Sending #3, improved reiserfs_file_write for 2.5.64
PATCH 1/1 Sending #3, improved reiserfs_file_write for 2.5.64
Signature · 2 lines
-- Hans
Hello!
These three changesets implement reiserfs_file_write. Also third one exports generic_osync_inode,block_commit_write and remove_suid because these are now needed for reiserfs.
There was no reiserfs_file_write in the 2.4 port of reiserfs (and Hans was very unhappy about it).
With current 'one block at a time' algorithm, writes past the end of a file are slow because each new file block is separately added into the tree causing shifting of other items which is CPU expensive.
With this new implementation if you write into file with big enough chunks, it uses half as much CPU. Also this version is more SMP friendly than the current one.
There are some known-bad applications that break with this patch (ie. start to work very slow or even hang), particularly
kmail 3.04 (and earlier?) (consider upgrading to 3.1+).
If you hit a slowdown problem that you believe is related to increased "recommended i/o size", try to mount your fs with nolargeio=1 mount option (remount should work too).
You can pull these from bk://thebsh.namesys.com/bk/reiser3-linux-2.5-reiserfs_file_write
Diffstat:
fs/reiserfs/bitmap.c | 21 fs/reiserfs/do_balan.c | 104 ++-- fs/reiserfs/file.c | 1013 ++++++++++++++++++++++++++++++++++++++++- fs/reiserfs/inode.c | 54 +- fs/reiserfs/super.c | 11 fs/reiserfs/tail_conversion.c | 5 include/linux/reiserfs_fs.h | 4 include/linux/reiserfs_fs_sb.h | 1 kernel/ksyms.c | 3 9 files changed, 1148 insertions(+), 68 deletions(-)
Plain text patch:
# This is a BitKeeper generated patch for the following project:
# Project Name: Linux kernel tree
# This patch format is intended for GNU patch command version 2.5 or higher. # This patch includes the following deltas:
# ChangeSet 1.1085 -> 1.1088 # fs/reiserfs/file.c 1.18 -> 1.19 # kernel/ksyms.c 1.185 -> 1.186
# fs/reiserfs/do_balan.c 1.16 -> 1.17
# fs/reiserfs/inode.c 1.72 -> 1.74
# fs/reiserfs/super.c 1.59 -> 1.60
# include/linux/reiserfs_fs_sb.h 1.20 -> 1.21
# fs/reiserfs/bitmap.c 1.25 -> 1.26
# include/linux/reiserfs_fs.h 1.46 -> 1.47
# fs/reiserfs/tail_conversion.c 1.23 -> 1.24
#
# The following is the BitKeeper ChangeSet Log
# --------------------------------------------
# 03/03/05 [email protected] 1.1086
# reiserfs: Implement insertion of more than one unformatted pointer insertion at a time. This considerably speedups hole creation. # --------------------------------------------
# 03/03/05 [email protected] 1.1087
# reiserfs: reiserfs_file_write() implemenation. Ported from 2.4.
#
# This code should considerably speedup file appends in reiserfs,
# given that callers would do than in large chunks. In order # to iincerease amount of applications that will do I/O in large # chunks, the "recommended i/o size" st_blksize field in result # returned by stat() is set to 128k. # There are some known-bad applications that break in this case # (ie. start to work very slow or even hang), particularly # kmail 3.04 (and earlier?) (consider upgrading to 3.1+). # If you hit a slowdown problem that you believe is related to # increased "recommended i/o size", try to mount your fs with # nolargeio=1 mount option (remount should work too). # Of course in general you should better fix broken apps, not # disable