Neil,
Here is a set of fixes and answers to you questions/points. The new patch
was tested in my own environment again and worked fine.
1/ Why did you change nfsd_busy into an atomic_t? It is only ever
used or updated inside the Big-Kernel-Lock, so it doesn't need
to be atomic.
I
Neil,
Here is a set of fixes and answers to you questions/points. The new patch
was tested in my own environment again and worked fine.
1/ Why did you change nfsd_busy into an atomic_t? It is only ever
used or updated inside the Big-Kernel-Lock, so it doesn't need
to be atomic.
I
On Sunday November 12, [EMAIL PROTECTED] wrote:
>
> Hi,
>
> This is the recoded racache that uses list_head for several lists, e.g.,
> lru and free lists. I have tested it under SPEC SFS runs, and several other
> NFS loads myself.
Ok, I have taken a closer look at this code:
1/ Why did you
Hi,
This is the recoded racache that uses list_head for several lists, e.g.,
lru and free lists. I have tested it under SPEC SFS runs, and several other
NFS loads myself.
Here is the whole patch against test10.
=
diff -ruN nfsd.orig/nfsd.h
Hi,
This is the recoded racache that uses list_head for several lists, e.g.,
lru and free lists. I have tested it under SPEC SFS runs, and several other
NFS loads myself.
Here is the whole patch against test10.
=
diff -ruN nfsd.orig/nfsd.h
On Sunday November 12, [EMAIL PROTECTED] wrote:
Hi,
This is the recoded racache that uses list_head for several lists, e.g.,
lru and free lists. I have tested it under SPEC SFS runs, and several other
NFS loads myself.
Ok, I have taken a closer look at this code:
1/ Why did you change
On Friday November 10, [EMAIL PROTECTED] wrote:
> Hi,
>
> I made some optimizations on racache in nfsd in test10. The idea is to
> replace with existing fixed length table for readahead cache in NFSD with a
> hash table.
> The old racache is essentially ineffective in dealing with large # of
>
On Friday November 10, [EMAIL PROTECTED] wrote:
Hi,
I made some optimizations on racache in nfsd in test10. The idea is to
replace with existing fixed length table for readahead cache in NFSD with a
hash table.
The old racache is essentially ineffective in dealing with large # of
files,
Hi,
I made some optimizations on racache in nfsd in test10. The idea is to
replace with existing fixed length table for readahead cache in NFSD with a
hash table.
The old racache is essentially ineffective in dealing with large # of
files, and yet eats CPU cycles in scanning the table (even
Hi,
I made some optimizations on racache in nfsd in test10. The idea is to
replace with existing fixed length table for readahead cache in NFSD with a
hash table.
The old racache is essentially ineffective in dealing with large # of
files, and yet eats CPU cycles in scanning the table (even
10 matches
Mail list logo