path = ocfs2_new_path_from_et(&context->et); if (!path) {
ret = -ENOMEM;
mlog_errno(ret); goto out;
}
ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos); if (ret) {
mlog_errno(ret); goto out;
}
el = path_leaf_el(path);
index = ocfs2_search_extent_list(el, cpos); if (index == -1) {
ret = ocfs2_error(inode->i_sb, "Inode %llu has an extent at cpos %u which can no longer be found\n",
(unsignedlonglong)ino, cpos); goto out;
}
rec = &el->l_recs[index];
BUG_ON(ext_flags != rec->e_flags); /* * after moving/defraging to new location, the extent is not going * to be refcounted anymore.
*/
replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED;
ret = ocfs2_split_extent(handle, &context->et, path, index,
&replace_rec, context->meta_ac,
&context->dealloc); if (ret) {
mlog_errno(ret); goto out;
}
context->new_phys_cpos = new_p_cpos;
/* * need I to append truncate log for old clusters?
*/ if (old_blkno) { if (ext_flags & OCFS2_EXT_REFCOUNTED)
ret = ocfs2_decrease_refcount(inode, handle,
ocfs2_blocks_to_clusters(osb->sb,
old_blkno),
len, context->meta_ac,
&context->dealloc, 1); else
ret = ocfs2_truncate_log_append(osb, handle,
old_blkno, len);
}
/* * Using one journal handle to guarantee the data consistency in case * crash happens anywhere. * * XXX: defrag can end up with finishing partial extent as requested, * due to not enough contiguous clusters can be found in allocator.
*/ staticint ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
u32 cpos, u32 phys_cpos, u32 *len, int ext_flags)
{ int ret, credits = 0, extra_blocks = 0, partial = context->partial;
handle_t *handle; struct inode *inode = context->inode; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct inode *tl_inode = osb->osb_tl_inode; struct ocfs2_refcount_tree *ref_tree = NULL;
u32 new_phys_cpos, new_len;
u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos); int need_free = 0;
if ((ext_flags & OCFS2_EXT_REFCOUNTED) && *len) {
BUG_ON(!ocfs2_is_refcount_inode(inode));
BUG_ON(!context->refcount_loc);
ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
&ref_tree, NULL); if (ret) {
mlog_errno(ret); return ret;
}
ret = ocfs2_prepare_refcount_change_for_del(inode,
context->refcount_loc,
phys_blkno,
*len,
&credits,
&extra_blocks); if (ret) {
mlog_errno(ret); goto out;
}
}
ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
*len, 1,
&context->meta_ac,
extra_blocks, &credits); if (ret) {
mlog_errno(ret); goto out;
}
/* * should be using allocation reservation strategy there? * * if (context->data_ac) * context->data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
*/
inode_lock(tl_inode);
if (ocfs2_truncate_log_needs_flush(osb)) {
ret = __ocfs2_flush_truncate_log(osb); if (ret < 0) {
mlog_errno(ret); goto out_unlock_mutex;
}
}
/* * Make sure ocfs2_reserve_cluster is called after * __ocfs2_flush_truncate_log, otherwise, dead lock may happen. * * If ocfs2_reserve_cluster is called * before __ocfs2_flush_truncate_log, dead lock on global bitmap * may happen. *
*/
ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac); if (ret) {
mlog_errno(ret); goto out_unlock_mutex;
}
handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
mlog_errno(ret); goto out_unlock_mutex;
}
ret = __ocfs2_claim_clusters(handle, context->data_ac, 1, *len,
&new_phys_cpos, &new_len); if (ret) {
mlog_errno(ret); goto out_commit;
}
/* * allowing partial extent moving is kind of 'pros and cons', it makes * whole defragmentation less likely to fail, on the contrary, the bad * thing is it may make the fs even more fragmented after moving, let * userspace make a good decision here.
*/ if (new_len != *len) {
mlog(0, "len_claimed: %u, len: %u\n", new_len, *len); if (!partial) {
context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE;
ret = -ENOSPC;
need_free = 1; goto out_commit;
}
}
ret = __ocfs2_move_extent(handle, context, cpos, new_len, phys_cpos,
new_phys_cpos, ext_flags); if (ret)
mlog_errno(ret);
if (partial && (new_len != *len))
*len = new_len;
/* * Here we should write the new page out first if we are * in write-back mode.