this useful enchancement. # -------------------------------------------- # 03/03/05 [email protected] 1.1088 # export generic_osync_inode, block_commit_write, remove_suid. These are now used by reiserfs. # -------------------------------------------- # diff -Nru a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c --- a/fs/reiserfs/bitmap.c Wed Mar 5 13:44:35 2003 +++ b/fs/reiserfs/bitmap.c Wed Mar 5 13:44:35 2003 @@ -9,6 +9,7 @@ #include <linux/errno.h> #include <linux/buffer_head.h> #include <linux/kernel.h> +#include <linux/pagemap.h> #include <linux/reiserfs_fs_sb.h> #include <linux/reiserfs_fs_i.h>
@@ -733,7 +734,7 @@
int rest = amount_needed;
int nr_allocated;- while (rest > 0) {
+ while (rest > 0 && start <= finish) {
nr_allocated = scan_bitmap (hint->th, &start, finish, 1,
rest + prealloc_size, !hint->formatted_node, hint->block);
@@ -879,7 +880,9 @@
if ( !blocks )
return;
+ spin_lock(&REISERFS_SB(sb)->bitmap_lock);
REISERFS_SB(sb)->reserved_blocks += blocks;+ spin_unlock(&REISERFS_SB(sb)->bitmap_lock);
}
/* Unreserve @blocks amount of blocks in fs pointed by @sb */
@@ -896,6 +899,22 @@
if ( !blocks )
return;
+ spin_lock(&REISERFS_SB(sb)->bitmap_lock);
REISERFS_SB(sb)->reserved_blocks -= blocks;
+ spin_unlock(&REISERFS_SB(sb)->bitmap_lock);
RFALSE( REISERFS_SB(sb)->reserved_blocks < 0, "amount of blocks reserved became zero?");+}
+
+/* This function estimates how much pages we will be able to write to FS
+ used for reiserfs_file_write() purposes for now. */
+int reiserfs_can_fit_pages ( struct super_block *sb /* superblock of filesystem
+ to estimate space */ )
+{
+ unsigned long space;
+
+ spin_lock(&REISERFS_SB(sb)->bitmap_lock);
+ space = (SB_FREE_BLOCKS(sb) - REISERFS_SB(sb)->reserved_blocks) >> ( PAGE_CACHE_SHIFT - sb->s_blocksize_bits);
+ spin_unlock(&REISERFS_SB(sb)->bitmap_lock);
+
+ return space;
}
fs/reiserfs/do_balan.c +52 -52
@@ -319,8 +319,6 @@int new_item_len;int version; -RFALSE (!is_direct_le_ih (ih), -"PAP-12075: only direct inserted item can be broken. %h" , ih); ret_val =leaf_shift_left (tb, tb->lnum[0 ]-1 ,-1 );/* Calculate item length to insert to S[0] */
@@ -343,7 +341,7 @@ version =ih_version (ih);/* Calculate key component, item length and body to insert into S[0] */ -set_le_ih_k_offset ( ih,le_ih_k_offset ( ih ) + tb->lbytes ); +set_le_ih_k_offset ( ih,le_ih_k_offset ( ih ) + (tb->lbytes << (is_indirect_le_ih (ih)?tb->tb_sb->s_blocksize_bits -UNFM_P_SHIFT :0 )) );put_ih_item_len ( ih, new_item_len );if ( tb->lbytes > zeros_num ) {
@@ -452,23 +450,28 @@ih_item_len (B_N_PITEM_HEAD (tb->L[0 ],n+item_pos-ret_val)), l_n,body, zeros_num > l_n ? l_n : zeros_num ); - -RFALSE ( l_n && -is_indirect_le_ih (B_N_PITEM_HEAD - (tb->L[0 ], - n + item_pos - ret_val)), -"PAP-12110: pasting more than 1 unformatted node pointer into indirect item" ); -/* 0-th item in S0 can be only of DIRECT type when l_n != 0*/ { -int version; - - version =ih_version (B_N_PITEM_HEAD (tbS0,0 )); -set_le_key_k_offset (version,B_N_PKEY (tbS0,0 ), -le_key_k_offset (version,B_N_PKEY (tbS0,0 )) + l_n); - version =ih_version (B_N_PITEM_HEAD (tb->CFL[0 ],tb->lkey[0 ])); -set_le_key_k_offset (version,B_N_PDELIM_KEY (tb->CFL[0 ],tb->lkey[0 ]), -le_key_k_offset (version,B_N_PDELIM_KEY (tb->CFL[0 ],tb->lkey[0 ])) + l_n); +int version; +int temp_l = l_n; + +RFALSE (ih_item_len (B_N_PITEM_HEAD (tbS0,0 )), +"PAP-12106: item length must be 0" ); +RFALSE (comp_short_le_keys (B_N_PKEY (tbS0,0 ), +B_N_PKEY (tb->L[0 ], + n + item_pos - ret_val)), +"PAP-12107: items must be of the same file" ); +if (is_indirect_le_ih (B_N_PITEM_HEAD (tb->L[0 ], + n + item_pos - ret_val))) { + temp_l = l_n << (tb->tb_sb->s_blocksize_bits -UNFM_P_SHIFT ); + } +/* update key of first item in S0 */ + version =ih_version (B_N_PITEM_HEAD (tbS0,0 )); +set_le_key_k_offset (version,B_N_PKEY (tbS0,0 ), +le_key_k_offset (version,B_N_PKEY (tbS0,0 )) + temp_l); +/* update left delimiting key */ +set_le_key_k_offset (version,B_N_PDELIM_KEY (tb->CFL[0 ],tb->lkey[0 ]), +le_key_k_offset (version,B_N_PDELIM_KEY (tb->CFL[0 ],tb->lkey[0 ])) + temp_l); }/* Calculate new body, position in item and insert_size[0] */
@@ -537,7 +540,7 @@ );/* if appended item is indirect item, put unformatted node into un list */ if (is_indirect_le_ih (pasted)) -set_ih_free_space (pasted, ((struct unfm_nodeinfo *)body)->unfm_freespace); +set_ih_free_space (pasted,0 ); tb->insert_size[0 ] =0 ; zeros_num =0 ; }
@@ -565,15 +568,11 @@ {/* new item or its part falls to R[0] */ if ( item_pos == n - tb->rnum[0 ] +1 && tb->rbytes !=-1 ) {/* part of new item falls into R[0] */ -int old_key_comp, old_len, r_zeros_number; +loff_t old_key_comp, old_len, r_zeros_number;const char * r_body;int version;loff_t offset; -RFALSE ( !is_direct_le_ih (ih), -"PAP-12135: only direct item can be split. (%h)" , - ih); -leaf_shift_right (tb,tb->rnum[0 ]-1 ,-1 ); version =ih_version (ih);
@@ -582,7 +581,7 @@ old_len =ih_item_len (ih);/* Calculate key component and item length to insert into R[0] */ - offset =le_ih_k_offset ( ih ) + (old_len - tb->rbytes ); + offset =le_ih_k_offset ( ih ) + ((old_len - tb->rbytes )<<(is_indirect_le_ih (ih)?tb->tb_sb->s_blocksize_bits -UNFM_P_SHIFT :0 ));set_le_ih_k_offset ( ih, offset );put_ih_item_len ( ih, tb->rbytes);/* Insert part of the item into R[0] */
@@ -590,13 +589,13 @@ bi.bi_bh = tb->R[0 ]; bi.bi_parent = tb->FR[0 ]; bi.bi_position =get_right_neighbor_position (tb,0 ); -if ( offset - old_key_comp > zeros_num ) { +if ( (old_len - tb->rbytes) > zeros_num ) { r_zeros_number =0 ; - r_body = body + offset - old_key_comp - zeros_num; + r_body = body + (old_len - tb->rbytes) - zeros_num; }else { r_body = body; - r_zeros_number = zeros_num - (offset - old_key_comp); + r_zeros_number = zeros_num - (old_len - tb->rbytes); zeros_num -= r_zeros_number; }
@@ -707,12 +706,17 @@ {int version; +unsigned long temp_rem = n_rem; version =ih_version (B_N_PITEM_HEAD (tb->R[0 ],0 )); +if (is_indirect_le_key (version,B_N_PKEY (tb->R[0 ],0 ))){ + temp_rem = n_rem << (tb->tb_sb->s_blocksize_bits - +UNFM_P_SHIFT ); + }set_le_key_k_offset (version,B_N_PKEY (tb->R[0 ],0 ), -le_key_k_offset (version,B_N_PKEY (tb->R[0 ],0 )) + n_rem); +le_key_k_offset (version,B_N_PKEY (tb->R[0 ],0 )) + temp_rem);set_le_key_k_offset (version,B_N_PDELIM_KEY (tb->CFR[0 ],tb->rkey[0 ]), -le_key_k_offset (version,B_N_PDELIM_KEY (tb->CFR[0 ],tb->rkey[0 ])) + n_rem); +le_key_k_offset (version,B_N_PDELIM_KEY (tb->CFR[0 ],tb->rkey[0 ])) + temp_rem); }/* k_offset (B_N_PKEY(tb->R[0],0)) += n_rem; k_offset (B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) += n_rem;*/
