lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
/*
|
|
|
|
|
* Copyright (C) 2016 CNEX Labs
|
|
|
|
|
* Initial release: Javier Gonzalez <javier@cnexlabs.com>
|
|
|
|
|
* Matias Bjorling <matias@cnexlabs.com>
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
|
* modify it under the terms of the GNU General Public License version
|
|
|
|
|
* 2 as published by the Free Software Foundation.
|
|
|
|
|
*
|
|
|
|
|
* This program is distributed in the hope that it will be useful, but
|
|
|
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
|
* General Public License for more details.
|
|
|
|
|
*
|
|
|
|
|
* Implementation of a physical block-device target for Open-channel SSDs.
|
|
|
|
|
*
|
|
|
|
|
* pblk-sysfs.c - pblk's sysfs
|
|
|
|
|
*
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include "pblk.h"
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_luns_show(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
struct nvm_tgt_dev *dev = pblk->dev;
|
|
|
|
|
struct nvm_geo *geo = &dev->geo;
|
|
|
|
|
struct pblk_lun *rlun;
|
|
|
|
|
ssize_t sz = 0;
|
|
|
|
|
int i;
|
|
|
|
|
|
2018-01-05 21:16:03 +08:00
|
|
|
for (i = 0; i < geo->all_luns; i++) {
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
int active = 1;
|
|
|
|
|
|
|
|
|
|
rlun = &pblk->luns[i];
|
|
|
|
|
if (!down_trylock(&rlun->wr_sem)) {
|
|
|
|
|
active = 0;
|
|
|
|
|
up(&rlun->wr_sem);
|
|
|
|
|
}
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
|
|
|
|
"pblk: pos:%d, ch:%d, lun:%d - %d\n",
|
|
|
|
|
i,
|
2018-03-30 06:05:15 +08:00
|
|
|
rlun->bppa.a.ch,
|
|
|
|
|
rlun->bppa.a.lun,
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
active);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_rate_limiter(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
2018-01-05 21:16:13 +08:00
|
|
|
int free_blocks, free_user_blocks, total_blocks;
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
int rb_user_max, rb_user_cnt;
|
lightnvm: pblk: redesign GC algorithm
At the moment, in order to get enough read parallelism, we have recycled
several lines at the same time. This approach has proven not to work
well when reaching capacity, since we end up mixing valid data from all
lines, thus not maintaining a sustainable free/recycled line ratio.
The new design, relies on a two level workqueue mechanism. In the first
level, we read the metadata for a number of lines based on the GC list
they reside on (this is governed by the number of valid sectors in each
line). In the second level, we recycle a single line at a time. Here, we
issue reads in parallel, while a single GC write thread places data in
the write buffer. This design allows to (i) only move data from one line
at a time, thus maintaining a sane free/recycled ration and (ii)
maintain the GC writer busy with recycled data.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-26 17:57:27 +08:00
|
|
|
int rb_gc_max, rb_gc_cnt, rb_budget, rb_state;
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
2018-01-05 21:16:13 +08:00
|
|
|
free_blocks = pblk_rl_nr_free_blks(&pblk->rl);
|
|
|
|
|
free_user_blocks = pblk_rl_nr_user_free_blks(&pblk->rl);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
rb_user_max = pblk->rl.rb_user_max;
|
|
|
|
|
rb_user_cnt = atomic_read(&pblk->rl.rb_user_cnt);
|
|
|
|
|
rb_gc_max = pblk->rl.rb_gc_max;
|
|
|
|
|
rb_gc_cnt = atomic_read(&pblk->rl.rb_gc_cnt);
|
|
|
|
|
rb_budget = pblk->rl.rb_budget;
|
|
|
|
|
rb_state = pblk->rl.rb_state;
|
|
|
|
|
|
lightnvm: pblk: redesign GC algorithm
At the moment, in order to get enough read parallelism, we have recycled
several lines at the same time. This approach has proven not to work
well when reaching capacity, since we end up mixing valid data from all
lines, thus not maintaining a sustainable free/recycled line ratio.
