get rid of NR_OPEN and introduce a sysctl_nr_open
authorEric Dumazet <dada1@cosmosbay.com>
Wed, 6 Feb 2008 09:37:16 +0000 (01:37 -0800)
committerLinus Torvalds <torvalds@woody.linux-foundation.org>
Wed, 6 Feb 2008 18:41:06 +0000 (10:41 -0800)
commit9cfe015aa424b3c003baba3841a60dd9b5ad319b
tree5575e06efcf91018f860f2db43979e8e91aba1c3
parent774ed22c21ab95d582dfff38560f11cf290baeb4
get rid of NR_OPEN and introduce a sysctl_nr_open

NR_OPEN (historically set to 1024*1024) actually forbids processes to open
more than 1024*1024 handles.

Unfortunatly some production servers hit the not so 'ridiculously high
value' of 1024*1024 file descriptors per process.

Changing NR_OPEN is not considered safe because of vmalloc space potential
exhaust.

This patch introduces a new sysctl (/proc/sys/fs/nr_open) wich defaults to
1024*1024, so that admins can decide to change this limit if their workload
needs it.

[akpm@linux-foundation.org: export it for sparc64]
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Documentation/filesystems/proc.txt
Documentation/sysctl/fs.txt
arch/alpha/kernel/osf_sys.c
arch/mips/kernel/sysirix.c
arch/sparc64/kernel/sparc64_ksyms.c
arch/sparc64/solaris/fs.c
arch/sparc64/solaris/timod.c
fs/file.c
include/linux/fs.h
kernel/sys.c
kernel/sysctl.c