UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drbd: prepare for new striped layout of activity log 

Introduce two new on-disk meta data fields: al_stripes and al_stripe_size_4k
The intended use case is activity log on RAID 0 or similar.
Logically consecutive transactions will advance their on-disk position
by al_stripe_size_4k 4kB (transaction sized) blocks.

Right now, these are still asserted to be the backward compatible
values al_stripes = 1, al_stripe_size_4k = 8 (which amounts to 32kB).

Also introduce a caching member for meta_dev_idx in the in-core
structure: even though it is initially passed in in the rcu-protected
disk_conf structure, it cannot change without a detach/attach cycle.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Lars Ellenberg 2013-03-19 18:16:44 +01:00 committed by Jens Axboe
parent ae8bf312e9
commit 3a4d4eb3cb
4 changed files with 95 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
drivers/block/drbd/drbd_actlog.c
View File

@ -353,11 +353,11 @@ static unsigned int rs_extent_to_bm_page(unsigned int rs_enr)
static sector_t al_tr_number_to_on_disk_sector(struct drbd_conf *mdev)
{
const unsigned int stripes = 1;
const unsigned int stripe_size_4kB = MD_32kB_SECT/MD_4kB_SECT;
const unsigned int stripes = mdev->ldev->md.al_stripes;
const unsigned int stripe_size_4kB = mdev->ldev->md.al_stripe_size_4k;
/* transaction number, modulo on-disk ring buffer wrap around */
unsigned int t = mdev->al_tr_number % (stripe_size_4kB * stripes);
unsigned int t = mdev->al_tr_number % (mdev->ldev->md.al_size_4k);
/* ... to aligned 4k on disk block */
t = ((t % stripes) * stripe_size_4kB) + t/stripes;

48
drivers/block/drbd/drbd_int.h
View File

@ -755,6 +755,14 @@ struct drbd_md {
s32 al_offset; /* signed relative sector offset to activity log */
s32 bm_offset; /* signed relative sector offset to bitmap */
/* cached value of bdev->disk_conf->meta_dev_idx (see below) */
s32 meta_dev_idx;
/* see al_tr_number_to_on_disk_sector() */
u32 al_stripes;
u32 al_stripe_size_4k;
u32 al_size_4k; /* cached product of the above */
};
struct drbd_backing_dev {
@ -1862,38 +1870,24 @@ static inline sector_t drbd_get_max_capacity(struct drbd_backing_dev *bdev)
}
/**
* drbd_md_ss__() - Return the sector number of our meta data super block
* @mdev: DRBD device.
* drbd_md_ss() - Return the sector number of our meta data super block
* @bdev: Meta data block device.
*/
static inline sector_t drbd_md_ss__(struct drbd_conf *mdev,
struct drbd_backing_dev *bdev)
static inline sector_t drbd_md_ss(struct drbd_backing_dev *bdev)
{
int meta_dev_idx;
const int meta_dev_idx = bdev->md.meta_dev_idx;
rcu_read_lock();
meta_dev_idx = rcu_dereference(bdev->disk_conf)->meta_dev_idx;
rcu_read_unlock();
switch (meta_dev_idx) {
default: /* external, some index; this is the old fixed size layout */
return MD_128MB_SECT * meta_dev_idx;
case DRBD_MD_INDEX_INTERNAL:
/* with drbd08, internal meta data is always "flexible" */
case DRBD_MD_INDEX_FLEX_INT:
if (!bdev->backing_bdev) {
if (__ratelimit(&drbd_ratelimit_state)) {
dev_err(DEV, "bdev->backing_bdev==NULL\n");
dump_stack();
}
return 0;
}
/* sizeof(struct md_on_disk_07) == 4k
* position: last 4k aligned block of 4k size */
return (drbd_get_capacity(bdev->backing_bdev) & ~7ULL) - 8;
case DRBD_MD_INDEX_FLEX_EXT:
if (meta_dev_idx == DRBD_MD_INDEX_FLEX_EXT)
return 0;
}
/* Since drbd08, internal meta data is always "flexible".
* position: last 4k aligned block of 4k size */
if (meta_dev_idx == DRBD_MD_INDEX_INTERNAL ||
meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)
return (drbd_get_capacity(bdev->backing_bdev) & ~7ULL) - 8;
/* external, some index; this is the old fixed size layout */
return MD_128MB_SECT * bdev->md.meta_dev_idx;
}
static inline void

