lkml.org 
[lkml]   [2011]   [Sep]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: [PATCH 10/18] writeback: dirty position control - bdi reserve area
On Mon, Sep 12, 2011 at 06:19:38PM +0800, Peter Zijlstra wrote:
> On Wed, 2011-09-07 at 20:31 +0800, Wu Fengguang wrote:
> > > > + x_intercept = min(write_bw, freerun);
> > > > + if (bdi_dirty < x_intercept) {
> > >
> > > So the point of the freerun point is that we never throttle before it,
> > > so basically all the below shouldn't be needed at all, right?
> >
> > Yes!
> >
> > > > + if (bdi_dirty > x_intercept / 8) {
> > > > + pos_ratio *= x_intercept;
> > > > + do_div(pos_ratio, bdi_dirty);
> > > > + } else
> > > > + pos_ratio *= 8;
> > > > + }
> > > > +
> > > > return pos_ratio;
> > > > }
>
> Does that mean we can remove this whole block?

Right, if the bdi freerun concept is proved to work fine.

Unfortunately I find it mostly yields lower performance than bdi
reserve area. Patch is attached. If you would like me try other
patches, I can easily kick off new tests and redo the comparison.

Here is the nr_written numbers over various JBOD test cases,
the larger, the better:

bdi-reserve bdi-freerun diff case
---------------------------------------------------------------------------------------
38375271 31553807 -17.8% JBOD-10HDD-6G/xfs-100dd-1M-16p-5895M-20
30478879 28631491 -6.1% JBOD-10HDD-6G/xfs-10dd-1M-16p-5895M-20
29735407 28871956 -2.9% JBOD-10HDD-6G/xfs-1dd-1M-16p-5895M-20
30850350 28344165 -8.1% JBOD-10HDD-6G/xfs-2dd-1M-16p-5895M-20
17706200 16174684 -8.6% JBOD-10HDD-thresh=100M/xfs-100dd-1M-16p-5895M-100M
23374918 14376942 -38.5% JBOD-10HDD-thresh=100M/xfs-10dd-1M-16p-5895M-100M
20659278 19640375 -4.9% JBOD-10HDD-thresh=100M/xfs-1dd-1M-16p-5895M-100M
22517497 14552321 -35.4% JBOD-10HDD-thresh=100M/xfs-2dd-1M-16p-5895M-100M
68287850 61078553 -10.6% JBOD-10HDD-thresh=2G/xfs-100dd-1M-16p-5895M-2048M
33835247 32018425 -5.4% JBOD-10HDD-thresh=2G/xfs-10dd-1M-16p-5895M-2048M
30187817 29942083 -0.8% JBOD-10HDD-thresh=2G/xfs-1dd-1M-16p-5895M-2048M
30563144 30204022 -1.2% JBOD-10HDD-thresh=2G/xfs-2dd-1M-16p-5895M-2048M
34476862 34645398 +0.5% JBOD-10HDD-thresh=4G/xfs-10dd-1M-16p-5895M-4096M
30326479 30097263 -0.8% JBOD-10HDD-thresh=4G/xfs-1dd-1M-16p-5895M-4096M
30446767 30339683 -0.4% JBOD-10HDD-thresh=4G/xfs-2dd-1M-16p-5895M-4096M
40793956 45936678 +12.6% JBOD-10HDD-thresh=800M/xfs-100dd-1M-16p-5895M-800M
27481305 24867282 -9.5% JBOD-10HDD-thresh=800M/xfs-10dd-1M-16p-5895M-800M
25651257 22507406 -12.3% JBOD-10HDD-thresh=800M/xfs-1dd-1M-16p-5895M-800M
19849350 21298787 +7.3% JBOD-10HDD-thresh=800M/xfs-2dd-1M-16p-5895M-800M

raw data by "grep":

JBOD-10HDD-6G/xfs-100dd-1M-16p-5895M-20:10-3.1.0-rc4+/vmstat-end:nr_written 38375271
JBOD-10HDD-6G/xfs-10dd-1M-16p-5895M-20:10-3.1.0-rc4+/vmstat-end:nr_written 30478879
JBOD-10HDD-6G/xfs-1dd-1M-16p-5895M-20:10-3.1.0-rc4+/vmstat-end:nr_written 29735407
JBOD-10HDD-6G/xfs-2dd-1M-16p-5895M-20:10-3.1.0-rc4+/vmstat-end:nr_written 30850350
JBOD-10HDD-thresh=100M/xfs-100dd-1M-16p-5895M-100M:10-3.1.0-rc4+/vmstat-end:nr_written 17706200
JBOD-10HDD-thresh=100M/xfs-10dd-1M-16p-5895M-100M:10-3.1.0-rc4+/vmstat-end:nr_written 23374918
JBOD-10HDD-thresh=100M/xfs-1dd-1M-16p-5895M-100M:10-3.1.0-rc4+/vmstat-end:nr_written 20659278
JBOD-10HDD-thresh=100M/xfs-2dd-1M-16p-5895M-100M:10-3.1.0-rc4+/vmstat-end:nr_written 22517497
JBOD-10HDD-thresh=2G/xfs-100dd-1M-16p-5895M-2048M:10-3.1.0-rc4+/vmstat-end:nr_written 68287850
JBOD-10HDD-thresh=2G/xfs-10dd-1M-16p-5895M-2048M:10-3.1.0-rc4+/vmstat-end:nr_written 33835247
JBOD-10HDD-thresh=2G/xfs-1dd-1M-16p-5895M-2048M:10-3.1.0-rc4+/vmstat-end:nr_written 30187817
JBOD-10HDD-thresh=2G/xfs-2dd-1M-16p-5895M-2048M:10-3.1.0-rc4+/vmstat-end:nr_written 30563144
JBOD-10HDD-thresh=4G/xfs-10dd-1M-16p-5895M-4096M:10-3.1.0-rc4+/vmstat-end:nr_written 34476862
JBOD-10HDD-thresh=4G/xfs-1dd-1M-16p-5895M-4096M:10-3.1.0-rc4+/vmstat-end:nr_written 30326479
JBOD-10HDD-thresh=4G/xfs-2dd-1M-16p-5895M-4096M:10-3.1.0-rc4+/vmstat-end:nr_written 30446767
JBOD-10HDD-thresh=800M/xfs-100dd-1M-16p-5895M-800M:10-3.1.0-rc4+/vmstat-end:nr_written 40793956
JBOD-10HDD-thresh=800M/xfs-10dd-1M-16p-5895M-800M:10-3.1.0-rc4+/vmstat-end:nr_written 27481305
JBOD-10HDD-thresh=800M/xfs-1dd-1M-16p-5895M-800M:10-3.1.0-rc4+/vmstat-end:nr_written 25651257
JBOD-10HDD-thresh=800M/xfs-2dd-1M-16p-5895M-800M:10-3.1.0-rc4+/vmstat-end:nr_written 19849350

