parallel: implemented --minversion

This commit is contained in:
Ole Tange 2011-06-05 18:27:50 +02:00
parent 7ed9090560
commit 0a1d43bbda
3 changed files with 150 additions and 145 deletions

View file

@ -1,11 +1,138 @@
Til QUOTING:
FN="two spaces"
echo 1 | parallel -q echo {} "$FN"
# Prints 2 spaces between 'two' and 'spaces'
-q will not work with composed commands as it will quote the ; as
well. So composed commands have to be quoted by hand:
# Using export:
FN2="two spaces"
export FN2
echo 1 | parallel echo {} \"\$FN2\" \; echo \"\$FN2\" {}
# Prints 2 spaces between 'two' and 'spaces'
# Without export:
FN3="two spaces"
echo 1 | parallel echo {} \""$FN3"\" \; echo \'"$FN3"\' {}
# By quoting the space in the variable
FN4='two\ \ spaces'
echo 1 | parallel echo {} $FN4 \; echo $FN4 {}
= Bug? ==
locate .gz | parallel -X find {} -size +1000 -size -2000 | parallel --workdir ... -S .. --trc {/}.bz2 'zcat {} | bzip2 > {/}.bz2'
== Compare ==
http://code.google.com/p/spawntool/
http://code.google.com/p/push/
== Bug? ==
.parallel/config with --long-options
== SQL ==
Example with %0a as newline
sql :my_postgres?'\dt %0a SELECT * FROM users'
cat ~/.sql/aliases | parallel --colsep '\s' sql {1} '"select 0.14+3;" | grep -q 3.14 || (echo dead: {1}; exit 1)'
== FEX ==
fex syntax for splitting fields
http://www.semicomplete.com/projects/fex/
sql :foo 'select * from bar' | parallel --fex '|{1,2}' do_stuff {2} {1}
--autocolsep: Læs alle linjer.
Prøv fastlængde: Find tegn, som står i alle linjer på de samme pladser. Risiko for falske pos
Prøv fieldsep: Find eet tegn, som optræder det samme antal gange i alle linjer (tab sep)
Prøv klyngesep: Find den samme klynge tegn, som står samme antal gange i alle linjer (' | ' sep)
Fjern whitespace før og efter colonne
hvis der er n af tegn A og 2n af tegn B, så
a | b | c
Simpleste: tab sep
for hver linje
max,min count for hver char
for hver char
if max == min :
potentiel
min_potentiel = min(min_potentiel,min)
for potentiel:
if min % min_potentiel = 0: sepchars += potentiel,no of sepchars += min / min_potentiel
colsep = [sepchars]{no_of_sepchars}
# TODO max_line_length on remote
# TODO compute how many can be transferred within max_line_length
Postkort:
- Forside kun figur
- Bagside:
- Logo med figur - evt gnu.org/s/parallel
- kort grå tekst, der forklarer hvad det er.
- Eet eksempel: parallel gzip ::: *
- Link til video. http://nd.gd/0s
GNU parallel is a UNIX-tool for running commands in parallel.
To gzip all files running one job per CPU write:
parallel gzip ::: *
Watch the intro video to learn more: http://nd.gd/0s
Or read more about GNU parallel: www.gnu.org/s/parallel
job->start():
$jobslot = Global::jobslot->$sshlogin
sub get_jobslot {
my $sshlogin = shift;
my $jobslot_id = pop @Global::jobslots{$sshlogin};
if not defined $jobslot_id {
$jobslot_id = ++$Global::max_jobslot_id;
}
return $jobslot_id;
}
sub release_jobslot {
my $sshlogin = shift;
my $jobslot_id = shift;
push @Global::jobslots{$sshlogin}, $jobslot_id;
}
Test sshlogins in parallel. Assume parallel is in path
seq 1 10 | parallel -I {o} 'seq 1 255 | parallel echo ssh -oNoHostAuthenticationForLocalhost=true 127.0.{o}.{}' >/tmp/sshloginfile
seq 1 1000 | parallel --sshloginfile /tmp/sshloginfile echo
ssh -F /tmp/
Example:
Chop mbox into emails
Parallel sort
codecoverage
Testsuite: sem without ~/.parallel
Dont start:
* load
* memory free | head -n 2 | awk \{print\ \$4+\$6+\$7\}
* swap
* seek
vmstat\ 1\ 2\ \|\ tail\ -n1\ \|\ awk\ \{print\\\ \\\$7*\\\$8\}
Video 30. 36. 41. 48
@ -113,137 +240,6 @@ parallel convert -resize {3} -quality {2} {1} {1.}_{3}_q{2}.jpg :::: - ::: 25 50
# Find GNU Parallel at http://www.gnu.org/software/parallel/
Postkort:
- Forside kun figur
- Bagside:
- Logo med figur - evt gnu.org/s/parallel
- kort grå tekst, der forklarer hvad det er.
- Eet eksempel: parallel gzip ::: *
- Link til video. http://nd.gd/0s
GNU parallel is a UNIX-tool for running commands in parallel.
To gzip all files running one job per CPU write:
parallel gzip ::: *
Watch the intro video to learn more: http://nd.gd/0s
Or read more about GNU parallel: www.gnu.org/s/parallel
job->start():
$jobslot = Global::jobslot->$sshlogin
sub get_jobslot {
my $sshlogin = shift;
my $jobslot_id = pop @Global::jobslots{$sshlogin};
if not defined $jobslot_id {
$jobslot_id = ++$Global::max_jobslot_id;
}
return $jobslot_id;
}
sub release_jobslot {
my $sshlogin = shift;
my $jobslot_id = shift;
push @Global::jobslots{$sshlogin}, $jobslot_id;
}
Test sshlogins in parallel. Assume parallel is in path
seq 1 10 | parallel -I {o} 'seq 1 255 | parallel echo ssh -oNoHostAuthenticationForLocalhost=true 127.0.{o}.{}' >/tmp/sshloginfile
seq 1 1000 | parallel --sshloginfile /tmp/sshloginfile echo
ssh -F /tmp/
Example:
Chop mbox into emails
Parallel sort
codecoverage
Testsuite: sem without ~/.parallel
Til QUOTING:
FN="two spaces"
echo 1 | parallel -q echo {} "$FN"
# Prints 2 spaces between 'two' and 'spaces'
-q will not work with composed commands as it will quote the ; as
well. So composed commands have to be quoted by hand:
# Using export:
FN2="two spaces"
export FN2
echo 1 | parallel echo {} \"\$FN2\" \; echo \"\$FN2\" {}
# Prints 2 spaces between 'two' and 'spaces'
# Without export:
FN3="two spaces"
echo 1 | parallel echo {} \""$FN3"\" \; echo \'"$FN3"\' {}
# By quoting the space in the variable
FN4='two\ \ spaces'
echo 1 | parallel echo {} $FN4 \; echo $FN4 {}
= Bug? ==
locate .gz | parallel -X find {} -size +1000 -size -2000 | parallel --workdir ... -S .. --trc {/}.bz2 'zcat {} | bzip2 > {/}.bz2'
== Compare ==
http://code.google.com/p/spawntool/
http://code.google.com/p/push/
== Bug? ==
.parallel/config with --long-options
time find . -type f | parallel -j+0 --eta -S..,: --progress --trc {}.gz gzip {}
== SQL ==
Example with %0a as newline
sql :my_postgres?'\dt %0a SELECT * FROM users'
cat ~/.sql/aliases | parallel --colsep '\s' sql {1} '"select 0.14+3;" | grep -q 3.14 || (echo dead: {1}; exit 1)'
== FEX ==
fex syntax for splitting fields
http://www.semicomplete.com/projects/fex/
sql :foo 'select * from bar' | parallel --fex '|{1,2}' do_stuff {2} {1}
--autocolsep: Læs alle linjer.
Prøv fastlængde: Find tegn, som står i alle linjer på de samme pladser. Risiko for falske pos
Prøv fieldsep: Find eet tegn, som optræder det samme antal gange i alle linjer (tab sep)
Prøv klyngesep: Find den samme klynge tegn, som står samme antal gange i alle linjer (' | ' sep)
Fjern whitespace før og efter colonne
hvis der er n af tegn A og 2n af tegn B, så
a | b | c
Simpleste: tab sep
for hver linje
max,min count for hver char
for hver char
if max == min :
potentiel
min_potentiel = min(min_potentiel,min)
for potentiel:
if min % min_potentiel = 0: sepchars += potentiel,no of sepchars += min / min_potentiel
colsep = [sepchars]{no_of_sepchars}
# TODO max_line_length on remote
# TODO compute how many can be transferred within max_line_length
=head1 YouTube video --pipe
cp parallel.fasta parallel.mbox lucene.tar
@ -615,16 +611,6 @@ Test if -0 works on filenames ending in '\n'
One char options not used: A F G K O Q R Z c f
=head1 sem
Parallelize so this can be done:
mdm.screen find dir -execdir mdm-run cmd {} \;
Maybe:
find dir -execdir par$ --communication-file /tmp/comfile cmd {} \;
find dir -execdir mutex -j4 -b cmd {} \;
=head1 Unlikely
Accept signal INT instead of TERM to complete current running jobs but

View file

@ -403,6 +403,7 @@ sub options_hash {
"interactive|p" => \$::opt_p,
"verbose|t" => \$::opt_verbose,
"version|V" => \$::opt_version,
"minversion|min-version=i" => \$::opt_minversion,
"show-limits|showlimits" => \$::opt_show_limits,
"exit|x" => \$::opt_x,
# Semaphore
@ -530,6 +531,14 @@ sub parse_options {
if(defined $::opt_fg) { $Global::semaphore = 1; }
if(defined $::opt_bg) { $Global::semaphore = 1; }
if(defined $::opt_wait) { $Global::semaphore = 1; }
if(defined $::opt_minversion) {
version();
if($Global::version < $::opt_minversion) {
wait_and_exit(255);
} else {
wait_and_exit(0);
}
}
if(defined $::opt_nonall) {
# Append a dummy empty argument
push @ARGV, ":::", "";

View file

@ -621,6 +621,16 @@ See also B<-X> for context replace. If in doubt use B<-X> as that will
most likely do what is needed.
=item B<--minversion> I<version> (alpha testing)
Print the version GNU B<parallel> and exit. If the current version of
GNU B<parallel> is less than I<version> the exit code is
255. Otherwise it is 0.
This is useful for scripts that depend on features only available from
a certain version of GNU B<parallel>.
=item B<--onall> (alpha testing)
Run all the jobs on all computers given with B<--sshlogin>. GNU