Linux-bcache Archive on lore.kernel.org
 help / color / Atom feed
From: Coly Li <colyli@suse.de>
To: linux-bcache@vger.kernel.org
Cc: linux-block@vger.kernel.org, Coly Li <colyli@suse.de>
Subject: [RFC PATCH 14/16] bcache: add bucket_size_hi into struct cache_sb_disk for large bucket
Date: Sun,  5 Jul 2020 23:55:59 +0800
Message-ID: <20200705155601.5404-15-colyli@suse.de> (raw)
In-Reply-To: <20200705155601.5404-1-colyli@suse.de>

The large bucket feature is to extend bucket_size from 16bit to 32bit.

When create cache device on zoned device (e.g. zoned NVMe SSD), making
a single bucket cover one or more zones of the zoned device is the
simplest way to support zoned device as cache by bcache.

But current maximum bucket size is 16MB and a typical zone size of zoned
device is 256MB, this is the major motiviation to extend bucket size to
a larger bit width.

This patch is the basic and first change to support large bucket size,
the major changes it makes are,
- Add BCH_FEATURE_INCOMPAT_LARGE_BUCKET for the large bucket feature,
  INCOMPAT means it introduces incompatible on-disk format change.
- Add BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET) routines.
- Adds __le32 bucket_size_hi into struct cache_sb_disk at offset 0x8d0
  for the on-disk super block format.
- For the in-memory super block struct cache_sb, member bucket_size is
  extended from __u16 to __32.
- Add get_bucket_size() to combine the bucket_size and bucket_size_hi
  from struct cache_sb_disk into an unsigned int value.

Since we already have large bucket size helpers meta_bucket_pages(),
meta_bucket_bytes() and alloc_meta_bucket_pages(), they make sure when
bucket size > 8MB, the memory allocation for bcache meta data bucket
won't fail no matter how large the bucket size extended. So these meta
data buckets are handled properly when the bucket size width increase
from 16bit to 32bit, we don't need to worry about them.

Signed-off-by: Coly Li <colyli@suse.de>
---
 drivers/md/bcache/alloc.c    |  2 +-
 drivers/md/bcache/features.c | 22 ++++++++++++++++++++++
 drivers/md/bcache/features.h |  4 ++++
 drivers/md/bcache/movinggc.c |  4 ++--
 drivers/md/bcache/super.c    | 23 +++++++++++++++++++----
 drivers/md/bcache/sysfs.c    |  2 +-
 include/uapi/linux/bcache.h  |  5 +++--
 7 files changed, 52 insertions(+), 10 deletions(-)
 create mode 100644 drivers/md/bcache/features.c

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index a1df0d95151c..52035a78d836 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -87,7 +87,7 @@ void bch_rescale_priorities(struct cache_set *c, int sectors)
 {
 	struct cache *ca;
 	struct bucket *b;
-	unsigned int next = c->nbuckets * c->sb.bucket_size / 1024;
+	unsigned long next = c->nbuckets * c->sb.bucket_size / 1024;
 	unsigned int i;
 	int r;
 
diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c
new file mode 100644
index 000000000000..68297a3ec512
--- /dev/null
+++ b/drivers/md/bcache/features.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Feature set bits and string conversion.
+ * Inspired by ext4's features compat/incompat/ro_compat related code.
+ *
+ * Copyright 2020 Coly Li <colyli@suse.de>
+ *
+ */
+#include <linux/bcache.h>
+#include "bcache.h"
+
+struct feature {
+	int		compat;
+	unsigned int	mask;
+	const char	*string;
+};
+
+static struct feature feature_list[] = {
+	{BCH_FEATURE_COMPAT, BCH_FEATURE_INCOMPAT_LARGE_BUCKET,
+		"large_bucket"},
+	{0, 0, 0 },
+};
diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h
index 69332ef7be5d..251b57d73abd 100644
--- a/drivers/md/bcache/features.h
+++ b/drivers/md/bcache/features.h
@@ -24,6 +24,9 @@
 
 /* Feature set definition */
 
+/* Incompat feature set */
+#define BCH_FEATURE_INCOMPAT_LARGE_BUCKET	0x0001 /* 32bit bucket size */
+
 #define BCH_FEATURE_COMPAT_FUNCS(name, flagname) \
 static inline int bch_has_feature_##name(struct cache_sb *sb) \
 { \
@@ -75,4 +78,5 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \
 		~BCH##_FEATURE_INCOMPAT_##flagname; \
 }
 
+BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET);
 #endif
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 7891fb512736..046ef8062762 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -206,8 +206,8 @@ void bch_moving_gc(struct cache_set *c)
 	mutex_lock(&c->bucket_lock);
 
 	for_each_cache(ca, c, i) {
-		unsigned int sectors_to_move = 0;
-		unsigned int reserve_sectors = ca->sb.bucket_size *
+		unsigned long sectors_to_move = 0;
+		unsigned long reserve_sectors = ca->sb.bucket_size *
 			     fifo_used(&ca->free[RESERVE_MOVINGGC]);
 
 		ca->heap.used = 0;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2da6d5aa8c63..79bf6d9383bd 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -60,6 +60,17 @@ struct workqueue_struct *bch_journal_wq;
 
