1

##
## Directory of slave files to use
## This directory should contain the following files:
##    slaves-001  (1 host)
##    slaves-010  (10 hosts)
##    slaves-025  (25 hosts)
##    slaves-050  (50 hosts)
##    slaves-100  (100 hosts)
##    slaves-200  (200 hosts)
##
SLAVES_CONF_DIR="$HADOOP_CONF_DIR/slaves-000"

##
## What benchmarks to actually execute
##
BENCHMARK_SETS=( \
   "SORTGREP" \
   "BENCHMARKS2" \
)

## =====================================================
## SORTGREP BENCHMARK CONFIGURATION
## =====================================================

## ----------------------------
## Benchmarks
## ----------------------------
SORTGREP_BENCHMARK_TYPES=( \
      "Grep" \
)
## ----------------------------
## Data Sets
## ----------------------------
SORTGREP_DATA_SETS=( \
      "535MB" \
      "1TB" \
)
## ----------------------------
## 535MB Data Set Slave Configurations
## ----------------------------
SORTGREP_535MB_CLUSTER_CONFIGURATIONS=( \
   "slaves-001" \
   "slaves-010" \
   "slaves-025" \
   "slaves-050" \
   "slaves-100" \
)
## ----------------------------
## 1TB Data Set Slave Configurations
## ----------------------------
SORTGREP_1TB_CLUSTER_CONFIGURATIONS=( \
   "slaves-025" \
   "slaves-050" \
   "slaves-100" \
)
## ----------------------------
## Input Data
## ----------------------------
SORTGREP_INPUT_FILES=( ) # LEAVE BLANK
SORTGREP_INPUT_DIR=$ORIG_SORTGREP_DATA_DIR

## =====================================================
## BENCHMARKS2 CONFIGURATION
## =====================================================

## ----------------------------
## Benchmarks
## ----------------------------
BENCHMARKS2_BENCHMARK_TYPES=( \
   "Benchmark1" \
   "Benchmark2" \
   "Benchmark2a" \
   "Benchmark3" \
   "Benchmark4" \
)
## ----------------------------
## Data Sets
## ----------------------------
BENCHMARKS2_DATA_SETS=( \
      "FULL" \
)
## ----------------------------
## Cluster Configurations
## ----------------------------
BENCHMARKS2_FULL_CLUSTER_CONFIGURATIONS=( \
   "slaves-001" \
   "slaves-010" \
   "slaves-025" \
   "slaves-050" \
   "slaves-100" \
)
## ----------------------------
## Input Data
## ----------------------------
BENCHMARKS2_INPUT_FILES=( \
       "Rankings.dat" \
       "UserVisits.dat" \
       "docs" \
)
BENCHMARKS2_INPUT_DIR=$ORIG_BENCHMARK2_DATA_DIR