Linux-NFS Archive on lore.kernel.org
 help / color / Atom feed
From: Benny Halevy <bhalevy@tonian.com>
To: Jim Rees <rees@umich.edu>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>,
	linux-nfs@vger.kernel.org, peter honeyman <honey@citi.umich.edu>
Subject: Re: [PATCH v2 05/25] pnfs: ask for layout_blksize and save it in nfs_server
Date: Mon, 25 Jul 2011 10:24:23 -0400
Message-ID: <4E2D7C97.8070902@tonian.com> (raw)
In-Reply-To: <1311276865-29484-6-git-send-email-rees@umich.edu>

On 2011-07-21 15:34, Jim Rees wrote:
> From: Fred Isaman <iisaman@citi.umich.edu>
> 
> Block layout needs it to determine IO size.
> 
> Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
> Signed-off-by: Tao Guo <glorioustao@gmail.com>
> Signed-off-by: Benny Halevy <bhalevy@panasas.com>
> Signed-off-by: Benny Halevy <benny@tonian.com>
> ---
>  fs/nfs/client.c           |    1 +
>  fs/nfs/nfs4_fs.h          |    2 +-
>  fs/nfs/nfs4proc.c         |    5 +-
>  fs/nfs/nfs4xdr.c          |   99 +++++++++++++++++++++++++++++++++++++--------
>  include/linux/nfs_fs_sb.h |    4 +-
>  include/linux/nfs_xdr.h   |    3 +-
>  6 files changed, 92 insertions(+), 22 deletions(-)
> 
> diff --git a/fs/nfs/client.c b/fs/nfs/client.c
> index a9b1848..de00a37 100644
> --- a/fs/nfs/client.c
> +++ b/fs/nfs/client.c
> @@ -936,6 +936,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
>  	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
>  		server->wsize = NFS_MAX_FILE_IO_SIZE;
>  	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
> +	server->pnfs_blksize = fsinfo->blksize;
>  	set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);
>  
>  	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
> diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
> index c30aed2..b7ad2f0 100644
> --- a/fs/nfs/nfs4_fs.h
> +++ b/fs/nfs/nfs4_fs.h
> @@ -318,7 +318,7 @@ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
>  extern const u32 nfs4_fattr_bitmap[2];
>  extern const u32 nfs4_statfs_bitmap[2];
>  extern const u32 nfs4_pathconf_bitmap[2];
> -extern const u32 nfs4_fsinfo_bitmap[2];
> +extern const u32 nfs4_fsinfo_bitmap[3];
>  extern const u32 nfs4_fs_locations_bitmap[2];
>  
>  /* nfs4renewd.c */
> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
> index 784c1a2..e02f545 100644
> --- a/fs/nfs/nfs4proc.c
> +++ b/fs/nfs/nfs4proc.c
> @@ -140,12 +140,13 @@ const u32 nfs4_pathconf_bitmap[2] = {
>  	0
>  };
>  
> -const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE
> +const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
>  			| FATTR4_WORD0_MAXREAD
>  			| FATTR4_WORD0_MAXWRITE
>  			| FATTR4_WORD0_LEASE_TIME,
>  			FATTR4_WORD1_TIME_DELTA
> -			| FATTR4_WORD1_FS_LAYOUT_TYPES
> +			| FATTR4_WORD1_FS_LAYOUT_TYPES,
> +			FATTR4_WORD2_LAYOUT_BLKSIZE
>  };
>  
>  const u32 nfs4_fs_locations_bitmap[2] = {
> diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
> index a82dd40..5ce3c64 100644
> --- a/fs/nfs/nfs4xdr.c
> +++ b/fs/nfs/nfs4xdr.c
> @@ -113,7 +113,11 @@ static int nfs4_stat_to_errno(int);
>  #define encode_restorefh_maxsz  (op_encode_hdr_maxsz)
>  #define decode_restorefh_maxsz  (op_decode_hdr_maxsz)
>  #define encode_fsinfo_maxsz	(encode_getattr_maxsz)
> -#define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + 15)
> +/* The 5 accounts for the PNFS attributes, and assumes that at most three
> + * layout types will be returned.
> + */
> +#define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + \
> +				 nfs4_fattr_bitmap_maxsz + 4 + 8 + 5)
>  #define encode_renew_maxsz	(op_encode_hdr_maxsz + 3)
>  #define decode_renew_maxsz	(op_decode_hdr_maxsz)
>  #define encode_setclientid_maxsz \
> @@ -1123,6 +1127,35 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm
>  	hdr->replen += decode_getattr_maxsz;
>  }
>  
> +static void
> +encode_getattr_three(struct xdr_stream *xdr,
> +		     uint32_t bm0, uint32_t bm1, uint32_t bm2,
> +		     struct compound_hdr *hdr)
> +{
> +	__be32 *p;
> +
> +	p = reserve_space(xdr, 4);
> +	*p = cpu_to_be32(OP_GETATTR);
> +	if (bm2) {
> +		p = reserve_space(xdr, 16);
> +		*p++ = cpu_to_be32(3);
> +		*p++ = cpu_to_be32(bm0);
> +		*p++ = cpu_to_be32(bm1);
> +		*p = cpu_to_be32(bm2);
> +	} else if (bm1) {
> +		p = reserve_space(xdr, 12);
> +		*p++ = cpu_to_be32(2);
> +		*p++ = cpu_to_be32(bm0);
> +		*p = cpu_to_be32(bm1);
> +	} else {
> +		p = reserve_space(xdr, 8);
> +		*p++ = cpu_to_be32(1);
> +		*p = cpu_to_be32(bm0);
> +	}
> +	hdr->nops++;
> +	hdr->replen += decode_getattr_maxsz;
> +}
> +
>  static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
>  {
>  	encode_getattr_two(xdr, bitmask[0] & nfs4_fattr_bitmap[0],
> @@ -1131,8 +1164,11 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c
>  
>  static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
>  {
> -	encode_getattr_two(xdr, bitmask[0] & nfs4_fsinfo_bitmap[0],
> -			   bitmask[1] & nfs4_fsinfo_bitmap[1], hdr);
> +	encode_getattr_three(xdr,
> +			     bitmask[0] & nfs4_fsinfo_bitmap[0],
> +			     bitmask[1] & nfs4_fsinfo_bitmap[1],
> +			     bitmask[2] & nfs4_fsinfo_bitmap[2],
> +			     hdr);
>  }
>  
>  static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
> @@ -2643,7 +2679,7 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
>  	struct compound_hdr hdr = {
>  		.nops	= 0,
>  	};
> -	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
> +	const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
>  
>  	encode_compound_hdr(xdr, req, &hdr);
>  	encode_setclientid_confirm(xdr, arg, &hdr);
> @@ -2787,7 +2823,7 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req,
>  	struct compound_hdr hdr = {
>  		.minorversion = nfs4_xdr_minorversion(&args->la_seq_args),
>  	};
> -	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
> +	const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
>  
>  	encode_compound_hdr(xdr, req, &hdr);
>  	encode_sequence(xdr, &args->la_seq_args, &hdr);
> @@ -3068,14 +3104,17 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
>  		goto out_overflow;
>  	bmlen = be32_to_cpup(p);
>  
> -	bitmap[0] = bitmap[1] = 0;
> +	bitmap[0] = bitmap[1] = bitmap[2] = 0;
>  	p = xdr_inline_decode(xdr, (bmlen << 2));
>  	if (unlikely(!p))
>  		goto out_overflow;
>  	if (bmlen > 0) {
>  		bitmap[0] = be32_to_cpup(p++);
> -		if (bmlen > 1)
> -			bitmap[1] = be32_to_cpup(p);
> +		if (bmlen > 1) {
> +			bitmap[1] = be32_to_cpup(p++);
> +			if (bmlen > 2)
> +				bitmap[2] = be32_to_cpup(p);
> +		}
>  	}
>  	return 0;
>  out_overflow:
> @@ -3107,8 +3146,9 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3
>  			return ret;
>  		bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS;
>  	} else
> -		bitmask[0] = bitmask[1] = 0;
> -	dprintk("%s: bitmask=%08x:%08x\n", __func__, bitmask[0], bitmask[1]);
> +		bitmask[0] = bitmask[1] = bitmask[2] = 0;
> +	dprintk("%s: bitmask=%08x:%08x:%08x\n", __func__,
> +		bitmask[0], bitmask[1], bitmask[2]);
>  	return 0;
>  }
>  
> @@ -4162,7 +4202,7 @@ out_overflow:
