Linux NFS development
 help / color / mirror / Atom feed
From: andros@netapp.com
To: bhalevy@panasas.com
Cc: linux-nfs@vger.kernel.org, Andy Adamson <andros@netapp.com>
Subject: [PATCH 08/17] SQUASHME reset offset to mds_offset
Date: Thu, 10 Feb 2011 20:52:41 -0500	[thread overview]
Message-ID: <1297389170-26702-9-git-send-email-andros@netapp.com> (raw)
In-Reply-To: <1297389170-26702-8-git-send-email-andros@netapp.com>

From: Andy Adamson <andros@netapp.com>

squash into: pnfs-submit wave3 filelayout read done

Update the mds_offset in nfs_readpage_retry so that a failed short-read retry
to a DS gets correctly resent through the MDS.

Signed-off-by: Andy Adamson <andros@netapp.com>
---
 fs/nfs/nfs4proc.c |    4 +++-
 fs/nfs/read.c     |    1 +
 2 files changed, 4 insertions(+), 1 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 64a0d4f..f396853 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3108,10 +3108,12 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
 }
 
-/* Reset the the nfs_read_data to send the read to another server. */
+/* Reset the the nfs_read_data to send the read to the MDS. */
 void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data)
 {
 	dprintk("%s Reset task for i/o through \n", __func__);
+	/* offsets will differ in the dense stripe case */
+	data->args.offset = data->mds_offset;
 	data->ds_clp = NULL;
 	data->args.fh     = NFS_FH(data->inode);
 	data->read_done_cb = nfs4_read_done_cb;
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index cb0b239..896dc4e 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -393,6 +393,7 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data
 		return;
 
 	/* Yes, so retry the read at the end of the data */
+	data->mds_offset += resp->count;
 	argp->offset += resp->count;
 	argp->pgbase += resp->count;
 	argp->count -= resp->count;
-- 
1.6.6


  reply	other threads:[~2011-02-11 18:00 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-02-11  1:52 [PATCH 0/17] pnfs-submit-wave3-rev3 bug fixes and cleanup andros
2011-02-11  1:52 ` [PATCH 01/17] SQUASHME pnfs-submit wave3 fix nfs4_ds_connect bug andros
2011-02-11  1:52   ` [PATCH 02/17] SQUASHME fix filelayout_set_lo_fail logic andros
2011-02-11  1:52     ` [PATCH 03/17] SQUASHME rename orig_offset to mds_offset andros
2011-02-11  1:52       ` [PATCH 04/17] SQUASHME rename nfs_read_data call_ops ONE andros
2011-02-11  1:52         ` [PATCH 05/17] SQUASHME rename nfs_read_data call_ops TWO andros
2011-02-11  1:52           ` [PATCH 06/17] SQUASHME rename nfs_read_data call_ops THREE andros
2011-02-11  1:52             ` [PATCH 07/17] SQUASHME remove reset mds_offset from filelayout_rpc_call_done andros
2011-02-11  1:52               ` andros [this message]
2011-02-11  1:52                 ` [PATCH 09/17] SQUASHME cleanup read_pagelist declaration and comment andros
2011-02-11  1:52                   ` [PATCH 10/17] SQUASHME just return ds in nfs4_fl_prepare_ds andros
2011-02-11  1:52                     ` [PATCH 11/17] SQUASHME update pnfs_try_to_read_data comment andros
2011-02-11  1:52                       ` [PATCH 12/17] SQUASHME remove filelayout_async_handle_error comment andros
2011-02-11  1:52                         ` [PATCH 13/17] SQUASHME update nfs4_ds_connect comment andros
2011-02-11  1:52                           ` [PATCH 14/17] SQUASHME don't remove space andros
2011-02-11  1:52                             ` [PATCH 15/17] SQUASHME set non V41 pg_test to NULL andros
2011-02-11  1:52                               ` [PATCH 16/17] SQUASHME restore lost put_lseg code andros
2011-02-11  1:52                                 ` [PATCH 17/17] SQUASHME put_layout_hdr can remove nfsi->layout andros
2011-02-13  5:17 ` [PATCH 0/17] pnfs-submit-wave3-rev3 bug fixes and cleanup Benny Halevy

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1297389170-26702-9-git-send-email-andros@netapp.com \
    --to=andros@netapp.com \
    --cc=bhalevy@panasas.com \
    --cc=linux-nfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox