>> Anyone has better results ? > Yes, see following: > > jac...@work:~/temp$ time tar -cjf temp1.tar.bz2 debian > > real 0m18.830s > user 0m18.317s > sys 0m0.268s > jac...@work:~/temp$ time bash -c "tar -cf - debian | pbzip2 -c > > temp2.tar.bz2" > > real 0m10.494s > user 0m19.557s > sys 0m0.488s > > 10 is much less than 18.
n...@fugue:~/moko/devel$ time bzip2 linux-2.6.backup.diciembre.20.tar real 1m28.765s user 1m27.397s sys 0m1.180s n...@fugue:~/moko/devel$ time bzip2 -d linux-2.6.backup.diciembre.20.tar.bz2 real 0m46.583s user 0m45.019s sys 0m1.236s n...@fugue:~/moko/devel$ time pbzip2 -p2 linux-2.6.backup.diciembre.20.tar real 0m53.963s user 1m44.963s sys 0m1.944s Same here. Disk I/O was cached so this was only CPU.... pbzip2 can save about 40% wall clock time in this test (which has some data that is already compressed, it is a git repository). N.- -- To UNSUBSCRIBE, email to debian-user-requ...@lists.debian.org with a subject of "unsubscribe". Trouble? Contact listmas...@lists.debian.org