On Fri, Jun 21, 2024 at 10:37:29AM +0800, Hongbo Li wrote:
>
>
> On 2024/6/20 22:56, Jens Axboe wrote:
> > On 6/20/24 8:49 AM, Matthew Wilcox wrote:
> > > On Thu, Jun 20, 2024 at 10:16:02AM -0400, Kent Overstreet wrote:
> > > I'm more sympathetic to "lets relax the alignment requirements", since
> > > most IO devices actually can do IO to arbitrary boundaries (or at least
> > > reasonable boundaries, eg cacheline alignment or 4-byte alignment).
> > > The 512 byte alignment doesn't seem particularly rooted in any hardware
> > > restrictions.
> >
> > We already did, based on real world use cases to avoid copies just
> > because the memory wasn't aligned on a sector size boundary. It's
> > perfectly valid now to do:
> >
> > struct queue_limits lim {
> > .dma_alignment = 3,
> > };
> >
> > disk = blk_mq_alloc_disk(&tag_set, &lim, NULL);
> >
> > and have O_DIRECT with a 32-bit memory alignment work just fine, where
> Does this mean that file system can relax its alignment restrictions on
> offset or memory (not 512 or 4096)? Is it necessary to add alignment
> restrictions in the super block of file system? Because there are different
> alignment restrictions for different storage hardware driver.
A multidevice filesystem can't get rid of those checks becaause if
different devices have inconsistent restrictions that'll be quite the
source of confusion later.
And since devices can be hot-added, it does effectively need to be in
the superblock.
