MD: raid5 avoid unnecessary zero page for trim

We want to avoid zero discarded dev page, because it's useless for discard.
But if we don't zero it, another read/write hit such page in the cache and will
get inconsistent data.

To avoid zero the page, we don't set R5_UPTODATE flag after construction is
done. In this way, discard write request is still issued and finished, but read
will not hit the page. If the stripe gets accessed soon, we need reread the
stripe, but since the chance is low, the reread isn't a big deal.

Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 74dcf19cfe68ccde20ce786338b64dbeecf7683c..758b77296404789df3d10d25e3b1d85d0ebc617f 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -547,7 +547,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
                                rw = WRITE_FUA;
                        else
                                rw = WRITE;
-                       if (test_and_clear_bit(R5_Discard, &sh->dev[i].flags))
+                       if (test_bit(R5_Discard, &sh->dev[i].flags))
                                rw |= REQ_DISCARD;
                } else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
                        rw = READ;
@@ -1172,11 +1172,9 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
                                        set_bit(R5_WantFUA, &dev->flags);
                                if (wbi->bi_rw & REQ_SYNC)
                                        set_bit(R5_SyncIO, &dev->flags);
-                               if (wbi->bi_rw & REQ_DISCARD) {
-                                       memset(page_address(dev->page), 0,
-                                               STRIPE_SECTORS << 9);
+                               if (wbi->bi_rw & REQ_DISCARD)
                                        set_bit(R5_Discard, &dev->flags);
-                               } else
+                               else
                                        tx = async_copy_data(1, wbi, dev->page,
                                                dev->sector, tx);
                                wbi = r5_next_bio(wbi, dev->sector);
@@ -1194,7 +1192,7 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
        int pd_idx = sh->pd_idx;
        int qd_idx = sh->qd_idx;
        int i;
-       bool fua = false, sync = false;
+       bool fua = false, sync = false, discard = false;
 
        pr_debug("%s: stripe %llu\n", __func__,
                (unsigned long long)sh->sector);
@@ -1202,13 +1200,15 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
        for (i = disks; i--; ) {
                fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
                sync |= test_bit(R5_SyncIO, &sh->dev[i].flags);
+               discard |= test_bit(R5_Discard, &sh->dev[i].flags);
        }
 
        for (i = disks; i--; ) {
                struct r5dev *dev = &sh->dev[i];
 
                if (dev->written || i == pd_idx || i == qd_idx) {
-                       set_bit(R5_UPTODATE, &dev->flags);
+                       if (!discard)
+                               set_bit(R5_UPTODATE, &dev->flags);
                        if (fua)
                                set_bit(R5_WantFUA, &dev->flags);
                        if (sync)
@@ -1252,8 +1252,6 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
        }
        if (i >= sh->disks) {
                atomic_inc(&sh->count);
-               memset(page_address(sh->dev[pd_idx].page), 0,
-                       STRIPE_SECTORS << 9);
                set_bit(R5_Discard, &sh->dev[pd_idx].flags);
                ops_complete_reconstruct(sh);
                return;
@@ -1314,10 +1312,6 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
        }
        if (i >= sh->disks) {
                atomic_inc(&sh->count);
-               memset(page_address(sh->dev[sh->pd_idx].page), 0,
-                       STRIPE_SECTORS << 9);
-               memset(page_address(sh->dev[sh->qd_idx].page), 0,
-                       STRIPE_SECTORS << 9);
                set_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
                set_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
                ops_complete_reconstruct(sh);
@@ -2775,7 +2769,8 @@ static void handle_stripe_clean_event(struct r5conf *conf,
                if (sh->dev[i].written) {
                        dev = &sh->dev[i];
                        if (!test_bit(R5_LOCKED, &dev->flags) &&
-                               test_bit(R5_UPTODATE, &dev->flags)) {
+                           (test_bit(R5_UPTODATE, &dev->flags) ||
+                            test_and_clear_bit(R5_Discard, &dev->flags))) {
                                /* We can return any write requests */
                                struct bio *wbi, *wbi2;
                                pr_debug("Return write for disc %d\n", i);
@@ -3493,10 +3488,12 @@ static void handle_stripe(struct stripe_head *sh)
        if (s.written &&
            (s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
                             && !test_bit(R5_LOCKED, &pdev->flags)
-                            && test_bit(R5_UPTODATE, &pdev->flags)))) &&
+                            && (test_bit(R5_UPTODATE, &pdev->flags) ||
+                                test_bit(R5_Discard, &pdev->flags))))) &&
            (s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
                             && !test_bit(R5_LOCKED, &qdev->flags)
-                            && test_bit(R5_UPTODATE, &qdev->flags)))))
+                            && (test_bit(R5_UPTODATE, &qdev->flags) ||
+                                test_bit(R5_Discard, &qdev->flags))))))
                handle_stripe_clean_event(conf, sh, disks, &s.return_bi);
 
        /* Now we might consider reading some blocks, either to check/generate
@@ -3523,9 +3520,11 @@ static void handle_stripe(struct stripe_head *sh)
                /* All the 'written' buffers and the parity block are ready to
                 * be written back to disk
                 */
-               BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
+               BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags) &&
+                      !test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags));
                BUG_ON(sh->qd_idx >= 0 &&
-                      !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags));
+                      !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags) &&
+                      !test_bit(R5_Discard, &sh->dev[sh->qd_idx].flags));
                for (i = disks; i--; ) {
                        struct r5dev *dev = &sh->dev[i];
                        if (test_bit(R5_LOCKED, &dev->flags) &&