JBOD-10HDD-6G/xfs-100dd-1M-16p-5895M-20:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 31553807
JBOD-10HDD-6G/xfs-10dd-1M-16p-5895M-20:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 28631491
JBOD-10HDD-6G/xfs-1dd-1M-16p-5895M-20:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 28871956
JBOD-10HDD-6G/xfs-2dd-1M-16p-5895M-20:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 28344165
JBOD-10HDD-thresh=100M/xfs-100dd-1M-16p-5895M-100M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 16174684
JBOD-10HDD-thresh=100M/xfs-10dd-1M-16p-5895M-100M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 14376942
JBOD-10HDD-thresh=100M/xfs-1dd-1M-16p-5895M-100M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 19640375
JBOD-10HDD-thresh=100M/xfs-2dd-1M-16p-5895M-100M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 14552321
JBOD-10HDD-thresh=2G/xfs-100dd-1M-16p-5895M-2048M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 61078553
JBOD-10HDD-thresh=2G/xfs-10dd-1M-16p-5895M-2048M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 32018425
JBOD-10HDD-thresh=2G/xfs-1dd-1M-16p-5895M-2048M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 29942083
JBOD-10HDD-thresh=2G/xfs-2dd-1M-16p-5895M-2048M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 30204022
JBOD-10HDD-thresh=4G/xfs-10dd-1M-16p-5895M-4096M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 34645398
JBOD-10HDD-thresh=4G/xfs-1dd-1M-16p-5895M-4096M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 30097263
JBOD-10HDD-thresh=4G/xfs-2dd-1M-16p-5895M-4096M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 30339683
JBOD-10HDD-thresh=800M/xfs-100dd-1M-16p-5895M-800M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 45936678
JBOD-10HDD-thresh=800M/xfs-10dd-1M-16p-5895M-800M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 24867282
JBOD-10HDD-thresh=800M/xfs-1dd-1M-16p-5895M-800M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 22507406
JBOD-10HDD-thresh=800M/xfs-2dd-1M-16p-5895M-800M:10-3.1.0-rc4-bdi-freerun+/vmstat-end:nr_written 21298787
Subject:
Date: Wed Sep 14 22:57:43 CST 2011


Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
---
mm/page-writeback.c | 26 ++++++++------------------
1 file changed, 8 insertions(+), 18 deletions(-)

--- linux-next.orig/mm/page-writeback.c 2011-09-14 22:50:33.000000000 +0800
+++ linux-next/mm/page-writeback.c 2011-09-14 22:58:15.000000000 +0800
@@ -614,22 +614,6 @@ static unsigned long bdi_position_ratio(
} else
pos_ratio /= 4;

- /*
- * bdi reserve area, safeguard against dirty pool underrun and disk idle
- *
- * It may push the desired control point of global dirty pages higher
- * than setpoint. It's not necessary in single-bdi case because a
- * minimal pool of @freerun dirty pages will already be guaranteed.
- */
- x_intercept = min(write_bw, freerun);
- if (bdi_dirty < x_intercept) {
- if (bdi_dirty > x_intercept / 8) {
- pos_ratio *= x_intercept;
- do_div(pos_ratio, bdi_dirty);
- } else
- pos_ratio *= 8;
- }
-
return pos_ratio;
}

@@ -1089,8 +1073,14 @@ static void balance_dirty_pages(struct a
nr_dirty, bdi_thresh, bdi_dirty,
start_time);

- if (unlikely(!dirty_exceeded && bdi_async_underrun(bdi)))
- break;
+ freerun = min(bdi->avg_write_bandwidth + MIN_WRITEBACK_PAGES,
+ global_dirty_limit - nr_dirty) / 8;
+ if (!dirty_exceeded) {
+ if (unlikely(bdi_dirty < freerun))
+ break;
+ if (unlikely(bdi_async_underrun(bdi)))
+ break;
+ }

max_pause = bdi_max_pause(bdi, bdi_dirty);
\
 
 \ /
  Last update: 2011-09-18 16:19    [W:0.071 / U:0.064 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site