2009-01-05 05:32:31

by Theodore Ts'o

[permalink] [raw]
Subject: [PATCH] ext4: Add mount option to set kjournald's I/O priority

Signed-off-by: "Theodore Ts'o" <[email protected]>
Cc: Jens Axboe <[email protected]>
---
Documentation/filesystems/ext4.txt | 7 +++++++
fs/ext4/super.c | 29 +++++++++++++++++++++++++----
fs/ioprio.c | 3 ++-
include/linux/ioprio.h | 2 ++
4 files changed, 36 insertions(+), 5 deletions(-)

diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 3024f74..eb7b4ae 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -295,6 +295,13 @@ min_batch_time=usec This parameter sets the commit time (as
multi-threaded, synchronous workloads on very
fast disks, at the cost of increasing latency.

+journal_ioprio=prio The I/O priority (from 0 to 7, where 0 is the
+ highest priorty) which should be used for I/O
+ operations submitted by kjournald2 during a
+ commit operation. This defaults to 3, which is
+ a slightly higher priority than the default I/O
+ priority.
+
Data Mode
=========
There are 3 different data modes:
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d64d1c9..2650053 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1013,7 +1013,7 @@ enum {
Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
- Opt_inode_readahead_blks
+ Opt_inode_readahead_blks, Opt_journal_ioprio
};

static const match_table_t tokens = {
@@ -1074,6 +1074,7 @@ static const match_table_t tokens = {
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
+ {Opt_journal_ioprio, "journal_ioprio=%u"},
{Opt_err, NULL},
};

@@ -1098,8 +1099,11 @@ static ext4_fsblk_t get_sb_block(void **data)
return sb_block;
}

+#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+
static int parse_options(char *options, struct super_block *sb,
unsigned long *journal_devnum,
+ unsigned int *journal_ioprio,
ext4_fsblk_t *n_blocks_count, int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -1492,6 +1496,14 @@ set_qf_format:
return 0;
sbi->s_inode_readahead_blks = option;
break;
+ case Opt_journal_ioprio:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0 || option > 7)
+ break;
+ *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE,
+ option);
+ break;
default:
printk(KERN_ERR
"EXT4-fs: Unrecognized mount option \"%s\" "
@@ -1523,6 +1535,7 @@ set_qf_format:
"not specified.\n");
return 0;
}
+ set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
} else {
if (sbi->s_jquota_fmt) {
printk(KERN_ERR "EXT4-fs: journaled quota format "
@@ -2035,6 +2048,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
int features;
__u64 blocks_count;
int err;
+ unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;

sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
@@ -2141,7 +2155,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
set_opt(sbi->s_mount_opt, DELALLOC);


- if (!parse_options((char *) data, sb, &journal_devnum, NULL, 0))
+ if (!parse_options((char *) data, sb, &journal_devnum,
+ &journal_ioprio, NULL, 0))
goto failed_mount;

sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
@@ -3123,6 +3138,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
unsigned long old_sb_flags;
struct ext4_mount_options old_opts;
ext4_group_t g;
+ unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err;
#ifdef CONFIG_QUOTA
int i;
@@ -3141,11 +3157,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
for (i = 0; i < MAXQUOTAS; i++)
old_opts.s_qf_names[i] = sbi->s_qf_names[i];
#endif
+ if (sbi->s_journal && sbi->s_journal->j_task->io_context)
+ journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;

/*
* Allow the "check" option to be passed as a remount option.
*/
- if (!parse_options(data, sb, NULL, &n_blocks_count, 1)) {
+ if (!parse_options(data, sb, NULL, &journal_ioprio,
+ &n_blocks_count, 1)) {
err = -EINVAL;
goto restore_opts;
}
@@ -3158,8 +3177,10 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)

es = sbi->s_es;

- if (sbi->s_journal)
+ if (sbi->s_journal) {
ext4_init_journal_params(sb, sbi->s_journal);
+ set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+ }

if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
n_blocks_count > ext4_blocks_count(es)) {
diff --git a/fs/ioprio.c b/fs/ioprio.c
index da3cc46..3bd95dc 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -27,7 +27,7 @@
#include <linux/security.h>
#include <linux/pid_namespace.h>

-static int set_task_ioprio(struct task_struct *task, int ioprio)
+int set_task_ioprio(struct task_struct *task, int ioprio)
{
int err;
struct io_context *ioc;
@@ -64,6 +64,7 @@ static int set_task_ioprio(struct task_struct *task, int ioprio)
task_unlock(task);
return err;
}
+EXPORT_SYMBOL_GPL(set_task_ioprio);

asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
{
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index f98a656..76dad48 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -86,4 +86,6 @@ static inline int task_nice_ioclass(struct task_struct *task)
*/
extern int ioprio_best(unsigned short aprio, unsigned short bprio);

+extern int set_task_ioprio(struct task_struct *task, int ioprio);
+
#endif
--
1.6.0.4.8.g36f27.dirty