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 07/12] btrfs-progs: support discarding zoned device
Date: Fri, 7 Jun 2019 22:17:46 +0900 [thread overview]
Message-ID: <20190607131751.5359-7-naohiro.aota@wdc.com> (raw)
In-Reply-To: <20190607131751.5359-1-naohiro.aota@wdc.com>
All zones of zoned block devices should be reset before writing. Support
this by considering zone reset as a special case of block discard and block
zeroing. Of note is that only zones accepting random writes can be zeroed.
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
utils.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 88 insertions(+), 6 deletions(-)
diff --git a/utils.c b/utils.c
index a26fe7a5743c..c375b32953f7 100644
--- a/utils.c
+++ b/utils.c
@@ -123,6 +123,37 @@ static int discard_range(int fd, u64 start, u64 len)
return 0;
}
+/*
+ * Discard blocks in the zones of a zoned block device.
+ * Process this with zone size granularity so that blocks in
+ * conventional zones are discarded using discard_range and
+ * blocks in sequential zones are discarded though a zone reset.
+ */
+static int discard_zones(int fd, struct btrfs_zone_info *zinfo)
+{
+#ifdef BTRFS_ZONED
+ unsigned int i;
+
+ /* Zone size granularity */
+ for (i = 0; i < zinfo->nr_zones; i++) {
+ if (zinfo->zones[i].type == BLK_ZONE_TYPE_CONVENTIONAL) {
+ discard_range(fd, zinfo->zones[i].start << 9,
+ zinfo->zone_size);
+ } else if (zinfo->zones[i].cond != BLK_ZONE_COND_EMPTY) {
+ struct blk_zone_range range = {
+ zinfo->zones[i].start,
+ zinfo->zone_size >> 9 };
+ if (ioctl(fd, BLKRESETZONE, &range) < 0)
+ return errno;
+ }
+ }
+
+ return 0;
+#else
+ return -EIO;
+#endif
+}
+
/*
* Discard blocks in the given range in 1G chunks, the process is interruptible
*/
@@ -205,8 +236,38 @@ static int zero_blocks(int fd, off_t start, size_t len)
#define ZERO_DEV_BYTES SZ_2M
+static int zero_zone_blocks(int fd, struct btrfs_zone_info *zinfo,
+ off_t start, size_t len)
+{
+ size_t zone_len = zinfo->zone_size;
+ off_t ofst = start;
+ size_t count;
+ int ret;
+
+ /* Make sure that zero_blocks does not write sequential zones */
+ while (len > 0) {
+
+ /* Limit zero_blocks to a single zone */
+ count = min_t(size_t, len, zone_len);
+ if (count > zone_len - (ofst & (zone_len - 1)))
+ count = zone_len - (ofst & (zone_len - 1));
+
+ if (zone_is_random_write(zinfo, ofst)) {
+ ret = zero_blocks(fd, ofst, count);
+ if (ret != 0)
+ return ret;
+ }
+
+ len -= count;
+ ofst += count;
+ }
+
+ return 0;
+}
+
/* don't write outside the device by clamping the region to the device size */
-static int zero_dev_clamped(int fd, off_t start, ssize_t len, u64 dev_size)
+static int zero_dev_clamped(int fd, struct btrfs_zone_info *zinfo,
+ off_t start, ssize_t len, u64 dev_size)
{
off_t end = max(start, start + len);
@@ -219,6 +280,9 @@ static int zero_dev_clamped(int fd, off_t start, ssize_t len, u64 dev_size)
start = min_t(u64, start, dev_size);
end = min_t(u64, end, dev_size);
+ if (zinfo->model != ZONED_NONE)
+ return zero_zone_blocks(fd, zinfo, start, end - start);
+
return zero_blocks(fd, start, end - start);
}
@@ -566,6 +630,7 @@ int btrfs_get_zone_info(int fd, const char *file, int hmzoned,
int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
u64 max_block_count, unsigned opflags)
{
+ struct btrfs_zone_info zinfo;
u64 block_count;
struct stat st;
int i, ret;
@@ -584,13 +649,30 @@ int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
if (max_block_count)
block_count = min(block_count, max_block_count);
+ ret = btrfs_get_zone_info(fd, file, opflags & PREP_DEVICE_HMZONED,
+ &zinfo);
+ if (ret < 0)
+ return 1;
+
if (opflags & PREP_DEVICE_DISCARD) {
/*
* We intentionally ignore errors from the discard ioctl. It
* is not necessary for the mkfs functionality but just an
- * optimization.
+ * optimization. However, we cannot ignore zone discard (reset)
+ * errors for a zoned block device as this could result in the
+ * inability to write to non-empty sequential zones of the
+ * device.
*/
- if (discard_range(fd, 0, 0) == 0) {
+ if (zinfo.model != ZONED_NONE) {
+ printf("Resetting device zones %s (%u zones) ...\n",
+ file, zinfo.nr_zones);
+ if (discard_zones(fd, &zinfo)) {
+ fprintf(stderr,
+ "ERROR: failed to reset device '%s' zones\n",
+ file);
+ return 1;
+ }
+ } else if (discard_range(fd, 0, 0) == 0) {
if (opflags & PREP_DEVICE_VERBOSE)
printf("Performing full device TRIM %s (%s) ...\n",
file, pretty_size(block_count));
@@ -598,12 +680,12 @@ int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
}
}
- ret = zero_dev_clamped(fd, 0, ZERO_DEV_BYTES, block_count);
+ ret = zero_dev_clamped(fd, &zinfo, 0, ZERO_DEV_BYTES, block_count);
for (i = 0 ; !ret && i < BTRFS_SUPER_MIRROR_MAX; i++)
- ret = zero_dev_clamped(fd, btrfs_sb_offset(i),
+ ret = zero_dev_clamped(fd, &zinfo, btrfs_sb_offset(i),
BTRFS_SUPER_INFO_SIZE, block_count);
if (!ret && (opflags & PREP_DEVICE_ZERO_END))
- ret = zero_dev_clamped(fd, block_count - ZERO_DEV_BYTES,
+ ret = zero_dev_clamped(fd, &zinfo, block_count - ZERO_DEV_BYTES,
ZERO_DEV_BYTES, block_count);
if (ret < 0) {
--
2.21.0
next prev parent reply other threads:[~2019-06-07 13:19 UTC|newest]
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 ` [PATCH 04/12] btrfs-progs: Introduce zone block device helper functions Naohiro Aota
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 ` Naohiro Aota [this message]
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 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=20190607131751.5359-7-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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).