[PATCHSET v2 0/4] Add throttling for discards

[Jens Axboe <axboe@kernel.dk>]

I implemented support for discards in blk-wbt, so we treat them like
background writes. If we have competing foreground IO, then we may
throttle discards. Otherwise they should run at full speed.

Ran a quick local test case on a NVMe device. The test case here is
doing reads from a file, while other files are being delete. File
system is XFS. Three separate runs:

1) 'justreader' is just running the reader workload by itself.
2) 'nothrottle' is running the reader with the unlinks on the stock
   kernel.
3) 'throttled' is running the reader with the unlinks with the patches
   applied.

The fio run logs latencies in windows of 50msec, logging only the
worst latency seen in that window:

[read]
filename=file0
rw=randread
bs=4k
direct=1
ioengine=libaio
iodepth=8
write_lat_log=read_lat
log_avg_msec=50
log_max_value=1

Graph of the latencies here: http://kernel.dk/wbt-discard.jpg

As you can see, with the throttling, the latencies and performance is
the same as not having the unlinks running. They finish within 100msec
of each other, after having read 10G of data. Without the throttling
and unlinks running, we see spikes that are almost an order of magnitude
worse. The reader also takes 1 second longer to complete. 322MB/sec vs
313MB/sec. It's also visible in the higher Pxx. Here's the throttled
end of the percentiles:

     | 99.00th=[  145], 99.50th=[  153], 99.90th=[  180], 99.95th=[  198],
     | 99.99th=[  889]

and here's the unthrottled equivalent:

     | 99.00th=[  145], 99.50th=[  155], 99.90th=[  188], 99.95th=[  322],
     | 99.99th=[ 8586]


Changes since v1:

- Pass in enum wbt_flags for get_rq_wait()
- Turn wbt_should_throttle() into a switch statement

 blk-lib.c  |    7 +++---
 blk-stat.h |    6 ++---
 blk-wbt.c  |   70 ++++++++++++++++++++++++++++++++++++-------------------------
 blk-wbt.h  |    8 +++++-
 4 files changed, 55 insertions(+), 36 deletions(-)