The patch titled
vfs: avoid large kmalloc()s for the fdtable
has been removed from the -mm tree. Its filename was
vfs-avoid-large-kmallocs-for-the-fdtable.patch
This patch was dropped because it was merged into mainline or a subsystem tree
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: vfs: avoid large kmalloc()s for the fdtable
From: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Azurit reports large increases in system time after 2.6.36 when running
Apache. It was bisected down to a892e2d7dcdfa6c76e6 ("vfs: use kmalloc()
to allocate fdmem if possible").
That patch caused the vfs to use kmalloc() for very large allocations and
this is causing excessive work (and presumably excessive reclaim) within
the page allocator.
Fix it by falling back to vmalloc() earlier - when the allocation attempt
would have been considered "costly" by reclaim.
Reported-by: azurIt <azurit@xxxxxxxx>
Tested-by: azurIt <azurit@xxxxxxxx>
Cc: Changli Gao <xiaosuo@xxxxxxxxx>
Cc: Americo Wang <xiyou.wangcong@xxxxxxxxx>
Cc: Jiri Slaby <jslaby@xxxxxxx>
Acked-by: Eric Dumazet <eric.dumazet@xxxxxxxxx>
Cc: Mel Gorman <mel@xxxxxxxxx>
Cc: <stable@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/file.c | 18 +++++++++++-------
1 file changed, 11 insertions(+), 7 deletions(-)
diff -puN fs/file.c~vfs-avoid-large-kmallocs-for-the-fdtable fs/file.c
--- a/fs/file.c~vfs-avoid-large-kmallocs-for-the-fdtable
+++ a/fs/file.c
@@ -9,6 +9,7 @@
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/mmzone.h>
#include <linux/time.h>
#include <linux/sched.h>
#include <linux/slab.h>
@@ -39,14 +40,17 @@ int sysctl_nr_open_max = 1024 * 1024; /*
*/
static DEFINE_PER_CPU(struct fdtable_defer, fdtable_defer_list);
-static inline void *alloc_fdmem(unsigned int size)
+static void *alloc_fdmem(unsigned int size)
{
- void *data;
-
- data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
- if (data != NULL)
- return data;
-
+ /*
+ * Very large allocations can stress page reclaim, so fall back to
+ * vmalloc() if the allocation size will be considered "large" by the VM.
+ */
+ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+ void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
+ if (data != NULL)
+ return data;
+ }
return vmalloc(size);
}
_
Patches currently in -mm which might be from akpm@xxxxxxxxxxxxxxxxxxxx are
origin.patch
linux-next.patch
next-remove-localversion.patch
i-need-old-gcc.patch
arch-alpha-kernel-systblss-remove-debug-check.patch
drivers-i2c-busses-i2c-designware-corec-needs-delayh.patch
arch-x86-include-asm-delayh-fix-udelay-and-ndelay-for-8-bit-args.patch
drivers-gpu-drm-radeon-atomc-fix-warning.patch
leds-route-kbd-leds-through-the-generic-leds-layer.patch
backlight-add-backlight-type-fix.patch
backlight-add-backlight-type-fix-fix.patch
drivers-video-backlight-adp5520_blc-check-strict_strtoul-return-value-fix.patch
drivers-message-fusion-mptsasc-fix-warning.patch
osst-wrong-index-used-in-inner-loop-checkpatch-fixes.patch
drivers-scsi-osstc-fix-warning.patch
drbd-fix-warning.patch
drivers-usb-misc-usbtestc-fix-warning.patch
mm.patch
mm-nommu-sort-mm-mmap-list-properly-fix.patch
mm-per-node-vmstat-show-proper-vmstats-fix.patch
mm-mem-hotplug-update-pcp-stat_threshold-when-memory-hotplug-occur-fix.patch
mm-mmu_gather-rework-fix.patch
mm-uninline-large-generic-tlbh-functions.patch
mm-thp-optimize-memcg-charge-in-khugepaged-fix.patch
mm-convert-mm-cpu_vm_cpumask-into-cpumask_var_t-checkpatch-fixes.patch
writeback-sync-expired-inodes-first-in-background-writeback-fix.patch
vmscan-change-shrink_slab-interfaces-by-passing-shrink_control-fix.patch
vmscan-change-shrink_slab-interfaces-by-passing-shrink_control-fix-2.patch
vmscan-change-shrinker-api-by-passing-shrink_control-struct-fix.patch
vmscan-change-shrinker-api-by-passing-shrink_control-struct-fix-2.patch
frv-duplicate-output_buffer-of-e03-checkpatch-fixes.patch
hpet-factor-timer-allocate-from-open.patch
arch-alpha-include-asm-ioh-s-extern-inline-static-inline.patch
init-calibratec-fix-for-critical-bogomips-intermittent-calculation-failure-checkpatch-fixes.patch
init-calibratec-fix-for-critical-bogomips-intermittent-calculation-failure-fix.patch
printk-allocate-kernel-log-buffer-earlier-v2-checkpatch-fixes.patch
printk-allocate-kernel-log-buffer-earlier-v2-fix.patch
lru_cache-use-correct-type-in-sizeof-for-allocation-fix.patch
percpu_counter-change-return-value-and-add-comments-fix.patch
lib-hexdumpc-make-hex2bin-return-the-updated-src-address.patch
fs-binfmt_miscc-use-kernels-hex_to_bin-method-fix.patch
fs-binfmt_miscc-use-kernels-hex_to_bin-method-fix-fix.patch
fs-ncpfs-inodec-suppress-used-uninitialised-warning.patch
drivers-rtc-rtc-mrstc-use-release_mem_region-after-request_mem_region-fix.patch
rtc-driver-for-pt7c4338-chip-checkpatch-fixes.patch
rtc-driver-for-pt7c4338-chip-fix.patch
documentation-accounting-getdelaysc-handle-sendto-failures.patch
mm-move-enum-vm_event_item-into-a-standalone-header-file.patch
add-the-pagefault-count-into-memcg-stats-fix.patch
cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node.patch
cpusets-randomize-node-rotor-used-in-cpuset_mem_spread_node-cpusets-initialize-spread-rotor-lazily-fix.patch
fs-partitions-efic-corrupted-guid-partition-tables-can-cause-kernel-oops-fix.patch
scatterlist-new-helper-functions.patch
scatterlist-new-helper-functions-update-fix.patch
kexec-remove-kmsg_dump_kexec-fix.patch
journal_add_journal_head-debug.patch
mutex-subsystem-synchro-test-module-fix.patch
slab-leaks3-default-y.patch
put_bh-debug.patch
memblock-add-input-size-checking-to-memblock_find_region.patch
memblock-add-input-size-checking-to-memblock_find_region-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
