aboutsummaryrefslogtreecommitdiffstats
path: root/mm/page-writeback.c
diff options
context:
space:
mode:
authorPeter Zijlstra <a.p.zijlstra@chello.nl>2008-04-30 03:54:35 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2008-04-30 11:29:50 -0400
commit189d3c4a94ef19fca2a71a6a336e9fda900e25e7 (patch)
tree75c0de871fe9922885a2fa073f15806d829342fa /mm/page-writeback.c
parentb6f2fcbcfca9db2bd7aa24940224fcd3bbdbb8aa (diff)
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 <a.p.zijlstra@chello.nl> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page-writeback.c')
-rw-r--r--mm/page-writeback.c27
1 files changed, 26 insertions, 1 deletions
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e5b6b1190a95..4ac077f4269c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -243,6 +243,29 @@ static void task_dirty_limit(struct task_struct *tsk, long *pdirty)
243} 243}
244 244
245/* 245/*
246 *
247 */
248static DEFINE_SPINLOCK(bdi_lock);
249static unsigned int bdi_min_ratio;
250
251int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
252{
253 int ret = 0;
254 unsigned long flags;
255
256 spin_lock_irqsave(&bdi_lock, flags);
257 min_ratio -= bdi->min_ratio;
258 if (bdi_min_ratio + min_ratio < 100) {
259 bdi_min_ratio += min_ratio;
260 bdi->min_ratio += min_ratio;
261 } else
262 ret = -EINVAL;
263 spin_unlock_irqrestore(&bdi_lock, flags);
264
265 return ret;
266}
267
268/*
246 * Work out the current dirty-memory clamping and background writeout 269 * Work out the current dirty-memory clamping and background writeout
247 * thresholds. 270 * thresholds.
248 * 271 *
@@ -330,7 +353,7 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
330 *pdirty = dirty; 353 *pdirty = dirty;
331 354
332 if (bdi) { 355 if (bdi) {
333 u64 bdi_dirty = dirty; 356 u64 bdi_dirty;
334 long numerator, denominator; 357 long numerator, denominator;
335 358
336 /* 359 /*
@@ -338,8 +361,10 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
338 */ 361 */
339 bdi_writeout_fraction(bdi, &numerator, &denominator); 362 bdi_writeout_fraction(bdi, &numerator, &denominator);
340 363
364 bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
341 bdi_dirty *= numerator; 365 bdi_dirty *= numerator;
342 do_div(bdi_dirty, denominator); 366 do_div(bdi_dirty, denominator);
367 bdi_dirty += (dirty * bdi->min_ratio) / 100;
343 368
344 *pbdi_dirty = bdi_dirty; 369 *pbdi_dirty = bdi_dirty;
345 clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty); 370 clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);