Thread (26 messages) 26 messages, 11 authors, 2008-05-21

Re: [PATCH 0/4] (RESEND) ext3[34] barrier changes

From: Chris Mason <hidden>
Date: 2008-05-21 19:42:18
Also in: linux-fsdevel, lkml

On Wednesday 21 May 2008, Jamie Lokier wrote:
Theodore Tso wrote:
quoted
On Wed, May 21, 2008 at 11:03:24AM -0700, Andrew Morton wrote:
quoted
afaik there is no need to enable this feature if the machine (actually
the disks) are on a UPS, yes?
Yes, as long as you're confident that there won't be a kernel
bug/regression causing a lockup while the server is under severe
memory pressure while doing lots of fsync's, file creations, renames,
etc.  And as long as your 100% confident that UPS's will never fail,
janitors will never accidentally hit the Emergency Power Office
Can a kernel lockup cause this kind of corruption?
No
Will a system reboot wipe the disk's write cache?
Only if you reboot with the power switch (some test rigs do)
I had imagined only power loss would prevent the disk from
writing it's cache eventually; is that wrong?
-chris
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help