Re: [RFC][PATCH] Manage jbd allocations from its own slabs

On Thu, Aug 24, 2006 at 12:11:25PM -0700, Badari Pulavarty wrote:
> > Why can't you just use alloc_page?  I bet the whole slab overhead
> > eats more memory than what's wasted when using alloc_pages.  Especially
> > as the typical usecase is a 4k blocks filesystem with 4k pagesize
> > where the overhead of alloc_page is non-existant.
> 
> Yes. That was what proposed earlier. But for 1k, 2k allocations we
> end up wasting whole page.  Isn't it ? Thats why I created right
> sized slabs and disable slab-debug.  I guess, I can do this only for
> 1k, 2k filesystems and directly use alloc_page() for 4k and 8k - but
> that would make code ugly and also it doesn't handle cases for
> bigger base pagesize systems (64k power).

Is there some way we can cleanly have a shortcut case where we use
alloc_page() if fs_blocksize == PAGE_SIZE?  The efficiency gains for
what will be the common case on many architectures will probably make
this worthwhile....

						- Ted

-------------------------------------------------------------------------
Using Tomcat but need to do more? Need to support web services, security?
Get stuff done quickly with pre-integrated technology to make your job easier
Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642