@@ -736,13 +740,12 @@leaf_paste_in_buffer (&bi,0 , n_shift, tb->insert_size[0 ] - n_rem, r_body, r_zeros_number);if (is_indirect_le_ih (B_N_PITEM_HEAD (tb->R[0 ],0 ))) { - +#if 0 RFALSE ( n_rem,"PAP-12160: paste more than one unformatted node pointer" ); - -set_ih_free_space (B_N_PITEM_HEAD (tb->R[0 ],0 ), ((struct unfm_nodeinfo *)body)->unfm_freespace); +#endif +set_ih_free_space (B_N_PITEM_HEAD (tb->R[0 ],0 ),0 ); } - tb->insert_size[0 ] = n_rem;if ( ! n_rem ) pos_in_item ++;
@@ -781,7 +784,7 @@ }if (is_indirect_le_ih (pasted)) -set_ih_free_space (pasted, ((struct unfm_nodeinfo *)body)->unfm_freespace); +set_ih_free_space (pasted,0 ); zeros_num = tb->insert_size[0 ] =0 ; } }
@@ -858,12 +861,6 @@const char * r_body;int version; -RFALSE ( !is_direct_le_ih (ih), -/* The items which can be inserted are: -Stat_data item, direct item, indirect item and directory item which consist of only two entries "." and "..". -These items must not be broken except for a direct one. */ -"PAP-12205: non-direct item can not be broken when inserting" ); -/* Move snum[i]-1 items from S[0] to S_new[i] */ leaf_move_items (LEAF_FROM_S_TO_SNEW , tb, snum[i] -1 ,-1 , S_new[i]);/* Remember key component and item length */
@@ -873,7 +870,7 @@/* Calculate key component and item length to insert into S_new[i] */ set_le_ih_k_offset ( ih, -le_ih_k_offset (ih) + (old_len - sbytes[i] ) ); +le_ih_k_offset (ih) + ((old_len - sbytes[i] )<<(is_indirect_le_ih (ih)?tb->tb_sb->s_blocksize_bits -UNFM_P_SHIFT :0 )) );put_ih_item_len ( ih, sbytes[i] );
@@ -883,13 +880,13 @@ bi.bi_parent =0 ; bi.bi_position =0 ; -if (le_ih_k_offset (ih) - old_key_comp > zeros_num ) { +if ( (old_len - sbytes[i]) > zeros_num ) { r_zeros_number =0 ; - r_body = body + (le_ih_k_offset (ih) - old_key_comp) - zeros_num; + r_body = body + (old_len - sbytes[i]) - zeros_num; }else { r_body = body; - r_zeros_number = zeros_num - (le_ih_k_offset (ih) - old_key_comp); + r_zeros_number = zeros_num - (old_len - sbytes[i]); zeros_num -= r_zeros_number; }
@@ -1010,11 +1007,13 @@ tmp =B_N_PITEM_HEAD (S_new[i],0 );if (is_indirect_le_ih (tmp)) { -if (n_rem) -reiserfs_panic (tb->tb_sb,"PAP-12230: balance_leaf: invalid action with indirect item" ); -set_ih_free_space (tmp, ((struct unfm_nodeinfo *)body)->unfm_freespace); +set_ih_free_space (tmp,0 ); +set_le_ih_k_offset ( tmp,le_ih_k_offset (tmp) + + (n_rem << (tb->tb_sb->s_blocksize_bits -UNFM_P_SHIFT ))); + }else { +set_le_ih_k_offset ( tmp,le_ih_k_offset (tmp) + + n_rem ); } -set_le_ih_k_offset ( tmp,le_ih_k_offset (tmp) + n_rem ); } tb->insert_size[0 ] = n_rem;
@@ -1060,7 +1059,7 @@/* if we paste to indirect item update ih_free_space */ if (is_indirect_le_ih (pasted)) -set_ih_free_space (pasted, ((struct unfm_nodeinfo *)body)->unfm_freespace); +set_ih_free_space (pasted,0 ); zeros_num = tb->insert_size[0 ] =0 ; } }
@@ -1152,11 +1151,12 @@leaf_paste_in_buffer (&bi, item_pos, pos_in_item, tb->insert_size[0 ], body, zeros_num);if (is_indirect_le_ih (pasted)) { - +#if 0 RFALSE ( tb->insert_size[0 ] !=UNFM_P_SIZE ,"PAP-12280: insert_size for indirect item must be %d, not %d" ,UNFM_P_SIZE , tb->insert_size[0 ]); -set_ih_free_space (pasted, ((struct unfm_nodeinfo *)body)->unfm_freespace); +#endif +set_ih_free_space (pasted,0 ); } tb->insert_size[0 ] =0 ; }
fs/reiserfs/file.c +1012 -1
1,027 lines not on this page · raw message
fs/reiserfs/inode.c +44 -10
101 lines not on this page · raw message
fs/reiserfs/super.c +11 -0
