I have 8 Gbytes RAM, but why I can allocate 2.8 Gbytes RAM for a single process?
How to patch kernel so I have more than 2.8 Gbytes limitation?
Kernel:
---------------------------
Linux xxx.com 2.6.9-023stab046.2-enterprise #1 SMP Mon Dec 10 15:22:33
MSK 2007 i686 i686 i386 GNU/Linux
Mem:
---------------------------
# cat /proc/meminfo
MemTotal: 8296484 kB
MemFree: 50416 kB
Buffers: 64412 kB
Cached: 4927328 kB
SwapCached: 0 kB
Active: 6710828 kB
Inactive: 1065384 kB
HighTotal: 4980736 kB
HighFree: 1024 kB
LowTotal: 3315748 kB
LowFree: 49392 kB
SwapTotal: 10256376 kB
SwapFree: 10255732 kB
Dirty: 64 kB
Writeback: 0 kB
Mapped: 3054960 kB
Slab: 393224 kB
CommitLimit: 14404616 kB
Committed_AS: 6318152 kB
PageTables: 34892 kB
VmallocTotal: 303096 kB
VmallocUsed: 22360 kB
VmallocChunk: 280496 kB
CPU (8 processor id from 0-7), one of them is:
---------------------------
processor : 0
vendor_id : GenuineIntel
cpu family : 15
model : 6
model name : Intel(R) Xeon(TM) CPU 3.00GHz
stepping : 4
cpu MHz : 2993.054
cache size : 2048 KB
physical id : 0
siblings : 4
core id : 0
cpu cores : 2
fdiv_bug : no
hlt_bug : no
f00f_bug : no
coma_bug : no
fpu : yes
fpu_exception : yes
cpuid level : 6
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx
lm constant_tsc pni monitor ds_cpl est cid xtpr
bogomips : 5989.55
App to test memory limit:
---------------------------
#include <stdio.h>
#include <stdlib.h>
int main(){
size_t siz = 100 * 1024 * 1024 ;
size_t idx = 1 ;
void *ptr;
for (;;){
ptr = malloc ( siz * idx );
if(!ptr)
break ;
free(ptr);
idx++;
}
printf ("Max malloc %d * 100 MB \n", idx - 1 );
return (0);
}
App result: Max malloc 28 * 100 MB ==> 2.8 Gbytes
--
Regards,
Ady Wicaksono
Email:
ady.wicaksono at gmail.com
http://adywicaksono.wordpress.com/
On 25-02-08 08:44, Ady Wicaksono wrote:
> I have 8 Gbytes RAM, but why I can allocate 2.8 Gbytes RAM for a single
> process? How to patch kernel so I have more than 2.8 Gbytes limitation?
[ ... ]
> flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
> mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx
> lm constant_tsc pni monitor ds_cpl est cid xtpr
Run a 64-bit kernel and userspace. not a 32-bit.
Rene.
2008/2/25, Ady Wicaksono <[email protected]>:
> I have 8 Gbytes RAM, but why I can allocate 2.8 Gbytes RAM for a single process?
> How to patch kernel so I have more than 2.8 Gbytes limitation?
