From: Mingming Cao ext3_rsv_base.patch: Implements the base of in-memory block reservation and block allocation from reservation window. -basic reservation structure and operations -reservation based ext3 block allocation DESC ext3 reservations: fix performance regression EDESC From: Mingming Cao The ext3 reservation patches changed the non-reservation block allocation path. The changes does not cause the time regression on untar.sh, but changed the disk layout. So later when run read.sh or cp.sh, it sequentially caused the regression I saw. There is a performance optimization code previously presented in mainline kernel has removed, I thought it might not appropriate for the reservation case. It turns out it hurt the non-reservation case and not optimized for the reservation case. There are another changes that are considered for reservation turned on case but not optimized for the non-reservation change. I have tested the patch against 265-mm6 on my 8way, no regression there (with reservation and with no reservation, compare with 2.6.5). DESC ext3 block reservation patch set -- mount and ioctl feature EDESC From: Mingming Cao ext3_rsv_mount.patch: Adds features on top of the ext3_rsv_base.patch: - deal with earlier bogus -ENOSPC error - do block reservation only for regular file - make the ext3 reservation feature as a mount option: new mount option added: reservation - A pair of file ioctl commands are added for application to control the block reservation window size. DESC ext3 block reservation patch set -- dynamically increase reservation window EDESC From: Mingming Cao ext3_rsv_dw.patch: adjust the reservation window size dynamically. Start from the default reservation window size. If the hit ratio of the reservation window is more than 50%, double the reservation window size next time up to a certain upper limit. DESC ext3 reservation ifdef cleanup patch EDESC From: Mingming Cao remove ifdef EXT3_RESERVATION since now we have reservation/noreservation mount options. DESC ext3 reservation max window size check patch EDESC From: Mingming Cao Add check for maxium reservation window size when growing reservation window. DESC ext3 reservation file ioctl fix EDESC From: Mingming Cao Only allow application to modify the file's reservation window size when fs is mounted with reservation and the operation is performed on regular files. Signed-off-by: Andrew Morton --- 25-akpm/fs/ext3/balloc.c | 625 +++++++++++++++++++++++++++++++++---- 25-akpm/fs/ext3/file.c | 2 25-akpm/fs/ext3/ialloc.c | 5 25-akpm/fs/ext3/inode.c | 9 25-akpm/fs/ext3/ioctl.c | 24 + 25-akpm/fs/ext3/super.c | 19 + 25-akpm/include/linux/ext3_fs.h | 47 +- 25-akpm/include/linux/ext3_fs_i.h | 13 25-akpm/include/linux/ext3_fs_sb.h | 4 9 files changed, 666 insertions(+), 82 deletions(-) diff -puN fs/ext3/balloc.c~ext3_rsv_base fs/ext3/balloc.c --- 25/fs/ext3/balloc.c~ext3_rsv_base 2004-10-21 14:54:21.015728616 -0700 +++ 25-akpm/fs/ext3/balloc.c 2004-10-21 14:54:21.034725728 -0700 @@ -96,9 +96,87 @@ read_block_bitmap(struct super_block *sb error_out: return bh; } +/* + * The reservation window structure operations + * -------------------------------------------- + * Operations include: + * dump, find, add, remove, is_empty, find_next_reservable_window, etc. + * + * We use sorted double linked list for the per-filesystem reservation + * window list. (like in vm_region). + * + * Initially, we keep those small operations in the abstract functions, + * so later if we need a better searching tree than double linked-list, + * we could easily switch to that without changing too much + * code. + */ +static inline void rsv_window_dump(struct reserve_window *head, char *fn) +{ + struct reserve_window *rsv; + + printk("Block Allocation Reservation Windows Map (%s):\n", fn); + list_for_each_entry(rsv, &head->rsv_list, rsv_list) { + printk("reservation window 0x%p start: %d, end: %d\n", + rsv, rsv->rsv_start, rsv->rsv_end); + } +} + +static int +goal_in_my_reservation(struct reserve_window *rsv, int goal, + unsigned int group, struct super_block * sb) +{ + unsigned long group_first_block, group_last_block; + + group_first_block = le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block) + + group * EXT3_BLOCKS_PER_GROUP(sb); + group_last_block = group_first_block + EXT3_BLOCKS_PER_GROUP(sb) - 1; + + if ((rsv->rsv_start > group_last_block) || + (rsv->rsv_end < group_first_block)) + return 0; + if ((goal >= 0) && ((goal + group_first_block < rsv->rsv_start) + || (goal + group_first_block > rsv->rsv_end))) + return 0; + return 1; +} + +static inline void rsv_window_add(struct reserve_window *rsv, + struct reserve_window *prev) +{ + /* insert the new reservation window after the head */ + list_add(&rsv->rsv_list, &prev->rsv_list); +} + +static inline void rsv_window_remove(struct reserve_window *rsv) +{ + rsv->rsv_start = 0; + rsv->rsv_end = 0; + rsv->rsv_alloc_hit = 0; + list_del(&rsv->rsv_list); + INIT_LIST_HEAD(&rsv->rsv_list); +} + +static inline int rsv_is_empty(struct reserve_window *rsv) +{ + /* a valid reservation end block could not be 0 */ + return (rsv->rsv_end == 0); +} + +void ext3_discard_reservation(struct inode *inode) +{ + struct ext3_inode_info *ei = EXT3_I(inode); + struct reserve_window *rsv = &ei->i_rsv_window; + spinlock_t *rsv_lock = &EXT3_SB(inode->i_sb)->s_rsv_window_lock; + + if (!rsv_is_empty(rsv)) { + spin_lock(rsv_lock); + rsv_window_remove(rsv); + spin_unlock(rsv_lock); + } +} /* Free given blocks, update quota and i_blocks field */ -void ext3_free_blocks (handle_t *handle, struct inode * inode, +void ext3_free_blocks(handle_t *handle, struct inode *inode, unsigned long block, unsigned long count) { struct buffer_head *bitmap_bh = NULL; @@ -296,7 +374,7 @@ error_return: * data-writes at some point, and disable it for metadata allocations or * sync-data inodes. */ -static inline int ext3_test_allocatable(int nr, struct buffer_head *bh) +static int ext3_test_allocatable(int nr, struct buffer_head *bh) { int ret; struct journal_head *jh = bh2jh(bh); @@ -313,6 +391,33 @@ static inline int ext3_test_allocatable( return ret; } +static int +bitmap_search_next_usable_block(int start, struct buffer_head *bh, + int maxblocks) +{ + int next; + struct journal_head *jh = bh2jh(bh); + + /* + * The bitmap search --- search forward alternately through the actual + * bitmap and the last-committed copy until we find a bit free in + * both + */ + while (start < maxblocks) { + next = ext3_find_next_zero_bit(bh->b_data, maxblocks, start); + if (next >= maxblocks) + return -1; + if (ext3_test_allocatable(next, bh)) + return next; + jbd_lock_bh_state(bh); + if (jh->b_committed_data) + start = ext3_find_next_zero_bit(jh->b_committed_data, + maxblocks, next); + jbd_unlock_bh_state(bh); + } + return -1; +} + /* * Find an allocatable block in a bitmap. We honour both the bitmap and * its last-committed copy (if that exists), and perform the "most @@ -325,7 +430,6 @@ find_next_usable_block(int start, struct { int here, next; char *p, *r; - struct journal_head *jh = bh2jh(bh); if (start > 0) { /* @@ -337,6 +441,8 @@ find_next_usable_block(int start, struct * next 64-bit boundary is simple.. */ int end_goal = (start + 63) & ~63; + if (end_goal > maxblocks) + end_goal = maxblocks; here = ext3_find_next_zero_bit(bh->b_data, end_goal, start); if (here < end_goal && ext3_test_allocatable(here, bh)) return here; @@ -351,7 +457,7 @@ find_next_usable_block(int start, struct r = memscan(p, 0, (maxblocks - here + 7) >> 3); next = (r - ((char *)bh->b_data)) << 3; - if (next < maxblocks && ext3_test_allocatable(next, bh)) + if (next < maxblocks && next >= start && ext3_test_allocatable(next, bh)) return next; /* @@ -359,19 +465,8 @@ find_next_usable_block(int start, struct * bitmap and the last-committed copy until we find a bit free in * both */ - while (here < maxblocks) { - next = ext3_find_next_zero_bit(bh->b_data, maxblocks, here); - if (next >= maxblocks) - return -1; - if (ext3_test_allocatable(next, bh)) - return next; - jbd_lock_bh_state(bh); - if (jh->b_committed_data) - here = ext3_find_next_zero_bit(jh->b_committed_data, - maxblocks, next); - jbd_unlock_bh_state(bh); - } - return -1; + here = bitmap_search_next_usable_block(here, bh, maxblocks); + return here; } /* @@ -407,62 +502,456 @@ claim_block(spinlock_t *lock, int block, */ static int ext3_try_to_allocate(struct super_block *sb, handle_t *handle, int group, - struct buffer_head *bitmap_bh, int goal, int *errp) + struct buffer_head *bitmap_bh, int goal, struct reserve_window *my_rsv) { - int i; - int fatal; - int credits = 0; - - *errp = 0; + int group_first_block, start, end; - /* - * Make sure we use undo access for the bitmap, because it is critical - * that we do the frozen_data COW on bitmap buffers in all cases even - * if the buffer is in BJ_Forget state in the committing transaction. - */ - BUFFER_TRACE(bitmap_bh, "get undo access for new block"); - fatal = ext3_journal_get_undo_access(handle, bitmap_bh, &credits); - if (fatal) { - *errp = fatal; - goto fail; + /* we do allocation within the reservation window if we have a window */ + if (my_rsv) { + group_first_block = + le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block) + + group * EXT3_BLOCKS_PER_GROUP(sb); + if (my_rsv->rsv_start >= group_first_block) + start = my_rsv->rsv_start - group_first_block; + else + /* reservation window cross group boundary */ + start = 0; + end = my_rsv->rsv_end - group_first_block + 1; + if (end > EXT3_BLOCKS_PER_GROUP(sb)) + /* reservation window crosses group boundary */ + end = EXT3_BLOCKS_PER_GROUP(sb); + if ((start <= goal) && (goal < end)) + start = goal; + else + goal = -1; + } else { + if (goal > 0) + start = goal; + else + start = 0; + end = EXT3_BLOCKS_PER_GROUP(sb); } + BUG_ON(start > EXT3_BLOCKS_PER_GROUP(sb)); + repeat: if (goal < 0 || !ext3_test_allocatable(goal, bitmap_bh)) { - goal = find_next_usable_block(goal, bitmap_bh, - EXT3_BLOCKS_PER_GROUP(sb)); + goal = find_next_usable_block(start, bitmap_bh, end); if (goal < 0) goto fail_access; + if (!my_rsv) { + int i; - for (i = 0; i < 7 && goal > 0 && - ext3_test_allocatable(goal - 1, bitmap_bh); - i++, goal--); + for (i = 0; i < 7 && goal > start && + ext3_test_allocatable(goal - 1, + bitmap_bh); + i++, goal--) + ; + } } + start = goal; if (!claim_block(sb_bgl_lock(EXT3_SB(sb), group), goal, bitmap_bh)) { /* * The block was allocated by another thread, or it was * allocated and then freed by another thread */ + start++; goal++; - if (goal >= EXT3_BLOCKS_PER_GROUP(sb)) + if (start >= end) goto fail_access; goto repeat; } + if (my_rsv) + my_rsv->rsv_alloc_hit++; + return goal; +fail_access: + return -1; +} + +/** + * find_next_reservable_window(): + * find a reservable space within the given range + * It does not allocate the reservation window for now + * alloc_new_reservation() will do the work later. + * + * @search_head: the head of the searching list; + * This is not necessary the list head of the whole filesystem + * + * we have both head and start_block to assist the search + * for the reservable space. The list start from head, + * but we will shift to the place where start_block is, + * then start from there, we looking for a resevable space. + * + * @fs_rsv_head: per-filesystem reervation list head. + * + * @size: the target new reservation window size + * @group_first_block: the first block we consider to start + * the real search from + * + * @last_block: + * the maxium block number that our goal reservable space + * could start from. This is normally the last block in this + * group. The search will end when we found the start of next + * possiblereservable space is out of this boundary. + * This could handle the cross bounday reservation window request. + * + * basically we search from the given range, rather than the whole + * reservation double linked list, (start_block, last_block) + * to find a free region that of of my size and has not + * been reserved. + * + * on succeed, it returns the reservation window to be append to. + * failed, return NULL. + */ +static inline +struct reserve_window *find_next_reservable_window( + struct reserve_window *search_head, + struct reserve_window *fs_rsv_head, + unsigned long size, int *start_block, + int last_block) +{ + struct reserve_window *rsv; + int cur; + + /* TODO:make the start of the reservation window byte alligned */ + /*cur = *start_block & 8;*/ + cur = *start_block; + rsv = list_entry(search_head->rsv_list.next, + struct reserve_window, rsv_list); + while (rsv != fs_rsv_head) { + if (cur + size <= rsv->rsv_start) { + /* + * Found a reserveable space big enough. We could + * have a reservation across the group boundary here + */ + break; + } + if (cur <= rsv->rsv_end) + cur = rsv->rsv_end + 1; + + /* TODO? + * in the case we could not find a reservable space + * that is what is expected, during the re-search, we could + * remember what's the largest reservable space we could have + * and return that one. + * + * For now it will fail if we could not find the reservable + * space with expected-size (or more)... + */ + rsv = list_entry(rsv->rsv_list.next, + struct reserve_window, rsv_list); + if (cur > last_block) + return NULL; /* fail */ + } + /* + * we come here either : + * when we rearch to the end of the whole list, + * and there is empty reservable space after last entry in the list. + * append it to the end of the list. + * + * or we found one reservable space in the middle of the list, + * return the reservation window that we could append to. + * succeed. + */ + *start_block = cur; + return list_entry(rsv->rsv_list.prev, struct reserve_window, rsv_list); +} + +/** + * alloc_new_reservation()--allocate a new reservation window + * if there is an existing reservation, discard it first + * then allocate the new one from there + * otherwise allocate the new reservation from the given + * start block, or the beginning of the group, if a goal + * is not given. + * + * To make a new reservation, we search part of the filesystem + * reservation list(the list that inside the group). + * + * If we have a old reservation, the search goal is the end of + * last reservation. If we do not have a old reservatio, then we + * start from a given goal, or the first block of the group, if + * the goal is not given. + * + * We first find a reservable space after the goal, then from + * there,we check the bitmap for the first free block after + * it. If there is no free block until the end of group, then the + * whole group is full, we failed. Otherwise, check if the free + * block is inside the expected reservable space, if so, we + * succeed. + * If the first free block is outside the reseravle space, then + * start from the first free block, we search for next avalibale + * space, and go on. + * + * on succeed, a new reservation will be found and inserted into the list + * It contains at least one free block, and it is not overlap with other + * reservation window. + * + * failed: we failed to found a reservation window in this group + * + * @rsv: the reservation + * + * @goal: The goal. It is where the search for a + * free reservable space should start from. + * if we have a old reservation, start_block is the end of + * old reservation. Otherwise, + * if we have a goal(goal >0 ), then start from there, + * no goal(goal = -1), we start from the first block + * of the group. + * + * @sb: the super block + * @group: the group we are trying to do allocate in + * @bitmap_bh: the block group block bitmap + */ +static int alloc_new_reservation(struct reserve_window *my_rsv, + int goal, struct super_block *sb, + unsigned int group, struct buffer_head *bitmap_bh) +{ + struct reserve_window *search_head; + int group_first_block, group_end_block, start_block; + int first_free_block; + int reservable_space_start; + struct reserve_window *prev_rsv; + struct reserve_window *fs_rsv_head = &EXT3_SB(sb)->s_rsv_window_head; + unsigned long size; + + group_first_block = le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block) + + group * EXT3_BLOCKS_PER_GROUP(sb); + group_end_block = group_first_block + EXT3_BLOCKS_PER_GROUP(sb) - 1; + + if (goal < 0) + start_block = group_first_block; + else + start_block = goal + group_first_block; + + size = atomic_read(&my_rsv->rsv_goal_size); + /* if we have a old reservation, discard it first */ + if (!rsv_is_empty(my_rsv)) { + /* + * if the old reservation is cross group boundary + * we will come here when we just failed to allocate from + * the first part of the window. We still have another part + * that belongs to the next group. In this case, there is no + * point to discard our window and try to allocate a new one + * in this group(which will fail). we should + * keep the reservation window, just simply move on. + * + * Maybe we could shift the start block of the reservation + * window to the first block of next group. + */ + + if ((my_rsv->rsv_start <= group_end_block) && + (my_rsv->rsv_end > group_end_block)) + return -1; + + /* remember where we are before we discard the old one */ + if (my_rsv->rsv_end + 1 > start_block) + start_block = my_rsv->rsv_end + 1; + search_head = list_entry(my_rsv->rsv_list.prev, + struct reserve_window, rsv_list); + if ((my_rsv->rsv_alloc_hit > (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) { + /* + * if we previously allocation hit ration is greater than half + * we double the size of reservation window next time + * otherwise keep the same + */ + size = size * 2; + if (size > EXT3_MAX_RESERVE_BLOCKS) + size = EXT3_MAX_RESERVE_BLOCKS; + atomic_set(&my_rsv->rsv_goal_size, size); + } + rsv_window_remove(my_rsv); + } + else { + /* + * we don't have a reservation, + * we set our goal(start_block) and + * the list head for the search + */ + search_head = fs_rsv_head; + } + + /* + * find_next_reservable_window() simply find a reservable window + * inside the given range(start_block, group_end_block). + * + * To make sure the reservation window has a free bit inside it, we + * need to check the bitmap after we found a reservable window. + */ +retry: + prev_rsv = find_next_reservable_window(search_head, fs_rsv_head, size, + &start_block, group_end_block); + if (prev_rsv == NULL) + goto failed; + reservable_space_start = start_block; + /* + * On success, find_next_reservable_window() returns the + * reservation window where there is a reservable space after it. + * Before we reserve this reservable space, we need + * to make sure there is at least a free block inside this region. + * + * searching the first free bit on the block bitmap and copy of + * last committed bitmap alternatively, until