btrfs-progs: move min-resize implementation to inspect-internal

Signed-off-by: David Sterba <dsterba@suse.com>
This commit is contained in:
David Sterba 2015-07-20 17:29:24 +02:00
parent a57606e815
commit 934dd0e1f7
2 changed files with 242 additions and 254 deletions

View file

@ -1271,264 +1271,14 @@ static int cmd_defrag(int argc, char **argv)
}
static const char * const cmd_resize_usage[] = {
"btrfs filesystem resize [devid:][+/-]<newsize>[kKmMgGtTpPeE]|[devid:]max|[devid:]get_min_size <path>",
"btrfs filesystem resize [devid:][+/-]<newsize>[kKmMgGtTpPeE]|[devid:]max <path>",
"Resize a filesystem",
"If 'max' is passed, the filesystem will occupy all available space",
"on the device 'devid'.",
"If 'get_min_size' is passed, return the minimum size the device can",
"be shrunk to.",
"[kK] means KiB, which denotes 1KiB = 1024B, 1MiB = 1024KiB, etc.",
NULL
};
struct dev_extent_elem {
u64 start;
/* inclusive end */
u64 end;
struct list_head list;
};
static int add_dev_extent(struct list_head *list,
const u64 start, const u64 end,
const int append)
{
struct dev_extent_elem *e;
e = malloc(sizeof(*e));
if (!e)
return -ENOMEM;
e->start = start;
e->end = end;
if (append)
list_add_tail(&e->list, list);
else
list_add(&e->list, list);
return 0;
}
static void free_dev_extent_list(struct list_head *list)
{
while (!list_empty(list)) {
struct dev_extent_elem *e;
e = list_first_entry(list, struct dev_extent_elem, list);
list_del(&e->list);
free(e);
}
}
static int hole_includes_sb_mirror(const u64 start, const u64 end)
{
int i;
int ret = 0;
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
u64 bytenr = btrfs_sb_offset(i);
if (bytenr >= start && bytenr <= end) {
ret = 1;
break;
}
}
return ret;
}
static void adjust_dev_min_size(struct list_head *extents,
struct list_head *holes,
u64 *min_size)
{
/*
* If relocation of the block group of a device extent must happen (see
* below) scratch space is used for the relocation. So track here the
* size of the largest device extent that has to be relocated. We track
* only the largest and not the sum of the sizes of all relocated block
* groups because after each block group is relocated the running
* transaction is committed so that pinned space is released.
*/
u64 scratch_space = 0;
/*
* List of device extents is sorted by descending order of the extent's
* end offset. If some extent goes beyond the computed minimum size,
* which initially matches the sum of the lenghts of all extents,
* we need to check if the extent can be relocated to an hole in the
* device between [0, *min_size[ (which is what the resize ioctl does).
*/
while (!list_empty(extents)) {
struct dev_extent_elem *e;
struct dev_extent_elem *h;
int found = 0;
u64 extent_len;
u64 hole_len = 0;
e = list_first_entry(extents, struct dev_extent_elem, list);
if (e->end <= *min_size)
break;
/*
* Our extent goes beyond the computed *min_size. See if we can
* find a hole large enough to relocate it to. If not we must stop
* and set *min_size to the end of the extent.
*/
extent_len = e->end - e->start + 1;
list_for_each_entry(h, holes, list) {
hole_len = h->end - h->start + 1;
if (hole_len >= extent_len) {
found = 1;
break;
}
}
if (!found) {
*min_size = e->end + 1;
break;
}
/*
* If the hole found contains the location for a superblock
* mirror, we are pessimistic and require allocating one
* more extent of the same size. This is because the block
