diff options
| author | Chuck Lever <cel@netapp.com> | 2005-11-30 18:09:02 -0500 |
|---|---|---|
| committer | Trond Myklebust <Trond.Myklebust@netapp.com> | 2006-01-06 14:58:49 -0500 |
| commit | 40859d7ee64ed6bfad8a4e93f9bb5c1074afadff (patch) | |
| tree | ed4069423c3d6551035d5b6116f50452cdac4103 /fs/nfs/read.c | |
| parent | 325cfed9ae901320e9234b18c21434b783dbe342 (diff) | |
| download | kernel_samsung_smdk4412-40859d7ee64ed6bfad8a4e93f9bb5c1074afadff.zip kernel_samsung_smdk4412-40859d7ee64ed6bfad8a4e93f9bb5c1074afadff.tar.gz kernel_samsung_smdk4412-40859d7ee64ed6bfad8a4e93f9bb5c1074afadff.tar.bz2 | |
NFS: support large reads and writes on the wire
Most NFS server implementations allow up to 64KB reads and writes on the
wire. The Solaris NFS server allows up to a megabyte, for instance.
Now the Linux NFS client supports transfer sizes up to 1MB, too. This will
help reduce protocol and context switch overhead on read/write intensive NFS
workloads, and support larger atomic read and write operations on servers
that support them.
Test-plan:
Connectathon and iozone on mount point with wsize=rsize>32768 over TCP.
Tests with NFS over UDP to verify the maximum RPC payload size cap.
Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Diffstat (limited to 'fs/nfs/read.c')
| -rw-r--r-- | fs/nfs/read.c | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 2148624..05eb43f 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -83,7 +83,7 @@ static int nfs_readpage_sync(struct nfs_open_context *ctx, struct inode *inode, int result; struct nfs_read_data *rdata; - rdata = nfs_readdata_alloc(); + rdata = nfs_readdata_alloc(1); if (!rdata) return -ENOMEM; @@ -283,7 +283,7 @@ static int nfs_pagein_multi(struct list_head *head, struct inode *inode) nbytes = req->wb_bytes; for(;;) { - data = nfs_readdata_alloc(); + data = nfs_readdata_alloc(1); if (!data) goto out_bad; INIT_LIST_HEAD(&data->pages); @@ -339,7 +339,7 @@ static int nfs_pagein_one(struct list_head *head, struct inode *inode) if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE) return nfs_pagein_multi(head, inode); - data = nfs_readdata_alloc(); + data = nfs_readdata_alloc(NFS_SERVER(inode)->rpages); if (!data) goto out_bad; |