The new design, relies on a two level workqueue mechanism. In the first
level, we read the metadata for a number of lines based on the GC list
they reside on (this is governed by the number of valid sectors in each
line). In the second level, we recycle a single line at a time. Here, we
issue reads in parallel, while a single GC write thread places data in
the write buffer. This design allows to (i) only move data from one line
at a time, thus maintaining a sane free/recycled ration and (ii)
maintain the GC writer busy with recycled data.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-26 17:57:27 +08:00
|
|
|
total_blocks = pblk->rl.total_blocks;
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
return snprintf(page, PAGE_SIZE,
|
2018-01-05 21:16:13 +08:00
|
|
|
"u:%u/%u,gc:%u/%u(%u)(stop:<%u,full:>%u,free:%d/%d/%d)-%d\n",
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
rb_user_cnt,
|
|
|
|
|
rb_user_max,
|
|
|
|
|
rb_gc_cnt,
|
|
|
|
|
rb_gc_max,
|
|
|
|
|
rb_state,
|
|
|
|
|
rb_budget,
|
|
|
|
|
pblk->rl.high,
|
|
|
|
|
free_blocks,
|
2018-01-05 21:16:13 +08:00
|
|
|
free_user_blocks,
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
total_blocks,
|
|
|
|
|
READ_ONCE(pblk->rl.rb_user_active));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_gc_state_show(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
int gc_enabled, gc_active;
|
|
|
|
|
|
|
|
|
|
pblk_gc_sysfs_state_show(pblk, &gc_enabled, &gc_active);
|
|
|
|
|
return snprintf(page, PAGE_SIZE, "gc_enabled=%d, gc_active=%d\n",
|
|
|
|
|
gc_enabled, gc_active);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_stats(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
ssize_t sz;
|
|
|
|
|
|
|
|
|
|
sz = snprintf(page, PAGE_SIZE,
|
|
|
|
|
"read_failed=%lu, read_high_ecc=%lu, read_empty=%lu, read_failed_gc=%lu, write_failed=%lu, erase_failed=%lu\n",
|
|
|
|
|
atomic_long_read(&pblk->read_failed),
|
|
|
|
|
atomic_long_read(&pblk->read_high_ecc),
|
|
|
|
|
atomic_long_read(&pblk->read_empty),
|
|
|
|
|
atomic_long_read(&pblk->read_failed_gc),
|
|
|
|
|
atomic_long_read(&pblk->write_failed),
|
|
|
|
|
atomic_long_read(&pblk->erase_failed));
|
|
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_write_buffer(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
return pblk_rb_sysfs(&pblk->rwb, page);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
struct nvm_tgt_dev *dev = pblk->dev;
|
|
|
|
|
struct nvm_geo *geo = &dev->geo;
|
|
|
|
|
ssize_t sz = 0;
|
|
|
|
|
|
2018-03-30 06:05:21 +08:00
|
|
|
if (geo->version == NVM_OCSSD_SPEC_12) {
|
|
|
|
|
struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf;
|
|
|
|
|
struct nvm_addrf_12 *gppaf = (struct nvm_addrf_12 *)&geo->addrf;
|
2018-03-30 06:05:10 +08:00
|
|
|
|
2018-03-30 06:05:21 +08:00
|
|
|
sz = snprintf(page, PAGE_SIZE,
|
|
|
|
|
"g:(b:%d)blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
|
2018-03-30 06:05:19 +08:00
|
|
|
pblk->addrf_len,
|
2018-03-30 06:05:10 +08:00
|
|
|
ppaf->blk_offset, ppaf->blk_len,
|
|
|
|
|
ppaf->pg_offset, ppaf->pg_len,
|
|
|
|
|
ppaf->lun_offset, ppaf->lun_len,
|
|
|
|
|
ppaf->ch_offset, ppaf->ch_len,
|
|
|
|
|
ppaf->pln_offset, ppaf->pln_len,
|
2018-03-30 06:05:14 +08:00
|
|
|
ppaf->sec_offset, ppaf->sec_len);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
2018-03-30 06:05:21 +08:00
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
|
|
|
|
"d:blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
|
|
|
|
|
gppaf->blk_offset, gppaf->blk_len,
|
|
|
|
|
gppaf->pg_offset, gppaf->pg_len,
|
|
|
|
|
gppaf->lun_offset, gppaf->lun_len,
|
|
|
|
|
gppaf->ch_offset, gppaf->ch_len,
|
|
|
|
|
gppaf->pln_offset, gppaf->pln_len,
|
|
|
|
|
gppaf->sec_offset, gppaf->sec_len);
|
|
|
|
|
} else {
|
|
|
|
|
struct nvm_addrf *ppaf = &pblk->addrf;
|
|
|
|
|
struct nvm_addrf *gppaf = &geo->addrf;
|
|
|
|
|
|
|
|
|
|
sz = snprintf(page, PAGE_SIZE,
|
|
|
|
|
"pblk:(s:%d)ch:%d/%d,lun:%d/%d,chk:%d/%d/sec:%d/%d\n",
|
|
|
|
|
pblk->addrf_len,
|
|
|
|
|
ppaf->ch_offset, ppaf->ch_len,
|
|
|
|
|
ppaf->lun_offset, ppaf->lun_len,
|
|
|
|
|
ppaf->chk_offset, ppaf->chk_len,
|
|
|
|
|
ppaf->sec_offset, ppaf->sec_len);
|
|
|
|
|
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
|
|
|
|
"device:ch:%d/%d,lun:%d/%d,chk:%d/%d,sec:%d/%d\n",
|
|
|
|
|
gppaf->ch_offset, gppaf->ch_len,
|
|
|
|
|
gppaf->lun_offset, gppaf->lun_len,
