We've got a bit of an issue. From conversations on this list over the last few months, it appears as if enabling the write cache on an IDE drive is a "bad thing" when using a journaling file system s
Andi Kleen was experimenting with the ide cache flushing code in the Suse kernel and adding some flushing calls to XFS. We talked about the right place to add them, I am not sure if he has tried it y
I've tried it and also got it to work in an experimental state, but decided to rewrite it to use barriers instead. I didn't yet get around to do this rewrite. The reason for the rewrite is that just
Using barriers is surely the right approach, and lets the kernel use flushes or tag barriers as provided by the hardware. ? Both the SuSE kernel has the infrastructure, and the 2.5 kernels so as well
Unless I am mistaken, Jim is tied down to a fairly old kernel. Steve -- Steve Lord voice: +1-651-683-3511 Principal Engineer, Filesystem Software email: lord@xxxxxxx
I was thinking of the SuSE kernel. Wasn't aware that the queue flushing has been merged into 2.5 yet. My work was on 2.4-SuSE, but could be probably ported to 2.5 (but I'm waiting a few releases fir
I don't think the backend has been merged in 2.5 yet, at least I didn't send it in so far. The frontend is there though, so writing the support is trivial :-) I'll get the 2.5 bits in now. -- Jens Ax
Not too much of a problem, the barrier infrastructure + ide flush support really isn't that much code, didn't even take long to write. That just leaves the XFS parts, which I don't know anything abou
Have you thought about using ext3 in data=journal mode instead? Also make sure your disk honours the ATA write cache flush command, and that it doesn't throw away the cache contents on reboot/suspend
One feature we require that only XFS provides (as far as I know) is the ability to punch holes in files. We continually record video to a file and when the file gets too large, we just chop off the f
At 09:28 18-4-2002 -0600, Jim Buzbee wrote: We've got a bit of an issue. From conversations on this list over the last few months, it appears as if enabling the write cache on an IDE drive is a "bad
Anyone know what are the Linux distributions are doing by default? Now that they are including journaling filesystems as an option, I wonder if they turn write caching off on IDE drives. Jim
They don't. Only the BSDs turn it off by default, but everybody then just turns it on again. SuSe 8.0 also flushes caches explicitely for ext3 and reiserfs. -Andi
from mobile.sauter-bc.com (unknown [10.1.6.21]) by basel1.sauter-bc.com (Postfix) with ESMTP id 6D73257306; Fri, 19 Apr 2002 08:31:48 +0200 (CEST) Cc: XFS List <linux-xfs@xxxxxxxxxxx> Organization:
... I think I missed some of the "remount readonly" discussion. Can someone summarize what the problem is and the correct way we should be doing a controlled shutdown/reboot with XFS? ... The drive w
from mobile.sauter-bc.com (unknown [10.1.6.21]) by basel1.sauter-bc.com (Postfix) with ESMTP id C895D57306; Fri, 19 Apr 2002 17:13:18 +0200 (CEST) Cc: XFS List <linux-xfs@xxxxxxxxxxx> Organization:
Sorry, I can't resist: how about a pair of really large electrolytics? ;-) Okay, I'll go back under my "lurker" rock, now. -- kernel, n.: A part of an operating system that preserves the medieval tr
about a week after migrating my RH 7.2 desktop box to XFS, I started loosing setting in GNOME 1.4 and I also lost all of my bookmarks in mozilla 0.9.9, I did test XFS with a simulated powerfailure ju
Well, it should not be a compatibility issue... gnome seems to be particularly susceptible to this, it seems that our sync behavior may not be quite right. On the other hand, with a metadata journali