Messages in this thread |  | | Date | Thu, 20 Sep 2001 09:56:22 -0400 (EDT) | From | Alexander Viro <> | Subject | Re: Linux 2.4.10-pre11 |
| |
On Thu, 20 Sep 2001, Andrea Arcangeli wrote:
> > Umm... Not doing unnecessary work? Semantics of releasing a block device > > depends on the kind of use. BTW, I'm less than sure that fsync_dev() is > > the right thing for file access now that you've got that in pagecache - > > __block_fsync() seems to be more correct thing to do. > > Not really, blkdev isn't a filesystem. It will never have a superblock > and its own inodes and we also need to filemap_fdatasync/wait the > physical address space.
Had you actually read the fsync_dev()? Let me make it clear: you are flushing _buffer_ cache upon blkdev_put(bdev, BDEV_FILE). It was the right thing when file access went through buffer cache. It's blatantly wrong with page cache.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
|  |