|
|
|
|
|
gppaf->chk_offset, gppaf->chk_len,
|
|
|
|
|
gppaf->sec_offset, gppaf->sec_len);
|
|
|
|
|
}
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
struct nvm_tgt_dev *dev = pblk->dev;
|
|
|
|
|
struct nvm_geo *geo = &dev->geo;
|
|
|
|
|
struct pblk_line_meta *lm = &pblk->lm;
|
|
|
|
|
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
|
|
|
|
|
struct pblk_line *line;
|
|
|
|
|
ssize_t sz = 0;
|
|
|
|
|
int nr_free_lines;
|
|
|
|
|
int cur_data, cur_log;
|
2017-06-26 17:57:17 +08:00
|
|
|
int free_line_cnt = 0, closed_line_cnt = 0, emeta_line_cnt = 0;
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
int d_line_cnt = 0, l_line_cnt = 0;
|
|
|
|
|
int gc_full = 0, gc_high = 0, gc_mid = 0, gc_low = 0, gc_empty = 0;
|
2017-06-26 17:57:18 +08:00
|
|
|
int bad = 0, cor = 0;
|
2017-06-26 17:57:19 +08:00
|
|
|
int msecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0;
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
int map_weight = 0, meta_weight = 0;
|
|
|
|
|
|
|
|
|
|
spin_lock(&l_mg->free_lock);
|
|
|
|
|
cur_data = (l_mg->data_line) ? l_mg->data_line->id : -1;
|
|
|
|
|
cur_log = (l_mg->log_line) ? l_mg->log_line->id : -1;
|
|
|
|
|
nr_free_lines = l_mg->nr_free_lines;
|
|
|
|
|
|
|
|
|
|
list_for_each_entry(line, &l_mg->free_list, list)
|
|
|
|
|
free_line_cnt++;
|
|
|
|
|
spin_unlock(&l_mg->free_lock);
|
|
|
|
|
|
2017-06-26 17:57:17 +08:00
|
|
|
spin_lock(&l_mg->close_lock);
|
|
|
|
|
list_for_each_entry(line, &l_mg->emeta_list, list)
|
|
|
|
|
emeta_line_cnt++;
|
|
|
|
|
spin_unlock(&l_mg->close_lock);
|
|
|
|
|
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
spin_lock(&l_mg->gc_lock);
|
|
|
|
|
list_for_each_entry(line, &l_mg->gc_full_list, list) {
|
|
|
|
|
if (line->type == PBLK_LINETYPE_DATA)
|
|
|
|
|
d_line_cnt++;
|
|
|
|
|
else if (line->type == PBLK_LINETYPE_LOG)
|
|
|
|
|
l_line_cnt++;
|
|
|
|
|
closed_line_cnt++;
|
|
|
|
|
gc_full++;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
list_for_each_entry(line, &l_mg->gc_high_list, list) {
|
|
|
|
|
if (line->type == PBLK_LINETYPE_DATA)
|
|
|
|
|
d_line_cnt++;
|
|
|
|
|
else if (line->type == PBLK_LINETYPE_LOG)
|
|
|
|
|
l_line_cnt++;
|
|
|
|
|
closed_line_cnt++;
|
|
|
|
|
gc_high++;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
list_for_each_entry(line, &l_mg->gc_mid_list, list) {
|
|
|
|
|
if (line->type == PBLK_LINETYPE_DATA)
|
|
|
|
|
d_line_cnt++;
|
|
|
|
|
else if (line->type == PBLK_LINETYPE_LOG)
|
|
|
|
|
l_line_cnt++;
|
|
|
|
|
closed_line_cnt++;
|
|
|
|
|
gc_mid++;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
list_for_each_entry(line, &l_mg->gc_low_list, list) {
|
|
|
|
|
if (line->type == PBLK_LINETYPE_DATA)
|
|
|
|
|
d_line_cnt++;
|
|
|
|
|
else if (line->type == PBLK_LINETYPE_LOG)
|
|
|
|
|
l_line_cnt++;
|
|
|
|
|
closed_line_cnt++;
|
|
|
|
|
gc_low++;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
list_for_each_entry(line, &l_mg->gc_empty_list, list) {
|
|
|
|
|
if (line->type == PBLK_LINETYPE_DATA)
|
|
|
|
|
d_line_cnt++;
|
|
|
|
|
else if (line->type == PBLK_LINETYPE_LOG)
|
|
|
|
|
l_line_cnt++;
|
|
|
|
|
closed_line_cnt++;
|
|
|
|
|
gc_empty++;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
list_for_each_entry(line, &l_mg->bad_list, list)
|
|
|
|
|
bad++;
|
|
|
|
|
list_for_each_entry(line, &l_mg->corrupt_list, list)
|
|
|
|
|
cor++;
|
|
|
|
|
spin_unlock(&l_mg->gc_lock);
|
|
|
|
|
|
|
|
|
|
spin_lock(&l_mg->free_lock);
|
|
|
|
|
if (l_mg->data_line) {
|
|
|
|
|
cur_sec = l_mg->data_line->cur_sec;
|
|
|
|
|
msecs = l_mg->data_line->left_msecs;
|
2017-06-26 17:57:17 +08:00
|
|
|
vsc = le32_to_cpu(*l_mg->data_line->vsc);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
sec_in_line = l_mg->data_line->sec_in_line;
|
|
|
|
|
meta_weight = bitmap_weight(&l_mg->meta_bitmap,
|
|
|
|
|
PBLK_DATA_LINES);
|
|
|
|
|
map_weight = bitmap_weight(l_mg->data_line->map_bitmap,
|
|
|
|
|
lm->sec_per_line);
|
|
|
|
|
}
|
|
|
|
|
spin_unlock(&l_mg->free_lock);
|
|
|
|
|
|
|
|
|
|
if (nr_free_lines != free_line_cnt)
|
lightnvm: pblk: redesign GC algorithm
At the moment, in order to get enough read parallelism, we have recycled
several lines at the same time. This approach has proven not to work
well when reaching capacity, since we end up mixing valid data from all
lines, thus not maintaining a sustainable free/recycled line ratio.