77
drivers/block/drbd/drbd_main.c
View File

@ -2850,7 +2850,11 @@ struct meta_data_on_disk {
u32 bm_bytes_per_bit; /* BM_BLOCK_SIZE */
u32 la_peer_max_bio_size; /* last peer max_bio_size */
u8 reserved_u8[4096 - (7*8 + 8*4)];
/* see al_tr_number_to_on_disk_sector() */
u32 al_stripes;
u32 al_stripe_size_4k;
u8 reserved_u8[4096 - (7*8 + 10*4)];
} __packed;
/**
@ -2898,7 +2902,10 @@ void drbd_md_sync(struct drbd_conf *mdev)
buffer->bm_offset = cpu_to_be32(mdev->ldev->md.bm_offset);
buffer->la_peer_max_bio_size = cpu_to_be32(mdev->peer_max_bio_size);
D_ASSERT(drbd_md_ss__(mdev, mdev->ldev) == mdev->ldev->md.md_offset);
buffer->al_stripes = cpu_to_be32(mdev->ldev->md.al_stripes);
buffer->al_stripe_size_4k = cpu_to_be32(mdev->ldev->md.al_stripe_size_4k);
D_ASSERT(drbd_md_ss(mdev->ldev) == mdev->ldev->md.md_offset);
sector = mdev->ldev->md.md_offset;
if (drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
@ -2916,13 +2923,60 @@ out:
put_ldev(mdev);
}
static int check_activity_log_stripe_size(struct drbd_conf *mdev,
struct meta_data_on_disk *on_disk,
struct drbd_md *in_core)
{
u32 al_stripes = be32_to_cpu(on_disk->al_stripes);
u32 al_stripe_size_4k = be32_to_cpu(on_disk->al_stripe_size_4k);
u64 al_size_4k;
/* both not set: default to old fixed size activity log */
if (al_stripes == 0 && al_stripe_size_4k == 0) {
al_stripes = 1;
al_stripe_size_4k = MD_32kB_SECT/8;
}
/* some paranoia plausibility checks */
/* we need both values to be set */
if (al_stripes == 0 || al_stripe_size_4k == 0)
goto err;
al_size_4k = (u64)al_stripes * al_stripe_size_4k;
/* Upper limit of activity log area, to avoid potential overflow
* problems in al_tr_number_to_on_disk_sector(). As right now, more
* than 72 * 4k blocks total only increases the amount of history,
* limiting this arbitrarily to 16 GB is not a real limitation ;-) */
if (al_size_4k > (16 * 1024 * 1024/4))
goto err;
/* Lower limit: we need at least 8 transaction slots (32kB)
* to not break existing setups */
if (al_size_4k < MD_32kB_SECT/8)
goto err;
in_core->al_stripe_size_4k = al_stripe_size_4k;
in_core->al_stripes = al_stripes;
in_core->al_size_4k = al_size_4k;
return 0;
err:
dev_err(DEV, "invalid activity log striping: al_stripes=%u, al_stripe_size_4k=%u\n",
al_stripes, al_stripe_size_4k);
return -EINVAL;
}
/**
* drbd_md_read() - Reads in the meta data super block
* @mdev: DRBD device.
* @bdev: Device from which the meta data should be read in.
*
* Return 0 (NO_ERROR) on success, and an enum drbd_ret_code in case
* Return NO_ERROR on success, and an enum drbd_ret_code in case
* something goes wrong.
*
* Called exactly once during drbd_adm_attach()
*/
int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
{
@ -2937,6 +2991,10 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
if (!buffer)
goto out;
/* First, figure out where our meta data superblock is located. */
bdev->md.meta_dev_idx = bdev->disk_conf->meta_dev_idx;
bdev->md.md_offset = drbd_md_ss(bdev);
if (drbd_md_sync_page_io(mdev, bdev, bdev->md.md_offset, READ)) {
/* NOTE: can't do normal error processing here as this is
called BEFORE disk is attached */
@ -2954,40 +3012,43 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
rv = ERR_MD_UNCLEAN;
goto err;
}
rv = ERR_MD_INVALID;
if (magic != DRBD_MD_MAGIC_08) {
if (magic == DRBD_MD_MAGIC_07)
dev_err(DEV, "Found old (0.7) meta data magic. Did you \"drbdadm create-md\"?\n");
else
dev_err(DEV, "Meta data magic not found. Did you \"drbdadm create-md\"?\n");
rv = ERR_MD_INVALID;
goto err;
}
if (check_activity_log_stripe_size(mdev, buffer, &bdev->md))
goto err;
if (be32_to_cpu(buffer->al_offset) != bdev->md.al_offset) {
dev_err(DEV, "unexpected al_offset: %d (expected %d)\n",
be32_to_cpu(buffer->al_offset), bdev->md.al_offset);
rv = ERR_MD_INVALID;
goto err;
}
if (be32_to_cpu(buffer->bm_offset) != bdev->md.bm_offset) {
dev_err(DEV, "unexpected bm_offset: %d (expected %d)\n",
be32_to_cpu(buffer->bm_offset), bdev->md.bm_offset);
rv = ERR_MD_INVALID;
goto err;
}
if (be32_to_cpu(buffer->md_size_sect) != bdev->md.md_size_sect) {
dev_err(DEV, "unexpected md_size: %u (expected %u)\n",
be32_to_cpu(buffer->md_size_sect), bdev->md.md_size_sect);
rv = ERR_MD_INVALID;
goto err;
}
if (be32_to_cpu(buffer->bm_bytes_per_bit) != BM_BLOCK_SIZE) {
dev_err(DEV, "unexpected bm_bytes_per_bit: %u (expected %u)\n",
be32_to_cpu(buffer->bm_bytes_per_bit), BM_BLOCK_SIZE);
rv = ERR_MD_INVALID;
goto err;
}
rv = NO_ERROR;
bdev->md.la_size_sect = be64_to_cpu(buffer->la_size);
for (i = UI_CURRENT; i < UI_SIZE; i++)
bdev->md.uuid[i] = be64_to_cpu(buffer->uuid[i]);