 /* Superblock */
 
+static unsigned int get_bucket_size(struct cache_sb *sb, struct cache_sb_disk *s)
+{
+	unsigned int bucket_size = le16_to_cpu(s->bucket_size);
+
+	if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES &&
+	     bch_has_feature_large_bucket(sb))
+		bucket_size |= le32_to_cpu(s->bucket_size_hi) << 16;
+
+	return bucket_size;
+}
+
 static const char *read_super_basic(struct cache_sb *sb,  struct block_device *bdev,
 				     struct cache_sb_disk *s)
 {
@@ -68,7 +79,7 @@ static const char * read_super_basic(struct cache_sb *sb,  struct block_device *
 
 	sb->first_bucket= le16_to_cpu(s->first_bucket);
 	sb->nbuckets	= le64_to_cpu(s->nbuckets);
-	sb->bucket_size	= le16_to_cpu(s->bucket_size);
+	sb->bucket_size	= get_bucket_size(sb, s);
 
 	sb->nr_in_set	= le16_to_cpu(s->nr_in_set);
 	sb->nr_this_dev	= le16_to_cpu(s->nr_this_dev);
@@ -210,12 +221,16 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 			goto err;
 		break;
 	case BCACHE_SB_VERSION_CDEV_WITH_FEATURES:
-		err = read_super_basic(sb, bdev, s);
-		if (err)
-			goto err;
+		/*
+		 * Feature bits are needed in read_super_basic(),
+		 * convert them firstly.
+		 */
 		sb->feature_compat = le64_to_cpu(s->feature_compat);
 		sb->feature_incompat = le64_to_cpu(s->feature_incompat);
 		sb->feature_ro_compat = le64_to_cpu(s->feature_ro_compat);
+		err = read_super_basic(sb, bdev, s);
+		if (err)
+			goto err;
 		break;
 	default:
 		err = "Unsupported superblock version";
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 0dadec5a78f6..e7cecd5dc178 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -1078,7 +1078,7 @@ SHOW(__bch_cache)
 				"Dirty:		%zu%%\n"
 				"Metadata:	%zu%%\n"
 				"Average:	%llu\n"
-				"Sectors per Q:	%zu\n"
+				"Sectors per Q:	%lu\n"
 				"Quantiles:	[",
 				unused * 100 / (size_t) ca->sb.nbuckets,
 				available * 100 / (size_t) ca->sb.nbuckets,
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 046fa29533a8..ae0514a25763 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -213,7 +213,8 @@ struct cache_sb_disk {
 		__le16		keys;
 	};
 /*0d0*/	__le64			d[SB_JOURNAL_BUCKETS];	/* journal buckets */
-/*8d0*/
+/*8d0*/	__le32			bucket_size_hi;
+/*8d4*/
 };
 
 /*
@@ -248,9 +249,9 @@ struct cache_sb {
 		__u64		nbuckets;	/* device size */
 
 		__u16		block_size;	/* sectors */
-		__u16		bucket_size;	/* sectors */
 		__u16		nr_in_set;
 		__u16		nr_this_dev;
+		__u32		bucket_size;	/* sectors */
 	};
 	struct {
 		/* Backing devices */
-- 
2.26.2

  parent reply index

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-05 15:55 [RFC PATCH 00/16] bcache: extend bucket size to 32bit width Coly Li
2020-07-05 15:55 ` [RFC PATCH 01/16] bcache: add comments to mark member offset of struct cache_sb_disk Coly Li
2020-07-05 15:55 ` [RFC PATCH 02/16] bcache: add read_super_basic() to read major part of super block Coly Li
2020-07-05 15:55   ` Coly Li
2020-07-05 15:55 ` [RFC PATCH 03/16] bcache: add more accurate error information in read_super_basic() Coly Li
2020-07-05 15:55   ` Coly Li
2020-07-05 15:55 ` [RFC PATCH 04/16] bcache: disassemble the big if() checks in bch_cache_set_alloc() Coly Li
2020-07-05 15:55   ` Coly Li
2020-07-05 15:55 ` [RFC PATCH 05/16] bcache: fix super block seq numbers comparision in register_cache_set() Coly Li
2020-07-05 15:55 ` [RFC PATCH 06/16] bcache: increase super block version for cache device and backing device Coly Li
2020-07-05 15:55 ` [RFC PATCH 07/16] bcache: move bucket related code into read_super_basic() Coly Li
2020-07-05 15:55 ` [RFC PATCH 08/16] bcache: struct cache_sb is only for in-memory super block now Coly Li
2020-07-05 15:55 ` [RFC PATCH 09/16] bcache: introduce meta_bucket_pages() related helper routines Coly Li
2020-07-05 15:55   ` Coly Li
2020-07-05 15:55 ` [RFC PATCH 10/16] bcache: handle c->uuids properly for bucket size > 8MB Coly Li
2020-07-05 15:55 ` [RFC PATCH 11/16] bcache: handle cache prio_buckets and disk_buckets " Coly Li
2020-07-05 15:55 ` [RFC PATCH 12/16] bcache: handle cache set verify_ondisk " Coly Li
2020-07-05 15:55   ` Coly Li
2020-07-05 15:55 ` [RFC PATCH 13/16] bcache: handle btree node memory allocation " Coly Li
2020-07-05 15:55   ` Coly Li
2020-07-05 15:55 ` Coly Li [this message]
2020-07-05 15:56 ` [RFC PATCH 15/16] bcache: avoid extra memory allocation from mempool c->fill_iter Coly Li
2020-07-05 15:56 ` [RFC PATCH 16/16] bcache: avoid extra memory consumption in struct bbio for large bucket size 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=20200705155601.5404-15-colyli@suse.de \
    --to=colyli@suse.de \
    --cc=linux-bcache@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    /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