*/
ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, *len); if (ret)
mlog_errno(ret);
/* * make goal become cluster aligned.
*/
range->me_goal = ocfs2_block_to_cluster_start(inode->i_sb,
range->me_goal); /* * validate goal sits within global_bitmap, and return the victim * group desc
*/
ret = ocfs2_find_victim_alloc_group(inode, range->me_goal,
GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT,
&goal_bit, &gd_bh); if (ret) goto out;
bg = (struct ocfs2_group_desc *)gd_bh->b_data;
/* * moving goal is not allowed to start with a group desc blok(#0 blk) * let's compromise to the latter cluster.
*/ if (range->me_goal == le64_to_cpu(bg->bg_blkno))
range->me_goal += c_to_b;
/* * movement is not gonna cross two groups.
*/ if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
range->me_len) {
ret = -EINVAL; goto out;
} /* * more exact validations/adjustments will be performed later during * moving operation for each extent range.
*/
mlog(0, "extents get ready to be moved to #%llu block\n",
range->me_goal);
for (i = base_bit; i < le16_to_cpu(gd->bg_bits); i++) {
used = ocfs2_test_bit(i, (unsignedlong *)gd->bg_bitmap); if (used) { /* * we even tried searching the free chunk by jumping * a 'max_hop' distance, but still failed.
*/ if ((i - base_bit) > max_hop) {
*phys_cpos = 0; break;
}
if (last_free_bits)
last_free_bits = 0;
continue;
} else
last_free_bits++;
if (last_free_bits == move_len) {
i -= move_len;
*goal_bit = i;
*phys_cpos = base_cpos + i; break;
}
}
mlog(0, "found phys_cpos: %u to fit the wanted moving.\n", *phys_cpos);
}
if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) {
BUG_ON(!ocfs2_is_refcount_inode(inode));
BUG_ON(!context->refcount_loc);
ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
&ref_tree, NULL); if (ret) {
mlog_errno(ret); return ret;
}
ret = ocfs2_prepare_refcount_change_for_del(inode,
context->refcount_loc,
phys_blkno,
len,
&credits,
&extra_blocks); if (ret) {
mlog_errno(ret); goto out;
}
}
ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et,
len, 1,
&context->meta_ac,
extra_blocks, &credits); if (ret) {
mlog_errno(ret); goto out;
}
/* * need to count 2 extra credits for global_bitmap inode and * group descriptor.
*/
credits += OCFS2_INODE_UPDATE_CREDITS + 1;
inode_lock(tl_inode);
/* * ocfs2_move_extent() didn't reserve any clusters in lock_allocators() * logic, while we still need to lock the global_bitmap.
*/
gb_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT); if (!gb_inode) {
mlog(ML_ERROR, "unable to get global_bitmap inode\n");
ret = -EIO; goto out_unlock_tl_inode;
}
inode_lock(gb_inode);
ret = ocfs2_inode_lock(gb_inode, &gb_bh, 1); if (ret) {
mlog_errno(ret); goto out_unlock_gb_inode;
}
handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
mlog_errno(ret); goto out_unlock;
}
new_phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *new_phys_cpos);
ret = ocfs2_find_victim_alloc_group(inode, new_phys_blkno,
GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT,
&goal_bit, &gd_bh); if (ret) {
mlog_errno(ret); goto out_commit;
}
/* * probe the victim cluster group to find a proper * region to fit wanted movement, it even will perform * a best-effort attempt by compromising to a threshold * around the goal.
*/
ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop,
new_phys_cpos); if (!*new_phys_cpos) {
ret = -ENOSPC; goto out_commit;
}
ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
*new_phys_cpos, ext_flags); if (ret) {
mlog_errno(ret); goto out_commit;
}
gd = (struct ocfs2_group_desc *)gd_bh->b_data;
ret = ocfs2_alloc_dinode_update_counts(gb_inode, handle, gb_bh, len,
le16_to_cpu(gd->bg_chain)); if (ret) {
mlog_errno(ret); goto out_commit;
}
ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
goal_bit, len, 0, 0); if (ret) {
ocfs2_rollback_alloc_dinode_counts(gb_inode, gb_bh, len,
le16_to_cpu(gd->bg_chain));
mlog_errno(ret);
}
/* * Here we should write the new page out first if we are * in write-back mode.
