From: Nikolay Borisov <nborisov@suse.com>
To: linux-btrfs@vger.kernel.org
Cc: Nikolay Borisov <nborisov@suse.com>
Subject: [PATCH 2/3] btrfs: Introduce btrfs_io_geometry
Date: Mon, 3 Jun 2019 12:05:04 +0300 [thread overview]
Message-ID: <20190603090505.16800-3-nborisov@suse.com> (raw)
In-Reply-To: <20190603090505.16800-1-nborisov@suse.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
---
fs/btrfs/volumes.c | 98 ++++++++++++++++++++++++++++++++++++++++++++++
fs/btrfs/volumes.h | 2 +
2 files changed, 100 insertions(+)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 776f5c7ca7c5..b130f465ca6d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5907,6 +5907,104 @@ static bool need_full_stripe(enum btrfs_map_op op)
return (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS);
}
+/*
+ * btrfs_io_geometry - calculates the geomery of a particular (address, len)
+ * tuple. This information is used to calculate how big a
+ * particular bio can get before it straddles a stripe.
+ *
+ * @fs_info - The omnipresent btrfs structure
+ * @logical - Address that we want to figure out the geometry of
+ * @len - The length of IO we are going to perform, starting at @logical
+ * @op - Type of operation - Write or Read
+ * @io_geom - Pointer used to return values
+ *
+ * Returns < 0 in case a chunk for the given logical address cannot be found,
+ * usually shouldn't happen unless @logical is corrupted, 0 otherwise.
+ */
+int btrfs_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
+ u64 logical, u64 len, struct btrfs_io_geometry *io_geom)
+{
+ struct extent_map *em;
+ struct map_lookup *map;
+ u64 offset;
+ u64 stripe_offset;
+ u64 stripe_nr;
+ u64 stripe_len;
+ u64 raid56_full_stripe_start = (u64)-1;
+ int data_stripes;
+
+ ASSERT(op != BTRFS_MAP_DISCARD);
+
+ em = btrfs_get_chunk_map(fs_info, logical, len);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
+
+ map = em->map_lookup;
+ /* Offset of this logical address in the chunk */
+ offset = logical - em->start;
+ /* Len of a stripe in a chunk */
+ stripe_len = map->stripe_len;
+ /* Stripe wher this block falls in */
+ stripe_nr = div64_u64(offset, stripe_len);
+ /* Offset of stripe in the chunk */
+ stripe_offset = stripe_nr * stripe_len;
+ if (offset < stripe_offset) {
+ btrfs_crit(fs_info,
+ "stripe math has gone wrong, stripe_offset=%llu, offset=%llu, start=%llu, logical=%llu, stripe_len=%llu",
+ stripe_offset, offset, em->start, logical,
+ stripe_len);
+ free_extent_map(em);
+ return -EINVAL;
+ }
+
+ /* stripe_offset is the offset of this block in its stripe*/
+ stripe_offset = offset - stripe_offset;
+ data_stripes = nr_data_stripes(map);
+
+
+ if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+ u64 max_len = stripe_len - stripe_offset;
+
+ /*
+ * In case of raid56, we need to know the stripe aligned start
+ */
+ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+ unsigned long full_stripe_len = stripe_len * data_stripes;
+ raid56_full_stripe_start = offset;
+
+ /*
+ * Allow a write of a full stripe, but make sure we
+ * don't allow straddling of stripes
+ */
+ raid56_full_stripe_start = div64_u64(raid56_full_stripe_start,
+ full_stripe_len);
+ raid56_full_stripe_start *= full_stripe_len;
+
+ /*
+ * For writes to RAID[56], allow a full stripeset across
+ * all disks. For other RAID types and for RAID[56]
+ * reads, just allow a single stripe (on a single disk).
+ */
+ if (op == BTRFS_MAP_WRITE) {
+ max_len = stripe_len * data_stripes -
+ (offset - raid56_full_stripe_start);
+ }
+ }
+ len = min_t(u64, em->len - offset, max_len);
+ } else {
+ len = em->len - offset;
+ }
+
+ io_geom->len = len;
+ io_geom->offset = offset;
+ io_geom->stripe_len = stripe_len;
+ io_geom->stripe_nr = stripe_nr;
+ io_geom->stripe_offset = stripe_offset;
+ io_geom->raid56_stripe_offset = raid56_full_stripe_start;
+
+ return 0;
+}
+
static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
enum btrfs_map_op op,
u64 logical, u64 *length,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 7c1ddf35b7d4..f3bdf768bbab 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -421,6 +421,8 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
u64 logical, u64 *length,
struct btrfs_bio **bbio_ret);
+int btrfs_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
+ u64 logical, u64 len, struct btrfs_io_geometry *io_geom);
int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
u64 physical, u64 **logical, int *naddrs, int *stripe_len);
int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
--
2.17.1
next prev parent reply other threads:[~2019-06-03 9:05 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-03 9:05 [PATCH 0/3] refactoring __btrfs_map_block Nikolay Borisov
2019-06-03 9:05 ` [PATCH 1/3] btrfs: Introduce struct btrfs_io_geometry Nikolay Borisov
2019-06-05 7:35 ` Johannes Thumshirn
2019-06-05 12:37 ` David Sterba
2019-06-03 9:05 ` Nikolay Borisov [this message]
2019-06-05 8:01 ` [PATCH 2/3] btrfs: Introduce btrfs_io_geometry Johannes Thumshirn
2019-06-12 16:31 ` David Sterba
2019-06-03 9:05 ` [PATCH 3/3] btrfs: Use btrfs_io_geometry appropriately Nikolay Borisov
2019-06-12 16:29 ` David Sterba
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=20190603090505.16800-3-nborisov@suse.com \
--to=nborisov@suse.com \
--cc=linux-btrfs@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
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).