Messages in this thread | | | Date | Sun, 22 Feb 2009 20:23:36 -0500 | From | Theodore Tso <> | Subject | Re: vfs: Add MS_FLUSHONFSYNC mount flag |
| |
On Sun, Feb 22, 2009 at 06:46:51PM -0500, Jeff Garzik wrote: > > To be more clear / precise, this means actually performing the > guarantees we claim to the user. For example, > > fsync(2) on ext2 should trigger a storage device writeback cache flush > [or equivalent guarantee via FUA]. > > fsync(2) or journal commit on ext3 should trigger a flush [or equivalent > guarantee via FUA]. > > Though, certainly, the user should be able to disable this strict > behavior and trade correctness for performance.
No argument here. The *default* should be that we respect fsync(). However, the user should be able to configure with a reasonable amount of granularity tradeoffs between safety and performance and/or battery usage.
- Ted
| |