The new design, relies on a two level workqueue mechanism. In the first
level, we read the metadata for a number of lines based on the GC list
they reside on (this is governed by the number of valid sectors in each
line). In the second level, we recycle a single line at a time. Here, we
issue reads in parallel, while a single GC write thread places data in
the write buffer. This design allows to (i) only move data from one line
at a time, thus maintaining a sane free/recycled ration and (ii)
maintain the GC writer busy with recycled data.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-26 17:57:27 +08:00
|
|
|
pr_err("pblk: corrupted free line list:%d/%d\n",
|
|
|
|
|
nr_free_lines, free_line_cnt);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
sz = snprintf(page, PAGE_SIZE - sz,
|
|
|
|
|
"line: nluns:%d, nblks:%d, nsecs:%d\n",
|
2018-01-05 21:16:03 +08:00
|
|
|
geo->all_luns, lm->blk_per_line, lm->sec_per_line);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
2017-06-26 17:57:29 +08:00
|
|
|
"lines:d:%d,l:%d-f:%d,m:%d/%d,c:%d,b:%d,co:%d(d:%d,l:%d)t:%d\n",
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
cur_data, cur_log,
|
2017-06-26 17:57:29 +08:00
|
|
|
nr_free_lines,
|
|
|
|
|
emeta_line_cnt, meta_weight,
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
closed_line_cnt,
|
2017-06-26 17:57:17 +08:00
|
|
|
bad, cor,
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
d_line_cnt, l_line_cnt,
|
|
|
|
|
l_mg->nr_lines);
|
|
|
|
|
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
|
|
|
|
"GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, queue:%d\n",
|
|
|
|
|
gc_full, gc_high, gc_mid, gc_low, gc_empty,
|
2017-10-13 20:46:41 +08:00
|
|
|
atomic_read(&pblk->gc.read_inflight_gc));
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
2017-06-26 17:57:19 +08:00
|
|
|
"data (%d) cur:%d, left:%d, vsc:%d, s:%d, map:%d/%d (%d)\n",
|
|
|
|
|
cur_data, cur_sec, msecs, vsc, sec_in_line,
|
2017-06-26 17:57:29 +08:00
|
|
|
map_weight, lm->sec_per_line,
|
|
|
|
|
atomic_read(&pblk->inflight_io));
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
struct nvm_tgt_dev *dev = pblk->dev;
|
|
|
|
|
struct nvm_geo *geo = &dev->geo;
|
|
|
|
|
struct pblk_line_meta *lm = &pblk->lm;
|
|
|
|
|
ssize_t sz = 0;
|
|
|
|
|
|
|
|
|
|
sz = snprintf(page, PAGE_SIZE - sz,
|
|
|
|
|
"smeta - len:%d, secs:%d\n",
|
|
|
|
|
lm->smeta_len, lm->smeta_sec);
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
|
|
|
|
"emeta - len:%d, sec:%d, bb_start:%d\n",
|
2017-06-26 17:57:17 +08:00
|
|
|
lm->emeta_len[0], lm->emeta_sec[0],
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
lm->emeta_bb);
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
|
|
|
|
"bitmap lengths: sec:%d, blk:%d, lun:%d\n",
|
|
|
|
|
lm->sec_bitmap_len,
|
|
|
|
|
lm->blk_bitmap_len,
|
|
|
|
|
lm->lun_bitmap_len);
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
|
|
|
|
"blk_line:%d, sec_line:%d, sec_blk:%d\n",
|
|
|
|
|
lm->blk_per_line,
|
|
|
|
|
lm->sec_per_line,
|
2018-03-30 06:05:10 +08:00
|
|
|
geo->clba);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
|
}
|
|
|
|
|
|
2017-06-26 17:57:14 +08:00
|
|
|
static ssize_t pblk_sysfs_get_sec_per_write(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
return snprintf(page, PAGE_SIZE, "%d\n", pblk->sec_per_write);
|
|
|
|
|
}
|
|
|
|
|
|
2018-03-30 06:04:52 +08:00
|
|
|
static ssize_t pblk_get_write_amp(u64 user, u64 gc, u64 pad,
|
|
|
|
|
char *page)
|
|
|
|
|
{
|
|
|
|
|
int sz;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
sz = snprintf(page, PAGE_SIZE,
|
|
|
|
|
"user:%lld gc:%lld pad:%lld WA:",
|
|
|
|
|
user, gc, pad);
|
|
|
|
|
|
|
|
|
|
if (!user) {
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz, "NaN\n");
|
|
|
|
|
} else {
|
|
