On 02/15/2018 11:30 PM, Dave Chinner wrote:
On Thu, Feb 15, 2018 at 11:36:54AM +0200, Avi Kivity wrote:
On 02/15/2018 01:56 AM, Dave Chinner wrote:
A little bird whispered in my ear to try XFS_IOC_OPEN_BY_HANDLE to
avoid the the time update lock, so we'll be trying that next, to
emulate lazytime.
Biggest problem with that is it requires root permissions. It's not
a solution that can be deployed in practice, so I haven't bothered
suggesting it as something to try.
If you want to try lazytime, an easier test might be to rebuild the
kernel with this change below to support the lazytime mount option
and not log the timestamp updates. This is essentially the mechanism
that I'll use for this, but it will need to grow more stuff to have
the correct lazytime semantics...
We tried open by handle to see if lazytime would provide relief, but it
looks like it just pushes the lock acquisition to another place:
reactor-8 16033 [009] 1482121.241125: xfs:xfs_ilock:
dev 9:2 ino 0xc0004bac flags ILOCK_EXCL caller kretprobe_trampoline
7fffa01ca572 xfs_ilock ([kernel.kallsyms])
7fff8105f5a0 kretprobe_trampoline ([kernel.kallsyms])
7fff812bd2ea iomap_apply ([kernel.kallsyms])
7fff812bdb81 iomap_dio_rw ([kernel.kallsyms])
7fffa01bbc26 xfs_file_dio_aio_write ([kernel.kallsyms])
7fffa01bc13f xfs_file_write_iter ([kernel.kallsyms])
7fff812ab24f aio_write ([kernel.kallsyms])
7fff812ab90e do_io_submit ([kernel.kallsyms])
7fff812ac4c0 sys_io_submit ([kernel.kallsyms])
7fff81005917 do_syscall_64 ([kernel.kallsyms])
7fff81802115 return_from_SYSCALL_64 ([kernel.kallsyms])
f27f9 syscall (/usr/lib64/libc-2.17.so)
1c [unknown] ([unknown])
142e60 reactor_backend_epoll::~reactor_backend_epoll
(/usr/bin/scylla)
Probably, iomap_apply calls xfs_file_iomap_begin, which calls xfs_ilock().
It consults need_excl_ilock() to see whether it wants to lock or not:
static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
{
/*
* COW writes will allocate delalloc space, so we need to make sure
* to take the lock exclusively here.
*/
if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE |
IOMAP_ZERO)))
return true;
if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE))
return true;
return false;
}
However, that function can EAGAIN (it does for IOLOCK) so maybe we can
change xfs_ilock to xfs_ilock_nowait and teach it about not waiting for
ILOCK too.
--
To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