* group could be in the worst case used by a single extent
* with a size >= (block_group.length - superblock.size).
*/
if (hole_includes_sb_mirror(h->start,
h->start + extent_len - 1))
*min_size += extent_len;
if (hole_len > extent_len) {
h->start += extent_len;
} else {
list_del(&h->list);
free(h);
}
list_del(&e->list);
free(e);
if (extent_len > scratch_space)
scratch_space = extent_len;
}
if (scratch_space) {
*min_size += scratch_space;
/*
* Chunk allocation requires inserting/updating items in the
* chunk tree, so often this can lead to the need of allocating
* a new system chunk too, which has a maximum size of 32Mb.
*/
*min_size += 32 * 1024 * 1024;
}
}
static int get_min_size(int fd, DIR *dirstream, const char *amount)
{
int ret = 1;
char *p = strstr(amount, ":");
u64 devid = 1;
/*
* Device allocations starts at 1Mb or at the value passed through the
* mount option alloc_start if it's bigger than 1Mb. The alloc_start
* option is used for debugging and testing only, and recently the
* possibility of deprecating/removing it has been discussed, so we
* ignore it here.
*/
u64 min_size = 1 * 1024 * 1024ull;
struct btrfs_ioctl_search_args args;
struct btrfs_ioctl_search_key *sk = &args.key;
u64 last_pos = (u64)-1;
LIST_HEAD(extents);
LIST_HEAD(holes);
if (p && sscanf(amount, "%llu:get_min_size", &devid) != 1) {
fprintf(stderr, "Invalid parameter: %s\n", amount);
goto out;
}
memset(&args, 0, sizeof(args));
sk->tree_id = BTRFS_DEV_TREE_OBJECTID;
sk->min_objectid = devid;
sk->max_objectid = devid;
sk->max_type = BTRFS_DEV_EXTENT_KEY;
sk->min_type = BTRFS_DEV_EXTENT_KEY;
sk->min_offset = 0;
sk->max_offset = (u64)-1;
sk->min_transid = 0;
sk->max_transid = (u64)-1;
sk->nr_items = 4096;
while (1) {
int i;
struct btrfs_ioctl_search_header *sh;
unsigned long off = 0;
ret = ioctl(fd, BTRFS_IOC_TREE_SEARCH, &args);
if (ret < 0) {
fprintf(stderr,
"Error invoking tree search ioctl: %s\n",
strerror(errno));
ret = 1;
goto out;
}
if (sk->nr_items == 0)
break;
for (i = 0; i < sk->nr_items; i++) {
struct btrfs_dev_extent *extent;
u64 len;
sh = (struct btrfs_ioctl_search_header *)(args.buf +
off);
off += sizeof(*sh);
extent = (struct btrfs_dev_extent *)(args.buf + off);
off += sh->len;
sk->min_objectid = sh->objectid;
sk->min_type = sh->type;
sk->min_offset = sh->offset + 1;
if (sh->objectid != devid ||
sh->type != BTRFS_DEV_EXTENT_KEY)
continue;
len = btrfs_stack_dev_extent_length(extent);
min_size += len;
ret = add_dev_extent(&extents, sh->offset,
sh->offset + len - 1, 0);
if (!ret && last_pos != (u64)-1 &&
last_pos != sh->offset)
ret = add_dev_extent(&holes, last_pos,
sh->offset - 1, 1);
if (ret) {
fprintf(stderr, "Error: %s\n", strerror(-ret));
ret = 1;
goto out;
}
last_pos = sh->offset + len;
}
if (sk->min_type != BTRFS_DEV_EXTENT_KEY ||
sk->min_objectid != devid)
break;
}
adjust_dev_min_size(&extents, &holes, &min_size);
printf("%llu bytes (%s)\n", min_size, pretty_size(min_size));
ret = 0;
out:
close_file_or_dir(fd, dirstream);
free_dev_extent_list(&extents);
free_dev_extent_list(&holes);
return ret;
}
static int cmd_resize(int argc, char **argv)
{
struct btrfs_ioctl_vol_args args;
@ -1570,9 +1320,6 @@ static int cmd_resize(int argc, char **argv)
return 1;
}
if (strstr(amount, "get_min_size"))
return get_min_size(fd, dirstream, amount);
printf("Resize '%s' of '%s'\n", path, amount);
memset(&args, 0, sizeof(args));
strncpy_null(args.name, amount);

