Hi,

with 2.6.4-mm2 I get following badness on boot:

Badness in as_insert_request at drivers/block/as-iosched.c:1513
Call Trace:
 [<c022e326>] as_insert_request+0x166/0x190
 [<c0225af8>] __elv_add_request+0x28/0x60
 [<c0228b9b>] __make_request+0x47b/0x540
 [<c0228d75>] generic_make_request+0x115/0x1d0
 [<c011efd0>] autoremove_wake_function+0x0/0x40
 [<c0228e80>] submit_bio+0x50/0xf0
 [<c0162f58>] __bio_add_page+0x88/0x110
 [<c016300c>] bio_add_page+0x2c/0x40
 [<c013be4f>] submit+0x9f/0xf0
 [<c03aa14a>] check_sig+0x1a/0x70
 [<c03aa4b6>] read_suspend_image+0x6/0x60
 [<c03aa565>] pmdisk_read+0x55/0x70
 [<c013b1a5>] pm_resume+0x15/0x90
 [<c039c7a3>] do_initcalls+0x23/0xc0
 [<c0103090>] init+0x0/0x150
 [<c01030c5>] init+0x35/0x150
 [<c0105288>] kernel_thread_helper+0x0/0x18
 [<c010528d>] kernel_thread_helper+0x5/0x18

After that one I get many badnesses in line 977 of the same file. I commented 
out that WARN_ON(..) to be able to capture the badness above. The message 
before the badness is: 
	PM: Reading pmdisk image.
After the badness following message is printed:
	PM: Resume from disk failed.

So there seems to be a conflict between PM-resume (btw, I did not use suspend 
to disk) and as-iosched. There is no problem if I use "elevator=cfq", 
"elevator=deadline" or "elevator=noop".

My .config is attached...

Regards
   Thomas Schlichter