btrfsprogs/0061-btrfs-progs-calculate-available-blocks-on-device-pro.patch
Tomáš Chvátal 5be20c4ea7 Accepting request 205320 from home:dsterba:branches:filesystems
SR: a few fixes, aimed for 13.1 RC2

- fsck updates
- more mkfs sanity checks
- qgroup rescan wait

OBS-URL: https://build.opensuse.org/request/show/205320
OBS-URL: https://build.opensuse.org/package/show/filesystems/btrfsprogs?expand=0&rev=144
2013-10-31 09:12:04 +00:00

234 lines
7.5 KiB
Diff

From db3c0b4f365acb5ee9fa7e37d440b2ef6ff5636c Mon Sep 17 00:00:00 2001
From: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Date: Thu, 5 Sep 2013 15:57:19 +0900
Subject: [PATCH 61/62] btrfs-progs: calculate available blocks on device
properly
I found that mkfs.btrfs aborts when assigned multi volumes contain
a small volume:
# parted /dev/sdf p
Model: LSI MegaRAID SAS RMB (scsi)
Disk /dev/sdf: 72.8GB
Sector size (logical/physical): 512B/512B
Partition Table: msdos
Number Start End Size Type File system Flags
1 32.3kB 72.4GB 72.4GB primary
2 72.4GB 72.8GB 461MB primary
# ./mkfs.btrfs -f /dev/sdf1 /dev/sdf2
:
SMALL VOLUME: forcing mixed metadata/data groups
adding device /dev/sdf2 id 2
mkfs.btrfs: volumes.c:852: btrfs_alloc_chunk: Assertion `!(ret)' failed.
Aborted (core dumped)
This failure of btrfs_alloc_chunk was caused by following steps:
1) since there is only small space in the small device, mkfs was
going to allocate a chunk from free space as much as available.
So mkfs called btrfs_alloc_chunk with
size = device->total_bytes - device->used_bytes.
2) (According to the comment in source code, to avoid overwriting
superblock,) btrfs_alloc_chunk starts taking chunks at an offset
of 1MB. It means that the layout of a disk will be like:
[[1MB at beginning for sb][allocated chunks]* ... free space ... ]
and you can see that the available free space for allocation is:
avail = device->total_bytes - device->used_bytes - 1MB.
3) Therefore there is only free space 1MB less than requested. damn.
>From further investigations I also found that this issue is easily
reproduced by using -A, --alloc-start option:
# truncate --size=1G testfile
# ./mkfs.btrfs -A900M -f testfile
:
mkfs.btrfs: volumes.c:852: btrfs_alloc_chunk: Assertion `!(ret)' failed.
Aborted (core dumped)
In this case there is only 100MB for allocation but btrfs_alloc_chunk
was going to allocate more than the 100MB.
The root cause of both of above troubles is a same simple bug:
btrfs_chunk_alloc does not calculate available bytes properly even
though it researches how many devices have enough room to have a
chunk to be allocated.
So this patch introduces new function btrfs_device_avail_bytes()
which returns available bytes for allocation in specified device.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
---
ctree.h | 8 +++++
volumes.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
2 files changed, 106 insertions(+), 6 deletions(-)
diff --git a/ctree.h b/ctree.h
index 0b0d701fe679..90be7abe9ebf 100644
--- a/ctree.h
+++ b/ctree.h
@@ -811,6 +811,14 @@ struct btrfs_csum_item {
u8 csum;
} __attribute__ ((__packed__));
+/*
+ * We don't want to overwrite 1M at the beginning of device, even though
+ * there is our 1st superblock at 64k. Some possible reasons:
+ * - the first 64k blank is useful for some boot loader/manager
+ * - the first 1M could be scratched by buggy partitioner or somesuch
+ */
+#define BTRFS_BLOCK_RESERVED_1M_FOR_SUPER ((u64)1024 * 1024)
+
/* tag for the radix tree of block groups in ram */
#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0)
#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1)
diff --git a/volumes.c b/volumes.c
index 0ff22833d6be..e8d7f258dddb 100644
--- a/volumes.c
+++ b/volumes.c
@@ -268,7 +268,7 @@ static int find_free_dev_extent(struct btrfs_trans_handle *trans,
struct btrfs_dev_extent *dev_extent = NULL;
u64 hole_size = 0;