|
|
|
u64 wa_int;
|
|
|
|
|
u32 wa_frac;
|
|
|
|
|
|
|
|
|
|
wa_int = (user + gc + pad) * 100000;
|
|
|
|
|
wa_int = div_u64(wa_int, user);
|
|
|
|
|
wa_int = div_u64_rem(wa_int, 100000, &wa_frac);
|
|
|
|
|
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz, "%llu.%05u\n",
|
|
|
|
|
wa_int, wa_frac);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_get_write_amp_mileage(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
return pblk_get_write_amp(atomic64_read(&pblk->user_wa),
|
|
|
|
|
atomic64_read(&pblk->gc_wa), atomic64_read(&pblk->pad_wa),
|
|
|
|
|
page);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_get_write_amp_trip(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
return pblk_get_write_amp(
|
|
|
|
|
atomic64_read(&pblk->user_wa) - pblk->user_rst_wa,
|
|
|
|
|
atomic64_read(&pblk->gc_wa) - pblk->gc_rst_wa,
|
|
|
|
|
atomic64_read(&pblk->pad_wa) - pblk->pad_rst_wa, page);
|
|
|
|
|
}
|
|
|
|
|
|
2018-03-30 06:04:55 +08:00
|
|
|
static long long bucket_percentage(unsigned long long bucket,
|
|
|
|
|
unsigned long long total)
|
|
|
|
|
{
|
|
|
|
|
int p = bucket * 100;
|
|
|
|
|
|
|
|
|
|
p = div_u64(p, total);
|
|
|
|
|
|
|
|
|
|
return p;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
int sz = 0;
|
|
|
|
|
unsigned long long total;
|
|
|
|
|
unsigned long long total_buckets = 0;
|
|
|
|
|
int buckets = pblk->min_write_pgs - 1;
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
total = atomic64_read(&pblk->nr_flush) - pblk->nr_flush_rst;
|
|
|
|
|
if (!total) {
|
|
|
|
|
for (i = 0; i < (buckets + 1); i++)
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz,
|
|
|
|
|
"%d:0 ", i);
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz, "\n");
|
|
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < buckets; i++)
|
|
|
|
|
total_buckets += atomic64_read(&pblk->pad_dist[i]);
|
|
|
|
|
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz, "0:%lld%% ",
|
|
|
|
|
bucket_percentage(total - total_buckets, total));
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < buckets; i++) {
|
|
|
|
|
unsigned long long p;
|
|
|
|
|
|
|
|
|
|
p = bucket_percentage(atomic64_read(&pblk->pad_dist[i]),
|
|
|
|
|
total);
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz, "%d:%lld%% ",
|
|
|
|
|
i + 1, p);
|
|
|
|
|
}
|
|
|
|
|
sz += snprintf(page + sz, PAGE_SIZE - sz, "\n");
|
|
|
|
|
|
|
|
|
|
return sz;
|
|
|
|
|
}
|
|
|
|
|
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
#ifdef CONFIG_NVM_DEBUG
|
|
|
|
|
static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
|
|
|
|
|
{
|
|
|
|
|
return snprintf(page, PAGE_SIZE,
|
2018-03-30 06:04:55 +08:00
|
|
|
"%lu\t%lu\t%ld\t%llu\t%ld\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\n",
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
atomic_long_read(&pblk->inflight_writes),
|
|
|
|
|
atomic_long_read(&pblk->inflight_reads),
|
|
|
|
|
atomic_long_read(&pblk->req_writes),
|
2018-03-30 06:04:55 +08:00
|
|
|
(u64)atomic64_read(&pblk->nr_flush),
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
atomic_long_read(&pblk->padded_writes),
|
|
|
|
|
atomic_long_read(&pblk->padded_wb),
|
|
|
|
|
atomic_long_read(&pblk->sub_writes),
|
|
|
|
|
atomic_long_read(&pblk->sync_writes),
|
|
|
|
|
atomic_long_read(&pblk->recov_writes),
|
|
|
|
|
atomic_long_read(&pblk->recov_gc_writes),
|
|
|
|
|
atomic_long_read(&pblk->recov_gc_reads),
|
2017-06-26 17:57:13 +08:00
|
|
|
atomic_long_read(&pblk->cache_reads),
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
atomic_long_read(&pblk->sync_reads));
|
|
|
|
|
}
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page,
|
|
|
|
|
size_t len)
|
|
|
|
|
{
|
|
|
|
|
size_t c_len;
|
2017-06-30 23:56:36 +08:00
|
|
|
int force;
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
