On Wed, May 01, 2013 at 02:58:03PM +0800, Ric Mason wrote: > Hi Mel, > On 04/25/2013 02:57 AM, Mel Gorman wrote: > >As pointed out by Andrew Morton, the swap-over-NFS writeback is not setting > >PageWriteback before it is queued for direct IO. While swap pages do not > > Before commit commit 62c230bc1 (mm: add support for a filesystem to > activate swap files and use direct_IO for writing swap pages), swap > pages will write to page cache firstly and then writeback? > That commit added an *optional* address_space operations method that allowed a filesystem to use their aops->direct_IO method to write to a swapfile. The existing methods for writing swap files are still there so before and after commit 62c230bc1, swap partitions and most swapfiles (backed by filesystems that support bmap) are still the same. Look at swapfile.c, swap_state.c and page_io.c for the details on how swap gets activated, pages are added to swap cache and the writepage method used when aops->writepage is called to write the page to disk respectively. -- Mel Gorman SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>