Re: [Patch] document ext3 requirements (was Re: [RFD] Incremental fsck)

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Ric Wheeler <ric@...>
Cc: Al Boldi <a1426z@...>, Alan Cox <alan@...>, David Chinner <dgc@...>, <linux-kernel@...>, Pavel Machek <pavel@...>, Daniel Phillips <phillips@...>, Rik van Riel <riel@...>, Theodore Tso <tytso@...>, Valerie Henson <val.henson@...>
Date: Thursday, January 17, 2008 - 8:31 pm

Ric Wheeler <ric@emc.com> wrote on 01/17/2008 03:18:05 PM:

drive
enough

We weren't actually talking about writing out the cache.  While that was 
part of an earlier thread which ultimately conceded that disk drives most 
probably do not use the spinning disk energy to write out the cache, the 
claim was then made that the drive at least survives long enough to finish 
writing the sector it was writing, thereby maintaining the integrity of 
the data at the drive level.  People often say that a disk drive 
guarantees atomic writes at the sector level even in the face of a power 
failure.

But I heard some years ago from a disk drive engineer that that is a myth 
just like the rotational energy thing.  I added that to the discussion, 
but admitted that I haven't actually seen a disk drive write a partial 
sector.

Ted brought up the separate issue of the host sending garbage to the disk 
device because its own power is failing at the same time, which makes the 
integrity at the disk level moot (or even undesirable, as you'd rather 
write a bad sector than a good one with the wrong data).

--
Bryan Henderson                     IBM Almaden Research Center
San Jose CA                         Filesystems

--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[RFD] Incremental fsck, Al Boldi, (Tue Jan 8, 5:22 pm)
Re: [RFD] Incremental fsck, Alan, (Tue Jan 8, 5:31 pm)
Re: [RFD] Incremental fsck, Andreas Dilger, (Wed Jan 9, 5:16 am)
Re: [RFD] Incremental fsck, Daniel Phillips, (Sat Jan 12, 7:55 pm)
Re: [RFD] Incremental fsck, Rik van Riel, (Tue Jan 8, 5:41 pm)
Re: [RFD] Incremental fsck, Al Boldi, (Wed Jan 9, 12:40 am)
Re: [RFD] Incremental fsck, , (Wed Jan 9, 4:04 am)
Re: [RFD] Incremental fsck, Valerie Henson, (Wed Jan 9, 3:45 am)
Re: [RFD] Incremental fsck, Al Boldi, (Wed Jan 9, 7:52 am)
Re: [RFD] Incremental fsck, Theodore Tso, (Sat Jan 12, 10:51 am)
Re: [RFD] Incremental fsck, Daniel Phillips, (Sun Jan 13, 8:22 pm)
Re: [RFD] Incremental fsck, Pavel Machek, (Sun Jan 13, 1:19 pm)
Re: [RFD] Incremental fsck, Ric Wheeler, (Mon Jan 14, 9:04 pm)
Re: [RFD] Incremental fsck, Alan Cox, (Sun Jan 13, 1:41 pm)
Re: [Patch] document ext3 requirements (was Re: [RFD] Increm..., Szabolcs Szakacsits, (Thu Jan 17, 8:29 am)
Re: [Patch] document ext3 requirements (was Re: [RFD] Increm..., Christoph Hellwig, (Wed Jan 16, 12:38 pm)
Re: [Patch] document ext3 requirements (was Re: [RFD] Increm..., Bryan Henderson, (Thu Jan 17, 8:31 pm)
Re: [Patch] document ext3 requirements (was Re: [RFD] Increm..., linux-os (Dick Johnson), (Fri Jan 18, 11:16 am)
Re: [RFD] Incremental fsck, Al Boldi, (Sun Jan 13, 7:05 am)
Re: [RFD] Incremental fsck, Rik van Riel, (Wed Jan 9, 10:44 am)
Re: [RFD] Incremental fsck, Al Boldi, (Thu Jan 10, 9:26 am)