From: Mike Snitzer <snitzer@kernel.org>
To: linux-nfs@vger.kernel.org
Cc: Jeff Layton <jlayton@kernel.org>,
Chuck Lever <chuck.lever@oracle.com>,
Trond Myklebust <trondmy@hammerspace.com>,
snitzer@hammerspace.com
Subject: [for-6.11 PATCH 13/29] pnfs/flexfiles: Enable localio for flexfiles I/O
Date: Fri, 7 Jun 2024 10:26:30 -0400 [thread overview]
Message-ID: <20240607142646.20924-14-snitzer@kernel.org> (raw)
In-Reply-To: <20240607142646.20924-1-snitzer@kernel.org>
From: Trond Myklebust <trond.myklebust@hammerspace.com>
If the DS is local to this client, then we might be able to use local
I/O to write the data.
[snitm: rebase accounted for commit 0ede61d8589cc ("file: convert to SLAB_TYPESAFE_BY_RCU")]
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
fs/nfs/flexfilelayout/flexfilelayout.c | 109 +++++++++++++++++++++++--
fs/nfs/flexfilelayout/flexfilelayout.h | 2 +
2 files changed, 104 insertions(+), 7 deletions(-)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index ce6cb5d82427..0a9eccb44085 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -11,6 +11,7 @@
#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
+#include <linux/file.h>
#include <linux/sched/mm.h>
#include <linux/sunrpc/metrics.h>
@@ -162,6 +163,52 @@ decode_name(struct xdr_stream *xdr, u32 *id)
return 0;
}
+static struct file *
+ff_local_open_fh(struct pnfs_layout_segment *lseg,
+ u32 ds_idx,
+ struct nfs_client *clp,
+ const struct cred *cred,
+ struct nfs_fh *fh,
+ fmode_t mode)
+{
+ struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
+ struct file *filp, *new, __rcu **pfile;
+
+ if (!nfs_server_is_local(clp))
+ return NULL;
+ if (mode & FMODE_WRITE) {
+ /*
+ * Always request read and write access since this corresponds
+ * to a rw layout.
+ */
+ mode |= FMODE_READ;
+ pfile = &mirror->rw_file;
+ } else
+ pfile = &mirror->ro_file;
+
+ new = NULL;
+ rcu_read_lock();
+ filp = rcu_dereference(*pfile);
+ if (!filp) {
+ rcu_read_unlock();
+ new = nfs_local_open_fh(clp, cred, fh, mode);
+ if (IS_ERR(new))
+ return NULL;
+ rcu_read_lock();
+ /* try to swap in the pointer */
+ filp = cmpxchg(pfile, NULL, new);
+ if (!filp) {
+ filp = new;
+ new = NULL;
+ }
+ }
+ filp = get_file_rcu(&filp);
+ rcu_read_unlock();
+ if (new)
+ fput(new);
+ return filp;
+}
+
static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
const struct nfs4_ff_layout_mirror *m2)
{
@@ -237,8 +284,15 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
+ struct file *filp;
const struct cred *cred;
+ filp = rcu_access_pointer(mirror->ro_file);
+ if (filp)
+ fput(filp);
+ filp = rcu_access_pointer(mirror->rw_file);
+ if (filp)
+ fput(filp);
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
cred = rcu_access_pointer(mirror->ro_cred);
@@ -414,6 +468,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
struct nfs4_ff_layout_mirror *mirror;
struct cred *kcred;
const struct cred __rcu *cred;
+ const struct cred __rcu *old;
kuid_t uid;
kgid_t gid;
u32 ds_count, fh_count, id;
@@ -513,13 +568,26 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
mirror = ff_layout_add_mirror(lh, fls->mirror_array[i]);
if (mirror != fls->mirror_array[i]) {
+ struct file *filp;
+
/* swap cred ptrs so free_mirror will clean up old */
if (lgr->range.iomode == IOMODE_READ) {
- cred = xchg(&mirror->ro_cred, cred);
- rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
+ old = xchg(&mirror->ro_cred, cred);
+ rcu_assign_pointer(fls->mirror_array[i]->ro_cred, old);
+ /* drop file if creds changed */
+ if (old != cred) {
+ filp = rcu_dereference_protected(xchg(&mirror->ro_file, NULL), 1);
+ if (filp)
+ fput(filp);
+ }
} else {
- cred = xchg(&mirror->rw_cred, cred);
- rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
+ old = xchg(&mirror->rw_cred, cred);
+ rcu_assign_pointer(fls->mirror_array[i]->rw_cred, old);
