vfs: add support for a lazytime mount option

Add a new mount option which enables a new "lazytime" mode.  This mode
causes atime, mtime, and ctime updates to only be made to the
in-memory version of the inode.  The on-disk times will only get
updated when (a) if the inode needs to be updated for some non-time
related change, (b) if userspace calls fsync(), syncfs() or sync(), or
(c) just before an undeleted inode is evicted from memory.

This is OK according to POSIX because there are no guarantees after a
crash unless userspace explicitly requests via a fsync(2) call.

For workloads which feature a large number of random write to a
preallocated file, the lazytime mount option significantly reduces
writes to the inode table.  The repeated 4k writes to a single block
will result in undesirable stress on flash devices and SMR disk
drives.  Even on conventional HDD's, the repeated writes to the inode
table block will trigger Adjacent Track Interference (ATI) remediation
latencies, which very negatively impact long tail latencies --- which
is a very big deal for web serving tiers (for example).

Google-Bug-Id: 18297052

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 8 insertions, 2 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 0ae0df55000b..915feea94c66 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -69,10 +69,10 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
         unsigned long background_thresh;
         unsigned long dirty_thresh;
         unsigned long bdi_thresh;
-        unsigned long nr_dirty, nr_io, nr_more_io;
+        unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time;
         struct inode *inode;
 
-        nr_dirty = nr_io = nr_more_io = 0;
+        nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0;
         spin_lock(&wb->list_lock);
         list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
                 nr_dirty++;
@@ -80,6 +80,9 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
                 nr_io++;
         list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
                 nr_more_io++;
+        list_for_each_entry(inode, &wb->b_dirty_time, i_wb_list)
+                if (inode->i_state & I_DIRTY_TIME)
+                        nr_dirty_time++;
         spin_unlock(&wb->list_lock);
 
         global_dirty_limits(&background_thresh, &dirty_thresh);
@@ -98,6 +101,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
                    "b_dirty:            %10lu\n"
                    "b_io:               %10lu\n"
                    "b_more_io:          %10lu\n"
+                   "b_dirty_time:       %10lu\n"
                    "bdi_list:           %10u\n"
                    "state:              %10lx\n",
                    (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
@@ -111,6 +115,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
                    nr_dirty,
                    nr_io,
                    nr_more_io,
+                   nr_dirty_time,
                    !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 
@@ -418,6 +423,7 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
         INIT_LIST_HEAD(&wb->b_dirty);
         INIT_LIST_HEAD(&wb->b_io);
         INIT_LIST_HEAD(&wb->b_more_io);
+        INIT_LIST_HEAD(&wb->b_dirty_time);
         spin_lock_init(&wb->list_lock);
         INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
 }