struct drbd_backing_dev *bdev)
{
sector_t md_size_sect = 0;
- unsigned int al_size_sect = MD_32kB_SECT;
- int meta_dev_idx;
+ unsigned int al_size_sect = bdev->md.al_size_4k * 8;
- 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) {
+ switch (bdev->md.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: */
bdev->md.bm_offset = -md_size_sect + MD_4kB_SECT;
break;
}
- rcu_read_unlock();
}
/* input size is expected to be in KB */
enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds_flags flags) __must_hold(local)
{
sector_t prev_first_sect, prev_size; /* previous meta location */
- sector_t la_size, u_size;
+ sector_t la_size_sect, u_size;
sector_t size;
char ppb[10];
prev_first_sect = drbd_md_first_sector(mdev->ldev);
prev_size = mdev->ldev->md.md_size_sect;
- la_size = mdev->ldev->md.la_size_sect;
+ la_size_sect = mdev->ldev->md.la_size_sect;
/* TODO: should only be some assert here, not (re)init... */
drbd_md_set_sector_offsets(mdev, mdev->ldev);
if (rv == dev_size_error)
goto out;
- la_size_changed = (la_size != mdev->ldev->md.la_size_sect);
+ la_size_changed = (la_size_sect != mdev->ldev->md.la_size_sect);
md_moved = prev_first_sect != drbd_md_first_sector(mdev->ldev)
|| prev_size != mdev->ldev->md.md_size_sect;
drbd_md_mark_dirty(mdev);
}
- if (size > la_size)
+ if (size > la_size_sect)
rv = grew;
- if (size < la_size)
+ if (size < la_size_sect)
rv = shrunk;
out:
lc_unlock(mdev->act_log);
sector_t u_size, int assume_peer_has_space)
{
sector_t p_size = mdev->p_size; /* partner's disk size. */
- sector_t la_size = bdev->md.la_size_sect; /* last agreed size. */
+ sector_t la_size_sect = bdev->md.la_size_sect; /* last agreed size. */
sector_t m_size; /* my size */
sector_t size = 0;
if (p_size && m_size) {
size = min_t(sector_t, p_size, m_size);
} else {
- if (la_size) {
- size = la_size;
+ if (la_size_sect) {
+ size = la_size_sect;
if (m_size && m_size < size)
size = m_size;
if (p_size && p_size < size)
return 0 != (flags & DRBD_GENL_F_SET_DEFAULTS);
}
-static void enforce_disk_conf_limits(struct disk_conf *dc)
+static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev)
{
- if (dc->al_extents < DRBD_AL_EXTENTS_MIN)
- dc->al_extents = DRBD_AL_EXTENTS_MIN;
- if (dc->al_extents > DRBD_AL_EXTENTS_MAX)
- dc->al_extents = DRBD_AL_EXTENTS_MAX;
+ /* This is limited by 16 bit "slot" numbers,
+ * and by available on-disk context storage.
+ *
+ * Also (u16)~0 is special (denotes a "free" extent).
+ *
+ * One transaction occupies one 4kB on-disk block,
+ * we have n such blocks in the on disk ring buffer,
+ * the "current" transaction may fail (n-1),
+ * and there is 919 slot numbers context information per transaction.
+ *
+ * 72 transaction blocks amounts to more than 2**16 context slots,
+ * so cap there first.
+ */
+ const unsigned int max_al_nr = DRBD_AL_EXTENTS_MAX;
+ const unsigned int sufficient_on_disk =
+ (max_al_nr + AL_CONTEXT_PER_TRANSACTION -1)
+ /AL_CONTEXT_PER_TRANSACTION;
- if (dc->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX)
- dc->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX;
+ unsigned int al_size_4k = bdev->md.al_size_4k;
+
+ if (al_size_4k > sufficient_on_disk)
+ return max_al_nr;
+
+ return (al_size_4k - 1) * AL_CONTEXT_PER_TRANSACTION;
}
int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
if (!expect(new_disk_conf->resync_rate >= 1))
new_disk_conf->resync_rate = 1;
- enforce_disk_conf_limits(new_disk_conf);
+ if (new_disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
+ new_disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
+ if (new_disk_conf->al_extents > drbd_al_extents_max(mdev->ldev))
+ new_disk_conf->al_extents = drbd_al_extents_max(mdev->ldev);
+
+ if (new_disk_conf->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX)
+ new_disk_conf->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX;
fifo_size = (new_disk_conf->c_plan_ahead * 10 * SLEEP_TIME) / HZ;
if (fifo_size != mdev->rs_plan_s->size) {
goto fail;
}
- enforce_disk_conf_limits(new_disk_conf);
+ if (new_disk_conf->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX)
+ new_disk_conf->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX;
new_plan = fifo_alloc((new_disk_conf->c_plan_ahead * 10 * SLEEP_TIME) / HZ);
if (!new_plan) {
goto fail;
}
+ write_lock_irq(&global_state_lock);
+ retcode = drbd_resync_after_valid(mdev, new_disk_conf->resync_after);
+ write_unlock_irq(&global_state_lock);
+ if (retcode != NO_ERROR)
+ goto fail;
+
rcu_read_lock();
nc = rcu_dereference(mdev->tconn->net_conf);
if (nc) {
goto fail;
}
- /* RT - for drbd_get_max_capacity() DRBD_MD_INDEX_FLEX_INT */
- drbd_md_set_sector_offsets(mdev, nbc);
+ /* Read our meta data super block early.
