linux.git/drivers/lightnvm/pblk-write.c, branch v4.14

lightnvm: pblk: remove unnecessary checks

2017-07-07T19:17:36+00:00

Remove unnecessary checks when freeing dma memory in the completion
path.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: control I/O flow also on tear down

2017-07-07T19:17:34+00:00

When removing a pblk instance, control the write I/O flow to the
controller as we do in the fast path.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: remove target using async. I/Os

2017-06-30T17:08:18+00:00

When removing a pblk instance, pad the current line using asynchronous
I/O. This reduces the removal time from ~1 minute in the worst case to a
couple of seconds.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: use vmalloc for GC data buffer

2017-06-30T17:08:18+00:00

For now, we allocate a per I/O buffer for GC data. Since the potential
size of the buffer is 256KB and GC is not in the fast path, do this
allocation with vmalloc. This puts lets pressure on the memory
allocator at no performance cost.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: fail gracefully on irrec. error

2017-06-26T22:27:39+00:00

Due to user writes being decoupled from media writes because of the need
of an intermediate write buffer, irrecoverable media write errors lead
to pblk stalling; user writes fill up the buffer and end up in an
infinite retry loop.

In order to let user writes fail gracefully, it is necessary for pblk to
keep track of its own internal state and prevent further writes from
being placed into the write buffer.

This patch implements a state machine to keep track of internal errors
and, in case of failure, fail further user writes in an standard way.
Depending on the type of error, pblk will do its best to persist
buffered writes (which are already acknowledged) and close down on a
graceful manner. This way, data might be recovered by re-instantiating
pblk. Such state machine paves out the way for a state-based FTL log.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: set mempool and workqueue params.

2017-06-26T22:27:39+00:00

Make constants to define sizes for internal mempools and workqueues. In
this process, adjust the values to be more meaningful given the internal
constrains of the FTL. In order to do this for workqueues, separate the
current auxiliary workqueue into two dedicated workqueues to manage
lines being closed and bad blocks.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: cleanup unnecessary code

2017-06-26T22:27:39+00:00

Cleanup unnecessary headers and code lines.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: simplify meta. memory allocation

2017-06-26T22:27:39+00:00

smeta size will always be suitable for a kmalloc allocation. Simplify
the code and leave the vmalloc fallback only for emeta, where the pblk
configuration has an impact.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: delete redundant buffer pointer

2017-06-26T22:27:39+00:00

After refactoring the metadata path, the backpointer controlling
synced I/Os in a line becomes unnecessary; metadata is scheduled
on the write thread, thus we know when the end of the line is reached
and act on it directly.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe

lightnvm: pblk: sched. metadata on write thread

2017-06-26T22:27:39+00:00

At the moment, line metadata is persisted on a separate work queue, that
is kicked each time that a line is closed. The assumption when designing
this was that freeing the write thread from creating a new write request
was better than the potential impact of writes colliding on the media
(user I/O and metadata I/O). Experimentation has proven that this
assumption is wrong; collision can cause up to 25% of bandwidth and
introduce long tail latencies on the write thread, which potentially
cause user write threads to spend more time spinning to get a free entry
on the write buffer.

This patch moves the metadata logic to the write thread. When a line is
closed, remaining metadata is written in memory and is placed on a
metadata queue. The write thread then takes the metadata corresponding
to the previous line, creates the write request and schedules it to
minimize collisions on the media. Using this approach, we see that we
can saturate the media's bandwidth, which helps reducing both write
latencies and the spinning time for user writer threads.

Signed-off-by: Javier González 
Signed-off-by: Matias Bjørling 
Signed-off-by: Jens Axboe