c_len = strcspn(page, "\n");
|
|
|
|
|
if (c_len >= len)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
if (kstrtouint(page, 0, &force))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
2017-06-30 23:56:36 +08:00
|
|
|
pblk_gc_sysfs_force(pblk, force);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
|
|
|
|
|
return len;
|
|
|
|
|
}
|
|
|
|
|
|
2017-06-26 17:57:14 +08:00
|
|
|
static ssize_t pblk_sysfs_set_sec_per_write(struct pblk *pblk,
|
|
|
|
|
const char *page, size_t len)
|
|
|
|
|
{
|
|
|
|
|
size_t c_len;
|
|
|
|
|
int sec_per_write;
|
|
|
|
|
|
|
|
|
|
c_len = strcspn(page, "\n");
|
|
|
|
|
if (c_len >= len)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
if (kstrtouint(page, 0, &sec_per_write))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
if (sec_per_write < pblk->min_write_pgs
|
|
|
|
|
|| sec_per_write > pblk->max_write_pgs
|
|
|
|
|
|| sec_per_write % pblk->min_write_pgs != 0)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
pblk_set_sec_per_write(pblk, sec_per_write);
|
|
|
|
|
|
|
|
|
|
return len;
|
|
|
|
|
}
|
|
|
|
|
|
2018-03-30 06:04:52 +08:00
|
|
|
static ssize_t pblk_sysfs_set_write_amp_trip(struct pblk *pblk,
|
|
|
|
|
const char *page, size_t len)
|
|
|
|
|
{
|
|
|
|
|
size_t c_len;
|
|
|
|
|
int reset_value;
|
|
|
|
|
|
|
|
|
|
c_len = strcspn(page, "\n");
|
|
|
|
|
if (c_len >= len)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
if (kstrtouint(page, 0, &reset_value))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
if (reset_value != 0)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
pblk->user_rst_wa = atomic64_read(&pblk->user_wa);
|
|
|
|
|
pblk->pad_rst_wa = atomic64_read(&pblk->pad_wa);
|
|
|
|
|
pblk->gc_rst_wa = atomic64_read(&pblk->gc_wa);
|
|
|
|
|
|
|
|
|
|
return len;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
2018-03-30 06:04:55 +08:00
|
|
|
static ssize_t pblk_sysfs_set_padding_dist(struct pblk *pblk,
|
|
|
|
|
const char *page, size_t len)
|
|
|
|
|
{
|
|
|
|
|
size_t c_len;
|
|
|
|
|
int reset_value;
|
|
|
|
|
int buckets = pblk->min_write_pgs - 1;
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
c_len = strcspn(page, "\n");
|
|
|
|
|
if (c_len >= len)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
if (kstrtouint(page, 0, &reset_value))
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
if (reset_value != 0)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < buckets; i++)
|
|
|
|
|
atomic64_set(&pblk->pad_dist[i], 0);
|
|
|
|
|
|
|
|
|
|
pblk->nr_flush_rst = atomic64_read(&pblk->nr_flush);
|
|
|
|
|
|
|
|
|
|
return len;
|
|
|
|
|
}
|
|
|
|
|
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
static struct attribute sys_write_luns = {
|
|
|
|
|
.name = "write_luns",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_rate_limiter_attr = {
|
|
|
|
|
.name = "rate_limiter",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_gc_state = {
|
|
|
|
|
.name = "gc_state",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_errors_attr = {
|
|
|
|
|
.name = "errors",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_rb_attr = {
|
|
|
|
|
.name = "write_buffer",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_stats_ppaf_attr = {
|
|
|
|
|
.name = "ppa_format",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_lines_attr = {
|
|
|
|
|
.name = "lines",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_lines_info_attr = {
|
|
|
|
|
.name = "lines_info",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_gc_force = {
|
|
|
|
|
.name = "gc_force",
|
|
|
|
|
.mode = 0200,
|
|
|
|
|
};
|
|
|
|
|
|
2017-06-26 17:57:14 +08:00
|
|
|
static struct attribute sys_max_sec_per_write = {
|
|
|
|
|
.name = "max_sec_per_write",
|
|
|
|
|
.mode = 0644,
|
|
|
|
|
};
|
|
|
|
