From 189d3c4a94ef19fca2a71a6a336e9fda900e25e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Apr 2008 00:54:35 -0700 Subject: mm: bdi: allow setting a minimum for the bdi dirty limit Under normal circumstances each device is given a part of the total write-back cache that relates to its current avg writeout speed in relation to the other devices. min_ratio - allows one to assign a minimum portion of the write-back cache to a particular device. This is useful in situations where you might want to provide a minimum QoS. (One request for this feature came from flash based storage people who wanted to avoid writing out at all costs - they of course needed some pdflush hacks as well) max_ratio - allows one to assign a maximum portion of the dirty limit to a particular device. This is useful in situations where you want to avoid one device taking all or most of the write-back cache. Eg. an NFS mount that is prone to get stuck, or a FUSE mount which you don't trust to play fair. Add "min_ratio" to /sys/class/bdi. This indicates the minimum percentage of the global dirty threshold allocated to this bdi. [mszeredi@suse.cz] - fix parsing in min_ratio_store() - document new sysfs attribute Signed-off-by: Peter Zijlstra Signed-off-by: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e5b6b1190a9..4ac077f4269 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -242,6 +242,29 @@ static void task_dirty_limit(struct task_struct *tsk, long *pdirty) *pdirty = dirty; } +/* + * + */ +static DEFINE_SPINLOCK(bdi_lock); +static unsigned int bdi_min_ratio; + +int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) +{ + int ret = 0; + unsigned long flags; + + spin_lock_irqsave(&bdi_lock, flags); + min_ratio -= bdi->min_ratio; + if (bdi_min_ratio + min_ratio < 100) { + bdi_min_ratio += min_ratio; + bdi->min_ratio += min_ratio; + } else + ret = -EINVAL; + spin_unlock_irqrestore(&bdi_lock, flags); + + return ret; +} + /* * Work out the current dirty-memory clamping and background writeout * thresholds. @@ -330,7 +353,7 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty, *pdirty = dirty; if (bdi) { - u64 bdi_dirty = dirty; + u64 bdi_dirty; long numerator, denominator; /* @@ -338,8 +361,10 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty, */ bdi_writeout_fraction(bdi, &numerator, &denominator); + bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100; bdi_dirty *= numerator; do_div(bdi_dirty, denominator); + bdi_dirty += (dirty * bdi->min_ratio) / 100; *pbdi_dirty = bdi_dirty; clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty); -- cgit v1.2.3