kernel.git/fs/nfs/read.c, branch linux-3.3.yHosts the 0x221E linux distro kernel.
https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-3.3.y2012-05-07T15:53:18ZNFS: put open context on error in nfs_pagein_multi2012-05-07T15:53:18ZFred Isaman2012-04-20T18:47:34Zurn:sha1:3fe0c6c3bf2c2915f80e292ff1cb908ee31acd7e
commit 73fb7bc7c57d971b11f2e00536ac2d3e316e0609 upstream.
Signed-off-by: Fred Isaman <iisaman@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
NFS: Revert pnfs ugliness from the generic NFS read code path2011-11-10T19:50:26ZTrond Myklebust2011-11-10T19:30:37Zurn:sha1:62e4a76987eab2b7fa952546614bc83e5bfc9d3e
pNFS-specific code belongs in the pnfs layer. It should not be
hijacking generic NFS read or write code paths.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
NFS: Get rid of the nfs_rdata_mempool2011-10-19T20:58:38ZTrond Myklebust2011-10-19T19:17:29Zurn:sha1:b6ee8cd2642f6d822dd1a4ba62298b65ff99b72e
We don't need a mempool in order to guarantee reliable NFS read performance.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
NFS: Don't rely on PageError in nfs_readpage_release_partial2011-10-19T20:58:38ZTrond Myklebust2011-10-19T19:17:29Zurn:sha1:fba730050d1246d0e6ef44e026e0b584732fec2b
Don't rely on the PageError flag to tell us if one of the partial reads of
the page failed. Instead, replace that with a dedicated flag in the
struct nfs_page.
Then clean out redundant uses of the PageError flag: the VM no longer
checks it for reads.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
NFS: Get rid of unnecessary calls to ClearPageError() in read code2011-10-19T20:58:37ZTrond Myklebust2011-10-19T19:17:29Zurn:sha1:fbb5a9abf0d589e9471dc93b18025b7b921d22c9
The generic file read code does that for us anyway.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
NFS: Get rid of nfs_restart_rpc()2011-10-19T20:58:30ZTrond Myklebust2011-10-19T19:17:29Zurn:sha1:d00c5d43866720963a265fa3129f3203cac35b8e
It can trivially be replaced with rpc_restart_call_prepare.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
pnfs: recoalesce when ld read pagelist fails2011-10-18T16:08:14ZPeng Tao2011-09-23T01:50:15Zurn:sha1:9b7eecdcfeb943f130d86bbc249fde4994b6fe30
For pnfs pagelist read failure, we need to pg_recoalesce and resend IO to
mds.
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Cc: stable@kernel.org [3.0]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Merge branch 'master' into devel and apply fixup from Stephen Rothwell:2011-07-25T18:53:52ZStephen Rothwell2011-07-25T17:59:46Zurn:sha1:5f00bcb38ef9a980a33c6dbdc0044964b05f22dd
vfs/nfs: fixup for nfs_open_context change
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
nfs_open_context doesn't need struct path either2011-07-20T05:43:44ZAl Viro2011-06-22T22:40:12Zurn:sha1:3d4ff43d895c50319af45eb4bf04a4618eccdf76
just dentry, please...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
NFS: Clean up - simplify the switch to read/write-through-MDS2011-07-15T13:12:22ZTrond Myklebust2011-07-13T19:59:57Zurn:sha1:1f9453578f059d2651aa6c6b16756627fc9f2a74
Use nfs_pageio_reset_read_mds and nfs_pageio_reset_write_mds instead of
completely reinitialising the struct nfs_pageio_descriptor.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>