Linux-bcache Archive on lore.kernel.org
 help / color / Atom feed
From: Coly Li <colyli@suse.de>
To: axboe@kernel.dk
Cc: linux-bcache@vger.kernel.org, linux-block@vger.kernel.org,
	Coly Li <colyli@suse.de>, Jianpeng Ma <jianpeng.ma@intel.com>,
	Qiaowei Ren <qiaowei.ren@intel.com>
Subject: [PATCH 17/20] bcache: support storing bcache journal into NVDIMM meta device
Date: Wed, 10 Feb 2021 13:07:39 +0800
Message-ID: <20210210050742.31237-18-colyli@suse.de> (raw)
In-Reply-To: <20210210050742.31237-1-colyli@suse.de>

This patch implements two methods to store bcache journal to,
1) __journal_write_unlocked() for block interface device
   The latency method to compose bio and issue the jset bio to cache
   device (e.g. SSD). c->journal.key.ptr[0] indicates the LBA on cache
   device to store the journal jset.
2) __journal_nvdimm_write_unlocked() for memory interface NVDIMM
   Use memory interface to access NVDIMM pages and store the jset by
   memcpy_flushcache(). c->journal.key.ptr[0] indicates the linear
   address from the NVDIMM pages to store the journal jset.

For lagency configuration without NVDIMM meta device, journal I/O is
handled by __journal_write_unlocked() with existing code logic. If the
NVDIMM meta device is used (by bcache-tools), the journal I/O will
be handled by __journal_nvdimm_write_unlocked() and go into the NVDIMM
pages.

And when NVDIMM meta device is used, sb.d[] stores the linear addresses
from NVDIMM pages (no more bucket index), in journal_reclaim() the
journaling location in c->journal.key.ptr[0] should also be updated by
linear address from NVDIMM pages (no more LBA combined by sectors offset
and bucket index).

Signed-off-by: Coly Li <colyli@suse.de>
Cc: Jianpeng Ma <jianpeng.ma@intel.com>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
---
 drivers/md/bcache/journal.c | 111 ++++++++++++++++++++++++------------
 1 file changed, 75 insertions(+), 36 deletions(-)

diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 1f16d8e497cf..b242fcb47ce2 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -596,6 +596,8 @@ static void do_journal_discard(struct cache *ca)
 		return;
 	}
 
+	BUG_ON(bch_has_feature_nvdimm_meta(&ca->sb));
+
 	switch (atomic_read(&ja->discard_in_flight)) {
 	case DISCARD_IN_FLIGHT:
 		return;
@@ -661,9 +663,13 @@ static void journal_reclaim(struct cache_set *c)
 		goto out;
 
 	ja->cur_idx = next;
-	k->ptr[0] = MAKE_PTR(0,
-			     bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
-			     ca->sb.nr_this_dev);
+	if (!bch_has_feature_nvdimm_meta(&ca->sb))
+		k->ptr[0] = MAKE_PTR(0,
+			bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
+			ca->sb.nr_this_dev);
+	else
+		k->ptr[0] = ca->sb.d[ja->cur_idx];
+
 	atomic_long_inc(&c->reclaimed_journal_buckets);
 
 	bkey_init(k);
@@ -729,46 +735,21 @@ static void journal_write_unlock(struct closure *cl)
 	spin_unlock(&c->journal.lock);
 }
 
-static void journal_write_unlocked(struct closure *cl)
+
+static void __journal_write_unlocked(struct cache_set *c)
 	__releases(c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
-	struct cache *ca = c->cache;
-	struct journal_write *w = c->journal.cur;
 	struct bkey *k = &c->journal.key;
-	unsigned int i, sectors = set_blocks(w->data, block_bytes(ca)) *
-		ca->sb.block_size;
-
+	struct journal_write *w = c->journal.cur;
+	struct closure *cl = &c->journal.io;
+	struct cache *ca = c->cache;
 	struct bio *bio;
 	struct bio_list list;
+	unsigned int i, sectors = set_blocks(w->data, block_bytes(ca)) *
+		ca->sb.block_size;
 
 	bio_list_init(&list);
 
-	if (!w->need_write) {
-		closure_return_with_destructor(cl, journal_write_unlock);
-		return;
-	} else if (journal_full(&c->journal)) {
-		journal_reclaim(c);
-		spin_unlock(&c->journal.lock);
-
-		btree_flush_write(c);
-		continue_at(cl, journal_write, bch_journal_wq);
-		return;
-	}
-
-	c->journal.blocks_free -= set_blocks(w->data, block_bytes(ca));
-
-	w->data->btree_level = c->root->level;
-
-	bkey_copy(&w->data->btree_root, &c->root->key);
-	bkey_copy(&w->data->uuid_bucket, &c->uuid_bucket);
-
-	w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
-	w->data->magic		= jset_magic(&ca->sb);
-	w->data->version	= BCACHE_JSET_VERSION;
-	w->data->last_seq	= last_seq(&c->journal);
-	w->data->csum		= csum_set(w->data);
-
 	for (i = 0; i < KEY_PTRS(k); i++) {
 		ca = PTR_CACHE(c, k, i);
 		bio = &ca->journal.bio;
@@ -793,7 +774,6 @@ static void journal_write_unlocked(struct closure *cl)
 
 		ca->journal.seq[ca->journal.cur_idx] = w->data->seq;
 	}
-
 	/* If KEY_PTRS(k) == 0, this jset gets lost in air */
 	BUG_ON(i == 0);
 
