|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
|
#! /bin/bash
### $1: file with list of ALCA types you want to process; remember to put for each of them
### an ALCARECO style cfg in Alignment/CommonAlignmentProducer/python/
#
### $2: number, if greater than 2 it cleans the CASTOR area before starting (optional)
source /afs/cern.ch/cms/caf/setup.sh
curdir=$(pwd)
#CASTOR_OUT="/castor/cern.ch/cms/store/user/bonato/CRAFTReproSkims/Craft09/4T/"
ALCAFILELIST=$1
CASTOR_OUT="<CASTOROUT>"
DQM_OUT="${curdir}/MONITORING/DQM/"
MAXEVENTS=10000
#curdir=$( pwd )
#check if output directory exists
nsls /castor/cern.ch/cms/$CASTOR_OUT
if [ $? -ne 0 ]
then
echo "Output directory: "
echo /castor/cern.ch/cms/$CASTOR_OUT
echo "does not exist. Please check the scripts. Exiting."
exit 1
fi
#check if DQM output directory exists
ls $DQM_OUT
if [ $? -ne 0 ]
then
echo "DQM directory: "
echo $DQM_OUT
echo "does not exist. Please check the scripts. Exiting."
exit 1
fi
## Clean output directory
if [ $# -gt 1 ]
then
if [ $2 -gt 2 ]
then
if [ $(nsls -l /castor/cern.ch/cms/$CASTOR_OUT | wc -l ) -gt 1 ] #there is always the dir 'logfiles'
then
echo "Cleaning output directory: $CASTOR_OUT"
for file in $(nsls /castor/cern.ch/cms/$CASTOR_OUT/ | grep "Skimmed" )
do
#echo
rfrm /castor/cern.ch/cms/$CASTOR_OUT/$file
done
for file in $(nsls /castor/cern.ch/cms/$CASTOR_OUT/logfiles/)
do
#echo
rfrm /castor/cern.ch/cms/$CASTOR_OUT/logfiles/$file
done
fi
fi #end if $2 > 2
fi #end if $# > 2
#really needed ?
#export STAGE_SVCCLASS=cmscaf
for ALCATAG in $( cat $ALCAFILELIST )
do
echo
echo "*****************************************"
echo "*** Starting the ALCATAG: ${ALCATAG}"
echo "*****************************************"
echo
# DAT_FILE="/afs/cern.ch/cms/CAF/CMSALCA/ALCA_TRACKERALIGN/HIP/bonato/DEVEL/HIPWorkflow/ALCARECOskim/v1.4/data/${ALCATAG}.dat"
DAT_FILE="${curdir}/../data/${ALCATAG}.dat"
TPL_FILE="TkAlCaRecoSkimming.${ALCATAG}.tpl"
TAG=$ALCATAG #"CRAFT"
JOBTAG="ALCASkim_"$TAG
BASE_TPL=$(basename "$TPL_FILE" .tpl)
echo ""
echo "I am in $curdir"
INDEX=1
# echo "*******************************"
# echo "Starting the show"
# echo
TOTFILES=0
for i in $( cat $DAT_FILE )
do
#pick the total nr events in this file from the previously produced nevents.out
let TOTFILES=TOTFILES+1
TOTEVTS=$(sed -n $TOTFILES'p' ../data/nevents${ALCATAG}.out)
#echo "The file #$TOTFILES has $TOTEVTS events"
if [ $TOTEVTS == 0 ]
then
continue
fi
TOTSPLITS=$(( ( $TOTEVTS / $MAXEVENTS ) +1 ))
firstev=0
lastev=-1
#echo "I will split it into $TOTSPLITS"
if [ $TOTSPLITS > 1 ]
then
nsplits=1
while [ $nsplits -le $TOTSPLITS ]
do
#echo "Splitting the file $TOTFILE : $nsplits"
firstev=$(( $MAXEVENTS*$(( $nsplits-1 ))+1 ))
lastev=$MAXEVENTS #$(( ($MAXEVENTS*$nsplits) ))
JOB=$JOBTAG"_file"$INDEX
CFG_FILE=$BASE_TPL"."$TAG"_cfg."$INDEX".py"
sed -e "s|<JOB>|${JOB}|g" -e "s|<INPATH>|${i}|g" -e "s|<INIEVT>|${firstev}|g" -e "s|<FINEVT>|${lastev}|g" -e "s|<ALCATAG>|${TAG}|g" < $TPL_FILE > $CFG_FILE
let INDEX=INDEX+1
let nsplits=nsplits+1
# if [ $INDEX -ge 3 ]
# then
# echo "Reached a maximum number of files: $INDEX. Stopping the submission"
# break
# fi
done
else #file is small and does not contain too many events
firstev=0
lastev=-1
JOB=$JOBTAG"_file"$INDEX
CFG_FILE=$BASE_TPL"."$TAG"_cfg."$INDEX".py"
sed -e "s|<JOB>|${JOB}|g" -e "s|<INPATH>|${i}|g" -e "s|<INIEVT>|${firstev}|g" -e "s|<FINEVT>|${lastev}|g" -e "s|<ALCATAG>|${TAG}|g" < $TPL_FILE > $CFG_FILE
let INDEX=INDEX+1
# if [ $INDEX -ge 3 ]
# then
# echo "Reached a maximum number of files: $INDEX. Stopping the submission"
# break
# fi
fi
# if [ $INDEX -ge 3 ]
# then
# echo "Reached a maximum number of files: $INDEX. Stopping the submission"
# break
# fi
#echo "--- moving to next file. At the moment INDEX=$INDEX"
done
TOTCFGFILES=$(( $INDEX -1 ))
#echo "Tot cfg files: $TOTCFGFILES"
##second loop submitting what we prepared before
INDEX=1
while [ $INDEX -le $TOTCFGFILES ]
do
JOBNAME="ALCASkim"$TAG"_"$INDEX
LOGFILE="${JOBNAME}.log"
CFG_FILE=$BASE_TPL"."$TAG"_cfg."$INDEX".py"
echo "Submitting $JOBNAME with config file $CFG_FILE"
REM=0
let "REM=$INDEX % 300"
if [ $REM -lt 100 ]
then
#echo "dummy A"
bsub -q cmscaf1nd -J $JOBNAME -oo $LOGFILE skim_exec.sh "$curdir/$CFG_FILE" "$CASTOR_OUT" "$DQM_OUT"
elif [ $REM -lt 200 ]
then
#echo "dummy B"
bsub -q cmsexpress -J $JOBNAME -oo $LOGFILE skim_exec.sh "$curdir/$CFG_FILE" "$CASTOR_OUT" "$DQM_OUT"
else
#echo "dummy C"
bsub -q cmscaf1nd -J $JOBNAME -oo $LOGFILE skim_exec.sh "$curdir/$CFG_FILE" "$CASTOR_OUT" "$DQM_OUT"
fi
##fi #dummy
let INDEX=INDEX+1
done
done #end 'for loop' on ALCA categories
#cd $curdir
#mv "$BASE_TPL"*".py" $DQM_OUT/../logfiles/
|