Re: [PATCH 4/8] knfsd: repcache: split hash index

[Greg Banks <gnb@sgi.com>]

On Mon, Oct 16, 2006 at 08:23:30PM +1000, Neil Brown wrote:
> On Monday October 16, gnb@sgi.com wrote:
> > 
> > Let's look at the maths.  If we were to limit cache_buckets[] to a
> > single page, I calculate that would give us 186 entries on ia64, 46
> > on x86_64, and 68 on i386 (fewer if various spinlock-related config
> > options are enabled).  That's too low on x86_64 but fine on the other
> > platforms.  With a single order-1 allocation we could cover most
> > bases.
> 
> I had thought that ____cacheline_aligned_in_smp would have padded it
> more making few entries per page, but that probably isn't important.

Ooops, you're right.  That makes the numbers 128 on ia64, 42 on
x86_64, and 64 on i386.

> > Alternatively, we could allocate the buckets separately and make
> > cache_buckets[] an array of pointers to buckets.  Then we could do a
> > single (say) 128*sizeof(svc_cache_bucket*) allocation plus (say) 128 *
> > sizeof(svc_cache_bucket) allocations, all of which would be order 0.
> > Now we've effectively got a 3-level fat tree keyed on hash value.
> > 
> > The more I think about it, the more I like this idea.
> > 
> 
> Me too.

Righto, new patches probably tomorrow.

Greg.
-- 
Greg Banks, R&D Software Engineer, SGI Australian Software Group.
I don't speak for SGI.

-------------------------------------------------------------------------
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
_______________________________________________
NFS maillist  -  NFS@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nfs