| To: | Eric Sandeen <sandeen@xxxxxxxxxx> |
|---|---|
| Subject: | Re: [PATCH/RFC] pass dio_complete proper offset from finished_one_bio |
| From: | Eric Sandeen <sandeen@xxxxxxxxxx> |
| Date: | Tue, 28 Nov 2006 08:09:50 -0600 |
| Cc: | linux-fsdevel@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx, rtc@xxxxxx |
| In-reply-to: | <45691753.60500@xxxxxxxxxx> |
| References: | <45691753.60500@xxxxxxxxxx> |
| Sender: | xfs-bounce@xxxxxxxxxxx |
| User-agent: | Thunderbird 1.5.0.8 (Macintosh/20061025) |
Eric Sandeen wrote: We saw problems w/ xfs doing AIO+DIO into a sparse file. https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=217098 It seemed that xfs was doing "extent conversion" at the wrong offsets, so written regions came up as unwritten (zeros) and stale data was exposed in the region after the write. Thanks to Peter Backes for the very nice testcase. This also broke xen with blktap over xfs. Hrmph. Zach's changes in -mm magically made this go away... I was about to submit a proper patch against -mm but it seem to be not needed. So, now digging around to see why that is, and what exactly "fixed" things. -Eric |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: TAKE 956783 - xfs_dm_getall_dmattr() doesn't check if the user buffer is at valid address, Vlad Apostolov |
|---|---|
| Next by Date: | get xfs_quota info as regular user, Rene Salmon |
| Previous by Thread: | [PATCH/RFC] pass dio_complete proper offset from finished_one_bio, Eric Sandeen |
| Next by Thread: | TAKE 958534 - [clone 958472] dmf does not work with mangrove 1.0 enhanced dmapi module, Vlad Apostolov |
| Indexes: | [Date] [Thread] [Top] [All Lists] |