+ * This also sets other on-disk offsets. */
+ retcode = drbd_md_read(mdev, nbc);
+ if (retcode != NO_ERROR)
+ goto fail;
+
+ if (new_disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
+ new_disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
+ if (new_disk_conf->al_extents > drbd_al_extents_max(nbc))
+ new_disk_conf->al_extents = drbd_al_extents_max(nbc);
if (drbd_get_max_capacity(nbc) < new_disk_conf->disk_size) {
dev_err(DEV, "max capacity %llu smaller than disk size %llu\n",
if (!get_ldev_if_state(mdev, D_ATTACHING))
goto force_diskless;
- drbd_md_set_sector_offsets(mdev, nbc);
-
if (!mdev->bitmap) {
if (drbd_bm_init(mdev)) {
retcode = ERR_NOMEM;
}
}
- retcode = drbd_md_read(mdev, nbc);
- if (retcode != NO_ERROR)
- goto force_diskless_dec;
-
if (mdev->state.conn < C_CONNECTED &&
mdev->state.role == R_PRIMARY &&
(mdev->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) {
return SS_SUCCESS;
case SS_PRIMARY_NOP:
/* Our state checking code wants to see the peer outdated. */
- rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING,
- pdsk, D_OUTDATED), CS_VERBOSE);
+ rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING, pdsk, D_OUTDATED), 0);
+
+ if (rv == SS_OUTDATE_WO_CONN) /* lost connection before graceful disconnect succeeded */
+ rv = conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_VERBOSE);
+
break;
case SS_CW_FAILED_BY_PEER:
/* The peer probably wants to see us outdated. */
wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
drbd_flush_workqueue(mdev);
- retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T), CS_ORDERED);
-
- if (retcode < SS_SUCCESS && retcode != SS_NEED_CONNECTION)
- retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T));
-
- while (retcode == SS_NEED_CONNECTION) {
- spin_lock_irq(&mdev->tconn->req_lock);
- if (mdev->state.conn < C_CONNECTED)
- retcode = _drbd_set_state(_NS(mdev, disk, D_INCONSISTENT), CS_VERBOSE, NULL);
- spin_unlock_irq(&mdev->tconn->req_lock);
-
- if (retcode != SS_NEED_CONNECTION)
- break;
-
+ /* If we happen to be C_STANDALONE R_SECONDARY, just change to
+ * D_INCONSISTENT, and set all bits in the bitmap. Otherwise,
+ * try to start a resync handshake as sync target for full sync.
+ */
+ if (mdev->state.conn == C_STANDALONE && mdev->state.role == R_SECONDARY) {
+ retcode = drbd_request_state(mdev, NS(disk, D_INCONSISTENT));
+ if (retcode >= SS_SUCCESS) {
+ if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write,
+ "set_n_write from invalidate", BM_LOCKED_MASK))
+ retcode = ERR_IO_MD_DISK;
+ }
+ } else
retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T));
- }
drbd_resume_io(mdev);
out:
wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
drbd_flush_workqueue(mdev);
- retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S), CS_ORDERED);
- if (retcode < SS_SUCCESS) {
- if (retcode == SS_NEED_CONNECTION && mdev->state.role == R_PRIMARY) {
- /* The peer will get a resync upon connect anyways.
- * Just make that into a full resync. */
- retcode = drbd_request_state(mdev, NS(pdsk, D_INCONSISTENT));
- if (retcode >= SS_SUCCESS) {
- if (drbd_bitmap_io(mdev, &drbd_bmio_set_susp_al,
- "set_n_write from invalidate_peer",
- BM_LOCKED_SET_ALLOWED))
- retcode = ERR_IO_MD_DISK;
- }
- } else
- retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
- }
+ /* If we happen to be C_STANDALONE R_PRIMARY, just set all bits
+ * in the bitmap. Otherwise, try to start a resync handshake
+ * as sync source for full sync.
+ */
+ if (mdev->state.conn == C_STANDALONE && mdev->state.role == R_PRIMARY) {
+ /* The peer will get a resync upon connect anyways. Just make that
+ into a full resync. */
+ retcode = drbd_request_state(mdev, NS(pdsk, D_INCONSISTENT));
+ if (retcode >= SS_SUCCESS) {
+ if (drbd_bitmap_io(mdev, &drbd_bmio_set_susp_al,
+ "set_n_write from invalidate_peer",
+ BM_LOCKED_SET_ALLOWED))
+ retcode = ERR_IO_MD_DISK;
+ }
+ } else
+ retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
drbd_resume_io(mdev);
out:
CS_VERBOSE + CS_WAIT_COMPLETE);
idr_remove(&mdev->tconn->volumes, mdev->vnr);
idr_remove(&minors, mdev_to_minor(mdev));
+ destroy_workqueue(mdev->submit.wq);
del_gendisk(mdev->vdisk);
synchronize_rcu();
kref_put(&mdev->kref, &drbd_minor_destroy);
projects / ~andy / linux / blobdiff