we found a allocatable + * block. Search start from the start block of the reservable space + * we just found. + */ + first_free_block = bitmap_search_next_usable_block( + reservable_space_start - group_first_block, + bitmap_bh, group_end_block - group_first_block + 1); + + if (first_free_block < 0) { + /* + * no free block left on the bitmap, no point + * to reserve the space. return failed. + */ + goto failed; + } + start_block = first_free_block + group_first_block; + /* + * check if the first free block is within the + * free space we just found + */ + if ((start_block >= reservable_space_start) && + (start_block < reservable_space_start + size)) + goto found_rsv_window; + /* + * if the first free bit we found is out of the reservable space + * this means there is no free block on the reservable space + * we should continue search for next reservable space, + * start from where the free block is, + * we also shift the list head to where we stopped last time + */ + search_head = prev_rsv; + goto retry; + +found_rsv_window: + /* + * great! the reservable space contains some free blocks. + * Insert it to the list. + */ + rsv_window_add(my_rsv, prev_rsv); + my_rsv->rsv_start = reservable_space_start; + my_rsv->rsv_end = my_rsv->rsv_start + size - 1; + return 0; /* succeed */ +failed: + return -1; /* failed */ +} - BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for bitmap block"); - fatal = ext3_journal_dirty_metadata(handle, bitmap_bh); +/* + * This is the main function used to allocate a new block and its reservation + * window. + * + * Each time when a new block allocation is need, first try to allocate from + * its own reservation. If it does not have a reservation window, instead of + * looking for a free bit on bitmap first, then look up the reservation list to + * see if it is inside somebody else's reservation window, we try to allocate a + * reservation window for it start from the goal first. Then do the block + * allocation within the reservation window. + * + * This will aviod keep searching the reservation list again and again when + * someboday is looking for a free block(without reservation), and there are + * lots of free blocks, but they are all being reserved + * + * We use a sorted double linked list for the per-filesystem reservation list. + * The insert, remove and find a free space(non-reserved) operations for the + * sorted double linked list should be fast. + * + */ +static int +ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, + unsigned int group, struct buffer_head *bitmap_bh, + int goal, struct reserve_window * my_rsv, + int *errp) +{ + spinlock_t *rsv_lock; + unsigned long group_first_block; + int ret = 0; + int fatal; + int credits = 0; + + *errp = 0; + + /* + * Make sure we use undo access for the bitmap, because it is critical + * that we do the frozen_data COW on bitmap buffers in all cases even + * if the buffer is in BJ_Forget state in the committing transaction. + */ + BUFFER_TRACE(bitmap_bh, "get undo access for new block"); + fatal = ext3_journal_get_undo_access(handle, bitmap_bh, &credits); if (fatal) { *errp = fatal; - goto fail; + return -1; + } + + /* + * we don't deal with reservation when + * filesystem is mounted without reservation + * or the file is not a regular file + * of last attemp of allocating a block with reservation turn on failed + */ + if (my_rsv == NULL ) { + ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh, goal, NULL); + goto out; + } + rsv_lock = &EXT3_SB(sb)->s_rsv_window_lock; + /* + * goal is a group relative block number (if there is a goal) + * 0 < goal < EXT3_BLOCKS_PER_GROUP(sb) + * first block is a filesystem wide block number + * first block is the block number of the first block in this group + */ + group_first_block = le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block) + + group * EXT3_BLOCKS_PER_GROUP(sb); + + /* + * Basically we will allocate a new block from inode's reservation + * window. + * + * We need to allocate a new reservation window, if: + * a) inode does not have a reservation window; or + * b) last attemp of allocating a block from existing reservation + * failed; or + * c) we come here with a goal and with a reservation window + * + * We do not need to allocate a new reservation window if we come here + * at the beginning with a goal and the goal is inside the window, or + * or we don't have a goal but already have a reservation window. + * then we could go to allocate from the reservation window directly. + */ + while (1) { + if (rsv_is_empty(my_rsv) || (ret < 0) || + !goal_in_my_reservation(my_rsv, goal, group, sb)) { + spin_lock(rsv_lock); + ret = alloc_new_reservation(my_rsv, goal, sb, + group, bitmap_bh); + spin_unlock(rsv_lock); + if (ret < 0) + break; /* failed */ + + if (!goal_in_my_reservation(my_rsv, goal, group, sb)) + goal = -1; + } + ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh, goal, + my_rsv); + if (ret >= 0) + break; /* succeed */ + } +out: + if (ret >= 0) { + BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for " + "bitmap block"); + fatal = ext3_journal_dirty_metadata(handle, bitmap_bh); + if (fatal) { + *errp = fatal; + return -1; + } + return ret; } - return goal; -fail_access: BUFFER_TRACE(bitmap_bh, "journal_release_buffer"); ext3_journal_release_buffer(handle, bitmap_bh, credits); -fail: - return -1; + return ret; } static int ext3_has_free_blocks(struct ext3_sb_info *sbi) @@ -503,15 +992,16 @@ int ext3_should_retry_alloc(struct super * bitmap, and then for any free bit if that fails. * This function also updates quota and i_blocks field. */ -int -ext3_new_block(handle_t *handle, struct inode *inode, unsigned long goal, int *errp) +int ext3_new_block(handle_t *handle, struct inode *inode, + unsigned long goal, int *errp) { - struct buffer_head *bitmap_bh = NULL; /* bh */ - struct buffer_head *gdp_bh; /* bh2 */ - int group_no; /* i */ - int ret_block; /* j */ - int bgi; /* blockgroup iteration index */ - int target_block; /* tmp */ + struct buffer_head *bitmap_bh = NULL; + struct buffer_head *gdp_bh; + int group_no; + int goal_group; + int ret_block; + int bgi; /* blockgroup iteration index */ + int target_block; int fatal = 0, err; int performed_allocation = 0; int free_blocks; @@ -519,6 +1009,7 @@ ext3_new_block(handle_t *handle, struct struct ext3_group_desc *gdp; struct ext3_super_block *es; struct ext3_sb_info *sbi; + struct reserve_window *my_rsv = NULL; #ifdef EXT3FS_DEBUG static int goal_hits, goal_attempts; #endif @@ -540,7 +1031,8 @@ ext3_new_block(handle_t *handle, struct sbi = EXT3_SB(sb); es = EXT3_SB(sb)->s_es; ext3_debug("goal=%lu.\n", goal); - + if (test_opt(sb, RESERVATION) && S_ISREG(inode->i_mode)) + my_rsv = &EXT3_I(inode)->i_rsv_window; if (!ext3_has_free_blocks(sbi)) { *errp = -ENOSPC; goto out; @@ -558,6 +1050,8 @@ ext3_new_block(handle_t *handle, struct if (!gdp) goto io_error; + goal_group = group_no; +retry: free_blocks = le16_to_cpu(gdp->bg_free_blocks_count); if (free_blocks > 0) { ret_block = ((goal - le32_to_cpu(es->s_first_data_block)) % @@ -565,8 +1059,8 @@ ext3_new_block(handle_t *handle, struct bitmap_bh = read_block_bitmap(sb, group_no); if (!bitmap_bh) goto io_error; - ret_block = ext3_try_to_allocate(sb, handle, group_no, - bitmap_bh, ret_block, &fatal); + ret_block = ext3_try_to_allocate_with_rsv(sb, handle, group_no, + bitmap_bh, ret_block, my_rsv, &fatal); if (fatal) goto out; if (ret_block >= 0) @@ -594,14 +1088,25 @@ ext3_new_block(handle_t *handle, struct bitmap_bh = read_block_bitmap(sb, group_no); if (!bitmap_bh) goto io_error; - ret_block = ext3_try_to_allocate(sb, handle, group_no, - bitmap_bh, -1, &fatal); + ret_block = ext3_try_to_allocate_with_rsv(sb, handle, group_no, + bitmap_bh, -1, my_rsv, &fatal); if (fatal) goto out; if (ret_block >= 0) goto allocated; } - + /* + * We may end up a bogus ealier ENOSPC error due to + * filesystem is "full" of reservations, but + * there maybe indeed free blocks avaliable on disk + * In this case, we just forget about the reservations + * just do block allocation as without reservations. + */ + if (my_rsv) { + my_rsv = NULL; + group_no = goal_group; + goto retry; + } /* No space left on the device */ *errp = -ENOSPC; goto out; diff -puN fs/ext3/file.c~ext3_rsv_base fs/ext3/file.c --- 25/fs/ext3/file.c~ext3_rsv_base 2004-10-21 14:54:21.016728464 -0700 +++ 25-akpm/fs/ext3/file.c 2004-10-21 14:54:21.034725728 -0700 @@ -33,6 +33,8 @@ */ static int ext3_release_file (struct inode * inode, struct file * filp) { + if (filp->f_mode & FMODE_WRITE) + ext3_discard_reservation(inode); if (is_dx(inode) && filp->private_data) ext3_htree_free_dir_info(filp->private_data); diff -puN fs/ext3/ialloc.c~ext3_rsv_base fs/ext3/ialloc.c --- 25/fs/ext3/ialloc.c~ext3_rsv_base 2004-10-21 14:54:21.017728312 -0700 +++ 25-akpm/fs/ext3/ialloc.c 2004-10-21 14:54:21.035725576 -0700 @@ -582,6 +582,11 @@ got: ei->i_file_acl = 0; ei->i_dir_acl = 0; ei->i_dtime = 0; + ei->i_rsv_window.rsv_start = 0; + ei->i_rsv_window.rsv_end = 0; + atomic_set(&ei->i_rsv_window.rsv_goal_size, EXT3_DEFAULT_RESERVE_BLOCKS); + ei->i_rsv_window.rsv_alloc_hit = 0; + INIT_LIST_HEAD(&ei->i_rsv_window.rsv_list); ei->i_block_group = group; ext3_set_inode_flags(inode); diff -puN fs/ext3/inode.c~ext3_rsv_base fs/ext3/inode.c --- 25/fs/ext3/inode.c~ext3_rsv_base 2004-10-21 