aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation/sysctl/vm.txt
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation/sysctl/vm.txt')
-rw-r--r--Documentation/sysctl/vm.txt20
1 files changed, 19 insertions, 1 deletions
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 2f1aae32a5d9..6910c0136f8d 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -26,12 +26,13 @@ Currently, these files are in /proc/sys/vm:
26- min_free_kbytes 26- min_free_kbytes
27- laptop_mode 27- laptop_mode
28- block_dump 28- block_dump
29- drop-caches
29 30
30============================================================== 31==============================================================
31 32
32dirty_ratio, dirty_background_ratio, dirty_expire_centisecs, 33dirty_ratio, dirty_background_ratio, dirty_expire_centisecs,
33dirty_writeback_centisecs, vfs_cache_pressure, laptop_mode, 34dirty_writeback_centisecs, vfs_cache_pressure, laptop_mode,
34block_dump, swap_token_timeout: 35block_dump, swap_token_timeout, drop-caches:
35 36
36See Documentation/filesystems/proc.txt 37See Documentation/filesystems/proc.txt
37 38
@@ -102,3 +103,20 @@ This is used to force the Linux VM to keep a minimum number
102of kilobytes free. The VM uses this number to compute a pages_min 103of kilobytes free. The VM uses this number to compute a pages_min
103value for each lowmem zone in the system. Each lowmem zone gets 104value for each lowmem zone in the system. Each lowmem zone gets
104a number of reserved free pages based proportionally on its size. 105a number of reserved free pages based proportionally on its size.
106
107==============================================================
108
109percpu_pagelist_fraction
110
111This is the fraction of pages at most (high mark pcp->high) in each zone that
112are allocated for each per cpu page list. The min value for this is 8. It
113means that we don't allow more than 1/8th of pages in each zone to be
114allocated in any single per_cpu_pagelist. This entry only changes the value
115of hot per cpu pagelists. User can specify a number like 100 to allocate
1161/100th of each zone to each per cpu page list.
117
118The batch value of each per cpu pagelist is also updated as a result. It is
119set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8)
120
121The initial value is zero. Kernel does not use this value at boot time to set
122the high water marks for each per cpu page list.