哪些Linux设置可能导致C ++程序运行：
jellyfish count -m 31 -t 40 -C -s 105 -o k_u_hash_0 pe.cor.fa
在终端中执行该命令但是在bash脚本中崩溃时工作正常吗？在后一种情况下，它在退出之前要求411428571480字节 - 立即。这很奇怪，因为当以交互方式运行时，顶部会在开始运行后几分钟内显示10个Gb of Virt和Res内存。
ulimit -a
显示：
core file size (blocks, -c) 0
data seg size (kbytes, -d) unlimited
scheduling priority (-e) 0
file size (blocks, -f) unlimited
pending signals (-i) 2067197
max locked memory (kbytes, -l) 64
max memory size (kbytes, -m) unlimited
open files (-n) 1024
pipe size (512 bytes, -p) 8
POSIX message queues (bytes, -q) 819200
real-time priority (-r) 0
stack size (kbytes, -s) 10240
cpu time (seconds, -t) unlimited
max user processes (-u) 1024
virtual memory (kbytes, -v) unlimited
file locks (-x) unlimited
/ proc / meminfo显示：
CommitLimit: 615693660 kB
Committed_AS: 48320500 kB
calloc_test
Testing 4294967296
Testing 8589934592
Testing 17179869184
Testing 34359738368
Testing 68719476736
Testing 137438953472
Testing 274877906944
Testing 549755813888
Testing 1099511627776
FAILED
也就是说，它能够分配一个549 Gb的块，比一个水母要求的块大，并且内存分配在两种环境中表现相同。
在任何一种情况下都没有设置 LD_LIBRARY_PATH 。
有人可以建议在两种环境中可能有什么不同，以解释内存分配程序子集的操作差异吗？ （此时为一个子集。）
谢谢。
根据要求，这是脚本（仅限于故障点加上3个额外行）：
#!/bin/bash
# assemble.sh generated by masurca
CONFIG_PATH="/home/mathog/do_masurca/project.cfg"
CMD_PATH="/home/mathog/MaSuRCA/bin/masurca"
# Test that we support <() redirection
(eval "cat <(echo test) >/dev/null" 2>/dev/null) || {
echo >&2 "ERROR: The shell used is missing important features."
echo >&2 " Run the assembly script directly as './$0'"
exit 1
}
# Parse command line switches
while getopts ":rc" o; do
case "${o}" in
c)
echo "configuration file is '$CONFIG_PATH'"
exit 0
;;
r)
echo "Rerunning configuration"
exec perl "$CMD_PATH" "$CONFIG_PATH"
echo "Failed to rerun configuration"
exit 1
;;
*)
echo "Usage: $0 [-r] [-c]"
exit 1
;;
esac
done
set +e
# Set some paths and prime system to save environment variables
save () {
(echo -n "$1=\""; eval "echo -n \"\$$1\""; echo '"') >> environment.sh
}
GC=
RC=
NC=
if tty -s < /dev/fd/1 2> /dev/null; then
GC='\e[0;32m'
RC='\e[0;31m'
NC='\e[0m'
fi
log () {
d=$(date)
echo -e "${GC}[$d]${NC} $@"
}
fail () {
d=$(date)
echo -e "${RC}[$d]${NC} $@"
exit 1
}
signaled () {
fail Interrupted
}
trap signaled TERM QUIT INT
rm -f environment.sh; touch environment.sh
# To run tasks in parallel
run_bg () {
semaphore -j $NUM_THREADS --id masurca_$$ -- "$@"
}
run_wait () {
semaphore -j $NUM_THREADS --id masurca_$$ --wait
}
export PATH="/home/mathog/MaSuRCA/bin:/home/mathog/MaSuRCA/bin/../CA/Linux-amd64/bin:$PATH"
save PATH
export PERL5LIB=/home/mathog/MaSuRCA/bin/../lib/perl${PERL5LIB:+:$PERL5LIB}
save PERL5LIB
NUM_THREADS=40
save NUM_THREADS
log 'Processing pe library reads'
rm -rf meanAndStdevByPrefix.pe.txt
echo 'pe 400 20' >> meanAndStdevByPrefix.pe.txt
run_bg rename_filter_fastq 'pe' <(exec expand_fastq '/home/mathog/SPUR_datasets/pe_400_R1.fastq' | awk '{if(length($0>200)) print substr($0,1,200); else print $0;}') <(exec expand_fastq '/home/mathog/SPUR_datasets/pe_400_R2.fastq' | awk '{if(length($0>200)) print substr($0,1,200); else print $0;}' ) > 'pe.renamed.fastq'
