Linux NFS development
 help / color / mirror / Atom feed
From: Trond Myklebust <trond.myklebust@primarydata.com>
To: linux-nfs@vger.kernel.org
Subject: [PATCH 09/14] pnfs/flexfiles: count io stat in rpc_count_stats callback
Date: Sat, 26 Dec 2015 18:20:55 -0500	[thread overview]
Message-ID: <1451172060-28238-9-git-send-email-trond.myklebust@primarydata.com> (raw)
In-Reply-To: <1451172060-28238-8-git-send-email-trond.myklebust@primarydata.com>

From: Peng Tao <tao.peng@primarydata.com>

If client ever restarts IO due to some errors, we'll endup
mis-counting IO stats if we do the counting in .rpc_done
callback. Move it to .rpc_count_stats callback that is only
called when releasing RPC.

Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index b392156e6743..5ede5c26c757 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1516,11 +1516,6 @@ static void ff_layout_write_call_done(struct rpc_task *task, void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
-	nfs4_ff_layout_stat_io_end_write(task,
-			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
-			hdr->args.count, hdr->res.count,
-			hdr->res.verf->committed);
-
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags) &&
 	    task->tk_status == 0) {
 		nfs4_sequence_done(task, &hdr->res.seq_res);
@@ -1535,6 +1530,11 @@ static void ff_layout_write_count_stats(struct rpc_task *task, void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
+	nfs4_ff_layout_stat_io_end_write(task,
+			FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx),
+			hdr->args.count, hdr->res.count,
+			hdr->res.verf->committed);
+
 	rpc_count_iostats_metrics(task,
 	    &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]);
 }
@@ -1567,6 +1567,11 @@ static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data)
 
 static void ff_layout_commit_done(struct rpc_task *task, void *data)
 {
+	pnfs_generic_write_commit_done(task, data);
+}
+
+static void ff_layout_commit_count_stats(struct rpc_task *task, void *data)
+{
 	struct nfs_commit_data *cdata = data;
 	struct nfs_page *req;
 	__u64 count = 0;
@@ -1580,13 +1585,6 @@ static void ff_layout_commit_done(struct rpc_task *task, void *data)
 			FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index),
 			count, count, NFS_FILE_SYNC);
 
-	pnfs_generic_write_commit_done(task, data);
-}
-
-static void ff_layout_commit_count_stats(struct rpc_task *task, void *data)
-{
-	struct nfs_commit_data *cdata = data;
-
 	rpc_count_iostats_metrics(task,
 	    &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]);
 }
-- 
2.5.0


  reply	other threads:[~2015-12-26 23:21 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-26 23:20 [PATCH 01/14] pNFS/flexfiles: Support server-supplied layoutstats sampling period Trond Myklebust
2015-12-26 23:20 ` [PATCH 02/14] NFS41: pop some layoutget errors to application Trond Myklebust
2015-12-26 23:20   ` [PATCH 03/14] nfs: clean up rest of reqs when failing to add one Trond Myklebust
2015-12-26 23:20     ` [PATCH 04/14] nfs: centralize pgio error cleanup Trond Myklebust
2015-12-26 23:20       ` [PATCH 05/14] nfs: handle request add failure properly Trond Myklebust
2015-12-26 23:20         ` [PATCH 06/14] nfs: only remove page from mapping if launder_page fails Trond Myklebust
2015-12-26 23:20           ` [PATCH 07/14] NFS41: map NFS4ERR_LAYOUTUNAVAILABLE to ENODATA Trond Myklebust
2015-12-26 23:20             ` [PATCH 08/14] pnfs/flexfiles: do not mark delay-like status as DS failure Trond Myklebust
2015-12-26 23:20               ` Trond Myklebust [this message]
2015-12-26 23:20                 ` [PATCH 10/14] pNFS/flexfiles: Don't prevent flexfiles client from retrying LAYOUTGET Trond Myklebust
2015-12-26 23:20                   ` [PATCH 11/14] pNFS/flexfiles: Don't mark the entire layout as failed, when returning it Trond Myklebust
2015-12-26 23:20                     ` [PATCH 12/14] pNFS/flexfiles: Fix a statistics gathering imbalance Trond Myklebust
2015-12-26 23:20                       ` [PATCH 13/14] pNFS: Add flag to track if we've called nfs4_ff_layout_stat_io_start_read/write Trond Myklebust
2015-12-26 23:21                         ` [PATCH 14/14] pNFS/flexfiles: Ensure we record layoutstats even if RPC is terminated early Trond Myklebust
2016-01-04 20:12                         ` [PATCH 13/14] pNFS: Add flag to track if we've called nfs4_ff_layout_stat_io_start_read/write Benjamin Coddington
2016-01-04 16:29       ` [PATCH 04/14] nfs: centralize pgio error cleanup Benjamin Coddington
2016-01-04 15:48     ` [PATCH 03/14] nfs: clean up rest of reqs when failing to add one Benjamin Coddington

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=1451172060-28238-9-git-send-email-trond.myklebust@primarydata.com \
    --to=trond.myklebust@primarydata.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