5
drivers/block/drbd/drbd_nl.c
View File

@ -727,24 +727,23 @@ static void drbd_md_set_sector_offsets(struct drbd_conf *mdev,
rcu_read_lock();
meta_dev_idx = rcu_dereference(bdev->disk_conf)->meta_dev_idx;
bdev->md.md_offset = drbd_md_ss(bdev);
switch (meta_dev_idx) {
default:
/* v07 style fixed size indexed meta data */
bdev->md.md_size_sect = MD_128MB_SECT;
bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
bdev->md.al_offset = MD_4kB_SECT;
bdev->md.bm_offset = MD_4kB_SECT + al_size_sect;
break;
case DRBD_MD_INDEX_FLEX_EXT:
/* just occupy the full device; unit: sectors */
bdev->md.md_size_sect = drbd_get_capacity(bdev->md_bdev);
bdev->md.md_offset = 0;
bdev->md.al_offset = MD_4kB_SECT;
bdev->md.bm_offset = MD_4kB_SECT + al_size_sect;
break;
case DRBD_MD_INDEX_INTERNAL:
case DRBD_MD_INDEX_FLEX_INT:
bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
/* al size is still fixed */
bdev->md.al_offset = -al_size_sect;
/* we need (slightly less than) ~ this much bitmap sectors: */