From: andros@netapp.com
To: trond.myklebust@netapp.com
Cc: linux-nfs@vger.kernel.org, Andy Adamson <andros@netapp.com>
Subject: [PATCH 1/4] NFSv4.1 mdsthreshold attribute xdr
Date: Wed, 23 May 2012 05:02:34 -0400 [thread overview]
Message-ID: <1337763757-1566-1-git-send-email-andros@netapp.com> (raw)
From: Andy Adamson <andros@netapp.com>
We only support one layout type per file system, so one threshold_item4 per
mdsthreshold4.
Signed-off-by: Andy Adamson <andros@netapp.com>
---
fs/nfs/nfs4xdr.c | 125 ++++++++++++++++++++++++++++++++++++++++++++++-
include/linux/nfs4.h | 7 +++
include/linux/nfs_xdr.h | 10 ++++
3 files changed, 140 insertions(+), 2 deletions(-)
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index db040e9..db199f8 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -99,9 +99,12 @@ static int nfs4_stat_to_errno(int);
#define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2))
#define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
#define nfs4_group_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
+/* We support only one layout type per file system */
+#define decode_mdsthreshold_maxsz (1 + 1 + nfs4_fattr_bitmap_maxsz + 1 + 8)
/* This is based on getfattr, which uses the most attributes: */
#define nfs4_fattr_value_maxsz (1 + (1 + 2 + 2 + 4 + 2 + 1 + 1 + 2 + 2 + \
- 3 + 3 + 3 + nfs4_owner_maxsz + nfs4_group_maxsz))
+ 3 + 3 + 3 + nfs4_owner_maxsz + \
+ nfs4_group_maxsz + decode_mdsthreshold_maxsz))
#define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \
nfs4_fattr_value_maxsz)
#define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz)
@@ -1170,6 +1173,16 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c
bitmask[1] & nfs4_fattr_bitmap[1], hdr);
}
+static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask,
+ struct compound_hdr *hdr)
+{
+ encode_getattr_three(xdr,
+ bitmask[0] & nfs4_fattr_bitmap[0],
+ bitmask[1] & nfs4_fattr_bitmap[1],
+ bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD,
+ hdr);
+}
+
static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
{
encode_getattr_three(xdr,
@@ -2161,7 +2174,7 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_putfh(xdr, args->fh, &hdr);
encode_open(xdr, args, &hdr);
encode_getfh(xdr, &hdr);
- encode_getfattr(xdr, args->bitmask, &hdr);
+ encode_getfattr_open(xdr, args->bitmask, &hdr);
encode_nops(&hdr);
}
@@ -4183,6 +4196,110 @@ xdr_error:
return status;
}
+static int decode_threshold_hint(struct xdr_stream *xdr,
+ uint32_t *bitmap,
+ uint64_t *res,
+ uint32_t hint_bit)
+{
+ __be32 *p;
+
+ *res = 0;
+ if (likely(bitmap[0] & hint_bit)) {
+ p = xdr_inline_decode(xdr, 8);
+ if (unlikely(!p))
+ goto out_overflow;
+ xdr_decode_hyper(p, res);
+ }
+ return 0;
+out_overflow:
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+}
+
+static int decode_first_threshold_item4(struct xdr_stream *xdr,
+ struct nfs4_threshold *res)
+{
+ __be32 *p, *savep;
+ uint32_t bitmap[3] = {0,}, attrlen;
+ int status;
+
+ /* layout type */
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p)) {
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+ }
+ res->l_type = be32_to_cpup(p);
+
+ /* thi_hintset bitmap */
+ status = decode_attr_bitmap(xdr, bitmap);
+ if (status < 0)
+ goto xdr_error;
+
+ /* thi_hintlist length */
+ status = decode_attr_length(xdr, &attrlen, &savep);
+ if (status < 0)
+ goto xdr_error;
+ /* thi_hintlist */
+ status = decode_threshold_hint(xdr, bitmap, &res->rd_sz, THRESHOLD_RD);
+ if (status < 0)
+ goto xdr_error;
+ status = decode_threshold_hint(xdr, bitmap, &res->wr_sz, THRESHOLD_WR);
+ if (status < 0)
+ goto xdr_error;
+ status = decode_threshold_hint(xdr, bitmap, &res->rd_io_sz,
+ THRESHOLD_RD_IO);
+ if (status < 0)
+ goto xdr_error;
