Heinz Diehl wrote:
> On 08.08.2010, Marcus Kool wrote:
>
>> vm.swappiness=20
>> vm.vfs_cache_pressure=50
>
> Do you have some numbers that actually show a significant improvement?
No. I have experience. It seems that Amos has the same.
> I think at least swappiness should better be 100 here, to free as much as
> possible memory. Unused applications hanging around for a long
> time can conserve quite a lot of pagecache which otherwise could be used
> actively.
Do you have any proof to support this theory?
> The inode cache on a system with 4 TB of diskspace is not more than ca.
> 400-500 MB, I doubt it makes sense to increase the kernels focus
> on reclaiming more pagecache (which you trying to preserve by lowering
> swappiness).
The vfs_cache_pressure is used when where is pressure: when the system
is running low on memory. Always bad, but Linux has a configurable
choice: free up some memory by reducing the file cache or free up
some memory reducing the inode cache. Squid uses a lot of inodes/files.
and inodes are the index of the file system, you need them to access
files. Making a preference for inodes over file buffers is a good
choice.
Received on Mon Aug 09 2010 - 04:19:24 MDT
This archive was generated by hypermail 2.2.0 : Mon Aug 09 2010 - 12:00:02 MDT