+ if (old != cred) {
+ filp = rcu_dereference_protected(xchg(&mirror->rw_file, NULL), 1);
+ if (filp)
+ fput(filp);
+ }
}
ff_layout_free_mirror(fls->mirror_array[i]);
fls->mirror_array[i] = mirror;
@@ -1757,6 +1825,7 @@ ff_layout_read_pagelist(struct nfs_pageio_descriptor *desc,
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct file *filp;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
@@ -1803,12 +1872,20 @@ ff_layout_read_pagelist(struct nfs_pageio_descriptor *desc,
hdr->args.offset = offset;
hdr->mds_offset = offset;
+ /* Start IO accounting for local read */
+ filp = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+ FMODE_READ);
+ if (filp) {
+ hdr->task.tk_start = ktime_get();
+ ff_layout_read_record_layoutstats_start(&hdr->task, hdr);
+ }
+
/* Perform an asynchronous read to ds */
nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, ds_cred,
ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
- 0, RPC_TASK_SOFTCONN, NULL);
+ 0, RPC_TASK_SOFTCONN, filp);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1829,6 +1906,7 @@ ff_layout_write_pagelist(struct nfs_pageio_descriptor *desc,
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct file *filp;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
@@ -1873,12 +1951,20 @@ ff_layout_write_pagelist(struct nfs_pageio_descriptor *desc,
*/
hdr->args.offset = offset;
+ /* Start IO accounting for local write */
+ filp = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+ FMODE_READ|FMODE_WRITE);
+ if (filp) {
+ hdr->task.tk_start = ktime_get();
+ ff_layout_write_record_layoutstats_start(&hdr->task, hdr);
+ }
+
/* Perform an asynchronous write */
nfs_initiate_pgio(desc, ds->ds_clp, ds_clnt, hdr, ds_cred,
ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
- sync, RPC_TASK_SOFTCONN, NULL);
+ sync, RPC_TASK_SOFTCONN, filp);
put_cred(ds_cred);
return PNFS_ATTEMPTED;
@@ -1912,6 +1998,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
struct pnfs_layout_segment *lseg = data->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
+ struct file *filp;
struct nfs4_ff_layout_mirror *mirror;
const struct cred *ds_cred;
u32 idx;
@@ -1950,10 +2037,18 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
if (fh)
data->args.fh = fh;
+ /* Start IO accounting for local commit */
+ filp = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
+ FMODE_READ|FMODE_WRITE);
+ if (filp) {
+ data->task.tk_start = ktime_get();
+ ff_layout_commit_record_layoutstats_start(&data->task, data);
+ }
+
ret = nfs_initiate_commit(ds->ds_clp, ds_clnt, data, ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_commit_call_ops_v3 :
&ff_layout_commit_call_ops_v4,
- how, RPC_TASK_SOFTCONN, NULL);
+ how, RPC_TASK_SOFTCONN, filp);
put_cred(ds_cred);
return ret;
out_err:
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index f84b3fb0dddd..8e042df5a2c9 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -82,7 +82,9 @@ struct nfs4_ff_layout_mirror {
struct nfs_fh *fh_versions;
nfs4_stateid stateid;
const struct cred __rcu *ro_cred;
+ struct file __rcu *ro_file;
const struct cred __rcu *rw_cred;
+ struct file __rcu *rw_file;
refcount_t ref;
spinlock_t lock;
unsigned long flags;
--
2.44.0
next prev parent reply other threads:[~2024-06-07 14:27 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-07 14:26 [for-6.11 PATCH 00/29] nfs/nfsd: add support for localio bypass Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 01/29] nfs: pass nfs_client to nfs_initiate_pgio Mike Snitzer
2024-06-10 12:02 ` Jeff Layton
2024-06-07 14:26 ` [for-6.11 PATCH 02/29] nfs: pass nfs_client to nfs_initiate_commit Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 03/29] nfs: pass descriptor thru nfs_initiate_pgio path Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 04/29] sunrpc: handle NULL req->defer in cache_defer_req Mike Snitzer
