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: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 6 insertions, 0 deletions

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 155e42a26293..22e61cd4f801 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -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