From a2f4870697a5bcf4a87073ec6b32dd2928c1211d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 17 Mar 2015 12:23:19 -0400 Subject: fs: make sure the timestamps for lazytime inodes eventually get written Jan Kara pointed out that if there is an inode which is constantly getting dirtied with I_DIRTY_PAGES, an inode with an updated timestamp will never be written since inode->dirtied_when is constantly getting updated. We fix this by adding an extra field to the inode, dirtied_time_when, so inodes with a stale dirtytime can get detected and handled. In addition, if we have a dirtytime inode caused by an atime update, and there is no write activity on the file system, we need to have a secondary system to make sure these inodes get written out. We do this by setting up a second delayed work structure which wakes up the CPU much more rarely compared to writeback_expire_centisecs. Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b4d71b5e1ff2..f4131e8ead74 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -604,6 +604,7 @@ struct inode { struct mutex i_mutex; unsigned long dirtied_when; /* jiffies of first dirtying */ + unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_wb_list; /* backing dev IO list */ -- cgit v1.2.3 From 1efff914afac8a965ad63817ecf8861a927c2ace Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 17 Mar 2015 12:23:32 -0400 Subject: fs: add dirtytime_expire_seconds sysctl Add a tuning knob so we can adjust the dirtytime expiration timeout, which is very useful for testing lazytime. Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/fs-writeback.c | 11 +++++++++++ include/linux/writeback.h | 3 +++ kernel/sysctl.c | 8 ++++++++ 3 files changed, 22 insertions(+) (limited to 'include') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 2cfcd74faf87..32a8bbd7a9ad 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1188,6 +1188,17 @@ static int __init start_dirtytime_writeback(void) } __initcall(start_dirtytime_writeback); +int dirtytime_interval_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + mod_delayed_work(system_wq, &dirtytime_work, 0); + return ret; +} + static noinline void block_dump___mark_inode_dirty(struct inode *inode) { if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 00048339c23e..b2dd371ec0ca 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -130,6 +130,7 @@ extern int vm_dirty_ratio; extern unsigned long vm_dirty_bytes; extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; +extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; @@ -146,6 +147,8 @@ extern int dirty_ratio_handler(struct ctl_table *table, int write, extern int dirty_bytes_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +int dirtytime_interval_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); struct ctl_table; int dirty_writeback_centisecs_handler(struct ctl_table *, int, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 88ea2d6e0031..ce410bb9f2e1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1227,6 +1227,14 @@ static struct ctl_table vm_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, + { + .procname = "dirtytime_expire_seconds", + .data = &dirtytime_expire_interval, + .maxlen = sizeof(dirty_expire_interval), + .mode = 0644, + .proc_handler = dirtytime_interval_handler, + .extra1 = &zero, + }, { .procname = "nr_pdflush_threads", .mode = 0444 /* read-only */, -- cgit v1.2.3