速度问题 [英] speed problems
问题描述
嗨组，
我前段时间对Python感兴趣并将一个简单的
perl脚本转换为python。该脚本非常简单，它从一些maillog文件中生成一个
发现的病毒列表，以便进一步处理。
我发现这里存在巨大的差异脚本的执行时间，
支持perl，我无法确定出现了什么问题;
perl运行：
0.07实际0.05用户0.01 sys
0.07实际0.05用户0.01 sys
0.07实际0.04用户0.02 sys
python运行：
0.27实际0.23用户0.03 sys
0.28实际0.21用户0.05 sys
0.27实际0.19用户0.06 sys
这是使用一个小的未压缩日志文件（1.4M）测量的。每当需要解压缩东西时，差异
会变得更大。
以下是这两个脚本，请你看看并告诉我我在哪里/>
应该寻找优化吗？
perl：
my（@maillogs）=（
" / home / logs / maillog"，" /home/logs/maillog.0.gz" ;,
" /home/logs/maillog.1.gz"，" / home / logs /maillog.2.gz"，
" /home/logs/maillog.3.gz" ;,
）;
my（$ gzip）=" / usr / bin / gzip" ;;
my（$ bzip2）=" / usr / bin / bzip2" ;;
my（$ total）= 0.0;
my（％virstat）;
foreach my logfile（@maillogs）
{
if（-f $ logfile）
{
＃是压缩的吗？
if（$ logfile =〜/\。[bg] z2？$ /）
{
if（！open LF，" $ gzip -cd $ logfile | "）
{
打开LF，" $ bzip2 -cd $ logfile |"或者
死无法解压'$ logfile''\ nn" ;;
}
}
else
{
open LF，"< $ logfile"或者死无法打开'$ logfile''\ n" ;;
}
while（< LF>）
{
if（/ INFECTED /）
{
＃我们只需要病毒名称
$ _ =〜s /.* INFECTED。* \（（。*）\）。* / $ 1 / g;
＃如果发现多个病毒
if（/，/）
{
＃拆分他们
my（@vir）= split /，/，$ _;
foreach my $ v（@vir）
{
chomp $ v;
$ virstat {$ v } ++;
$ total ++;
}
}
else
{
chomp;
$ virstat {$ _} ++;
$ total ++;
}
}
}
关闭LF;
}
＃else
＃{
#print STDERR"''$ logfile''不存在，跳过它。\ n" ;;
＃} < br $>
}
预计我的$ v（排序键％virstat）
{
我的$ p =（$ virstat {$ v} / $ total）* 100;
$ p = sprintf"％s：\ t％5.2f %%"，$ v，$ p;
print" $ p\\\
" ;;
}
＃--- perl脚本结束---
python：
import os
导入字符串
导入重新
maillogs = [
" / home / logs / maillog" ;，" /home/logs/maillog.0.gz"，
" /home/logs/maillog.1.gz" ;,&home/logs/maillog.2.gz" ;，
" /home/logs/maillog.3.gz"
]
virstat = {}
total = 0.0＃keep this float
maillogs中的logfile：
if os.path.isfile（logfile）：
＃是压缩的吗？
如果logfile [-3：] ==''。gz''：
import gzip
lf = gzip.GzipFile（logfile，" r" ）
else：
if logfile [-4：] ==''。bz2''：
import bz2
lf = bz2.BZ2File（logfile，" r"）
else：
#uncompressed
lf = open（logfile， r，
for lf.readlines（）中的行：
if string.count（line，" INFECTED"）：
vname = re.compile（" INFECTED \（（。*）\）"）。search（line）.group（1）
if string.count（ vname，"，"）：
for vnam in string.split（vname，"，"）：
如果vnam不在virstat中：
virstat [vnam] = 1
否则：
virstat [vnam] + = 1
总计+ = 1
else：
如果vname不在virstat中：
virstat [vname] = 1
else：
virstat [vname] + = 1
总计+ = 1
lf.close（）
＃else：
#print" logfile''％s''不存在，跳过它。 ％logfile
$ v $ b for vname in virstat.keys（）：
p =（virstat [vname] / total）* 100
print"％s：％5.2f %%" ％（vname，p）
＃--- python脚本结束---
感谢您提供的任何帮助，
种类问候，
Axel
gzip）=" / usr / bin / gzip" ;;
my（
bzip2）=" / usr / bin / bzip2" ;;
my（
total）= 0.0;
my（％virstat）;
foreach my
Hi group,
I''ve become interested in Python a while ago and just converted a simple
perl script to python. The script is very simple, it generates a list of
found virusses from some maillog files for further processing.