>  static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
>  {
>  	__be32 *savep;
> -	uint32_t attrlen, bitmap[2] = {0};
> +	uint32_t attrlen, bitmap[3] = {0};
>  	int status;
>  
>  	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
> @@ -4188,7 +4228,7 @@ xdr_error:
>  static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
>  {
>  	__be32 *savep;
> -	uint32_t attrlen, bitmap[2] = {0};
> +	uint32_t attrlen, bitmap[3] = {0};
>  	int status;
>  
>  	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
> @@ -4220,7 +4260,7 @@ xdr_error:
>  static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf)
>  {
>  	__be32 *savep;
> -	uint32_t attrlen, bitmap[2] = {0};
> +	uint32_t attrlen, bitmap[3] = {0};
>  	int status;
>  
>  	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
> @@ -4360,7 +4400,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
>  {
>  	__be32 *savep;
>  	uint32_t attrlen,
> -		 bitmap[2] = {0};
> +		 bitmap[3] = {0};
>  	int status;
>  
>  	status = decode_op_hdr(xdr, OP_GETATTR);
> @@ -4446,10 +4486,32 @@ static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap,
>  	return status;
>  }
>  
> +/*
> + * The prefered block size for layout directed io
> + */
> +static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
> +				      uint32_t *res)
> +{
> +	__be32 *p;
> +
> +	dprintk("%s: bitmap is %x\n", __func__, bitmap[2]);
> +	*res = 0;
> +	if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) {
> +		p = xdr_inline_decode(xdr, 4);
> +		if (unlikely(!p)) {
> +			print_overflow_msg(__func__, xdr);
> +			return -EIO;
> +		}
> +		*res = be32_to_cpup(p);
> +		bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE;
> +	}
> +	return 0;
> +}
> +
>  static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
>  {
>  	__be32 *savep;
> -	uint32_t attrlen, bitmap[2];
> +	uint32_t attrlen, bitmap[3];
>  	int status;
>  
>  	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
> @@ -4477,6 +4539,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
>  	status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype);
>  	if (status != 0)
>  		goto xdr_error;
> +	status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize);
> +	if (status)
> +		goto xdr_error;
>  
>  	status = verify_attr_len(xdr, savep, attrlen);
>  xdr_error:
> @@ -4896,7 +4961,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
>  {
>  	__be32 *savep;
>  	uint32_t attrlen,
> -		 bitmap[2] = {0};
> +		 bitmap[3] = {0};
>  	struct kvec *iov = req->rq_rcv_buf.head;
>  	int status;
>  
> @@ -6849,7 +6914,7 @@ out:
>  int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
>  		       int plus)
>  {
> -	uint32_t bitmap[2] = {0};
> +	uint32_t bitmap[3] = {0};
>  	uint32_t len;
>  	__be32 *p = xdr_inline_decode(xdr, 4);
>  	if (unlikely(!p))
> diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
> index 4faeac8..6e6ab4a 100644
> --- a/include/linux/nfs_fs_sb.h
> +++ b/include/linux/nfs_fs_sb.h
> @@ -132,7 +132,7 @@ struct nfs_server {
>  #endif
>  
>  #ifdef CONFIG_NFS_V4
> -	u32			attr_bitmask[2];/* V4 bitmask representing the set
> +	u32			attr_bitmask[3];/* V4 bitmask representing the set
>  						   of attributes supported on this
>  						   filesystem */
>  	u32			cache_consistency_bitmask[2];
> @@ -145,6 +145,8 @@ struct nfs_server {
>  						   filesystem */
>  	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
>  	struct rpc_wait_queue	roc_rpcwaitq;
> +	void			*pnfs_ld_data; /* per mount point data */