>
> Kernel:
> ---------------------------
> Linux xxx.com 2.6.9-023stab046.2-enterprise #1 SMP Mon Dec 10 15:22:33
> MSK 2007 i686 i686 i386 GNU/Linux
>
> Mem:
> ---------------------------
> # cat /proc/meminfo
> MemTotal: 8296484 kB
> MemFree: 50416 kB
> Buffers: 64412 kB
> Cached: 4927328 kB
> SwapCached: 0 kB
> Active: 6710828 kB
> Inactive: 1065384 kB
> HighTotal: 4980736 kB
> HighFree: 1024 kB
> LowTotal: 3315748 kB
> LowFree: 49392 kB
> SwapTotal: 10256376 kB
> SwapFree: 10255732 kB
> Dirty: 64 kB
> Writeback: 0 kB
> Mapped: 3054960 kB
> Slab: 393224 kB
> CommitLimit: 14404616 kB
> Committed_AS: 6318152 kB
> PageTables: 34892 kB
> VmallocTotal: 303096 kB
> VmallocUsed: 22360 kB
> VmallocChunk: 280496 kB
>
>
> CPU (8 processor id from 0-7), one of them is:
> ---------------------------
> processor : 0
> vendor_id : GenuineIntel
> cpu family : 15
> model : 6
> model name : Intel(R) Xeon(TM) CPU 3.00GHz
> stepping : 4
> cpu MHz : 2993.054
> cache size : 2048 KB
> physical id : 0
> siblings : 4
> core id : 0
> cpu cores : 2
> fdiv_bug : no
> hlt_bug : no
> f00f_bug : no
> coma_bug : no
> fpu : yes
> fpu_exception : yes
> cpuid level : 6
> wp : yes
> flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
> mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx
> lm constant_tsc pni monitor ds_cpl est cid xtpr
> bogomips : 5989.55
>
> App to test memory limit:
> ---------------------------
> #include <stdio.h>
> #include <stdlib.h>
>
> int main(){
> size_t siz = 100 * 1024 * 1024 ;
> size_t idx = 1 ;
> void *ptr;
>
> for (;;){
> ptr = malloc ( siz * idx );
> if(!ptr)
> break ;
> free(ptr);
> idx++;
> }
> printf ("Max malloc %d * 100 MB \n", idx - 1 );
> return (0);
> }
>
> App result: Max malloc 28 * 100 MB ==> 2.8 Gbytes
1. It's a 32-bit processor Xeon with 8 GiB of RAM. OK?
2. The 32-bit userspace's process is always limited to <3.0 GiB ( < 0xC0000000 )
3. Enable PAE (64 GB option in the kernel) to address the 8 GiB of RAM
using PAE,
also you can have many processes of ~3 GiB per process.
I'm not sure if the PAE's three-level paging works efficient in linux.
;)
J.C. Pizarro schrieb:
> 2008/2/25, Ady Wicaksono <[email protected]>:
>> I have 8 Gbytes RAM, but why I can allocate 2.8 Gbytes RAM for a single process?
>> How to patch kernel so I have more than 2.8 Gbytes limitation?
>>
>> Kernel:
>> ---------------------------
>> Linux xxx.com 2.6.9-023stab046.2-enterprise #1 SMP Mon Dec 10 15:22:33
>> MSK 2007 i686 i686 i386 GNU/Linux
>>
>> Mem:
>> ---------------------------
>> # cat /proc/meminfo
>> MemTotal: 8296484 kB
>> MemFree: 50416 kB
>> Buffers: 64412 kB
>> Cached: 4927328 kB
>> SwapCached: 0 kB
>> Active: 6710828 kB
>> Inactive: 1065384 kB
>> HighTotal: 4980736 kB
>> HighFree: 1024 kB
>> LowTotal: 3315748 kB
>> LowFree: 49392 kB
>> SwapTotal: 10256376 kB
>> SwapFree: 10255732 kB
>> Dirty: 64 kB
>> Writeback: 0 kB
>> Mapped: 3054960 kB
>> Slab: 393224 kB
>> CommitLimit: 14404616 kB
>> Committed_AS: 6318152 kB
>> PageTables: 34892 kB
>> VmallocTotal: 303096 kB
>> VmallocUsed: 22360 kB
>> VmallocChunk: 280496 kB
>>
>>
>> CPU (8 processor id from 0-7), one of them is:
>> ---------------------------
>> processor : 0
>> vendor_id : GenuineIntel
>> cpu family : 15
>> model : 6
>> model name : Intel(R) Xeon(TM) CPU 3.00GHz
>> stepping : 4
>> cpu MHz : 2993.054
>> cache size : 2048 KB
>> physical id : 0
>> siblings : 4
>> core id : 0
>> cpu cores : 2
>> fdiv_bug : no
>> hlt_bug : no
>> f00f_bug : no
>> coma_bug : no
>> fpu : yes
>> fpu_exception : yes
>> cpuid level : 6
>> wp : yes
>> flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
>> mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx
>> lm constant_tsc pni monitor ds_cpl est cid xtpr
>> bogomips : 5989.55
>>
>> App to test memory limit:
>> ---------------------------
>> #include <stdio.h>
>> #include <stdlib.h>
>>
>> int main(){
>> size_t siz = 100 * 1024 * 1024 ;
>> size_t idx = 1 ;
>> void *ptr;
>>
>> for (;;){
>> ptr = malloc ( siz * idx );
>> if(!ptr)
>> break ;
>> free(ptr);
>> idx++;
>> }
>> printf ("Max malloc %d * 100 MB \n", idx - 1 );
>> return (0);
>> }
>>
>> App result: Max malloc 28 * 100 MB ==> 2.8 Gbytes
>
> 1. It's a 32-bit processor Xeon with 8 GiB of RAM. OK?
