bcache: finish incremental GC

In GC thread, we record the latest GC key in gc_done, which is expected
to be used for incremental GC, but in currently code, we didn't realize
it. When GC runs, front side IO would be blocked until the GC over, it
would be a long time if there is a lot of btree nodes.

This patch realizes incremental GC, the main ideal is that, when there
are front side I/Os, after GC some nodes (100), we stop GC, release locker
of the btree node, and go to process the front side I/Os for some times
(100 ms), then go back to GC again.

By this patch, when we doing GC, I/Os are not blocked all the time, and
there is no obvious I/Os zero jump problem any more.

Patch v2: Rename some variables and macros name as Coly suggested.

Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 21 insertions, 1 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 3226d38bf859..872ef4d67711 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -474,6 +474,7 @@ struct cache {
 
 struct gc_stat {
         size_t                  nodes;
+        size_t                  nodes_pre;
         size_t                  key_bytes;
 
         size_t                  nkeys;
@@ -604,6 +605,10 @@ struct cache_set {
          */
         atomic_t                rescale;
         /*
+         * used for GC, identify if any front side I/Os is inflight
+         */
+        atomic_t                search_inflight;
+        /*
          * When we invalidate buckets, we use both the priority and the amount
          * of good data to determine which buckets to reuse first - to weight
          * those together consistently we keep track of the smallest nonzero
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 547c9eedc2f4..b4407ba12667 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -90,6 +90,8 @@
 
 #define MAX_NEED_GC             64
 #define MAX_SAVE_PRIO           72
+#define MIN_GC_NODES            100
+#define GC_SLEEP_MS             100
 
 #define PTR_DIRTY_BIT           (((uint64_t) 1 << 36))
 
@@ -1585,6 +1587,13 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
                 memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1));
                 r->b = NULL;
 
+                if (atomic_read(&b->c->search_inflight) &&
+                    gc->nodes >= gc->nodes_pre + MIN_GC_NODES) {
+                        gc->nodes_pre =  gc->nodes;
+                        ret = -EAGAIN;
+                        break;
+                }
+
                 if (need_resched()) {
                         ret = -EAGAIN;
                         break;
@@ -1753,7 +1762,10 @@ static void bch_btree_gc(struct cache_set *c)
                 closure_sync(&writes);
                 cond_resched();
 
-                if (ret && ret != -EAGAIN)
+                if (ret == -EAGAIN)
+                        schedule_timeout_interruptible(msecs_to_jiffies
+                                                       (GC_SLEEP_MS));
+                else if (ret)
                         pr_warn("gc failed!");
         } while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 97707b0c54ce..43af905920f5 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -701,6 +701,8 @@ static void search_free(struct closure *cl)
 {
         struct search *s = container_of(cl, struct search, cl);
 
+        atomic_dec(&s->d->c->search_inflight);
+
         if (s->iop.bio)
                 bio_put(s->iop.bio);
 
@@ -718,6 +720,7 @@ static inline struct search *search_alloc(struct bio *bio,
 
         closure_init(&s->cl, NULL);
         do_bio_hook(s, bio, request_endio);
+        atomic_inc(&d->c->search_inflight);
 
         s->orig_bio             = bio;
         s->cache_miss           = NULL;