On Mon, 2018-12-17 at 11:28 -0700, Jens Axboe wrote:

As I'm sure you're all aware, the merge window is coming up. This time
it happens to coincide with that is a holiday for most. My plan is to
send in an EARLY pull request to Linus, Thursday at the latest. If you're
sitting on anything that should go in with the initial merge, then I need
to have it ASAP.

I'll do a later pull about a week in with things that were missed, but
I'm really hoping to make that fixes only. Any driver updates etc should
go in now.

Hi Jens,

If I run blktests/srp/002 against Linus' master branch then that test passes,
no matter how many times I run that test. If I run that test against your
for-next branch however (commit 6a252f2772c0) then that test hangs. The output
of my list-pending-block-requests script is as follows when the hang occurs:

dm-0
dm-1
dm-1/hctx0/active:0
dm-1/hctx0/flags:alloc_policy=FIFO SHOULD_MERGE|SG_MERGE
dm-1/hctx0/tags:nr_tags=2048
dm-1/hctx0/tags:nr_reserved_tags=0
dm-1/hctx0/tags:active_queues=0
dm-1/hctx0/tags:bitmap_tags:
dm-1/hctx0/tags:depth=2048
dm-1/hctx0/tags:busy=798
dm-1/hctx0/tags:cleared=935
dm-1/hctx0/tags:bits_per_word=64
dm-1/hctx0/tags:map_nr=32
dm-1/hctx0/tags:alloc_hint={682, 463, 595, 1923, 841, 628}
dm-1/hctx0/tags:wake_batch=8
dm-1/hctx0/tags:wake_index=0
dm-1/hctx0/tags:ws_active=0
dm-1/hctx0/tags:ws={
dm-1/hctx0/tags:	{.wait_cnt=8, .wait=inactive},
dm-1/hctx0/tags:	{.wait_cnt=8, .wait=inactive},
dm-1/hctx0/tags:	{.wait_cnt=8, .wait=inactive},
dm-1/hctx0/tags:	{.wait_cnt=8, .wait=inactive},
dm-1/hctx0/tags:	{.wait_cnt=8, .wait=inactive},
dm-1/hctx0/tags:	{.wait_cnt=8, .wait=inactive},
dm-1/hctx0/tags:	{.wait_cnt=8, .wait=inactive},
dm-1/hctx0/tags:	{.wait_cnt=8, .wait=inactive},
dm-1/hctx0/tags:}
dm-1/hctx0/tags:round_robin=0
dm-1/hctx0/tags:min_shallow_depth=4294967295
dm-1/hctx0/tags_bitmap:00000000: ff03 feff ffff ffff ffff ffff ffff ffff
dm-1/hctx0/tags_bitmap:00000010: ffff ffff ffff ffff ffff 1f70 0040 0100
dm-1/hctx0/tags_bitmap:00000020: ffff ffef f7bf ffe7 ffff ffff ffff ffdf
dm-1/hctx0/tags_bitmap:00000030: ffff ffff ffff ffff ffff ffff ffff ffff
dm-1/hctx0/tags_bitmap:00000040: ffff ffff ffff ff7f ffff ffff ffff ffff
dm-1/hctx0/tags_bitmap:00000050: ffff ffff ffff ffff ffff ffff ffff ffff
dm-1/hctx0/tags_bitmap:00000060: f3ff 1fe0 ffff f19f ffff ffff ffff ffff
dm-1/hctx0/tags_bitmap:00000070: ffff fff7 9bff fff7 0fec 1300 00e0 1f01
dm-1/hctx0/tags_bitmap:00000080: ffff ffff ffff e189 ff0f 90ff ffff ffff
dm-1/hctx0/tags_bitmap:00000090: ffff ffff ffff ffff ffff 0300 00fd 0780
dm-1/hctx0/tags_bitmap:000000a0: ffff ffff ffff ffff ff0f 0000 0000 5400
dm-1/hctx0/tags_bitmap:000000b0: ffff ffff ffff ffff ffff ffff ffff ff0f
dm-1/hctx0/tags_bitmap:000000c0: ffff ffff ffff ff3f ffff ffff ffff 7f1c
dm-1/hctx0/tags_bitmap:000000d0: ffff ffff ffff ffff ffff ffff ffff ffff
dm-1/hctx0/tags_bitmap:000000e0: ffff ffff 0f00 0040 1de0 1400 3cdf 0300
dm-1/hctx0/tags_bitmap:000000f0: ffff ffff 1f1c 7cfb ffff ffff ffff 1fef
dm-1/state:SAME_COMP|NONROT|IO_STAT|INIT_DONE|STATS|REGISTERED|QUIESCED
dm-1/queue/scheduler:[none] bfq kyber mq-deadline 
dm-2
loop0
loop1
loop2
loop3
loop4
loop5
loop6
loop7
nullb0
nullb1
sda
sdb
sdc
sdd
sde
sdf
sdg
sdh
vda

Bart.