raid5: add an option to avoid copy data from bio to stripe cache

The stripe cache has two goals:
1. cache data, so next time if data can be found in stripe cache, disk access
can be avoided.
2. stable data. data is copied from bio to stripe cache and calculated parity.
data written to disk is from stripe cache, so if upper layer changes bio data,
data written to disk isn't impacted.

In my environment, I can guarantee 2 will not happen. And BDI_CAP_STABLE_WRITES
can guarantee 2 too. For 1, it's not common too. block plug mechanism will
dispatch a bunch of sequentail small requests together. And since I'm using
SSD, I'm using small chunk size. It's rare case stripe cache is really useful.

So I'd like to avoid the copy from bio to stripe cache and it's very helpful
for performance. In my 1M randwrite tests, avoid the copy can increase the
performance more than 30%.

Of course, this shouldn't be enabled by default. It's reported enabling
BDI_CAP_STABLE_WRITES can harm some workloads before, so I added an option to
control it.

Neilb:
  changed BUG_ON to WARN_ON
  Removed some assignments from raid5_build_block which are now not needed.

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 348a857ab0fff23bba5d5b79611dd190ac031a77..d69fd9888c2c52a7263a21f6b797007330465960 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -487,6 +487,7 @@ static void shrink_buffers(struct stripe_head *sh)
        int num = sh->raid_conf->pool_size;
 
        for (i = 0; i < num ; i++) {
+               WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
                p = sh->dev[i].page;
                if (!p)
                        continue;
@@ -507,6 +508,7 @@ static int grow_buffers(struct stripe_head *sh)
                        return 1;
                }
                sh->dev[i].page = page;
+               sh->dev[i].orig_page = page;
        }
        return 0;
 }
@@ -863,6 +865,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
                        if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
                                bi->bi_rw |= REQ_NOMERGE;
 
+                       if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
+                               WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+                       sh->dev[i].vec.bv_page = sh->dev[i].page;
                        bi->bi_vcnt = 1;
                        bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
                        bi->bi_io_vec[0].bv_offset = 0;
@@ -907,6 +912,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
                        else
                                rbi->bi_iter.bi_sector = (sh->sector
                                                  + rrdev->data_offset);
+                       if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
+                               WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+                       sh->dev[i].rvec.bv_page = sh->dev[i].page;
                        rbi->bi_vcnt = 1;
                        rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
                        rbi->bi_io_vec[0].bv_offset = 0;
@@ -935,8 +943,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 }
 
 static struct dma_async_tx_descriptor *
-async_copy_data(int frombio, struct bio *bio, struct page *page,
-       sector_t sector, struct dma_async_tx_descriptor *tx)
+async_copy_data(int frombio, struct bio *bio, struct page **page,
+       sector_t sector, struct dma_async_tx_descriptor *tx,
+       struct stripe_head *sh)
 {
        struct bio_vec bvl;
        struct bvec_iter iter;
@@ -973,11 +982,16 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
                if (clen > 0) {
                        b_offset += bvl.bv_offset;
                        bio_page = bvl.bv_page;
-                       if (frombio)
-                               tx = async_memcpy(page, bio_page, page_offset,
+                       if (frombio) {
+                               if (sh->raid_conf->skip_copy &&
+                                   b_offset == 0 && page_offset == 0 &&
+                                   clen == STRIPE_SIZE)
+                                       *page = bio_page;
+                               else
+                                       tx = async_memcpy(*page, bio_page, page_offset,
                                                  b_offset, clen, &submit);
-                       else
-                               tx = async_memcpy(bio_page, page, b_offset,
+                       } else
+                               tx = async_memcpy(bio_page, *page, b_offset,
                                                  page_offset, clen, &submit);
                }
                /* chain the operations */
@@ -1053,8 +1067,8 @@ static void ops_run_biofill(struct stripe_head *sh)
                        spin_unlock_irq(&sh->stripe_lock);
                        while (rbi && rbi->bi_iter.bi_sector <
                                dev->sector + STRIPE_SECTORS) {
-                               tx = async_copy_data(0, rbi, dev->page,
-                                       dev->sector, tx);
+                               tx = async_copy_data(0, rbi, &dev->page,
+                                       dev->sector, tx, sh);
                                rbi = r5_next_bio(rbi, dev->sector);
                        }
                }
@@ -1392,6 +1406,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
                        BUG_ON(dev->written);
                        wbi = dev->written = chosen;
                        spin_unlock_irq(&sh->stripe_lock);
+                       WARN_ON(dev->page != dev->orig_page);
 