14:54:21.019728008 -0700 +++ 25-akpm/fs/ext3/inode.c 2004-10-21 14:54:21.038725120 -0700 @@ -187,6 +187,8 @@ static int ext3_journal_test_restart(han */ void ext3_put_inode(struct inode *inode) { + if (!is_bad_inode(inode)) + ext3_discard_reservation(inode); } /* @@ -2086,6 +2088,8 @@ void ext3_truncate(struct inode * inode) if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return; + ext3_discard_reservation(inode); + /* * We have to lock the EOF page here, because lock_page() nests * outside journal_start(). @@ -2478,7 +2482,10 @@ void ext3_read_inode(struct inode * inod ei->i_disksize = inode->i_size; inode->i_generation = le32_to_cpu(raw_inode->i_generation); ei->i_block_group = iloc.block_group; - + ei->i_rsv_window.rsv_start = 0; + ei->i_rsv_window.rsv_end= 0; + atomic_set(&ei->i_rsv_window.rsv_goal_size, EXT3_DEFAULT_RESERVE_BLOCKS); + INIT_LIST_HEAD(&ei->i_rsv_window.rsv_list); /* * NOTE! The in-memory inode i_data array is in little-endian order * even on big-endian machines: we do NOT byteswap the block numbers! diff -puN fs/ext3/ioctl.c~ext3_rsv_base fs/ext3/ioctl.c --- 25/fs/ext3/ioctl.c~ext3_rsv_base 2004-10-21 14:54:21.020727856 -0700 +++ 25-akpm/fs/ext3/ioctl.c 2004-10-21 14:54:21.038725120 -0700 @@ -20,6 +20,7 @@ int ext3_ioctl (struct inode * inode, st { struct ext3_inode_info *ei = EXT3_I(inode); unsigned int flags; + unsigned short rsv_window_size; ext3_debug ("cmd = %u, arg = %lu\n", cmd, arg); @@ -151,6 +152,29 @@ flags_err: return ret; } #endif + case EXT3_IOC_GETRSVSZ: + if (test_opt(inode->i_sb, RESERVATION) && S_ISREG(inode->i_mode)) { + rsv_window_size = atomic_read(&ei->i_rsv_window.rsv_goal_size); + return put_user(rsv_window_size, (int *)arg); + } + return -ENOTTY; + case EXT3_IOC_SETRSVSZ: + if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode)) + return -ENOTTY; + + if (IS_RDONLY(inode)) + return -EROFS; + + if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + return -EACCES; + + if (get_user(rsv_window_size, (int *)arg)) + return -EFAULT; + + if (rsv_window_size > EXT3_MAX_RESERVE_BLOCKS) + rsv_window_size = EXT3_MAX_RESERVE_BLOCKS; + atomic_set(&ei->i_rsv_window.rsv_goal_size, rsv_window_size); + return 0; default: return -ENOTTY; } diff -puN fs/ext3/super.c~ext3_rsv_base fs/ext3/super.c --- 25/fs/ext3/super.c~ext3_rsv_base 2004-10-21 14:54:21.022727552 -0700 +++ 25-akpm/fs/ext3/super.c 2004-10-21 14:54:21.040724816 -0700 @@ -579,7 +579,8 @@ enum { Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro, Opt_nouid32, Opt_check, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov, - Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_noload, + Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, + Opt_reservation, Opt_noreservation, Opt_noload, Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, @@ -611,6 +612,8 @@ static match_table_t tokens = { {Opt_nouser_xattr, "nouser_xattr"}, {Opt_acl, "acl"}, {Opt_noacl, "noacl"}, + {Opt_reservation, "reservation"}, + {Opt_noreservation, "noreservation"}, {Opt_noload, "noload"}, {Opt_commit, "commit=%u"}, {Opt_journal_update, "journal=update"}, @@ -765,6 +768,12 @@ static int parse_options (char * options printk("EXT3 (no)acl options not supported\n"); break; #endif + case Opt_reservation: + set_opt(sbi->s_mount_opt, RESERVATION); + break; + case Opt_noreservation: + clear_opt(sbi->s_mount_opt, RESERVATION); + break; case Opt_journal_update: /* @@@ FIXME */ /* Eventually we will want to be able to create @@ -1469,6 +1478,14 @@ static int ext3_fill_super (struct super sbi->s_gdb_count = db_count; get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); + /* per fileystem reservation list head & lock */ + spin_lock_init(&sbi->s_rsv_window_lock); + INIT_LIST_HEAD(&sbi->s_rsv_window_head.rsv_list); + sbi->s_rsv_window_head.rsv_start = 0; + sbi->s_rsv_window_head.rsv_end = 0; + sbi->s_rsv_window_head.rsv_alloc_hit = 0; + atomic_set(&sbi->s_rsv_window_head.rsv_goal_size, 0); + /* * set up enough so that it can read an inode */ diff -puN include/linux/ext3_fs.h~ext3_rsv_base include/linux/ext3_fs.h --- 25/include/linux/ext3_fs.h~ext3_rsv_base 2004-10-21 14:54:21.024727248 -0700 +++ 25-akpm/include/linux/ext3_fs.h 2004-10-21 14:54:21.042724512 -0700 @@ -33,6 +33,11 @@ struct statfs; #undef EXT3FS_DEBUG /* + * Define EXT3_RESERVATION to reserve data blocks for expanding files + */ +#define EXT3_DEFAULT_RESERVE_BLOCKS 8 +#define EXT3_MAX_RESERVE_BLOCKS 1024 +/* * Always enable hashed directories */ #define CONFIG_EXT3_INDEX @@ -202,6 +207,8 @@ struct ext3_group_desc #ifdef CONFIG_JBD_DEBUG #define EXT3_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) #endif +#define EXT3_IOC_GETRSVSZ _IOR('r', 1, long) +#define EXT3_IOC_SETRSVSZ _IOW('r', 2, long) /* * Structure of an inode on the disk @@ -300,25 +307,26 @@ struct ext3_inode { /* * Mount flags */ -#define EXT3_MOUNT_CHECK 0x0001 /* Do mount-time checks */ -#define EXT3_MOUNT_OLDALLOC 0x0002 /* Don't use the new Orlov allocator */ -#define EXT3_MOUNT_GRPID 0x0004 /* Create files with directory's group */ -#define EXT3_MOUNT_DEBUG 0x0008 /* Some debugging messages */ -#define EXT3_MOUNT_ERRORS_CONT 0x0010 /* Continue on errors */ -#define EXT3_MOUNT_ERRORS_RO 0x0020 /* Remount fs ro on errors */ -#define EXT3_MOUNT_ERRORS_PANIC 0x0040 /* Panic on errors */ -#define EXT3_MOUNT_MINIX_DF 0x0080 /* Mimics the Minix statfs */ -#define EXT3_MOUNT_NOLOAD 0x0100 /* Don't use existing journal*/ -#define EXT3_MOUNT_ABORT 0x0200 /* Fatal error detected */ -#define EXT3_MOUNT_DATA_FLAGS 0x0C00 /* Mode for data writes: */ - #define EXT3_MOUNT_JOURNAL_DATA 0x0400 /* Write data to journal */ - #define EXT3_MOUNT_ORDERED_DATA 0x0800 /* Flush data before commit */ - #define EXT3_MOUNT_WRITEBACK_DATA 0x0C00 /* No data ordering */ -#define EXT3_MOUNT_UPDATE_JOURNAL 0x1000 /* Update the journal format */ -#define EXT3_MOUNT_NO_UID32 0x2000 /* Disable 32-bit UIDs */ -#define EXT3_MOUNT_XATTR_USER 0x4000 /* Extended user attributes */ -#define EXT3_MOUNT_POSIX_ACL 0x8000 /* POSIX Access Control Lists */ -#define EXT3_MOUNT_BARRIER 0x10000 /* Use block barriers */ +#define EXT3_MOUNT_CHECK 0x00001 /* Do mount-time checks */ +#define EXT3_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */ +#define EXT3_MOUNT_GRPID 0x00004 /* Create files with directory's group */ +#define EXT3_MOUNT_DEBUG 0x00008 /* Some debugging messages */ +#define EXT3_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ +#define EXT3_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ +#define EXT3_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ +#define EXT3_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ +#define EXT3_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ +#define EXT3_MOUNT_ABORT 0x00200 /* Fatal error detected */ +#define EXT3_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ +#define EXT3_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ +#define EXT3_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ +#define EXT3_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ +#define EXT3_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ +#define EXT3_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ +#define EXT3_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ +#define EXT3_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ +#define EXT3_MOUNT_RESERVATION 0x10000 /* Preallocation */ +#define EXT3_MOUNT_BARRIER 0x20000 /* Use block barriers */ /* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H @@ -723,6 +731,7 @@ extern void ext3_put_inode (struct inode extern void ext3_delete_inode (struct inode *); extern int ext3_sync_inode (handle_t *, struct inode *); extern void ext3_discard_prealloc (struct inode *); +extern void ext3_discard_reservation (struct inode *); extern void ext3_dirty_inode(struct inode *); extern int ext3_change_inode_journal_flag(struct inode *, int); extern void ext3_truncate (struct inode *); diff -puN include/linux/ext3_fs_i.h~ext3_rsv_base include/linux/ext3_fs_i.h --- 25/include/linux/ext3_fs_i.h~ext3_rsv_base 2004-10-21 14:54:21.025727096 -0700 +++ 25-akpm/include/linux/ext3_fs_i.h 2004-10-21 14:54:21.042724512 -0700 @@ -18,8 +18,16 @@ #include +struct reserve_window { + struct list_head rsv_list; + __u32 rsv_start; + __u32 rsv_end; + atomic_t rsv_goal_size; + __u32 rsv_alloc_hit; +}; + /* - * second extended file system inode data in memory + * third extended file system inode data in memory */ struct ext3_inode_info { __le32 i_data[15]; /* unconverted */ @@ -57,6 +65,9 @@ struct ext3_inode_info { * allocation when we detect linearly ascending requests. */ __u32 i_next_alloc_goal; + /* block reservation window */ + struct reserve_window i_rsv_window; + __u32 i_dir_start_lookup; #ifdef CONFIG_EXT3_FS_XATTR /* diff -puN include/linux/ext3_fs_sb.h~ext3_rsv_base include/linux/ext3_fs_sb.h --- 25/include/linux/ext3_fs_sb.h~ext3_rsv_base 2004-10-21 14:54:21.026726944 -0700 +++ 25-akpm/include/linux/ext3_fs_sb.h 2004-10-21 14:54:21.042724512 -0700 @@ -59,6 +59,10 @@ struct ext3_sb_info { struct percpu_counter s_dirs_counter; struct blockgroup_lock s_blockgroup_lock; + /* head of the per fs reservation window tree */ + spinlock_t s_rsv_window_lock; + struct reserve_window s_rsv_window_head; + /* Journaling */ struct inode * s_journal_inode; struct journal_s * s_journal; _