Re: [PATCH] 2.4.20 Direct IO patch for NFS. (Note: a trivial API change...)
From: Trond Myklebust <hidden>
Date: 2002-09-30 18:57:58
Also in:
linux-fsdevel, lkml
Possibly related (same subject, not in this thread)
- 2002-09-30 · Re: [PATCH] 2.4.20 Direct IO patch for NFS. (Note: a trivial API change...) · Alan Cox <hidden>
- 2002-09-30 · Re: [PATCH] 2.4.20 Direct IO patch for NFS. (Note: a trivial API change...) · Andrew Morton <hidden>
- 2002-09-30 · Re: [PATCH] 2.4.20 Direct IO patch for NFS. (Note: a trivial API change...) · Trond Myklebust <hidden>
- 2002-09-30 · Re: [PATCH] 2.4.20 Direct IO patch for NFS. (Note: a trivial API change...) · Christoph Hellwig <hch@infradead.org>
- 2002-09-30 · [PATCH] 2.4.20 Direct IO patch for NFS. (Note: a trivial API change...) · Trond Myklebust <hidden>
quoted
quoted
quoted
quoted
" " == Matthew Wilcox [off-list ref] writes:
>> -static int blkdev_direct_IO(int rw, struct inode * inode,
>> struct kiobuf * iobuf, unsigned long blocknr, int blocksize)
>> +static int blkdev_direct_IO(int rw, struct file * filp, struct
>> kiobuf * iobuf, unsigned long blocknr, int blocksize) {
>> + struct inode * inode =
>> filp->f_dentry->d_inode->i_mapping->host;
>> return generic_direct_IO(rw, inode, iobuf, blocknr, blocksize,
>> blkdev_get_block); }
>>
> isn't that two dereferences more than necessary for a local
> filesystem?
IIRC this is an issue with block filesystems: the i_mapping->host may
differ from d_inode.
It is in any case just the exact same dereference that is being made
in the current version of generic_file_direct_IO(). The API change
simply moves this dereference down into the filesystem code.
Cheers,
Trond
-------------------------------------------------------
This sf.net email is sponsored by:ThinkGeek
Welcome to geek heaven.
http://thinkgeek.com/sf
_______________________________________________
NFS maillist - NFS@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nfs