> You need to save 48 bytes per inode to fit one more into a slab with
> a 32 byte L1 cache slot; 120 bytes per inode, 64 byte L1 cache slot.
> And that's just a generic inode_cache object. Something that is really
> used, like ext3_inode_cache or nfs_inode_cache is going to take more
> doing. Moving a field from the generic inode to the filesystem specific
> inode acheives nothing.
for the inode slab it would very much make sense to tell the slab
allocator to not do any kind of cacheline alignment at all, just because
of the wasted space...
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
