Linux-BTRFS Archive on lore.kernel.org
 help / color / Atom feed
From: Naohiro Aota <naohiro.aota@wdc.com>
To: linux-btrfs@vger.kernel.org, David Sterba <dsterba@suse.com>
Cc: "Chris Mason" <clm@fb.com>, "Josef Bacik" <josef@toxicpanda.com>,
	"Qu Wenruo" <wqu@suse.com>, "Nikolay Borisov" <nborisov@suse.com>,
	linux-kernel@vger.kernel.org, "Hannes Reinecke" <hare@suse.com>,
	linux-fsdevel@vger.kernel.org,
	"Damien Le Moal" <damien.lemoal@wdc.com>,
	"Matias Bjørling" <mb@lightnvm.io>,
	"Johannes Thumshirn" <jthumshirn@suse.de>,
	"Bart Van Assche" <bvanassche@acm.org>,
	"Naohiro Aota" <naohiro.aota@wdc.com>
Subject: [PATCH 04/12] btrfs-progs: Introduce zone block device helper functions
Date: Fri,  7 Jun 2019 22:17:43 +0900
Message-ID: <20190607131751.5359-4-naohiro.aota@wdc.com> (raw)
In-Reply-To: <20190607131751.5359-1-naohiro.aota@wdc.com>

This patch introduce several zone related functions: btrfs_get_zones() to
get zone information from the specified device and put the information in
zinfo, and zone_is_random_write() to check if a zone accept random writes.

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 utils.c   | 194 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 utils.h   |  16 +++++
 volumes.h |  28 ++++++++
 3 files changed, 238 insertions(+)

diff --git a/utils.c b/utils.c
index 7d5a1f3b7f8d..d50304b1be80 100644
--- a/utils.c
+++ b/utils.c
@@ -359,6 +359,200 @@ out:
 	return ret;
 }
 