pnfs_ld_data seems to be used first only in [PATCH 13/25]
"pnfsblock: call and parse getdevicelist"

Benny

> +	u32			pnfs_blksize; /* layout_blksize attr */
>  
>  	/* the following fields are protected by nfs_client->cl_lock */
>  	struct rb_root		state_owners;
> diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
> index 21f333e..94f27e5 100644
> --- a/include/linux/nfs_xdr.h
> +++ b/include/linux/nfs_xdr.h
> @@ -122,6 +122,7 @@ struct nfs_fsinfo {
>  	struct timespec		time_delta; /* server time granularity */
>  	__u32			lease_time; /* in seconds */
>  	__u32			layouttype; /* supported pnfs layout driver */
> +	__u32			blksize; /* preferred pnfs io block size */
>  };
>  
>  struct nfs_fsstat {
> @@ -954,7 +955,7 @@ struct nfs4_server_caps_arg {
>  };
>  
>  struct nfs4_server_caps_res {
> -	u32				attr_bitmask[2];
> +	u32				attr_bitmask[3];
>  	u32				acl_bitmask;
>  	u32				has_links;
>  	u32				has_symlinks;

  reply index

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-07-21 19:34 [PATCH v2 00/25] add block layout driver to pnfs client Jim Rees
2011-07-21 19:34 ` [PATCH v2 01/25] pnfs: GETDEVICELIST Jim Rees
2011-07-21 19:34 ` [PATCH v2 02/25] pnfs: add set-clear layoutdriver interface Jim Rees
2011-07-21 19:34 ` [PATCH v2 03/25] NFS41: Let layoutcommit handle multiple segments Jim Rees
2011-07-21 19:34 ` [PATCH v2 04/25] NFS41: save layoutcommit cred after first successful layoutget Jim Rees
2011-07-21 19:34 ` [PATCH v2 05/25] pnfs: ask for layout_blksize and save it in nfs_server Jim Rees
2011-07-25 14:24   ` Benny Halevy [this message]
2011-07-21 19:34 ` [PATCH v2 06/25] pnfs: cleanup_layoutcommit Jim Rees
2011-07-25 14:26   ` Benny Halevy
2011-07-21 19:34 ` [PATCH v2 07/25] pnfsblock: add blocklayout Kconfig option, Makefile, and stubs Jim Rees
2011-07-25 14:30   ` Benny Halevy
2011-07-25 14:38     ` Myklebust, Trond
2011-07-25 14:50       ` Benny Halevy
2011-07-25 17:25         ` Myklebust, Trond
2011-07-25 18:26           ` Benny Halevy
2011-07-26 17:18             ` Peng Tao
2011-07-21 19:34 ` [PATCH v2 08/25] pnfsblock: basic extent code Jim Rees
2011-07-21 19:34 ` [PATCH v2 09/25] pnfsblock: add device operations Jim Rees
2011-07-21 19:34 ` [PATCH v2 10/25] pnfsblock: remove " Jim Rees
2011-07-21 19:34 ` [PATCH v2 11/25] pnfsblock: lseg alloc and free Jim Rees
2011-07-25 14:43   ` Benny Halevy
2011-07-21 19:34 ` [PATCH v2 12/25] pnfsblock: merge extents Jim Rees
2011-07-21 19:34 ` [PATCH v2 13/25] pnfsblock: call and parse getdevicelist Jim Rees
2011-07-21 19:34 ` [PATCH v2 14/25] pnfsblock: xdr decode pnfs_block_layout4 Jim Rees
2011-07-21 19:34 ` [PATCH v2 15/25] pnfsblock: bl_find_get_extent Jim Rees
2011-07-21 19:34 ` [PATCH v2 16/25] pnfsblock: add extent manipulation functions Jim Rees
2011-07-21 19:34 ` [PATCH v2 17/25] pnfsblock: merge rw extents Jim Rees
2011-07-21 19:34 ` [PATCH v2 18/25] pnfsblock: encode_layoutcommit Jim Rees
2011-07-21 19:34 ` [PATCH v2 19/25] pnfsblock: cleanup_layoutcommit Jim Rees
2011-07-21 19:34 ` [PATCH v2 20/25] pnfsblock: bl_read_pagelist Jim Rees
2011-07-21 19:34 ` [PATCH v2 21/25] pnfsblock: bl_write_pagelist Jim Rees
2011-07-21 19:34 ` [PATCH v2 22/25] pnfsblock: note written INVAL areas for layoutcommit Jim Rees
2011-07-21 19:34 ` [PATCH v2 23/25] pnfsblock: use pageio_ops api Jim Rees
2011-07-21 19:34 ` [PATCH v2 24/25] pnfsblock: write_pagelist handle zero invalid extents Jim Rees
2011-07-21 19:34 ` [PATCH v2 25/25] NFS41: Drop lseg ref before fallthru to MDS Jim Rees

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=4E2D7C97.8070902@tonian.com \
    --to=bhalevy@tonian.com \
    --cc=Trond.Myklebust@netapp.com \
    --cc=honey@citi.umich.edu \
    --cc=linux-nfs@vger.kernel.org \
    --cc=rees@umich.edu \
    /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

Linux-NFS Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nfs/0 linux-nfs/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nfs linux-nfs/ https://lore.kernel.org/linux-nfs \
		linux-nfs@vger.kernel.org
	public-inbox-index linux-nfs

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-nfs


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git