@@ -805,6 +785,65 @@ static void journal_write_unlocked(struct closure *cl)
 
 	while ((bio = bio_list_pop(&list)))
 		closure_bio_submit(c, bio, cl);
+}
+
+static void __journal_nvdimm_write_unlocked(struct cache_set *c)
+	__releases(c->journal.lock)
+{
+	struct journal_write *w = c->journal.cur;
+	struct cache *ca = c->cache;
+	unsigned int sectors;
+
+	sectors = set_blocks(w->data, block_bytes(ca)) * ca->sb.block_size;
+	atomic_long_add(sectors, &ca->meta_sectors_written);
+
+	memcpy_flushcache((void *)c->journal.key.ptr[0], w->data, sectors << 9);
+
+	c->journal.key.ptr[0] += sectors << 9;
+	ca->journal.seq[ca->journal.cur_idx] = w->data->seq;
+
+	atomic_dec_bug(&fifo_back(&c->journal.pin));
+	bch_journal_next(&c->journal);
+	journal_reclaim(c);
+
+	spin_unlock(&c->journal.lock);
+}
+
+static void journal_write_unlocked(struct closure *cl)
+{
+	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	struct cache *ca = c->cache;
+	struct journal_write *w = c->journal.cur;
+
+	if (!w->need_write) {
+		closure_return_with_destructor(cl, journal_write_unlock);
+		return;
+	} else if (journal_full(&c->journal)) {
+		journal_reclaim(c);
+		spin_unlock(&c->journal.lock);
+
+		btree_flush_write(c);
+		continue_at(cl, journal_write, bch_journal_wq);
+		return;
+	}
+
+	c->journal.blocks_free -= set_blocks(w->data, block_bytes(ca));
+
+	w->data->btree_level = c->root->level;
+
+	bkey_copy(&w->data->btree_root, &c->root->key);
+	bkey_copy(&w->data->uuid_bucket, &c->uuid_bucket);
+
+	w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
+	w->data->magic		= jset_magic(&ca->sb);
+	w->data->version	= BCACHE_JSET_VERSION;
+	w->data->last_seq	= last_seq(&c->journal);
+	w->data->csum		= csum_set(w->data);
+
+	if (!bch_has_feature_nvdimm_meta(&ca->sb))
+		__journal_write_unlocked(c);
+	else
+		__journal_nvdimm_write_unlocked(c);
 
 	continue_at(cl, journal_write_done, NULL);
 }
-- 
2.26.2


  parent reply index

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-10  5:07 [PATCH 00/20] bcache patches for Linux v5.12 Coly Li
2021-02-10  5:07 ` [PATCH 01/20] bcache: consider the fragmentation when update the writeback rate Coly Li
2021-02-10  5:07 ` [PATCH 02/20] bcache: Fix register_device_aync typo Coly Li
2021-02-10  5:07 ` [PATCH 03/20] Revert "bcache: Kill btree_io_wq" Coly Li
2021-02-10  5:07 ` [PATCH 04/20] bcache: Give btree_io_wq correct semantics again Coly Li
2021-02-10  5:07 ` [PATCH 05/20] bcache: Move journal work to new flush wq Coly Li
2021-02-10  5:07 ` [PATCH 06/20] bcache: Avoid comma separated statements Coly Li
2021-02-10  5:07 ` [PATCH 07/20] bcache: add initial data structures for nvm pages Coly Li
2021-02-10 15:09   ` Jens Axboe
2021-02-11  3:58     ` Coly Li
2021-02-10  5:07 ` [PATCH 08/20] bcache: initialize the nvm pages allocator Coly Li
2021-02-10  5:07 ` [PATCH 09/20] bcache: initialization of the buddy Coly Li
2021-02-10  5:07 ` [PATCH 10/20] bcache: bch_nvm_alloc_pages() " Coly Li
2021-02-10  5:07 ` [PATCH 11/20] bcache: bch_nvm_free_pages() " Coly Li
2021-02-10  5:07 ` [PATCH 12/20] bcache: get allocated pages from specific owner Coly Li
2021-02-10  5:07 ` [PATCH 13/20] bcache: persist owner info when alloc/free pages Coly Li
2021-02-10  5:07 ` [PATCH 14/20] bcache: use bucket index for SET_GC_MARK() in bch_btree_gc_finish() Coly Li
2021-02-10  5:07 ` [PATCH 15/20] bcache: add BCH_FEATURE_INCOMPAT_NVDIMM_META into incompat feature set Coly Li
2021-02-10  5:07 ` [PATCH 16/20] bcache: initialize bcache journal for NVDIMM meta device Coly Li
2021-02-10  5:07 ` Coly Li [this message]
2021-02-18 21:21   ` [PATCH 17/20] bcache: support storing bcache journal into " Nix
2021-02-10  5:07 ` [PATCH 18/20] bcache: read jset from NVDIMM pages for journal replay Coly Li
2021-02-10  5:07 ` [PATCH 19/20] bcache: add sysfs interface register_nvdimm_meta to register NVDIMM meta device Coly Li
2021-02-10  5:07 ` [PATCH 20/20] bcache: only initialize nvm-pages allocator when CONFIG_BCACHE_NVM_PAGES configured Coly Li
2021-02-10 15:11 ` [PATCH 00/20] bcache patches for Linux v5.12 Jens Axboe
2021-02-12 16:09   ` Coly Li

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210210050742.31237-18-colyli@suse.de \
    --to=colyli@suse.de \
    --cc=axboe@kernel.dk \
    --cc=jianpeng.ma@intel.com \
    --cc=linux-bcache@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=qiaowei.ren@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-bcache Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-bcache/0 linux-bcache/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-bcache linux-bcache/ https://lore.kernel.org/linux-bcache \
		linux-bcache@vger.kernel.org
	public-inbox-index linux-bcache

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-bcache


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git