Re: softupdates and ext2

Marc Espie (espie@quatramaran.ens.fr)
Tue, 13 Apr 1999 17:48:07 +0200


In article <Pine.BSI.3.95.990331035716.22407O-100000@blues.jpj.net> you write:
>> I made some benchs and it seems rather fast (about 5 to 10% slower than
>> the async mount, which is what Linux does).

>It does that by default, but (for ext2 at least) you can mount with the
>"sync" option to have at least the metadata written synchronously. It is
>much slower than the asynchronous way, but I would do it if the unclean
>shutdowns couldn't be prevented.

`softupdates' is somewhere in-between.
The normal mode of ext2fs is similar to the async mode of Berkeley FFS,
performance and security-wise, whereas the sync-mode of ext2fs would be
on a par with the older strategy of Berkeley FFS, and soft-updates is
almost on a par with ext2fs' normal mode for speed, and sync-mode for
robustness.

(not taking into account other factors, such as dentries, or the buffer-cache,
or uvm, which are all important things for a file-system perfs otherwise.
Heck, my BSD background shows :) )

-
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/