+ status = decode_threshold_hint(xdr, bitmap, &res->wr_io_sz,
+ THRESHOLD_WR_IO);
+ if (status < 0)
+ goto xdr_error;
+
+ status = verify_attr_len(xdr, savep, attrlen);
+ res->bm = bitmap[0];
+
+ dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n",
+ __func__, res->bm, res->rd_sz, res->wr_sz, res->rd_io_sz,
+ res->wr_io_sz);
+xdr_error:
+ dprintk("%s ret=%d!\n", __func__, status);
+ return status;
+}
+
+/*
+ * Thresholds on pNFS direct I/O vrs MDS I/O
+ */
+static int decode_attr_mdsthreshold(struct xdr_stream *xdr,
+ uint32_t *bitmap,
+ struct nfs4_threshold *res)
+{
+ __be32 *p;
+ int status = 0;
+ uint32_t num;
+
+ if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U)))
+ return -EIO;
+ if (likely(bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD)) {
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ goto out_overflow;
+ num = be32_to_cpup(p);
+ if (num == 0)
+ return 0;
+ if (num > 1)
+ printk(KERN_INFO "%s: Warning: Multiple pNFS layout "
+ "drivers per filesystem not supported\n",
+ __func__);
+
+ status = decode_first_threshold_item4(xdr, res);
+ }
+ return status;
+out_overflow:
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+}
+
static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
struct nfs_fattr *fattr, struct nfs_fh *fh,
struct nfs4_fs_locations *fs_loc,
@@ -4289,6 +4406,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
goto xdr_error;
fattr->valid |= status;
+ status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold);
+ if (status < 0)
+ goto xdr_error;
+
xdr_error:
dprintk("%s: xdr returned %d\n", __func__, -status);
return status;
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 0987146..72b6bad 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -526,6 +526,13 @@ enum lock_type4 {
#define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23)
#define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30)
#define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1)
+#define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4)
+
+/* MDS threshold bitmap bits */
+#define THRESHOLD_RD (1UL << 0)
+#define THRESHOLD_WR (1UL << 1)
+#define THRESHOLD_RD_IO (1UL << 2)
+#define THRESHOLD_WR_IO (1UL << 3)
#define NFSPROC4_NULL 0
#define NFSPROC4_COMPOUND 1
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 2e53a3f..5b8e42e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -35,6 +35,15 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid
return a->major == b->major && a->minor == b->minor;
}
+struct nfs4_threshold {
+ __u32 bm;
+ __u32 l_type;
+ __u64 rd_sz;
+ __u64 wr_sz;
+ __u64 rd_io_sz;
+ __u64 wr_io_sz;
+};
+
struct nfs_fattr {
unsigned int valid; /* which fields are valid */
umode_t mode;
@@ -67,6 +76,7 @@ struct nfs_fattr {
unsigned long gencount;
struct nfs4_string *owner_name;
struct nfs4_string *group_name;
+ struct nfs4_threshold *mdsthreshold; /* pNFS threshold hints */
};
#define NFS_ATTR_FATTR_TYPE (1U << 0)
--
1.7.7.6
next reply other threads:[~2012-05-23 13:03 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-23 9:02 andros [this message]
2012-05-23 9:02 ` [PATCH 2/4] NFSv4.1 cache mdsthreshold values on OPEN andros
2012-05-23 9:02 ` [PATCH 3/4] NFSv4.1 add nfs_inode book keeping for mdsthreshold andros
2012-05-23 18:19 ` Myklebust, Trond
2012-05-23 18:41 ` Adamson, Andy
2012-05-23 9:02 ` [PATCH 4/4] NFSv4.1 test the mdsthreshold hint parameters andros
2012-05-23 13:25 ` Boaz Harrosh
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=1337763757-1566-1-git-send-email-andros@netapp.com \
--to=andros@netapp.com \
--cc=linux-nfs@vger.kernel.org \
--cc=trond.myklebust@netapp.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;
as well as URLs for NNTP newsgroup(s).