No, its not. cpuinfo indicates that it understands 64 bit (X86_FEATURE_LM)
> 2. The 32-bit userspace's process is always limited to <3.0 GiB ( < 0xC0000000 )
Yep thats right.
> 3. Enable PAE (64 GB option in the kernel) to address the 8 GiB of RAM
> using PAE,
He did already enable it as indicated by /proc/meminfo...
> also you can have many processes of ~3 GiB per process.
> I'm not sure if the PAE's three-level paging works efficient in linux.
>
> ;)
I'm not sure either.
Best regard,
Arnd
On 2/24/08, Ady Wicaksono <[email protected]> wrote:
> I have 8 Gbytes RAM, but why I can allocate 2.8 Gbytes RAM for a single process?
> How to patch kernel so I have more than 2.8 Gbytes limitation?
>
> Kernel:
> ---------------------------
> Linux xxx.com 2.6.9-023stab046.2-enterprise #1 SMP Mon Dec 10 15:22:33
> MSK 2007 i686 i686 i386 GNU/Linux
You really need to use 64 bit kernel AND 64 bit userspace to use more
than 3gigs per process.
Masoud
> Mem:
> ---------------------------
> # cat /proc/meminfo
> MemTotal: 8296484 kB
> MemFree: 50416 kB
> Buffers: 64412 kB
> Cached: 4927328 kB
> SwapCached: 0 kB
> Active: 6710828 kB
> Inactive: 1065384 kB
> HighTotal: 4980736 kB
> HighFree: 1024 kB
> LowTotal: 3315748 kB
> LowFree: 49392 kB
> SwapTotal: 10256376 kB
> SwapFree: 10255732 kB
> Dirty: 64 kB
> Writeback: 0 kB
> Mapped: 3054960 kB
> Slab: 393224 kB
> CommitLimit: 14404616 kB
> Committed_AS: 6318152 kB
> PageTables: 34892 kB
> VmallocTotal: 303096 kB
> VmallocUsed: 22360 kB
> VmallocChunk: 280496 kB
>
>
> CPU (8 processor id from 0-7), one of them is:
> ---------------------------
> processor : 0
> vendor_id : GenuineIntel
> cpu family : 15
> model : 6
> model name : Intel(R) Xeon(TM) CPU 3.00GHz
> stepping : 4
> cpu MHz : 2993.054
> cache size : 2048 KB
> physical id : 0
> siblings : 4
> core id : 0
> cpu cores : 2
> fdiv_bug : no
> hlt_bug : no
> f00f_bug : no
> coma_bug : no
> fpu : yes
> fpu_exception : yes
> cpuid level : 6
> wp : yes
> flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
> mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx
> lm constant_tsc pni monitor ds_cpl est cid xtpr
> bogomips : 5989.55
>
> App to test memory limit:
> ---------------------------
> #include <stdio.h>
> #include <stdlib.h>
>
> int main(){
> size_t siz = 100 * 1024 * 1024 ;
> size_t idx = 1 ;
> void *ptr;
>
> for (;;){
> ptr = malloc ( siz * idx );
> if(!ptr)
> break ;
> free(ptr);
> idx++;
> }
> printf ("Max malloc %d * 100 MB \n", idx - 1 );
> return (0);
> }
>
> App result: Max malloc 28 * 100 MB ==> 2.8 Gbytes
>
>
> --
> Regards,
>
> Ady Wicaksono
> Email:
> ady.wicaksono at gmail.com
> http://adywicaksono.wordpress.com/
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>