+enum btrfs_zoned_model zoned_model(const char *file)
+{
+	char model[32];
+	int ret;
+
+	ret = queue_param(file, "zoned", model, sizeof(model));
+	if (ret <= 0)
+		return ZONED_NONE;
+
+	if (strncmp(model, "host-aware", 10) == 0)
+		return ZONED_HOST_AWARE;
+	if (strncmp(model, "host-managed", 12) == 0)
+		return ZONED_HOST_MANAGED;
+
+	return ZONED_NONE;
+}
+
+size_t zone_size(const char *file)
+{
+	char chunk[32];
+	int ret;
+
+	ret = queue_param(file, "chunk_sectors", chunk, sizeof(chunk));
+	if (ret <= 0)
+		return 0;
+
+	return strtoul((const char *)chunk, NULL, 10) << 9;
+}
+
+#ifdef BTRFS_ZONED
+int zone_is_random_write(struct btrfs_zone_info *zinfo, u64 bytenr)
+{
+	unsigned int zno;
+
+	if (zinfo->model == ZONED_NONE)
+		return 1;
+
+	zno = bytenr / zinfo->zone_size;
+
+	/*
+	 * Only sequential write required zones on host-managed
+	 * devices cannot be written randomly.
+	 */
+	return zinfo->zones[zno].type != BLK_ZONE_TYPE_SEQWRITE_REQ;
+}
+
+#define BTRFS_REPORT_NR_ZONES	8192
+
+static int btrfs_get_zones(int fd, const char *file, u64 block_count,
+			   struct btrfs_zone_info *zinfo)
+{
+	size_t zone_bytes = zone_size(file);
+	size_t rep_size;
+	u64 sector = 0;
+	struct blk_zone_report *rep;
+	struct blk_zone *zone;
+	unsigned int i, n = 0;
+	int ret;
+
+	/*
+	 * Zones are guaranteed (by the kernel) to be a power of 2 number of
+	 * sectors. Check this here and make sure that zones are not too
+	 * small.
+	 */
+	if (!zone_bytes || (zone_bytes & (zone_bytes - 1))) {
+		error("ERROR: Illegal zone size %zu (not a power of 2)\n",
+		      zone_bytes);
+		exit(1);
+	}
+	if (zone_bytes < BTRFS_MKFS_SYSTEM_GROUP_SIZE) {
+		error("ERROR: Illegal zone size %zu (smaller than %d)\n",
+		      zone_bytes,
+		      BTRFS_MKFS_SYSTEM_GROUP_SIZE);
+		exit(1);
+	}
+
+	/* Allocate the zone information array */
+	zinfo->zone_size = zone_bytes;
+	zinfo->nr_zones = block_count / zone_bytes;
+	if (block_count & (zone_bytes - 1))
+		zinfo->nr_zones++;
+	zinfo->zones = calloc(zinfo->nr_zones, sizeof(struct blk_zone));
+	if (!zinfo->zones) {
+		error("No memory for zone information\n");
+		exit(1);
+	}
+
+	/* Allocate a zone report */
+	rep_size = sizeof(struct blk_zone_report) +
+		sizeof(struct blk_zone) * BTRFS_REPORT_NR_ZONES;
+	rep = malloc(rep_size);
+	if (!rep) {
+		error("No memory for zones report\n");
+		exit(1);
+	}
+
+	/* Get zone information */
+	zone = (struct blk_zone *)(rep + 1);
+	while (n < zinfo->nr_zones) {
+
+		memset(rep, 0, rep_size);
+		rep->sector = sector;
+		rep->nr_zones = BTRFS_REPORT_NR_ZONES;
+
+		ret = ioctl(fd, BLKREPORTZONE, rep);
+		if (ret != 0) {
+			error("ioctl BLKREPORTZONE failed (%s)\n",
+			      strerror(errno));
+			exit(1);
+		}
+
+		if (!rep->nr_zones)
+			break;
+
+		for (i = 0; i < rep->nr_zones; i++) {
+			if (n >= zinfo->nr_zones)
+				break;
+			memcpy(&zinfo->zones[n], &zone[i],
+			       sizeof(struct blk_zone));
+			sector = zone[i].start + zone[i].len;
+			n++;
+		}
+
+	}
+
+	/*
+	 * We need at least one random write zone (a conventional zone or
+	 * a sequential write preferred zone on a host-aware device).
+	 */
+	if (!zone_is_random_write(zinfo, 0)) {
+		error("ERROR: No conventional zone at block 0\n");
+		exit(1);
+	}
+
+	zinfo->nr_zones = n;
+
+	free(rep);
+
+	return 0;
+}
+
+#endif
+
+int btrfs_get_zone_info(int fd, const char *file, int hmzoned,
+			struct btrfs_zone_info *zinfo)
+{
+	struct stat st;
+	int ret;
+
+	memset(zinfo, 0, sizeof(struct btrfs_zone_info));
+
+	ret = fstat(fd, &st);
+	if (ret < 0) {
+		error("unable to stat %s\n", file);
+		return 1;
+	}
+
+	if (!S_ISBLK(st.st_mode))
+		return 0;
+
+	/* Check zone model */
+	zinfo->model = zoned_model(file);
+	if (zinfo->model == ZONED_NONE)
+		return 0;
+
+	if (zinfo->model == ZONED_HOST_MANAGED && !hmzoned) {
+		error("%s: host-managed zoned block device (enable zone block device support with -O hmzoned)\n",
+		      file);
+		return -1;
+	}
+
+	if (!hmzoned) {
+		/* Treat host-aware devices as regular devices */
+		zinfo->model = ZONED_NONE;
+		return 0;
+	}
+
+#ifdef BTRFS_ZONED
+	/* Get zone information */
+	ret = btrfs_get_zones(fd, file, btrfs_device_size(fd, &st), zinfo);
+	if (ret != 0)
+		return ret;
+#else
+	error("%s: Unsupported host-%s zoned block device\n",
+	      file, zinfo->model == ZONED_HOST_MANAGED ? "managed" : "aware");
+	if (zinfo->model == ZONED_HOST_MANAGED)
+		return -1;
+
+	printf("%s: heandling host-aware block device as a regular disk\n",
+	       file);
+#endif
+	return 0;
+}
+
 int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
 		u64 max_block_count, unsigned opflags)
 {
diff --git a/utils.h b/utils.h
index 47321f62c8e0..f5e5c5bec66a 100644
--- a/utils.h
+++ b/utils.h
@@ -69,6 +69,7 @@ void units_set_base(unsigned *units, unsigned base);
 #define	PREP_DEVICE_ZERO_END	(1U << 0)
 #define	PREP_DEVICE_DISCARD	(1U << 1)
 #define	PREP_DEVICE_VERBOSE	(1U << 2)
+#define	PREP_DEVICE_HMZONED	(1U << 3)
 
 #define SEEN_FSID_HASH_SIZE 256
 struct seen_fsid {
@@ -78,10 +79,25 @@ struct seen_fsid {
 	int fd;
 };
 
