aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/filesystems/ext4.txt25
-rw-r--r--fs/ext4/super.c30
2 files changed, 45 insertions, 10 deletions
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 5c484aec2ba..97882df0486 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -183,8 +183,8 @@ commit=nrsec (*) Ext4 can be told to sync all its data and metadata
performance.
barrier=<0|1(*)> This enables/disables the use of write barriers in
- the jbd code. barrier=0 disables, barrier=1 enables.
- This also requires an IO stack which can support
+barrier(*) the jbd code. barrier=0 disables, barrier=1 enables.
+nobarrier This also requires an IO stack which can support
barriers, and if jbd gets an error on a barrier
write, it will disable again with a warning.
Write barriers enforce proper on-disk ordering
@@ -192,6 +192,9 @@ barrier=<0|1(*)> This enables/disables the use of write barriers in
safe to use, at some performance penalty. If
your disks are battery-backed in one way or another,
disabling barriers may safely improve performance.
+ The mount options "barrier" and "nobarrier" can
+ also be used to enable or disable barriers, for
+ consistency with other ext4 mount options.
inode_readahead=n This tuning parameter controls the maximum
number of inode table blocks that ext4's inode
@@ -313,6 +316,24 @@ journal_ioprio=prio The I/O priority (from 0 to 7, where 0 is the
a slightly higher priority than the default I/O
priority.
+auto_da_alloc(*) Many broken applications don't use fsync() when
+noauto_da_alloc replacing existing files via patterns such as
+ fd = open("foo.new")/write(fd,..)/close(fd)/
+ rename("foo.new", "foo"), or worse yet,
+ fd = open("foo", O_TRUNC)/write(fd,..)/close(fd).
+ If auto_da_alloc is enabled, ext4 will detect
+ the replace-via-rename and replace-via-truncate
+ patterns and force that any delayed allocation
+ blocks are allocated such that at the next
+ journal commit, in the default data=ordered
+ mode, the data blocks of the new file are forced
+ to disk before the rename() operation is
+ commited. This provides roughly the same level
+ of guarantees as ext3, and avoids the
+ "zero-length" problem that can happen when a
+ system crashes before the delayed allocation
+ blocks are forced to disk.
+
Data Mode
=========
There are 3 different data modes:
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 45d07cf9df3..9987bba99db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -867,7 +867,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",data_err=abort");
if (test_opt(sb, NO_AUTO_DA_ALLOC))
- seq_puts(seq, ",auto_da_alloc=0");
+ seq_puts(seq, ",noauto_da_alloc");
ext4_show_quota_options(seq, sb);
return 0;
@@ -1018,7 +1018,7 @@ enum {
Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
- Opt_auto_da_alloc, Opt_noload, Opt_nobh, Opt_bh,
+ Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_nobh, Opt_bh,
Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
Opt_journal_update, Opt_journal_dev,
Opt_journal_checksum, Opt_journal_async_commit,
@@ -1026,8 +1026,8 @@ enum {
Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
- Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
- Opt_grpquota, Opt_i_version,
+ Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize,
+ Opt_usrquota, Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
Opt_inode_readahead_blks, Opt_journal_ioprio
};
@@ -1080,6 +1080,8 @@ static const match_table_t tokens = {
{Opt_quota, "quota"},
{Opt_usrquota, "usrquota"},
{Opt_barrier, "barrier=%u"},
+ {Opt_barrier, "barrier"},
+ {Opt_nobarrier, "nobarrier"},
{Opt_i_version, "i_version"},
{Opt_stripe, "stripe=%u"},
{Opt_resize, "resize"},
@@ -1088,6 +1090,8 @@ static const match_table_t tokens = {
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
{Opt_journal_ioprio, "journal_ioprio=%u"},
{Opt_auto_da_alloc, "auto_da_alloc=%u"},
+ {Opt_auto_da_alloc, "auto_da_alloc"},
+ {Opt_noauto_da_alloc, "noauto_da_alloc"},
{Opt_err, NULL},
};
@@ -1422,9 +1426,14 @@ set_qf_format:
case Opt_abort:
set_opt(sbi->s_mount_opt, ABORT);
break;
+ case Opt_nobarrier:
+ clear_opt(sbi->s_mount_opt, BARRIER);
+ break;
case Opt_barrier:
- if (match_int(&args[0], &option))
- return 0;
+ if (match_int(&args[0], &option)) {
+ set_opt(sbi->s_mount_opt, BARRIER);
+ break;
+ }
if (option)
set_opt(sbi->s_mount_opt, BARRIER);
else
@@ -1485,9 +1494,14 @@ set_qf_format:
*journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE,
option);
break;
+ case Opt_noauto_da_alloc:
+ set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
+ break;
case Opt_auto_da_alloc:
- if (match_int(&args[0], &option))
- return 0;
+ if (match_int(&args[0], &option)) {
+ clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
+ break;
+ }
if (option)
clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
else