Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 76758390 authored by Hans Holmberg's avatar Hans Holmberg Committed by Jens Axboe
Browse files

lightnvm: pblk: export write amplification counters to sysfs 



In a SSD, write amplification, WA, is defined as the average
number of page writes per user page write. Write amplification
negatively affects write performance and decreases the lifetime
of the disk, so it's a useful metric to add to sysfs.

In plkb's case, the number of writes per user sector is the sum of:

    (1) number of user writes
    (2) number of sectors written by the garbage collector
    (3) number of sectors padded (i.e. due to syncs)

This patch adds persistent counters for 1-3 and two sysfs attributes
to export these along with WA calculated with five decimals:

    write_amp_mileage: the accumulated write amplification stats
                      for the lifetime of the pblk instance

    write_amp_trip: resetable stats to facilitate delta measurements,
                    values reset at creation and if 0 is written
                    to the attribute.

64-bit counters are used as a 32 bit counter would wrap around
already after about 17 TB worth of user data. It will take a
long long time before the 64 bit sector counters wrap around.

The counters are stored after the bad block bitmap in the first
emeta sector of each written line. There is plenty of space in the
first emeta sector, so we don't need to bump the major version of
the line data format.

Signed-off-by: default avatarHans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: default avatarJavier González <javier@cnexlabs.com>
Signed-off-by: default avatarMatias Bjørling <mb@lightnvm.io>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent d0ab0b1a

drivers/lightnvm/pblk-cache.c

+4 −0
Original line number Diff line number Diff line
@@ -63,6 +63,8 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags) 
		bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);

	}



	atomic64_add(nr_entries, &pblk->user_wa);



#ifdef CONFIG_NVM_DEBUG

	atomic_long_add(nr_entries, &pblk->inflight_writes);

	atomic_long_add(nr_entries, &pblk->req_writes);
@@ -117,6 +119,8 @@ int pblk_write_gc_to_cache(struct pblk *pblk, struct pblk_gc_rq *gc_rq) 
	WARN_ONCE(gc_rq->secs_to_gc != valid_entries,

					"pblk: inconsistent GC write\n");



	atomic64_add(valid_entries, &pblk->gc_wa);



#ifdef CONFIG_NVM_DEBUG

	atomic_long_add(valid_entries, &pblk->inflight_writes);

	atomic_long_add(valid_entries, &pblk->recov_gc_writes);

drivers/lightnvm/pblk-core.c

+6 −0
Original line number Diff line number Diff line
@@ -1630,11 +1630,16 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line) 
	struct pblk_line_meta *lm = &pblk->lm;

	struct pblk_emeta *emeta = line->emeta;

	struct line_emeta *emeta_buf = emeta->buf;

	struct wa_counters *wa = emeta_to_wa(lm, emeta_buf);



	/* No need for exact vsc value; avoid a big line lock and take aprox. */

	memcpy(emeta_to_vsc(pblk, emeta_buf), l_mg->vsc_list, lm->vsc_list_len);

	memcpy(emeta_to_bb(emeta_buf), line->blk_bitmap, lm->blk_bitmap_len);



	wa->user = cpu_to_le64(atomic64_read(&pblk->user_wa));

	wa->pad = cpu_to_le64(atomic64_read(&pblk->pad_wa));

	wa->gc = cpu_to_le64(atomic64_read(&pblk->gc_wa));



	emeta_buf->nr_valid_lbas = cpu_to_le64(line->nr_valid_lbas);

	emeta_buf->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, emeta_buf));
@@ -1837,6 +1842,7 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba, 
#endif

	/* Invalidate and discard padded entries */

	if (lba == ADDR_EMPTY) {

		atomic64_inc(&pblk->pad_wa);

#ifdef CONFIG_NVM_DEBUG

		atomic_long_inc(&pblk->padded_wb);

#endif

drivers/lightnvm/pblk-init.c

+9 −2
Original line number Diff line number Diff line
@@ -559,8 +559,8 @@ static unsigned int calc_emeta_len(struct pblk *pblk) 


	/* Round to sector size so that lba_list starts on its own sector */

	lm->emeta_sec[1] = DIV_ROUND_UP(

			sizeof(struct line_emeta) + lm->blk_bitmap_len,

			geo->sec_size);

			sizeof(struct line_emeta) + lm->blk_bitmap_len +

			sizeof(struct wa_counters), geo->sec_size);

	lm->emeta_len[1] = lm->emeta_sec[1] * geo->sec_size;



	/* Round to sector size so that vsc_list starts on its own sector */
@@ -991,6 +991,13 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk, 
	if (flags & NVM_TARGET_FACTORY)

		pblk_setup_uuid(pblk);



	atomic64_set(&pblk->user_wa, 0);

	atomic64_set(&pblk->pad_wa, 0);

	atomic64_set(&pblk->gc_wa, 0);

	pblk->user_rst_wa = 0;

	pblk->pad_rst_wa = 0;

	pblk->gc_rst_wa = 0;



#ifdef CONFIG_NVM_DEBUG

	atomic_long_set(&pblk->inflight_writes, 0);

	atomic_long_set(&pblk->padded_writes, 0);

drivers/lightnvm/pblk-map.c

+2 −0
Original line number Diff line number Diff line
@@ -65,6 +65,8 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry, 
			lba_list[paddr] = cpu_to_le64(w_ctx->lba);

			if (lba_list[paddr] != addr_empty)

				line->nr_valid_lbas++;

			else

				atomic64_inc(&pblk->pad_wa);

		} else {

			lba_list[paddr] = meta_list[i].lba = addr_empty;

			__pblk_map_invalidate(pblk, line, paddr);

drivers/lightnvm/pblk-rb.c

+3 −0
Original line number Diff line number Diff line
@@ -622,6 +622,9 @@ unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd, 
		}

	}



	atomic64_add(pad, &((struct pblk *)

			(container_of(rb, struct pblk, rwb)))->pad_wa);



#ifdef CONFIG_NVM_DEBUG

	atomic_long_add(pad, &((struct pblk *)

			(container_of(rb, struct pblk, rwb)))->padded_writes);