View file

@ -338,6 +338,247 @@ out:
return !!ret;
}
struct dev_extent_elem {
u64 start;
/* inclusive end */
u64 end;
struct list_head list;
};
static int add_dev_extent(struct list_head *list,
const u64 start, const u64 end,
const int append)
{
struct dev_extent_elem *e;
e = malloc(sizeof(*e));
if (!e)
return -ENOMEM;
e->start = start;
e->end = end;
if (append)
list_add_tail(&e->list, list);
else
list_add(&e->list, list);
return 0;
}
static void free_dev_extent_list(struct list_head *list)
{
while (!list_empty(list)) {
struct dev_extent_elem *e;
e = list_first_entry(list, struct dev_extent_elem, list);
list_del(&e->list);
free(e);
}
}
static int hole_includes_sb_mirror(const u64 start, const u64 end)
{
int i;
int ret = 0;
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
u64 bytenr = btrfs_sb_offset(i);
if (bytenr >= start && bytenr <= end) {
ret = 1;
break;
}
}
return ret;
}
static void adjust_dev_min_size(struct list_head *extents,
struct list_head *holes,
u64 *min_size)
{
/*
* If relocation of the block group of a device extent must happen (see
* below) scratch space is used for the relocation. So track here the
* size of the largest device extent that has to be relocated. We track
* only the largest and not the sum of the sizes of all relocated block
* groups because after each block group is relocated the running
* transaction is committed so that pinned space is released.
*/
u64 scratch_space = 0;
/*
* List of device extents is sorted by descending order of the extent's
* end offset. If some extent goes beyond the computed minimum size,
* which initially matches the sum of the lenghts of all extents,
* we need to check if the extent can be relocated to an hole in the
* device between [0, *min_size[ (which is what the resize ioctl does).
*/
while (!list_empty(extents)) {
struct dev_extent_elem *e;
struct dev_extent_elem *h;
int found = 0;
u64 extent_len;
u64 hole_len = 0;
e = list_first_entry(extents, struct dev_extent_elem, list);
if (e->end <= *min_size)
break;
/*
* Our extent goes beyond the computed *min_size. See if we can
* find a hole large enough to relocate it to. If not we must stop
* and set *min_size to the end of the extent.
*/
extent_len = e->end - e->start + 1;
list_for_each_entry(h, holes, list) {
hole_len = h->end - h->start + 1;
if (hole_len >= extent_len) {
found = 1;
break;
}
}
if (!found) {
*min_size = e->end + 1;
break;
}
/*
* If the hole found contains the location for a superblock
* mirror, we are pessimistic and require allocating one
* more extent of the same size. This is because the block
* group could be in the worst case used by a single extent
* with a size >= (block_group.length - superblock.size).
*/
if (hole_includes_sb_mirror(h->start,
h->start + extent_len - 1))
*min_size += extent_len;
if (hole_len > extent_len) {
h->start += extent_len;
} else {
list_del(&h->list);
free(h);
}
list_del(&e->list);
free(e);
if (extent_len > scratch_space)
scratch_space = extent_len;
}
if (scratch_space) {
*min_size += scratch_space;
/*
* Chunk allocation requires inserting/updating items in the
* chunk tree, so often this can lead to the need of allocating
* a new system chunk too, which has a maximum size of 32Mb.
*/
*min_size += 32 * 1024 * 1024;
}
}
static int get_min_size(int fd, DIR *dirstream, u64 devid)
{
int ret = 1;
/*
* Device allocations starts at 1Mb or at the value passed through the
* mount option alloc_start if it's bigger than 1Mb. The alloc_start
* option is used for debugging and testing only, and recently the
* possibility of deprecating/removing it has been discussed, so we
* ignore it here.
*/
u64 min_size = 1 * 1024 * 1024ull;
struct btrfs_ioctl_search_args args;
struct btrfs_ioctl_search_key *sk = &args.key;
u64 last_pos = (u64)-1;
LIST_HEAD(extents);
LIST_HEAD(holes);
memset(&args, 0, sizeof(args));
sk->tree_id = BTRFS_DEV_TREE_OBJECTID;
sk->min_objectid = devid;
sk->max_objectid = devid;
sk->max_type = BTRFS_DEV_EXTENT_KEY;
sk->min_type = BTRFS_DEV_EXTENT_KEY;
sk->min_offset = 0;
sk->max_offset = (u64)-1;
sk->min_transid = 0;
sk->max_transid = (u64)-1;
sk->nr_items = 4096;
while (1) {
int i;
struct btrfs_ioctl_search_header *sh;
unsigned long off = 0;
ret = ioctl(fd, BTRFS_IOC_TREE_SEARCH, &args);
if (ret < 0) {
fprintf(stderr,
"Error invoking tree search ioctl: %s\n",
strerror(errno));
ret = 1;
goto out;
}
if (sk->nr_items == 0)
break;
for (i = 0; i < sk->nr_items; i++) {
struct btrfs_dev_extent *extent;
u64 len;
sh = (struct btrfs_ioctl_search_header *)(args.buf +
off);
off += sizeof(*sh);
extent = (struct btrfs_dev_extent *)(args.buf + off);
off += sh->len;
sk->min_objectid = sh->objectid;
sk->min_type = sh->type;
sk->min_offset = sh->offset + 1;
if (sh->objectid != devid ||
sh->type != BTRFS_DEV_EXTENT_KEY)
continue;
len = btrfs_stack_dev_extent_length(extent);
min_size += len;
ret = add_dev_extent(&extents, sh->offset,
sh->offset + len - 1, 0);
if (!ret && last_pos != (u64)-1 &&
last_pos != sh->offset)
ret = add_dev_extent(&holes, last_pos,
sh->offset - 1, 1);
if (ret) {
fprintf(stderr, "Error: %s\n", strerror(-ret));
ret = 1;
goto out;
}
last_pos = sh->offset + len;
}
if (sk->min_type != BTRFS_DEV_EXTENT_KEY ||
sk->min_objectid != devid)
break;
}
adjust_dev_min_size(&extents, &holes, &min_size);
printf("%llu bytes (%s)\n", min_size, pretty_size(min_size));
ret = 0;
out:
close_file_or_dir(fd, dirstream);
free_dev_extent_list(&extents);
free_dev_extent_list(&holes);
return ret;
}
static const char inspect_cmd_group_info[] =
"query various internal information";