@@ -532,6 +532,11 @@ {NULL, 0} }; +int reiserfs_default_io_size =128 *1024 ;/* Default recommended I/O size is 128k. +There might be broken applications that are +confused by this. Use nolargeio mount option +to get usual i/o size = PAGE_SIZE. +*/ /* proceed only one option from a list *cur - string containing of mount options opts - array of options which are accepted
@@ -657,6 +662,7 @@ {"block-allocator", 'a', balloc, -1}, {"resize", 'r', 0, -1}, {"jdev", 'j', 0, -1}, + {"nolargeio", 'w', 0, -1}, {NULL, 0, 0, -1} };
@@ -688,6 +694,10 @@ } } +if ( c =='w' ) { + reiserfs_default_io_size =PAGE_SIZE ; + } +if (c =='j' ) {if (arg && *arg && jdev_name) { *jdev_name = arg;
@@ -1318,6 +1328,7 @@reiserfs_proc_register ( s,"oidmap" , reiserfs_oidmap_in_proc );reiserfs_proc_register ( s,"journal" , reiserfs_journal_in_proc );init_waitqueue_head (&(sbi->s_wait)); + sbi->bitmap_lock =SPIN_LOCK_UNLOCKED ;return (0 );
fs/reiserfs/tail_conversion.c +2 -3
@@ -30,7 +30,7 @@key of unfm pointer to be pasted */ int n_blk_size, n_retval;/* returned value for reiserfs_insert_item and clones */ -struct unfm_nodeinfo unfm_ptr;/* Handle on an unformatted node +unp_t unfm_ptr;/* Handle on an unformatted node that will be inserted in the tree. */
@@ -59,8 +59,7 @@ p_le_ih =PATH_PITEM_HEAD (path); - unfm_ptr.unfm_nodenum =cpu_to_le32 (unbh->b_blocknr); - unfm_ptr.unfm_freespace =0 ;// ??? + unfm_ptr =cpu_to_le32 (unbh->b_blocknr);if (is_statdata_le_ih (p_le_ih) ) {/* Insert new indirect item. */
include/linux/reiserfs_fs.h +3 -1
@@ -1268,6 +1268,7 @@/* Size of pointer to the unformatted node. */ #define UNFM_P_SIZE (sizeof(unp_t)) +#define UNFM_P_SHIFT 2// in in-core inode key is stored on le form #define INODE_PKEY (inode) ((struct key *)(REISERFS_I(inode)->i_key))
@@ -1838,7 +1839,7 @@void padd_item (char * item,int total_length,int length);/* inode.c */ - +void restart_transaction (struct reiserfs_transaction_handle *th,struct inode *inode,struct path *path);void reiserfs_read_locked_inode (struct inode * inode,struct reiserfs_iget_args *args) ;int reiserfs_find_actor (struct inode * inode,void *p) ;int reiserfs_init_locked_inode (struct inode * inode,void *p) ;
@@ -2111,6 +2112,7 @@#endif void reiserfs_claim_blocks_to_be_allocated (struct super_block *sb,int blocks);void reiserfs_release_claimed_blocks (struct super_block *sb,int blocks); +int reiserfs_can_fit_pages (struct super_block *sb);/* hashes.c */ __u32 keyed_hash (const signed char *msg,int len);
include/linux/reiserfs_fs_sb.h +1 -0
@@ -397,6 +397,7 @@reiserfs_proc_info_data_t s_proc_info_data;struct proc_dir_entry *procdir;int reserved_blocks;/* amount of blocks reserved for further allocations */ +spinlock_t bitmap_lock;/* this lock on now only used to protect reserved_blocks variable */ };/* Definitions of reiserfs on-disk properties: */
kernel/ksyms.c +3 -0
@@ -223,6 +223,7 @@EXPORT_SYMBOL (generic_cont_expand);EXPORT_SYMBOL (cont_prepare_write);EXPORT_SYMBOL (generic_commit_write); +EXPORT_SYMBOL (block_commit_write);EXPORT_SYMBOL (block_truncate_page);EXPORT_SYMBOL (generic_block_bmap);EXPORT_SYMBOL (generic_file_read);
@@ -571,6 +572,8 @@EXPORT_SYMBOL (make_bad_inode);EXPORT_SYMBOL (is_bad_inode);EXPORT_SYMBOL (__inode_dir_notify); +EXPORT_SYMBOL (generic_osync_inode); +EXPORT_SYMBOL (remove_suid);#ifdef CONFIG_UID16 EXPORT_SYMBOL (overflowuid);