lightnvm: pblk: add padding distribution sysfs attribute

When pblk receives a sync, all data up to that point in the write buffer
must be comitted to persistent storage, and as flash memory comes with a
minimal write size there is a significant cost involved both in terms
of time for completing the sync and in terms of write amplification
padded sectors for filling up to the minimal write size.

In order to get a better understanding of the costs involved for syncs,
Add a sysfs attribute to pblk: padded_dist, showing a normalized
distribution of sectors padded. In order to facilitate measurements of
specific workloads during the lifetime of the pblk instance, the
distribution can be reset by writing 0 to the attribute.

Do this by introducing counters for each possible padding:
{0..(minimal write size - 1)} and calculate the normalized distribution
when showing the attribute.

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

1 files changed, 14 insertions, 2 deletions

diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 0ffc17ccf1cc..8416910ee8bf 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -921,6 +921,7 @@ static void pblk_free(struct pblk *pblk)
 {
         pblk_luns_free(pblk);
         pblk_lines_free(pblk);
+        kfree(pblk->pad_dist);
         pblk_line_meta_free(pblk);
         pblk_core_free(pblk);
         pblk_l2p_free(pblk);
@@ -998,11 +999,13 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
         pblk->pad_rst_wa = 0;
         pblk->gc_rst_wa = 0;
 
+        atomic64_set(&pblk->nr_flush, 0);
+        pblk->nr_flush_rst = 0;
+
 #ifdef CONFIG_NVM_DEBUG
         atomic_long_set(&pblk->inflight_writes, 0);
         atomic_long_set(&pblk->padded_writes, 0);
         atomic_long_set(&pblk->padded_wb, 0);
-        atomic_long_set(&pblk->nr_flush, 0);
         atomic_long_set(&pblk->req_writes, 0);
         atomic_long_set(&pblk->sub_writes, 0);
         atomic_long_set(&pblk->sync_writes, 0);
@@ -1034,10 +1037,17 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
                 goto fail_free_luns;
         }
 
+        pblk->pad_dist = kzalloc((pblk->min_write_pgs - 1) * sizeof(atomic64_t),
+                                 GFP_KERNEL);
+        if (!pblk->pad_dist) {
+                ret = -ENOMEM;
+                goto fail_free_line_meta;
+        }
+
         ret = pblk_core_init(pblk);
         if (ret) {
                 pr_err("pblk: could not initialize core\n");
-                goto fail_free_line_meta;
+                goto fail_free_pad_dist;
         }
 
         ret = pblk_l2p_init(pblk);
@@ -1097,6 +1107,8 @@ fail_free_l2p:
         pblk_l2p_free(pblk);
 fail_free_core:
         pblk_core_free(pblk);
+fail_free_pad_dist:
+        kfree(pblk->pad_dist);
 fail_free_line_meta:
         pblk_line_meta_free(pblk);
 fail_free_luns: