Original __btrfs_alloc_chunk() use max_chunk_size to limit chunk size,
however it mixed the on-disk space with logical space.
When comes to 10% of writable space, max_chunk_size is used with on-disk
size, but it is also used as logical space size limit, so it is very
confusing and causing inconsistence in different profile.

For example:
on M single, D single 5G btrfs single device,
data chunk is limited to 512M due to 10% limit.

on M RAID1, D RAID1 10Gx2 btrfs 2 devices,
data chunk is limited to 2G due to 10% limit is mixed with on-disk
space, causing the logical chunk space to 1G, twice than single device.

This patch will make the logical and on-disk space limit independent and
clear and solve the above inconsistence.

Signed-off-by: Qu Wenruo <quwen...@cn.fujitsu.com>
---
changelog:
v2:
   Newly introduced.
---
 fs/btrfs/volumes.c | 40 ++++++++++++++++++++++++++--------------
 1 file changed, 26 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0144790..8e74b34 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4235,10 +4235,12 @@ static int __btrfs_alloc_chunk(struct 
btrfs_trans_handle *trans,
        int ncopies;            /* how many copies to data has */
        int ret;
        u64 max_stripe_size;
-       u64 max_chunk_size;
+       u64 max_logical_size;   /* Up limit on chunk's logical size */
+       u64 max_physical_size;  /* Up limit on a chunk's on-disk size */
        u64 stripe_size;
        u64 num_bytes;
        u64 raid_stripe_len = BTRFS_STRIPE_LEN;
+       int need_bump = 0;
        int ndevs;
        int i;
        int j;
@@ -4260,7 +4262,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle 
*trans,
 
        if (type & BTRFS_BLOCK_GROUP_DATA) {
                max_stripe_size = 1024 * 1024 * 1024;
-               max_chunk_size = 10 * max_stripe_size;
+               max_logical_size = 10 * max_stripe_size;
                if (!devs_max)
                        devs_max = BTRFS_MAX_DEVS(info->chunk_root);
        } else if (type & BTRFS_BLOCK_GROUP_METADATA) {
@@ -4269,12 +4271,12 @@ static int __btrfs_alloc_chunk(struct 
btrfs_trans_handle *trans,
                        max_stripe_size = 1024 * 1024 * 1024;
                else
                        max_stripe_size = 256 * 1024 * 1024;
-               max_chunk_size = max_stripe_size;
+               max_logical_size = max_stripe_size;
                if (!devs_max)
                        devs_max = BTRFS_MAX_DEVS(info->chunk_root);
        } else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
                max_stripe_size = 32 * 1024 * 1024;
-               max_chunk_size = 2 * max_stripe_size;
+               max_logical_size = 2 * max_stripe_size;
                if (!devs_max)
                        devs_max = BTRFS_MAX_DEVS_SYS_CHUNK;
        } else {
@@ -4284,8 +4286,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle 
*trans,
        }
 
        /* we don't want a chunk larger than 10% of writeable space */
-       max_chunk_size = min(div_factor(fs_devices->total_rw_bytes, 1),
-                            max_chunk_size);
+       max_physical_size = div_factor(fs_devices->total_rw_bytes, 1);
 
        devices_info = kzalloc(sizeof(*devices_info) * fs_devices->rw_devices,
                               GFP_NOFS);
@@ -4391,15 +4392,21 @@ static int __btrfs_alloc_chunk(struct 
btrfs_trans_handle *trans,
                data_stripes = num_stripes - 2;
        }
 
-       /*
-        * Use the number of data stripes to figure out how big this chunk
-        * is really going to be in terms of logical address space,
-        * and compare that answer with the max chunk size
-        */
-       if (stripe_size * data_stripes > max_chunk_size) {
-               u64 mask = (1ULL << 24) - 1;
-               stripe_size = max_chunk_size;
+       /* Restrict on-disk chunk size */
+       if (stripe_size * num_stripes > max_physical_size) {
+               stripe_size = max_physical_size;
+               do_div(stripe_size, num_stripes);
+               need_bump = 1;
+       }
+       /* restrict logical chunk size  */
+       if (stripe_size * data_stripes > max_logical_size) {
+               stripe_size = max_logical_size;
                do_div(stripe_size, data_stripes);
+               need_bump = 1;
+       }
+
+       if (need_bump) {
+               u64 mask = (1ULL << 24) - 1;
 
                /* bump the answer up to a 16MB boundary */
                stripe_size = (stripe_size + mask) & ~mask;
@@ -4411,6 +4418,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle 
*trans,
                        stripe_size = devices_info[ndevs-1].max_avail;
        }
 
+       /*
+        * Special handle for DUP, since stripe_size is the largest free extent
+        * we found, DUP can only use half of it. Other profile's dev_stripes
+        * is always 1.
+        */
        do_div(stripe_size, dev_stripes);
 
        /* align to BTRFS_STRIPE_LEN */
-- 
2.2.1

--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to