                        while (wbi && wbi->bi_iter.bi_sector <
                                dev->sector + STRIPE_SECTORS) {
@@ -1401,9 +1416,15 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
                                        set_bit(R5_SyncIO, &dev->flags);
                                if (wbi->bi_rw & REQ_DISCARD)
                                        set_bit(R5_Discard, &dev->flags);
-                               else
-                                       tx = async_copy_data(1, wbi, dev->page,
-                                               dev->sector, tx);
+                               else {
+                                       tx = async_copy_data(1, wbi, &dev->page,
+                                               dev->sector, tx, sh);
+                                       if (dev->page != dev->orig_page) {
+                                               set_bit(R5_SkipCopy, &dev->flags);
+                                               clear_bit(R5_UPTODATE, &dev->flags);
+                                               clear_bit(R5_OVERWRITE, &dev->flags);
+                                       }
+                               }
                                wbi = r5_next_bio(wbi, dev->sector);
                        }
                }
@@ -1434,7 +1455,7 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
                struct r5dev *dev = &sh->dev[i];
 
                if (dev->written || i == pd_idx || i == qd_idx) {
-                       if (!discard)
+                       if (!discard && !test_bit(R5_SkipCopy, &dev->flags))
                                set_bit(R5_UPTODATE, &dev->flags);
                        if (fua)
                                set_bit(R5_WantFUA, &dev->flags);
@@ -1847,8 +1868,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
                osh = get_free_stripe(conf, hash);
                unlock_device_hash_lock(conf, hash);
                atomic_set(&nsh->count, 1);
-               for(i=0; i<conf->pool_size; i++)
+               for(i=0; i<conf->pool_size; i++) {
                        nsh->dev[i].page = osh->dev[i].page;
+                       nsh->dev[i].orig_page = osh->dev[i].page;
+               }
                for( ; i<newsize; i++)
                        nsh->dev[i].page = NULL;
                nsh->hash_lock_index = hash;
@@ -1904,6 +1927,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
                        if (nsh->dev[i].page == NULL) {
                                struct page *p = alloc_page(GFP_NOIO);
                                nsh->dev[i].page = p;
+                               nsh->dev[i].orig_page = p;
                                if (!p)
                                        err = -ENOMEM;
                        }
@@ -2141,24 +2165,20 @@ static void raid5_end_write_request(struct bio *bi, int error)
 }
 
 static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
-       
+
 static void raid5_build_block(struct stripe_head *sh, int i, int previous)
 {
        struct r5dev *dev = &sh->dev[i];
 
        bio_init(&dev->req);
        dev->req.bi_io_vec = &dev->vec;
-       dev->req.bi_vcnt++;
-       dev->req.bi_max_vecs++;
+       dev->req.bi_max_vecs = 1;
        dev->req.bi_private = sh;
-       dev->vec.bv_page = dev->page;
 
        bio_init(&dev->rreq);
        dev->rreq.bi_io_vec = &dev->rvec;
-       dev->rreq.bi_vcnt++;
-       dev->rreq.bi_max_vecs++;
+       dev->rreq.bi_max_vecs = 1;
        dev->rreq.bi_private = sh;
-       dev->rvec.bv_page = dev->page;
 
