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>
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index ed41cd7..ba3b88f 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -302,12 +302,12 @@
line->gc_group = PBLK_LINEGC_FULL;
move_list = &l_mg->gc_full_list;
}
- } else if (vsc < lm->mid_thrs) {
+ } else if (vsc < lm->high_thrs) {
if (line->gc_group != PBLK_LINEGC_HIGH) {
line->gc_group = PBLK_LINEGC_HIGH;
move_list = &l_mg->gc_high_list;
}
- } else if (vsc < lm->high_thrs) {
+ } else if (vsc < lm->mid_thrs) {
if (line->gc_group != PBLK_LINEGC_MID) {
line->gc_group = PBLK_LINEGC_MID;
move_list = &l_mg->gc_mid_list;
@@ -1199,6 +1199,7 @@
if (pblk_line_prepare(pblk, line)) {
pr_err("pblk: failed to prepare line %d\n", line->id);
list_add(&line->list, &l_mg->free_list);
+ l_mg->nr_free_lines++;
return NULL;
}
@@ -1465,6 +1466,8 @@
spin_unlock(&line->lock);
spin_unlock(&l_mg->gc_lock);
+
+ pblk_gc_should_kick(pblk);
}
void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line)