+struct btrfs_zone_info;
+
+enum btrfs_zoned_model zoned_model(const char *file);
+size_t zone_size(const char *file);
 int btrfs_make_root_dir(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root, u64 objectid);
 int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
 		u64 max_block_count, unsigned opflags);
+int btrfs_get_zone_info(int fd, const char *file, int hmzoned,
+			struct btrfs_zone_info *zinfo);
+#ifdef BTRFS_ZONED
+int zone_is_random_write(struct btrfs_zone_info *zinfo, u64 bytenr);
+#else
+static inline int zone_is_random_write(struct btrfs_zone_info *zinfo,
+				       u64 bytenr)
+{
+	return 1;
+}
+#endif
 int btrfs_add_to_fsid(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, int fd, const char *path,
 		      u64 block_count, u32 io_width, u32 io_align,
diff --git a/volumes.h b/volumes.h
index dbe9d3dea647..c9262ceaea93 100644
--- a/volumes.h
+++ b/volumes.h
@@ -22,12 +22,40 @@
 #include "kerncompat.h"
 #include "ctree.h"
 
+#ifdef BTRFS_ZONED
+#include <linux/blkzoned.h>
+#else
+struct blk_zone {
+	int dummy;
+};
+#endif
+
+/*
+ * Zoned block device models.
+ */
+enum btrfs_zoned_model {
+	ZONED_NONE = 0,
+	ZONED_HOST_AWARE,
+	ZONED_HOST_MANAGED,
+};
+
+/*
+ * Zone information for a zoned block device.
+ */
+struct btrfs_zone_info {
+	enum btrfs_zoned_model	model;
+	size_t			zone_size;
+	struct blk_zone		*zones;
+	unsigned int		nr_zones;
+};
+
 #define BTRFS_STRIPE_LEN	SZ_64K
 
 struct btrfs_device {
 	struct list_head dev_list;
 	struct btrfs_root *dev_root;
 	struct btrfs_fs_devices *fs_devices;
+	struct btrfs_zone_info zinfo;
 
 	u64 total_ios;
 