        dev->flags = 0;
        dev->sector = compute_blocknr(sh, i, previous);
@@ -2758,6 +2778,11 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
                /* and fail all 'written' */
                bi = sh->dev[i].written;
                sh->dev[i].written = NULL;
+               if (test_and_clear_bit(R5_SkipCopy, &sh->dev[i].flags)) {
+                       WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+                       sh->dev[i].page = sh->dev[i].orig_page;
+               }
+
                if (bi) bitmap_end = 1;
                while (bi && bi->bi_iter.bi_sector <
                       sh->dev[i].sector + STRIPE_SECTORS) {
@@ -3002,12 +3027,17 @@ static void handle_stripe_clean_event(struct r5conf *conf,
                        dev = &sh->dev[i];
                        if (!test_bit(R5_LOCKED, &dev->flags) &&
                            (test_bit(R5_UPTODATE, &dev->flags) ||
-                            test_bit(R5_Discard, &dev->flags))) {
+                            test_bit(R5_Discard, &dev->flags) ||
+                            test_bit(R5_SkipCopy, &dev->flags))) {
                                /* We can return any write requests */
                                struct bio *wbi, *wbi2;
                                pr_debug("Return write for disc %d\n", i);
                                if (test_and_clear_bit(R5_Discard, &dev->flags))
                                        clear_bit(R5_UPTODATE, &dev->flags);
+                               if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) {
+                                       WARN_ON(test_bit(R5_UPTODATE, &dev->flags));
+                                       dev->page = dev->orig_page;
+                               }
                                wbi = dev->written;
                                dev->written = NULL;
                                while (wbi && wbi->bi_iter.bi_sector <
@@ -3026,6 +3056,8 @@ static void handle_stripe_clean_event(struct r5conf *conf,
                                                0);
                        } else if (test_bit(R5_Discard, &dev->flags))
                                discard_pending = 1;
+                       WARN_ON(test_bit(R5_SkipCopy, &dev->flags));
+                       WARN_ON(dev->page != dev->orig_page);
                }
        if (!discard_pending &&
            test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
@@ -5365,6 +5397,50 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
                                        raid5_show_preread_threshold,
                                        raid5_store_preread_threshold);
 
+static ssize_t
+raid5_show_skip_copy(struct mddev *mddev, char *page)
+{
+       struct r5conf *conf = mddev->private;
+       if (conf)
+               return sprintf(page, "%d\n", conf->skip_copy);
+       else
+               return 0;
+}
+
+static ssize_t
+raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
+{
+       struct r5conf *conf = mddev->private;
+       unsigned long new;
+       if (len >= PAGE_SIZE)
+               return -EINVAL;
+       if (!conf)
+               return -ENODEV;
+
+       if (kstrtoul(page, 10, &new))
+               return -EINVAL;
+       new = !!new;
+       if (new == conf->skip_copy)
+               return len;
+
+       mddev_suspend(mddev);
+       conf->skip_copy = new;
+       if (new)
+               mddev->queue->backing_dev_info.capabilities |=
+                                               BDI_CAP_STABLE_WRITES;
+       else
+               mddev->queue->backing_dev_info.capabilities &=
+                                               ~BDI_CAP_STABLE_WRITES;
+       mddev_resume(mddev);
+       return len;
+}
+
+static struct md_sysfs_entry
+raid5_skip_copy = __ATTR(skip_copy, S_IRUGO | S_IWUSR,
+                                       raid5_show_skip_copy,
+                                       raid5_store_skip_copy);
+
+
 static ssize_t
 stripe_cache_active_show(struct mddev *mddev, char *page)
 {
@@ -5450,6 +5526,7 @@ static struct attribute *raid5_attrs[] =  {
        &raid5_stripecache_active.attr,
        &raid5_preread_bypass_threshold.attr,
        &raid5_group_thread_cnt.attr,
+       &raid5_skip_copy.attr,
        NULL,
 };
 static struct attribute_group raid5_attrs_group = {

diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 01ad8ae8f57830a04de4e1e30b731f74660bda62..bc72cd4be5f8e16eaa49add51fd39aaf34d3d4e3 100644 (file)
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -232,7 +232,7 @@ struct stripe_head {
                 */
                struct bio      req, rreq;
                struct bio_vec  vec, rvec;
-               struct page     *page;
+               struct page     *page, *orig_page;
                struct bio      *toread, *read, *towrite, *written;
                sector_t        sector;                 /* sector of this page */
                unsigned long   flags;
@@ -299,6 +299,7 @@ enum r5dev_flags {
                         * data in, and now is a good time to write it out.
                         */
        R5_Discard,     /* Discard the stripe */
+       R5_SkipCopy,    /* Don't copy data from bio to stripe cache */
 };
 
 /*
@@ -436,6 +437,7 @@ struct r5conf {
        atomic_t                pending_full_writes; /* full write backlog */
        int                     bypass_count; /* bypassed prereads */
        int                     bypass_threshold; /* preread nice */
+       int                     skip_copy; /* Don't copy data from bio to stripe cache */
        struct list_head        *last_hold; /* detect hold_list promotions */
 
        atomic_t                reshape_stripes; /* stripes with pending writes for reshape */