|
|
2018-03-30 06:04:52 +08:00
|
|
|
static struct attribute sys_write_amp_mileage = {
|
|
|
|
|
.name = "write_amp_mileage",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct attribute sys_write_amp_trip = {
|
|
|
|
|
.name = "write_amp_trip",
|
|
|
|
|
.mode = 0644,
|
|
|
|
|
};
|
|
|
|
|
|
2018-03-30 06:04:55 +08:00
|
|
|
static struct attribute sys_padding_dist = {
|
|
|
|
|
.name = "padding_dist",
|
|
|
|
|
.mode = 0644,
|
|
|
|
|
};
|
|
|
|
|
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
#ifdef CONFIG_NVM_DEBUG
|
|
|
|
|
static struct attribute sys_stats_debug_attr = {
|
|
|
|
|
.name = "stats",
|
|
|
|
|
.mode = 0444,
|
|
|
|
|
};
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
static struct attribute *pblk_attrs[] = {
|
|
|
|
|
&sys_write_luns,
|
|
|
|
|
&sys_rate_limiter_attr,
|
|
|
|
|
&sys_errors_attr,
|
|
|
|
|
&sys_gc_state,
|
|
|
|
|
&sys_gc_force,
|
2017-06-26 17:57:14 +08:00
|
|
|
&sys_max_sec_per_write,
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
&sys_rb_attr,
|
|
|
|
|
&sys_stats_ppaf_attr,
|
|
|
|
|
&sys_lines_attr,
|
|
|
|
|
&sys_lines_info_attr,
|
2018-03-30 06:04:52 +08:00
|
|
|
&sys_write_amp_mileage,
|
|
|
|
|
&sys_write_amp_trip,
|
2018-03-30 06:04:55 +08:00
|
|
|
&sys_padding_dist,
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
#ifdef CONFIG_NVM_DEBUG
|
|
|
|
|
&sys_stats_debug_attr,
|
|
|
|
|
#endif
|
|
|
|
|
NULL,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
|
|
|
|
|
char *buf)
|
|
|
|
|
{
|
|
|
|
|
struct pblk *pblk = container_of(kobj, struct pblk, kobj);
|
|
|
|
|
|
|
|
|
|
if (strcmp(attr->name, "rate_limiter") == 0)
|
|
|
|
|
return pblk_sysfs_rate_limiter(pblk, buf);
|
|
|
|
|
else if (strcmp(attr->name, "write_luns") == 0)
|
|
|
|
|
return pblk_sysfs_luns_show(pblk, buf);
|
|
|
|
|
else if (strcmp(attr->name, "gc_state") == 0)
|
|
|
|
|
return pblk_sysfs_gc_state_show(pblk, buf);
|
|
|
|
|
else if (strcmp(attr->name, "errors") == 0)
|
|
|
|
|
return pblk_sysfs_stats(pblk, buf);
|
|
|
|
|
else if (strcmp(attr->name, "write_buffer") == 0)
|
|
|
|
|
return pblk_sysfs_write_buffer(pblk, buf);
|
|
|
|
|
else if (strcmp(attr->name, "ppa_format") == 0)
|
|
|
|
|
return pblk_sysfs_ppaf(pblk, buf);
|
|
|
|
|
else if (strcmp(attr->name, "lines") == 0)
|
|
|
|
|
return pblk_sysfs_lines(pblk, buf);
|
|
|
|
|
else if (strcmp(attr->name, "lines_info") == 0)
|
|
|
|
|
return pblk_sysfs_lines_info(pblk, buf);
|
2017-06-26 17:57:14 +08:00
|
|
|
else if (strcmp(attr->name, "max_sec_per_write") == 0)
|
|
|
|
|
return pblk_sysfs_get_sec_per_write(pblk, buf);
|
2018-03-30 06:04:52 +08:00
|
|
|
else if (strcmp(attr->name, "write_amp_mileage") == 0)
|
|
|
|
|
return pblk_sysfs_get_write_amp_mileage(pblk, buf);
|
|
|
|
|
else if (strcmp(attr->name, "write_amp_trip") == 0)
|
|
|
|
|
return pblk_sysfs_get_write_amp_trip(pblk, buf);
|
2018-03-30 06:04:55 +08:00
|
|
|
else if (strcmp(attr->name, "padding_dist") == 0)
|
|
|
|
|
return pblk_sysfs_get_padding_dist(pblk, buf);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
#ifdef CONFIG_NVM_DEBUG
|
|
|
|
|
else if (strcmp(attr->name, "stats") == 0)
|
|
|
|
|
return pblk_sysfs_stats_debug(pblk, buf);
|
|
|
|
|
#endif
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static ssize_t pblk_sysfs_store(struct kobject *kobj, struct attribute *attr,
|
|
|
|
|
const char *buf, size_t len)
|
|
|
|
|
{
|
|
|
|
|
struct pblk *pblk = container_of(kobj, struct pblk, kobj);
|
|
|
|
|
|
lightnvm: pblk: redesign GC algorithm
At the moment, in order to get enough read parallelism, we have recycled
several lines at the same time. This approach has proven not to work
well when reaching capacity, since we end up mixing valid data from all
lines, thus not maintaining a sustainable free/recycled line ratio.
