smb3: add rasize mount parameter to improve readahead performance

In some cases readahead of more than the read size can help
(to allow parallel i/o of read ahead which can improve performance).

Ceph introduced a mount parameter "rasize" to allow controlling this.
Add mount parameter "rasize" to allow control of amount of readahead
requested of the server. If rasize not set, rasize defaults to
negotiated rsize as before.

Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>

Author: smfrench

fs/cifs/cifsfs.c

@@ -217,8 +217,11 @@ cifs_read_super(struct super_block *sb)
 	rc = super_setup_bdi(sb);
 	if (rc)
 		goto out_no_root;
-	/* tune readahead according to rsize */
-	sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE;
+	/* tune readahead according to rsize if readahead size not set on mount */
+	if (cifs_sb->ctx->rasize)
+		sb->s_bdi->ra_pages = cifs_sb->ctx->rasize / PAGE_SIZE;
+	else
+		sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE;
 
 	sb->s_blocksize = CIFS_MAX_MSGSIZE;
 	sb->s_blocksize_bits = 14;	/* default 2**14 = CIFS_MAX_MSGSIZE */
@@ -649,6 +652,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize);
 	seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize);
 	seq_printf(s, ",bsize=%u", cifs_sb->ctx->bsize);
+	if (cifs_sb->ctx->rasize)
+		seq_printf(s, ",rasize=%u", cifs_sb->ctx->rasize);
 	if (tcon->ses->server->min_offload)
 		seq_printf(s, ",esize=%u", tcon->ses->server->min_offload);
 	seq_printf(s, ",echo_interval=%lu",

fs/cifs/fs_context.c

@@ -137,6 +137,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
 	fsparam_u32("min_enc_offload", Opt_min_enc_offload),
 	fsparam_u32("esize", Opt_min_enc_offload),
 	fsparam_u32("bsize", Opt_blocksize),
+	fsparam_u32("rasize", Opt_rasize),
 	fsparam_u32("rsize", Opt_rsize),
 	fsparam_u32("wsize", Opt_wsize),
 	fsparam_u32("actimeo", Opt_actimeo),
@@ -941,6 +942,26 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		ctx->bsize = result.uint_32;
 		ctx->got_bsize = true;
 		break;
+	case Opt_rasize:
+		/*
+		 * readahead size realistically should never need to be
+		 * less than 1M (CIFS_DEFAULT_IOSIZE) or greater than 32M
+		 * (perhaps an exception should be considered in the
+		 * for the case of a large number of channels
+		 * when multichannel is negotiated) since that would lead
+		 * to plenty of parallel I/O in flight to the server.
+		 * Note that smaller read ahead sizes would
+		 * hurt performance of common tools like cp and scp
+		 * which often trigger sequential i/o with read ahead
+		 */
+		if ((result.uint_32 > (8 * SMB3_DEFAULT_IOSIZE)) ||
+		    (result.uint_32 < CIFS_DEFAULT_IOSIZE)) {
+			cifs_errorf(fc, "%s: Invalid rasize %d vs. %d\n",
+				__func__, result.uint_32, SMB3_DEFAULT_IOSIZE);
+			goto cifs_parse_mount_err;
+		}
+		ctx->rasize = result.uint_32;
+		break;
 	case Opt_rsize:
 		ctx->rsize = result.uint_32;
 		ctx->got_rsize = true;
@@ -1377,7 +1398,9 @@ int smb3_init_fs_context(struct fs_context *fc)
 	ctx->cred_uid = current_uid();
 	ctx->linux_uid = current_uid();
 	ctx->linux_gid = current_gid();
-	ctx->bsize = 1024 * 1024; /* can improve cp performance significantly */
+	/* By default 4MB read ahead size, 1MB block size */
+	ctx->bsize = CIFS_DEFAULT_IOSIZE; /* can improve cp performance significantly */
+	ctx->rasize = 0; /* 0 = use default (ie negotiated rsize) for read ahead pages */
 
 	/*
 	 * default to SFM style remapping of seven reserved characters

fs/cifs/fs_context.h

@@ -120,6 +120,7 @@ enum cifs_param {
 	Opt_dirmode,
 	Opt_min_enc_offload,
 	Opt_blocksize,
+	Opt_rasize,
 	Opt_rsize,
 	Opt_wsize,
 	Opt_actimeo,
@@ -235,6 +236,7 @@ struct smb3_fs_context {
 	/* reuse existing guid for multichannel */
 	u8 client_guid[SMB2_CLIENT_GUID_SIZE];
 	unsigned int bsize;
+	unsigned int rasize;
 	unsigned int rsize;
 	unsigned int wsize;
 	unsigned int min_offload;