mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-18 09:44:18 +08:00
a4bd217b43
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>
137 lines
4.2 KiB
C
137 lines
4.2 KiB
C
/*
|
|
* 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.
|
|
*
|
|
* pblk-map.c - pblk's lba-ppa mapping strategy
|
|
*
|
|
*/
|
|
|
|
#include "pblk.h"
|
|
|
|
static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
|
|
struct ppa_addr *ppa_list,
|
|
unsigned long *lun_bitmap,
|
|
struct pblk_sec_meta *meta_list,
|
|
unsigned int valid_secs)
|
|
{
|
|
struct pblk_line *line = pblk_line_get_data(pblk);
|
|
struct line_emeta *emeta = line->emeta;
|
|
struct pblk_w_ctx *w_ctx;
|
|
__le64 *lba_list = pblk_line_emeta_to_lbas(emeta);
|
|
u64 paddr;
|
|
int nr_secs = pblk->min_write_pgs;
|
|
int i;
|
|
|
|
paddr = pblk_alloc_page(pblk, line, nr_secs);
|
|
|
|
for (i = 0; i < nr_secs; i++, paddr++) {
|
|
/* ppa to be sent to the device */
|
|
ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
|
|
|
|
/* Write context for target bio completion on write buffer. Note
|
|
* that the write buffer is protected by the sync backpointer,
|
|
* and a single writer thread have access to each specific entry
|
|
* at a time. Thus, it is safe to modify the context for the
|
|
* entry we are setting up for submission without taking any
|
|
* lock or memory barrier.
|
|
*/
|
|
if (i < valid_secs) {
|
|
kref_get(&line->ref);
|
|
w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i);
|
|
w_ctx->ppa = ppa_list[i];
|
|
meta_list[i].lba = cpu_to_le64(w_ctx->lba);
|
|
lba_list[paddr] = cpu_to_le64(w_ctx->lba);
|
|
le64_add_cpu(&line->emeta->nr_valid_lbas, 1);
|
|
} else {
|
|
meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
|
|
lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
|
|
pblk_map_pad_invalidate(pblk, line, paddr);
|
|
}
|
|
}
|
|
|
|
if (pblk_line_is_full(line)) {
|
|
line = pblk_line_replace_data(pblk);
|
|
if (!line)
|
|
return;
|
|
}
|
|
|
|
pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap);
|
|
}
|
|
|
|
void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
|
|
unsigned long *lun_bitmap, unsigned int valid_secs,
|
|
unsigned int off)
|
|
{
|
|
struct pblk_sec_meta *meta_list = rqd->meta_list;
|
|
unsigned int map_secs;
|
|
int min = pblk->min_write_pgs;
|
|
int i;
|
|
|
|
for (i = off; i < rqd->nr_ppas; i += min) {
|
|
map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
|
|
pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
|
|
lun_bitmap, &meta_list[i], map_secs);
|
|
}
|
|
}
|
|
|
|
/* only if erase_ppa is set, acquire erase semaphore */
|
|
void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
|
|
unsigned int sentry, unsigned long *lun_bitmap,
|
|
unsigned int valid_secs, struct ppa_addr *erase_ppa)
|
|
{
|
|
struct nvm_tgt_dev *dev = pblk->dev;
|
|
struct nvm_geo *geo = &dev->geo;
|
|
struct pblk_line *e_line = pblk_line_get_data_next(pblk);
|
|
struct pblk_sec_meta *meta_list = rqd->meta_list;
|
|
unsigned int map_secs;
|
|
int min = pblk->min_write_pgs;
|
|
int i, erase_lun;
|
|
|
|
for (i = 0; i < rqd->nr_ppas; i += min) {
|
|
map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
|
|
pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
|
|
lun_bitmap, &meta_list[i], map_secs);
|
|
|
|
erase_lun = rqd->ppa_list[i].g.lun * geo->nr_chnls +
|
|
rqd->ppa_list[i].g.ch;
|
|
|
|
if (!test_bit(erase_lun, e_line->erase_bitmap)) {
|
|
if (down_trylock(&pblk->erase_sem))
|
|
continue;
|
|
|
|
set_bit(erase_lun, e_line->erase_bitmap);
|
|
e_line->left_eblks--;
|
|
*erase_ppa = rqd->ppa_list[i];
|
|
erase_ppa->g.blk = e_line->id;
|
|
|
|
/* Avoid evaluating e_line->left_eblks */
|
|
return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
|
|
valid_secs, i + min);
|
|
}
|
|
}
|
|
|
|
/* Erase blocks that are bad in this line but might not be in next */
|
|
if (unlikely(ppa_empty(*erase_ppa))) {
|
|
struct pblk_line_meta *lm = &pblk->lm;
|
|
|
|
i = find_first_zero_bit(e_line->erase_bitmap, lm->blk_per_line);
|
|
if (i == lm->blk_per_line)
|
|
return;
|
|
|
|
set_bit(i, e_line->erase_bitmap);
|
|
e_line->left_eblks--;
|
|
*erase_ppa = pblk->luns[i].bppa; /* set ch and lun */
|
|
erase_ppa->g.blk = e_line->id;
|
|
}
|
|
}
|