*/
ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, len); if (ret)
mlog_errno(ret);
out: if (context->meta_ac) {
ocfs2_free_alloc_context(context->meta_ac);
context->meta_ac = NULL;
}
if (ref_tree)
ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
return ret;
}
/* * Helper to calculate the defraging length in one run according to threshold.
*/ staticvoid ocfs2_calc_extent_defrag_len(u32 *alloc_size, u32 *len_defraged,
u32 threshold, int *skip)
{ if ((*alloc_size + *len_defraged) < threshold) { /* * proceed defragmentation until we meet the thresh
*/
*len_defraged += *alloc_size;
} elseif (*len_defraged == 0) { /* * XXX: skip a large extent.
*/
*skip = 1;
} else { /* * split this extent to coalesce with former pieces as * to reach the threshold. * * we're done here with one cycle of defragmentation * in a size of 'thresh', resetting 'len_defraged' * forces a new defragmentation.
*/
*alloc_size = threshold - *len_defraged;
*len_defraged = 0;
}
}
/* * extents moving happens in unit of clusters, for the sake * of simplicity, we may ignore two clusters where 'byte_start' * and 'byte_start + len' were within.
*/
move_start = ocfs2_clusters_for_bytes(osb->sb, range->me_start);
len_to_move = (range->me_start + range->me_len) >>
osb->s_clustersize_bits; if (len_to_move >= move_start)
len_to_move -= move_start; else
len_to_move = 0;
if (do_defrag) {
defrag_thresh = range->me_threshold >> osb->s_clustersize_bits; if (defrag_thresh <= 1) goto done;
} else
new_phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
range->me_goal);
ret = ocfs2_defrag_extent(context, cpos, phys_cpos,
&alloc_size, flags);
} else {
ret = ocfs2_move_extent(context, cpos, phys_cpos,
&new_phys_cpos, alloc_size,
flags);
new_phys_cpos += alloc_size;
}
if (ret < 0) {
mlog_errno(ret); goto out;
} /* * Invalidate extent cache after moving/defragging to prevent * stale cached data with outdated extent flags.
*/
ocfs2_extent_map_trunc(inode, cpos);
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) return -EROFS;
inode_lock(inode);
/* * This prevents concurrent writes from other nodes
*/
status = ocfs2_rw_lock(inode, 1); if (status) {
mlog_errno(status); goto out;
}
status = ocfs2_inode_lock(inode, &di_bh, 1); if (status) {
mlog_errno(status); goto out_rw_unlock;
}
/* * remember ip_xattr_sem also needs to be held if necessary
*/
down_write(&OCFS2_I(inode)->ip_alloc_sem);
status = __ocfs2_move_extents_range(di_bh, context);
up_write(&OCFS2_I(inode)->ip_alloc_sem); if (status) {
mlog_errno(status); goto out_inode_unlock;
}
/* * We update ctime for these changes
*/
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status); goto out_inode_unlock;
}
status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
OCFS2_JOURNAL_ACCESS_WRITE); if (status) {
mlog_errno(status); goto out_commit;
}
/* * ok, the default threshold for the defragmentation * is 1M, since our maximum clustersize was 1M also. * any thought?
*/ if (!range.me_threshold)
range.me_threshold = 1024 * 1024;
if (range.me_threshold > i_size_read(inode))
range.me_threshold = i_size_read(inode);
if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) {
context->auto_defrag = 1;
if (range.me_flags & OCFS2_MOVE_EXT_FL_PART_DEFRAG)
context->partial = 1;
} else { /* * first best-effort attempt to validate and adjust the goal * (physical address in block), while it can't guarantee later * operation can succeed all the time since global_bitmap may * change a bit over time.
*/
status = ocfs2_validate_and_adjust_move_goal(inode, &range); if (status) goto out_copy;
}
status = ocfs2_move_extents(context); if (status)
mlog_errno(status);
out_copy: /* * movement/defragmentation may end up being partially completed, * that's the reason why we need to return userspace the finished * length and new_offset even if failure happens somewhere.
*/ if (copy_to_user(argp, &range, sizeof(range)))
status = -EFAULT;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.