From: cel@kernel.org
To: NeilBrown <neil@brown.name>, Jeff Layton <jlayton@kernel.org>,
Olga Kornievskaia <okorniev@redhat.com>,
Dai Ngo <dai.ngo@oracle.com>, Tom Talpey <tom@talpey.com>,
Trond Myklebust <trond.myklebust@hammerspace.com>,
Anna Schumaker <anna@kernel.org>
Cc: sargun@sargun.me, <linux-nfs@vger.kernel.org>,
<linux-kernel@vger.kernel.org>
Subject: [PATCH v4 10/18] nfsd: add tracepoint to nfsd_readdir
Date: Sat, 3 May 2025 15:59:28 -0400 [thread overview]
Message-ID: <20250503195936.5083-11-cel@kernel.org> (raw)
In-Reply-To: <20250503195936.5083-1-cel@kernel.org>
From: Jeff Layton <jlayton@kernel.org>
Observe the start of NFS READDIR operations.
The NFS READDIR's count argument can be interesting when tuning a
client's readdir behavior.
However, the count argument is not passed to nfsd_readdir(). To
properly capture the count argument, this tracepoint must appear in
each proc function before the nfsd_readdir() call.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/nfs3proc.c | 2 ++
fs/nfsd/nfs4proc.c | 3 +++
fs/nfsd/nfsproc.c | 2 ++
fs/nfsd/trace.h | 26 ++++++++++++++++++++++++++
4 files changed, 33 insertions(+)
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 5d2b081072e8..80096a5c4865 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -625,6 +625,7 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp)
dprintk("nfsd: READDIR(3) %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
argp->count, (u32) argp->cookie);
+ trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie);
nfsd3_init_dirlist_pages(rqstp, resp, argp->count);
@@ -659,6 +660,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
argp->count, (u32) argp->cookie);
+ trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie);
nfsd3_init_dirlist_pages(rqstp, resp, argp->count);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 77895e099673..483fd8b26f9d 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -998,6 +998,9 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
u64 cookie = readdir->rd_cookie;
static const nfs4_verifier zeroverf;
+ trace_nfsd_vfs_readdir(rqstp, &cstate->current_fh,
+ readdir->rd_maxcount, readdir->rd_cookie);
+
/* no need to check permission - this will be done in nfsd_readdir() */
if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 6dda081eb24c..c561af30c37a 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -10,6 +10,7 @@
#include "cache.h"
#include "xdr.h"
#include "vfs.h"
+#include "trace.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -618,6 +619,7 @@ nfsd_proc_readdir(struct svc_rqst *rqstp)
dprintk("nfsd: READDIR %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
argp->count, argp->cookie);
+ trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie);
nfsd_init_dirlist_pages(rqstp, resp, argp->count);
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 46091d7f2260..bed58cf55c10 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -2553,6 +2553,32 @@ TRACE_EVENT(nfsd_vfs_rename,
)
);
+TRACE_EVENT(nfsd_vfs_readdir,
+ TP_PROTO(
+ const struct svc_rqst *rqstp,
+ const struct svc_fh *fhp,
+ u32 count,
+ u64 offset
+ ),
+ TP_ARGS(rqstp, fhp, count, offset),
+ TP_STRUCT__entry(
+ NFSD_TRACE_PROC_CALL_FIELDS(rqstp)
+ __field(u32, fh_hash)
+ __field(u32, count)
+ __field(u64, offset)
+ ),
+ TP_fast_assign(
+ NFSD_TRACE_PROC_CALL_ASSIGNMENTS(rqstp);
+ __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+ __entry->count = count;
+ __entry->offset = offset;
+ ),
+ TP_printk("xid=0x%08x fh_hash=0x%08x offset=%llu count=%u",
+ __entry->xid, __entry->fh_hash,
+ __entry->offset, __entry->count
+ )
+);
+
#endif /* _NFSD_TRACE_H */
#undef TRACE_INCLUDE_PATH
--
2.49.0
next prev parent reply other threads:[~2025-05-03 19:59 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-03 19:59 [PATCH v4 00/18] nfsd: observability improvements cel
2025-05-03 19:59 ` [PATCH v4 01/18] NFSD: Use sockaddr instead of a generic array cel
2025-05-03 20:29 ` Jeff Layton
2025-05-03 19:59 ` [PATCH v4 02/18] NFSD: Add a Call equivalent to the NFSD_TRACE_PROC_RES macros cel
2025-05-03 20:30 ` Jeff Layton
2025-05-03 19:59 ` [PATCH v4 03/18] nfsd: add a tracepoint for nfsd_setattr cel
2025-05-03 19:59 ` [PATCH v4 04/18] nfsd: add a tracepoint to nfsd_lookup_dentry cel
2025-05-03 19:59 ` [PATCH v4 05/18] nfsd: add nfsd_vfs_create tracepoints cel
2025-05-03 19:59 ` [PATCH v4 06/18] nfsd: add tracepoint to nfsd_symlink cel
2025-05-03 19:59 ` [PATCH v4 07/18] nfsd: add tracepoint to nfsd_link() cel
2025-05-03 20:30 ` Jeff Layton
2025-05-03 19:59 ` [PATCH v4 08/18] nfsd: add tracepoints for unlink events cel
2025-05-03 19:59 ` [PATCH v4 09/18] nfsd: add tracepoint to nfsd_rename cel
2025-05-03 19:59 ` cel [this message]
2025-05-03 19:59 ` [PATCH v4 11/18] nfsd: add tracepoint for getattr and statfs events cel
2025-05-03 19:59 ` [PATCH v4 12/18] nfsd: remove old v2/3 create path dprintks cel
2025-05-03 19:59 ` [PATCH v4 13/18] nfsd: remove old v2/3 SYMLINK dprintks cel
2025-05-03 19:59 ` [PATCH v4 14/18] nfsd: remove old LINK dprintks cel
2025-05-03 19:59 ` [PATCH v4 15/18] nfsd: remove REMOVE/RMDIR dprintks cel
2025-05-03 19:59 ` [PATCH v4 16/18] nfsd: remove dprintks for v2/3 RENAME events cel
2025-05-03 19:59 ` [PATCH v4 17/18] nfsd: remove legacy READDIR dprintks cel
2025-05-03 19:59 ` [PATCH v4 18/18] nfsd: remove legacy dprintks from GETATTR and STATFS codepaths cel
2025-05-03 20:32 ` [PATCH v4 00/18] nfsd: observability improvements Jeff Layton
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=20250503195936.5083-11-cel@kernel.org \
--to=cel@kernel.org \
--cc=anna@kernel.org \
--cc=dai.ngo@oracle.com \
--cc=jlayton@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=neil@brown.name \
--cc=okorniev@redhat.com \
--cc=sargun@sargun.me \
--cc=tom@talpey.com \
--cc=trond.myklebust@hammerspace.com \
/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