The new design, relies on a two level workqueue mechanism. In the first
level, we read the metadata for a number of lines based on the GC list
they reside on (this is governed by the number of valid sectors in each
line). In the second level, we recycle a single line at a time. Here, we
issue reads in parallel, while a single GC write thread places data in
the write buffer. This design allows to (i) only move data from one line
at a time, thus maintaining a sane free/recycled ration and (ii)
maintain the GC writer busy with recycled data.
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-26 17:57:27 +08:00
|
|
|
if (strcmp(attr->name, "gc_force") == 0)
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
return pblk_sysfs_gc_force(pblk, buf, len);
|
2017-06-26 17:57:14 +08:00
|
|
|
else if (strcmp(attr->name, "max_sec_per_write") == 0)
|
|
|
|
|
return pblk_sysfs_set_sec_per_write(pblk, buf, len);
|
2018-03-30 06:04:52 +08:00
|
|
|
else if (strcmp(attr->name, "write_amp_trip") == 0)
|
|
|
|
|
return pblk_sysfs_set_write_amp_trip(pblk, buf, len);
|
2018-03-30 06:04:55 +08:00
|
|
|
else if (strcmp(attr->name, "padding_dist") == 0)
|
|
|
|
|
return pblk_sysfs_set_padding_dist(pblk, buf, len);
|
lightnvm: physical block device (pblk) target
This patch introduces pblk, a host-side translation layer for
Open-Channel SSDs to expose them like block devices. The translation
layer allows data placement decisions, and I/O scheduling to be
managed by the host, enabling users to optimize the SSD for their
specific workloads.
An open-channel SSD has a set of LUNs (parallel units) and a
collection of blocks. Each block can be read in any order, but
writes must be sequential. Writes may also fail, and if a block
requires it, must also be reset before new writes can be
applied.
To manage the constraints, pblk maintains a logical to
physical address (L2P) table, write cache, garbage
collection logic, recovery scheme, and logic to rate-limit
user I/Os versus garbage collection I/Os.
The L2P table is fully-associative and manages sectors at a
4KB granularity. Pblk stores the L2P table in two places, in
the out-of-band area of the media and on the last page of a
line. In the cause of a power failure, pblk will perform a
scan to recover the L2P table.
The user data is organized into lines. A line is data
striped across blocks and LUNs. The lines enable the host to
reduce the amount of metadata to maintain besides the user
data and makes it easier to implement RAID or erasure coding
in the future.
pblk implements multi-tenant support and can be instantiated
multiple times on the same drive. Each instance owns a
portion of the SSD - both regarding I/O bandwidth and
capacity - providing I/O isolation for each case.
Finally, pblk also exposes a sysfs interface that allows
user-space to peek into the internals of pblk. The interface
is available at /dev/block/*/pblk/ where * is the block
device name exposed.
This work also contains contributions from:
Matias Bjørling <matias@cnexlabs.com>
Simon A. F. Lund <slund@cnexlabs.com>
Young Tack Jin <youngtack.jin@gmail.com>
Huaicheng Li <huaicheng@cs.uchicago.edu>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-16 02:55:50 +08:00
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static const struct sysfs_ops pblk_sysfs_ops = {
|
|
|
|
|
.show = pblk_sysfs_show,
|
|
|
|
|
.store = pblk_sysfs_store,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static struct kobj_type pblk_ktype = {
|
|
|
|
|
.sysfs_ops = &pblk_sysfs_ops,
|
|
|
|
|
.default_attrs = pblk_attrs,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
int pblk_sysfs_init(struct gendisk *tdisk)
|
|
|
|
|
{
|
|
|
|
|
struct pblk *pblk = tdisk->private_data;
|
|
|
|
|
struct device *parent_dev = disk_to_dev(pblk->disk);
|
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
|
|
ret = kobject_init_and_add(&pblk->kobj, &pblk_ktype,
|
|
|
|
|
kobject_get(&parent_dev->kobj),
|
|
|
|
|
"%s", "pblk");
|
|
|
|
|
if (ret) {
|
|
|
|
|
pr_err("pblk: could not register %s/pblk\n",
|
|
|
|
|
tdisk->disk_name);
|
|
|
|
|
return ret;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
kobject_uevent(&pblk->kobj, KOBJ_ADD);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void pblk_sysfs_exit(struct gendisk *tdisk)
|
|
|
|
|
{
|
|
|
|
|
struct pblk *pblk = tdisk->private_data;
|
|
|
|
|
|
|
|
|
|
kobject_uevent(&pblk->kobj, KOBJ_REMOVE);
|
|
|
|
|
kobject_del(&pblk->kobj);
|
|
|
|
|
kobject_put(&pblk->kobj);
|
|
|
|
|
}
|