[Lustre-discuss] How to change inode capacity

[Oleg Drokin]

Hello!

On Jan 29, 2009, at 9:58 PM, Satoshi Isono wrote:
> http://wiki.lustre.org/index.php?title=Lustre_FAQ
>    * What is the maximum number of files in a single file system? In  
> a single directory?
>
> So, if we use current Lustre 1.6.x on EXT3, we can only support  
> single MDT. Then, according to the limitation of the number of  
> inodes, we are able to use inodes up to 4 billion. This means that a  
> Lustre consisted on EXT3 can support 4 million files. Is it correct?
>

No. It is not 4 million, it is 4 billion files (in US billion means  
1000 times million (10億), so 1,000,000,000).

>> I *think* growing the size of the physical device and then using
>> resize2fs to increase an ext3(4?) filesystem will increase inode  
>> count.
>> I am however, doubtful that resize2fs will work with our ldiskfs
>> filesystems.  Perhaps resize2fs from an ext4 supporting version of
>> e2fsprogs will support doing that.  I have no idea -- never tried it.
> Another question to you, When changing #inodes into maximum number,  
> are there any demerit/un-merit points? I want to know the tradeoff  
> changing #inodes. In my site, the total OST capacity is 800TB and  
> size of MDT is 123207680 (123 million). What do you think about the  
> number of inodes which I will change?

The more inodes you have the less space free is left on the MDT  
filesystem. Of course the space on MDT is rarely used.
Another downside is the more inodes you have is the slower e2fsck  
would work on such a filesystem should you ever encounter
any fs-problems.
There is another fs-wide limit lustre currently imposes - it assumes  
that you cannot have more files (and hence inodes) then
you have (4k) blocks on your OSTs.

Bye,
     Oleg