2024-06-10 12:21 ` Jeff Layton
2024-06-11 1:03 ` NeilBrown
2024-06-11 2:57 ` Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 05/29] sunrpc: export svc_defer Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 06/29] sunrpc: add rpcauth_map_to_svc_cred Mike Snitzer
2024-06-10 12:19 ` Jeff Layton
2024-06-07 14:26 ` [for-6.11 PATCH 07/29] sunrpc: add and export rpc_ntop6_addr_noscopeid Mike Snitzer
2024-06-09 12:36 ` Jeff Layton
2024-06-10 16:33 ` Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 08/29] nfs: move nfs_stat_to_errno to nfs.h Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 09/29] NFS: Manage boot verifier correctly in the case of localio Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 10/29] nfs/nfsd: add "local io" support Mike Snitzer
2024-06-10 12:43 ` Jeff Layton
2024-06-10 16:42 ` Mike Snitzer
2024-06-12 2:25 ` Mike Snitzer
2024-06-12 3:17 ` NeilBrown
2024-06-12 3:41 ` Mike Snitzer
2024-06-12 4:09 ` NeilBrown
2024-06-12 4:48 ` Mike Snitzer
2024-06-12 6:30 ` NeilBrown
2024-06-07 14:26 ` [for-6.11 PATCH 11/29] NFS: Enable localio for non-pNFS I/O Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 12/29] nfs/flexfiles: check local DS when making DS connections Mike Snitzer
2024-06-07 14:26 ` Mike Snitzer [this message]
2024-06-07 14:26 ` [for-6.11 PATCH 14/29] NFS: Add tracepoints for nfs_local_enable and nfs_local_disable Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 15/29] NFS: Don't call filesystem write() routines directly Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 16/29] NFS: Don't call filesystem read() " Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 17/29] NFS: Use completion rather than flush_work() in nfs_local_commit() Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 18/29] NFS: localio writes need to use a normal workqueue Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 19/29] nfs/write: fix nfs_initiate_commit to return error from nfs_local_commit Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 20/29] nfs/localio: discontinue network address based localio setup Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 21/29] nfs_common: add NFS v3 LOCALIO protocol extension enablement Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 22/29] nfs: implement v3 client support for NFS_LOCALIO_PROGRAM Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 23/29] nfsd: implement v3 server " Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 24/29] nfs_common: add NFS v4 LOCALIO protocol extension enablement Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 25/29] nfs: implement v4 client support for NFS_LOCALIO_PROGRAM Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 26/29] nfsd: implement v4 server " Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 27/29] nfs/nfsd: switch GETUUID to using {encode,decode}_opaque_fixed Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 28/29] nfs/nfsd: consolidate {encode,decode}_opaque_fixed in nfs_xdr.h Mike Snitzer
2024-06-07 14:26 ` [for-6.11 PATCH 29/29] nfs/localio: move managing nfsd_open_local_fh symbol to nfs_common Mike Snitzer
2024-06-07 18:06 ` [for-6.11 PATCH 30/29] nfs/nfsd: ensure localio server always uses its network namespace Mike Snitzer
2024-06-09 15:44 ` Chuck Lever
2024-06-10 16:50 ` Mike Snitzer
2024-06-10 22:37 ` Mike Snitzer
2024-06-07 18:09 ` [for-6.11 PATCH 00/29] nfs/nfsd: add support for localio bypass Mike Snitzer
2024-06-10 12:47 ` Jeff Layton
2024-06-10 16:47 ` Mike Snitzer
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=20240607142646.20924-14-snitzer@kernel.org \
--to=snitzer@kernel.org \
--cc=chuck.lever@oracle.com \
--cc=jlayton@kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=snitzer@hammerspace.com \
--cc=trondmy@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