udp: calculate udp_mem based on low memory instead of all memory
Subsystems (3)
PATCH 1/1 udp: calculate udp_mem based on low memory instead of all memory
While working on UDP, I found a comment in udp_init() was outdated.
This patch could help some 32bit machines, and restore comment validity :)
No hurry, so I based it on top of my previous patch (net-next-2.6)
Thanks
[PATCH] udp: calculate udp_mem based on low memory instead of all memory
This patch mimics commit 57413ebc4e0f1e471a3b4db4aff9a85c083d090e (tcp: calculate tcp_mem based on low memory instead of all memory)
The udp_mem array which contains limits on the total amount of memory used by UDP sockets is calculated based on nr_all_pages. On a 32 bits x86 system, we should base this on the number of lowmem pages.
net/ipv4/udp.c +6 -3
@@ -81,6 +81,8 @@#include <asm/uaccess.h> #include <asm/ioctls.h> #include <linux/bootmem.h> +#include <linux/highmem.h> +#include <linux/swap.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h>
@@ -1751,15 +1753,16 @@ void __init udp_table_init(struct udp_table *table)void __init udp_init (void ) { -unsigned long limit; +unsigned long nr_pages, limit;udp_table_init (&udp_table);/* Set the pressure threshold up by the same strategy of TCP. It is a * fraction of global memory that is up to 1/2 at 256 MB, decreasing * toward zero with the amount of memory, with a floor of 128 pages. */ - limit =min (nr_all_pages,1UL <<(28 -PAGE_SHIFT )) >> (20 -PAGE_SHIFT ); - limit = (limit * (nr_all_pages >> (20 -PAGE_SHIFT ))) >> (PAGE_SHIFT -11 ); + nr_pages = totalram_pages - totalhigh_pages; + limit =min (nr_pages,1UL <<(28 -PAGE_SHIFT )) >> (20 -PAGE_SHIFT ); + limit = (limit * (nr_pages >> (20 -PAGE_SHIFT ))) >> (PAGE_SHIFT -11 ); limit =max (limit,128UL ); sysctl_udp_mem[0 ] = limit /4 *3 ; sysctl_udp_mem[1 ] = limit;
David Miller
maintainerFrom: Eric Dumazet <[email protected]>
Date: Wed, 29 Oct 2008 10:22:16 +0100
Quoted 5 lines
While working on UDP, I found a comment in
udp_init()was outdated.This patch could help some 32bit machines, and restore comment validity :)
No hurry, so I based it on top of my previous patch (net-next-2.6)
Thanks Eric, I'll apply this and also queue it up for submitting to -stable at some point.