I''ve found that there''s a huge difference in execution time for the scripts,
in favor of perl and I can''t pinpoint what''s going wrong;
perl runs:
0.07 real 0.05 user 0.01 sys
0.07 real 0.05 user 0.01 sys
0.07 real 0.04 user 0.02 sys
python runs:
0.27 real 0.23 user 0.03 sys
0.28 real 0.21 user 0.05 sys
0.27 real 0.19 user 0.06 sys
This was measured with a small uncompressed logfile (1.4M). The difference
grows much bigger whenever it needs to uncompress things.
Here are both scripts, could you please have a look and tell me where I
should look for optimizations?
perl:
my (@maillogs) = (
"/home/logs/maillog", "/home/logs/maillog.0.gz",
"/home/logs/maillog.1.gz", "/home/logs/maillog.2.gz",
"/home/logs/maillog.3.gz",
);
my ($gzip) = "/usr/bin/gzip";
my ($bzip2)= "/usr/bin/bzip2";
my ($total) = 0.0;
my (%virstat);
foreach my $logfile (@maillogs)
{
if ( -f $logfile )
{
# is it compressed?
if ( $logfile =~ /\.[bg]z2?$/ )
{
if ( !open LF, "$gzip -cd $logfile|" )
{
open LF, "$bzip2 -cd $logfile|" or
die "unable to uncompress ''$logfile''\n";
}
}
else
{
open LF, "<$logfile" or die "couldn''t open ''$logfile''\n";
}
while (<LF>)
{
if (/INFECTED/)
{
# we need only the virus name
$_ =~ s/.*INFECTED.*\((.*)\).*/$1/g;
# if multiple virusses found
if (/, /)
{
# split them
my (@vir) = split /, /, $_;
foreach my $v (@vir)
{
chomp $v;
$virstat{$v}++;
$total++;
}
}
else
{
chomp;
$virstat{$_}++;
$total++;
}
}
}
close LF;
}
# else
# {
# print STDERR "''$logfile'' doesn''t exist, skipping it.\n";
# }
}
foreach my $v (sort keys %virstat)
{
my $p = ($virstat{$v}/$total)*100;
$p = sprintf "%s:\t%5.2f%%", $v, $p;
print "$p\n";
}
#---end of perl script ---
python:
import os
import string
import re
maillogs = [
"/home/logs/maillog", "/home/logs/maillog.0.gz",
"/home/logs/maillog.1.gz", "/home/logs/maillog.2.gz",
"/home/logs/maillog.3.gz"
]
virstat={}
total=0.0 # keep this float
for logfile in maillogs:
if os.path.isfile( logfile ):
# is it compressed?
if logfile[-3:] == ''.gz'':
import gzip
lf = gzip.GzipFile( logfile, "r" )
else:
if logfile[-4:] == ''.bz2'':
import bz2
lf = bz2.BZ2File( logfile, "r" )
else:
# uncompressed
lf = open( logfile, "r" )
for line in lf.readlines():
if string.count( line, "INFECTED" ):
vname = re.compile( "INFECTED \((.*)\)" ).search( line ).group(1)
if string.count( vname, ", " ):
for vnam in string.split( vname, ", " ):
if vnam not in virstat:
virstat[vnam] = 1
else:
virstat[vnam] += 1
total += 1
else:
if vname not in virstat:
virstat[vname] = 1
else:
virstat[vname] += 1
total += 1
lf.close()
# else:
# print "logfile ''%s'' doesn''t exist, skipping it." % logfile
for vname in virstat.keys():
p = (virstat[vname]/total)*100
print "%s: %5.2f%%" % (vname, p)
#--- End of python script ---
Thanks for any help you can provide,
Kind regards,
Axel
gzip) = "/usr/bin/gzip";
my (
bzip2)= "/usr/bin/bzip2";
my (
total) = 0.0;
my (%virstat);
foreach my
这篇关于速度问题的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
