Wu Fengguang bb0822954a squeeze max-pause area and drop pass-good area ... Revert the pass-good area introduced in ffd1f609ab ("writeback: introduce max-pause and pass-good dirty limits") and make the max-pause area smaller and safe. This fixes ~30% performance regression in the ext3 data=writeback fio_mmap_randwrite_64k/fio_mmap_randrw_64k test cases, where there are 12 JBOD disks, on each disk runs 8 concurrent tasks doing reads+writes. Using deadline scheduler also has a regression, but not that big as CFQ, so this suggests we have some write starvation. The test logs show that - the disks are sometimes under utilized - global dirty pages sometimes rush high to the pass-good area for several hundred seconds, while in the mean time some bdi dirty pages drop to very low value (bdi_dirty << bdi_thresh). Then suddenly the global dirty pages dropped under global dirty threshold and bdi_dirty rush very high (for example, 2 times higher than bdi_thresh). During which time balance_dirty_pages() is not called at all. So the problems are 1) The random writes progress so slow that they break the assumption of the max-pause logic that "8 pages per 200ms is typically more than enough to curb heavy dirtiers". 2) The max-pause logic ignored task_bdi_thresh and thus opens the possibility for some bdi's to over dirty pages, leading to (bdi_dirty >> bdi_thresh) and then (bdi_thresh >> bdi_dirty) for others. 3) The higher max-pause/pass-good thresholds somehow leads to the bad swing of dirty pages. The fix is to allow the task to slightly dirty over task_bdi_thresh, but no way to exceed bdi_dirty and/or global dirty_thresh. Tests show that it fixed the JBOD regression completely (both behavior and performance), while still being able to cut down large pause times in balance_dirty_pages() for single-disk cases. Reported-by: Li Shaohua <shaohua.li@intel.com> Tested-by: Li Shaohua <shaohua.li@intel.com> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>		2011-08-19 22:42:07 +08:00
..
acpi	Merge branch 'apei-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6	2011-08-03 21:53:27 -10:00
asm-generic	Merge branch 'next/cross-platform' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/linux-arm-soc	2011-07-26 17:12:10 -07:00
crypto
drm	drm: Separate EDID Header Check from EDID Block Check	2011-08-04 14:39:35 +01:00
keys
linux	squeeze max-pause area and drop pass-good area	2011-08-19 22:42:07 +08:00
math-emu
media	[media] V4L: initial driver for ov5642 CMOS sensor	2011-07-27 17:56:09 -03:00
mtd
net	ipv4: route non-local sources for raw socket	2011-08-07 22:52:32 -07:00
pcmcia	Merge git://git.kernel.org/pub/scm/linux/kernel/git/brodo/pcmcia-2.6	2011-07-31 06:23:08 -10:00
rdma	atomic: use <linux/atomic.h>	2011-07-26 16:49:47 -07:00
rxrpc	atomic: use <linux/atomic.h>	2011-07-26 16:49:47 -07:00
scsi	Merge branch 'for-linus' of git://git.open-osd.org/linux-open-osd	2011-08-06 22:56:03 -07:00
sound	ASoC: omap: Update e-mail address of Jarkko Nikula	2011-08-12 11:45:10 +09:00
target
trace	Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4	2011-08-01 13:56:03 -10:00
video
xen
Kbuild