Jens Axboe b31dc66a54 [PATCH] Kill PF_SYNCWRITE flag ...

A process flag to indicate whether we are doing sync io is incredibly
ugly. It also causes performance problems when one does a lot of async
io and then proceeds to sync it. Part of the io will go out as async,
and the other part as sync. This causes a disconnect between the
previously submitted io and the synced io. For io schedulers such as CFQ,
this will cause us lost merges and suboptimal behaviour in scheduling.

Remove PF_SYNCWRITE completely from the fsync/msync paths, and let
the O_DIRECT path just directly indicate that the writes are sync
by using WRITE_SYNC instead.

Signed-off-by: Jens Axboe <axboe@suse.de>

2006-06-23 17:10:39 +02:00

..

bootmem.c

…

fadvise.c

…

filemap_xip.c

…

filemap.c

[PATCH] x86: cache pollution aware __copy_from_user_ll()

2006-06-23 07:42:56 -07:00

filemap.h

[PATCH] x86: cache pollution aware __copy_from_user_ll()

2006-06-23 07:42:56 -07:00

fremap.c

[PATCH] fix update_mmu_cache in fremap.c

2006-06-23 07:42:52 -07:00

highmem.c

…

hugetlb.c

[PATCH] tightening hugetlb strict accounting

2006-06-23 07:42:48 -07:00

internal.h

…

Kconfig

[PATCH] Swapless page migration: modify core logic

2006-06-23 07:42:50 -07:00

madvise.c

…

Makefile

…

memory_hotplug.c

[PATCH] update vm_total_pages at memory hotadd

2006-06-23 07:42:52 -07:00

memory.c

[PATCH] add page_mkwrite() vm_operations method

2006-06-23 07:42:51 -07:00

mempolicy.c

[PATCH] SELinux: add security_task_movememory calls to mm code

2006-06-23 07:42:54 -07:00

mempool.c

…

migrate.c

[PATCH] SELinux: add security_task_movememory calls to mm code

2006-06-23 07:42:54 -07:00

mincore.c

…

mlock.c

…

mmap.c

[PATCH] add page_mkwrite() vm_operations method

2006-06-23 07:42:51 -07:00

mmzone.c

…

mprotect.c

[PATCH] add page_mkwrite() vm_operations method

2006-06-23 07:42:51 -07:00

mremap.c

…

msync.c

[PATCH] Kill PF_SYNCWRITE flag

2006-06-23 17:10:39 +02:00

nommu.c

…

oom_kill.c

[PATCH] mm: fix typos in comments in mm/oom_kill.c

2006-06-23 07:42:47 -07:00

page_alloc.c

[PATCH] printk() should not be called under zone->lock

2006-06-23 07:42:52 -07:00

page_io.c

…

page-writeback.c

[PATCH] writeback: fix range handling

2006-06-23 07:42:49 -07:00

pdflush.c

[PATCH] More BUG_ON conversion

2006-06-23 07:43:08 -07:00

prio_tree.c

…

readahead.c

…

rmap.c

[PATCH] More page migration: use migration entries for file pages

2006-06-23 07:42:51 -07:00

shmem.c

[PATCH] migration: remove unnecessary PageSwapCache checks

2006-06-23 07:42:46 -07:00

slab.c

[PATCH] slab: kmalloc, kzalloc comments cleanup and fix

2006-06-23 07:42:52 -07:00

slob.c

…

sparse.c

[PATCH] sparsemem: record nid during memory present

2006-06-23 07:42:51 -07:00

swap_state.c

…

swap.c

[PATCH] percpu_counters: create lib/percpu_counter.c

2006-06-23 07:43:06 -07:00

swapfile.c

[PATCH] read_mapping_page for address space

2006-06-23 07:43:02 -07:00

thrash.c

…

tiny-shmem.c

…

truncate.c

[PATCH] Remove semi-softlockup from invalidate_mapping_pages

2006-06-23 07:43:07 -07:00

util.c

…

vmalloc.c

[PATCH] mm: introduce remap_vmalloc_range()

2006-06-23 07:42:49 -07:00

vmscan.c

[PATCH] initialise total_memory() earlier

2006-06-23 07:42:52 -07:00