run_wait
head -q -n 40000 pe.renamed.fastq | grep --text -v '^+' | grep --text -v '^@' > pe_data.tmp
export PE_AVG_READ_LENGTH=`awk '{if(length($1)>31){n+=length($1);m++;}}END{print int(n/m)}' pe_data.tmp`
save PE_AVG_READ_LENGTH
echo "Average PE read length $PE_AVG_READ_LENGTH"
KMER=`for f in pe.renamed.fastq;do head -n 80000 $f |tail -n 40000;done | perl -e 'while($line=<STDIN>){$line=<STDIN>;chomp($line);push(@lines,$line);$line=<STDIN>;$line=<STDIN>}$min_len=100000;$base_count=0;foreach $l(@lines){$base_count+=length($l);push(@lengths,length($l));@f=split("",$l);foreach $base(@f){if(uc($base) eq "G" || uc($base) eq "C"){$gc_count++}}} @lengths =sort {$b <=> $a} @lengths; $min_len=$lengths[int($#lengths*.75)]; $gc_ratio=$gc_count/$base_count;$kmer=0;if($gc_ratio<0.5){$kmer=int($min_len*.7);}elsif($gc_ratio>=0.5 && $gc_ratio<0.6){$kmer=int($min_len*.5);}else{$kmer=int($min_len*.33);} $kmer++ if($kmer%2==0); $kmer=31 if($kmer<31); $kmer=127 if($kmer>127); print $kmer'`
save KMER
echo "choosing kmer size of $KMER for the graph"
KMER_J=$KMER
MIN_Q_CHAR=`cat pe.renamed.fastq |head -n 50000 | awk 'BEGIN{flag=0}{if($0 ~ /^\+/){flag=1}else if(flag==1){print $0;flag=0}}' | perl -ne 'BEGIN{$q0_char="@";}{chomp;@f=split "";foreach $v(@f){if(ord($v)<ord($q0_char)){$q0_char=$v;}}}END{$ans=ord($q0_char);if($ans<64){print "33\n"}else{print "64\n"}}'`
save MIN_Q_CHAR
echo MIN_Q_CHAR: $MIN_Q_CHAR
JF_SIZE=`ls -l *.fastq | awk '{n+=$5}END{s=int(n/50); if(s>80000000000)printf "%.0f",s;else print "80000000000";}'`
save JF_SIZE
perl -e '{if(int('$JF_SIZE')>80000000000){print "WARNING: JF_SIZE set too low, increasing JF_SIZE to at least '$JF_SIZE', this automatic increase may be not enough!\n"}}'
log Creating mer database for Quorum.
quorum_create_database -t 40 -s $JF_SIZE -b 7 -m 24 -q $((MIN_Q_CHAR + 5)) -o quorum_mer_db.jf.tmp pe.renamed.fastq && mv quorum_mer_db.jf.tmp quorum_mer_db.jf
if [ 0 != 0 ]; then
fail Increase JF_SIZE in config file, the recommendation is to set this to genome_size*coverage/2
fi
log Error correct PE.
quorum_error_correct_reads -q $((MIN_Q_CHAR + 40)) --contaminant=/home/mathog/MaSuRCA/bin/../share/adapter.jf -m 1 -s 1 -g 1 -a 3 -t 40 -w 10 -e 3 -M quorum_mer_db.jf pe.renamed.fastq --no-discard -o pe.cor --verbose 1>quorum.err 2>&1 || {
mv pe.cor.fa pe.cor.fa.failed && fail Error correction of PE reads failed. Check pe.cor.log.
}
log Estimating genome size.
jellyfish count -m 31 -t 40 -C -s $JF_SIZE -o k_u_hash_0 pe.cor.fa
export ESTIMATED_GENOME_SIZE=`jellyfish histo -t 40 -h 1 k_u_hash_0 | tail -n 1 |awk '{print $2}'`
save ESTIMATED_GENOME_SIZE
echo "Estimated genome size: $ESTIMATED_GENOME_SIZE"
答案 0 :(得分：0)
脚本中存在（某些）无用的内存和CPU周期浪费：
cat pe.renamed.fastq | head -n 50000 | ...
你应该避免使用
无用的猫head -n 50000 pe.renamed.fastq | ...