| 1 |
On 1/17/2011 8:42 PM, William Kenworthy wrote: |
| 2 |
> |
| 3 |
> No swap contains pages from memory that have not been accessed for |
| 4 |
> awhile so they can be stored elsewhere freeing ram for actual active |
| 5 |
> pages. When they need to be accessed, they have to be swapped back in, |
| 6 |
> and often something swapped back out to make room for it. |
| 7 |
> |
| 8 |
> And for those with gigabytes of swap, keep in mind that the majority of |
| 9 |
> processors can only access up to 32 x 2G swapfiles under linux, so 4G is |
| 10 |
> only going to be half used. Some processors are only able to handle |
| 11 |
> very small swapfiles, whilst amd opterons can handle very large ones. |
| 12 |
> |
| 13 |
> It does appear however that some distros (redhat and suse ?) have |
| 14 |
> modified something to allow larger swap sizes on 64bit systems, but via |
| 15 |
> google it seems very muddy at the moment. |
| 16 |
> |
| 17 |
> On my mostly 32bit systems its only the opterons (which are running |
| 18 |
> 64bit systems) that can access more than 2G swap using gentoo-sources |
| 19 |
> kernels when I tested late last year. |
| 20 |
> |
| 21 |
> BillK |
| 22 |
|
| 23 |
On a 32bit x86 Linux OS your swap file or swap partitions can have a |
| 24 |
max size of 2GB. If you're using a kernel later than 2.4.10 you can have |
| 25 |
32 swap device and previous to that it was 8. With a 64bit Linux OS you |
| 26 |
can have swap devices of 64GB each. |
| 27 |
|
| 28 |
kashani |
Archives