-- 
2.21.0


  parent reply index

Thread overview: 79+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-07 13:10 [PATCH v2 00/19] btrfs zoned block device support Naohiro Aota
2019-06-07 13:10 ` [PATCH 01/19] btrfs: introduce HMZONED feature flag Naohiro Aota
2019-06-07 13:10 ` [PATCH 02/19] btrfs: Get zone information of zoned block devices Naohiro Aota
2019-06-13 13:58   ` Josef Bacik
2019-06-18  6:04     ` Naohiro Aota
2019-06-13 13:58   ` Josef Bacik
2019-06-17 18:57   ` David Sterba
2019-06-18  6:42     ` Naohiro Aota
2019-06-27 15:11       ` David Sterba
2019-06-07 13:10 ` [PATCH 03/19] btrfs: Check and enable HMZONED mode Naohiro Aota
2019-06-13 13:57   ` Josef Bacik
2019-06-18  6:43     ` Naohiro Aota
2019-06-07 13:10 ` [PATCH 04/19] btrfs: disable fallocate in " Naohiro Aota
2019-06-07 13:10 ` [PATCH 05/19] btrfs: disable direct IO " Naohiro Aota
2019-06-13 14:00   ` Josef Bacik
2019-06-18  8:17     ` Naohiro Aota
2019-06-07 13:10 ` [PATCH 06/19] btrfs: align dev extent allocation to zone boundary Naohiro Aota
2019-06-07 13:10 ` [PATCH 07/19] btrfs: do sequential extent allocation in HMZONED mode Naohiro Aota
2019-06-13 14:07   ` Josef Bacik
2019-06-18  8:28     ` Naohiro Aota
2019-06-18 13:37       ` Josef Bacik
2019-06-17 22:30   ` David Sterba
2019-06-18  8:49     ` Naohiro Aota
2019-06-27 15:28       ` David Sterba
2019-06-07 13:10 ` [PATCH 08/19] btrfs: make unmirroed BGs readonly only if we have at least one writable BG Naohiro Aota
2019-06-13 14:09   ` Josef Bacik
2019-06-18  7:42     ` Naohiro Aota
2019-06-18 13:35       ` Josef Bacik
2019-06-07 13:10 ` [PATCH 09/19] btrfs: limit super block locations in HMZONED mode Naohiro Aota
2019-06-13 14:12   ` Josef Bacik
2019-06-18  8:51     ` Naohiro Aota
2019-06-17 22:53   ` David Sterba
2019-06-18  9:01     ` Naohiro Aota
2019-06-27 15:35       ` David Sterba
2019-06-28  3:55   ` Anand Jain
2019-06-28  6:39     ` Naohiro Aota
2019-06-28  6:52       ` Anand Jain
2019-06-07 13:10 ` [PATCH 10/19] btrfs: rename btrfs_map_bio() Naohiro Aota
2019-06-07 13:10 ` [PATCH 11/19] btrfs: introduce submit buffer Naohiro Aota
2019-06-13 14:14   ` Josef Bacik
2019-06-17  3:16     ` Damien Le Moal
2019-06-18  0:00       ` David Sterba
2019-06-18  4:04         ` Damien Le Moal
2019-06-18 13:33       ` Josef Bacik
2019-06-19 10:32         ` Damien Le Moal
2019-06-07 13:10 ` [PATCH 12/19] btrfs: expire submit buffer on timeout Naohiro Aota
2019-06-13 14:15   ` Josef Bacik
2019-06-17  3:19     ` Damien Le Moal
2019-06-07 13:10 ` [PATCH 13/19] btrfs: avoid sync IO prioritization on checksum in HMZONED mode Naohiro Aota
2019-06-13 14:17   ` Josef Bacik
2019-06-07 13:10 ` [PATCH 14/19] btrfs: redirty released extent buffers in sequential BGs Naohiro Aota
2019-06-13 14:24   ` Josef Bacik
2019-06-18  9:09     ` Naohiro Aota
2019-06-07 13:10 ` [PATCH 15/19] btrfs: reset zones of unused block groups Naohiro Aota
2019-06-07 13:10 ` [PATCH 16/19] btrfs: wait existing extents before truncating Naohiro Aota
2019-06-13 14:25   ` Josef Bacik
2019-06-07 13:10 ` [PATCH 17/19] btrfs: shrink delayed allocation size in HMZONED mode Naohiro Aota
2019-06-13 14:27   ` Josef Bacik
2019-06-07 13:10 ` [PATCH 18/19] btrfs: support dev-replace " Naohiro Aota
2019-06-13 14:33   ` Josef Bacik
2019-06-18  9:14     ` Naohiro Aota
2019-06-07 13:10 ` [PATCH 19/19] btrfs: enable to mount HMZONED incompat flag Naohiro Aota
2019-06-07 13:17 ` [PATCH 01/12] btrfs-progs: build: Check zoned block device support Naohiro Aota
2019-06-07 13:17   ` [PATCH 02/12] btrfs-progs: utils: Introduce queue_param Naohiro Aota
2019-06-07 13:17   ` [PATCH 03/12] btrfs-progs: add new HMZONED feature flag Naohiro Aota
2019-06-07 13:17   ` Naohiro Aota [this message]
2019-06-07 13:17   ` [PATCH 05/12] btrfs-progs: load and check zone information Naohiro Aota
2019-06-07 13:17   ` [PATCH 06/12] btrfs-progs: avoid writing super block to sequential zones Naohiro Aota
2019-06-07 13:17   ` [PATCH 07/12] btrfs-progs: support discarding zoned device Naohiro Aota
2019-06-07 13:17   ` [PATCH 08/12] btrfs-progs: volume: align chunk allocation to zones Naohiro Aota
2019-06-07 13:17   ` [PATCH 09/12] btrfs-progs: do sequential allocation Naohiro Aota
2019-06-07 13:17   ` [PATCH 10/12] btrfs-progs: mkfs: Zoned block device support Naohiro Aota
2019-06-07 13:17   ` [PATCH 11/12] btrfs-progs: device-add: support HMZONED device Naohiro Aota
2019-06-07 13:17   ` [PATCH 12/12] btrfs-progs: introduce support for dev-place " Naohiro Aota
2019-06-12 17:51 ` [PATCH v2 00/19] btrfs zoned block device support David Sterba
2019-06-13  4:59   ` Naohiro Aota
2019-06-13 13:46     ` David Sterba
2019-06-14  2:07       ` Naohiro Aota
2019-06-17  2:44       ` Damien Le Moal

Reply instructions:

You may reply publically 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=20190607131751.5359-4-naohiro.aota@wdc.com \
    --to=naohiro.aota@wdc.com \
    --cc=bvanassche@acm.org \
    --cc=clm@fb.com \
    --cc=damien.lemoal@wdc.com \
    --cc=dsterba@suse.com \
    --cc=hare@suse.com \
    --cc=josef@toxicpanda.com \
    --cc=jthumshirn@suse.de \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mb@lightnvm.io \
    --cc=nborisov@suse.com \
    --cc=wqu@suse.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-BTRFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-btrfs/0 linux-btrfs/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-btrfs linux-btrfs/ https://lore.kernel.org/linux-btrfs \
		linux-btrfs@vger.kernel.org linux-btrfs@archiver.kernel.org
	public-inbox-index linux-btrfs


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


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