VM performance 2.2.x vs 2.4.0test-ac

From: Kjartan Maraas (kmaraas@online.no)
Date: Wed Jun 21 2000 - 14:09:47 EST


I have a perl script that is used to update the i18n status
table for the GNOME project. Running the script gives the
following information:

2.4.0pre1-ac18:

5431.53user 12.76system 1:35:58elapsed 94%CPU (0avgtext+0avgdata
0maxresident)k
0inputs+0outputs (268732major+222801minor)pagefaults 0swaps

2nd run:

5884.41user 12.94system 1:41:02elapsed 97%CPU (0avgtext+0avgdata
0maxresident)k
0inputs+0outputs (268755major+221548minor)pagefaults 0swaps
[kmaraas@km-lt ru]$

2.2.14-rh:

1156.70user 12.49system 22:07.45elapsed 88%CPU (0avgtext+0avgdata
0maxresident)k0inputs+0outputs (311567major+217502minor)pagefaults
0swaps

2nd run: Exactly the same.

So, the stock Red Hat kernel is about five! times faster at running this
script.

The script does the following:

It traverses a checked out copy of most of the modules in GNOME CVS.
- First it updates the .pot file by running xgettext on the source.
- Then it goes through all languages one-by-one and merges the .po
file with the newly created .pot file and writes some statistics
about the state of the translations in the .po file.

The script is available at: http://www.gnome.org/~kmaraas/status.pl

Cheers
Kjartan Maraas

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Fri Jun 23 2000 - 21:00:22 EST