Ext4 breaking the promise of data=ordered ?

Posted Mar 31, 2009 21:35 UTC (Tue) by sbergman27 (guest, #10767)
In reply to: Ext4 breaking the promise of data=ordered ? by mfleetwo
Parent article: From ext3 to ext4: An Interview with Theodore Ts'o (Linux Magazine)

In ext3, data=ordered was considered to be a reliability feature. Ted is clearly trying to spin it as only having been a security feature. (Which I happen to think is a load of crap.) Now that we have heard from Linus on the matter, I'm curious to hear Stephen Tweedie's views. Stephen Tweedie is the kind of dev whose filesystems you can really feel good entrusting your data to.

Ext4 breaking the promise of data=ordered ?

Posted Mar 31, 2009 22:57 UTC (Tue) by bojan (subscriber, #14302) [Link]

Since you mention Stephen, here is an interesting quote (from here: http://markmail.org/message/nkh4og2ymaavek73):

> Correct. Journaled data mode has the side-effect of maintaining a strict order for data writes, both with respect to each other (ie. writes in a given order will always preserve that order after a crash), and with respect to metadata such as timestamps. That's not a data integrity issue, but it is certainly a consistency issue; Unix semantics basically don't give you any consistency guarantees whatsoever unless the application is requesting consistent checkpoints via fsync/O_SYNC etc; but journaled data mode provides extra consistency nonetheless.

I think more than one person understands the _real_ semantics here.