u64 last_byte = 0;
- u64 search_start = 0;
+ u64 search_start = root->fs_info->alloc_start;
u64 search_end = device->total_bytes;
int ret;
int slot = 0;
@@ -283,10 +283,12 @@ static int find_free_dev_extent(struct btrfs_trans_handle *trans,
/* we don't want to overwrite the superblock on the drive,
* so we make sure to start at an offset of at least 1MB
*/
- search_start = max((u64)1024 * 1024, search_start);
+ search_start = max(BTRFS_BLOCK_RESERVED_1M_FOR_SUPER, search_start);
- if (root->fs_info->alloc_start + num_bytes <= device->total_bytes)
- search_start = max(root->fs_info->alloc_start, search_start);
+ if (search_start >= search_end) {
+ ret = -ENOSPC;
+ goto error;
+ }
key.objectid = device->devid;
key.offset = search_start;
@@ -660,6 +662,94 @@ static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target)
return 64 * 1024;
}
+/*
+ * btrfs_device_avail_bytes - count bytes available for alloc_chunk
+ *
+ * It is not equal to "device->total_bytes - device->bytes_used".
+ * We do not allocate any chunk in 1M at beginning of device, and not
+ * allowed to allocate any chunk before alloc_start if it is specified.
+ * So search holes from max(1M, alloc_start) to device->total_bytes.
+ */
+static int btrfs_device_avail_bytes(struct btrfs_trans_handle *trans,
+ struct btrfs_device *device,
+ u64 *avail_bytes)
+{
+ struct btrfs_path *path;
+ struct btrfs_root *root = device->dev_root;
+ struct btrfs_key key;
+ struct btrfs_dev_extent *dev_extent = NULL;
+ struct extent_buffer *l;
+ u64 search_start = root->fs_info->alloc_start;
+ u64 search_end = device->total_bytes;
+ u64 extent_end = 0;
+ u64 free_bytes = 0;
+ int ret;
+ int slot = 0;
+
+ search_start = max(BTRFS_BLOCK_RESERVED_1M_FOR_SUPER, search_start);
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ key.objectid = device->devid;
+ key.offset = root->fs_info->alloc_start;
+ key.type = BTRFS_DEV_EXTENT_KEY;
+
+ path->reada = 2;
+ ret = btrfs_search_slot(trans, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto error;
+ ret = btrfs_previous_item(root, path, 0, key.type);
+ if (ret < 0)
+ goto error;
+
+ while (1) {
+ l = path->nodes[0];
+ slot = path->slots[0];
+ if (slot >= btrfs_header_nritems(l)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret == 0)
+ continue;
+ if (ret < 0)
+ goto error;
+ break;
+ }
+ btrfs_item_key_to_cpu(l, &key, slot);
+
+ if (key.objectid < device->devid)
+ goto next;
+ if (key.objectid > device->devid)
+ break;
+ if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
+ goto next;
+ if (key.offset > search_end)
+ break;
+ if (key.offset > search_start)
+ free_bytes += key.offset - search_start;
+
+ dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
+ extent_end = key.offset + btrfs_dev_extent_length(l,
+ dev_extent);
+ if (extent_end > search_start)
+ search_start = extent_end;
+ if (search_start > search_end)
+ break;
+next:
+ path->slots[0]++;
+ cond_resched();
+ }
+
+ if (search_start < search_end)
+ free_bytes += search_end - search_start;
+
+ *avail_bytes = free_bytes;
+ ret = 0;
+error:
+ btrfs_free_path(path);
+ return ret;
+}
+
int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
struct btrfs_root *extent_root, u64 *start,
u64 *num_bytes, u64 type)
@@ -678,7 +768,7 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
u64 calc_size = 8 * 1024 * 1024;
u64 min_free;
u64 max_chunk_size = 4 * calc_size;
- u64 avail;
+ u64 avail = 0;
u64 max_avail = 0;
u64 percent_max;
int num_stripes = 1;
@@ -782,7 +872,9 @@ again:
/* build a private list of devices we will allocate from */
while(index < num_stripes) {
device = list_entry(cur, struct btrfs_device, dev_list);
- avail = device->total_bytes - device->bytes_used;
+ ret = btrfs_device_avail_bytes(trans, device, &avail);
+ if (ret)
+ return ret;
cur = cur->next;
if (avail >= min_free) {
list_move_tail(&device->dev_list, &private_devs);
--
1.8.3.1