| Message ID | 1464152979-103988-4-git-send-email-loghyr@primarydata.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Tue, 2016-05-24 at 22:09 -0700, Tom Haynes wrote: > Have a simple flex file server where the mds (NFSv4.1 or NFSv4.2) > is also the ds (NFSv3). I.e., the metadata and the data file are > the exact same file. > > This will allow testing of the flex file client. > > Simply add the "pnfs" export option to your export > in /etc/exports and mount from a client that supports > flex files. > > Signed-off-by: Tom Haynes <loghyr@primarydata.com> > --- > fs/nfsd/Makefile | 1 + > fs/nfsd/flexfilelayout.c | 148 ++++++++++++++++++++++++++++++++++++++++++++ > fs/nfsd/flexfilelayoutxdr.c | 116 ++++++++++++++++++++++++++++++++++ > fs/nfsd/flexfilelayoutxdr.h | 50 +++++++++++++++ > fs/nfsd/nfs4layouts.c | 10 +++ > fs/nfsd/pnfs.h | 3 + > 6 files changed, 328 insertions(+) > create mode 100644 fs/nfsd/flexfilelayout.c > create mode 100644 fs/nfsd/flexfilelayoutxdr.c > create mode 100644 fs/nfsd/flexfilelayoutxdr.h > > diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile > index 3ae5f3c..5f5d3a7 100644 > --- a/fs/nfsd/Makefile > +++ b/fs/nfsd/Makefile > @@ -20,3 +20,4 @@ nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ > nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o > nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o > nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o > +nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o > diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c > new file mode 100644 > index 0000000..d28b8a0 > --- /dev/null > +++ b/fs/nfsd/flexfilelayout.c > @@ -0,0 +1,148 @@ > +/* > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> > + * > + * The following implements a super-simple flex-file server > + * where the NFSv4.1 mds is also the ds. And the storage is > + * the same. I.e., writing to the mds via a NFSv4.1 WRITE > + * goes to the same location as the NFSv3 WRITE. > + */ > +#include > +#include > +#include > +#include > + > +#include > + > +#include > + > +#include "flexfilelayoutxdr.h" > +#include "pnfs.h" > + > +#define NFSDDBG_FACILITY NFSDDBG_PNFS > + > +static __be32 > +nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, > + struct nfsd4_layoutget *args) > +{ > + struct nfsd4_layout_seg *seg = &args->lg_seg; > + u32 block_size = (1 << inode->i_blkbits); > + u32 device_generation = 0; > + int error; > + > + struct pnfs_ff_layout *fl; > + > + if (seg->offset & (block_size - 1)) { > + dprintk("pnfsd: I/O misaligned\n"); > + goto out_layoutunavailable; > + } > + > + /* > + * The super simple flex file server has 1 mirror, 1 data server, > + * and 1 file handle. So instead of 4 allocs, do 1 for now. > + * Zero it out for the stateid - don't want junk in there! > + */ > + error = -ENOMEM; > + fl = kzalloc(sizeof(*fl), GFP_KERNEL); > + if (!fl) > + goto out_error; > + args->lg_content = fl; > + > + /* > + * Avoid layout commit, try to force the I/O to the DS, > + * and for fun, cause all IOMODE_RW layout segments to > + * effectively be WRITE only. > + */ > + fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS | > + FF_FLAGS_NO_READ_IO; > + > + fl->uid = inode->i_uid; > + fl->gid = inode->i_gid; > + > + error = nfsd4_set_deviceid(&fl->deviceid, fhp, device_generation); > + if (error) > + goto out_error; > + > + fl->fh.size = fhp->fh_handle.fh_size; > + memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size); > + > + /* Give whole file layout segments */ > + seg->offset = 0; > + seg->length = NFS4_MAX_UINT64; > + > + dprintk("GET: 0x%llx:0x%llx %d\n", seg->offset, seg->length, > + seg->iomode); > + return 0; > + > +out_error: > + kfree(fl); > + seg->length = 0; > + return nfserrno(error); > +out_layoutunavailable: > + seg->length = 0; > + return nfserr_layoutunavailable; > +} > + > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > +static __be32 > +nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, > + struct svc_rqst *rqstp, > + struct nfs4_client *clp, > + struct nfsd4_getdeviceinfo *gdp) > +{ > + struct pnfs_ff_device_addr *da; > + > + u16 port; > + char addr[INET6_ADDRSTRLEN]; > + > + if (sb->s_bdev != sb->s_bdev->bd_contains) > + return nfserr_inval; > + > + da = kzalloc(sizeof(struct pnfs_ff_device_addr), GFP_KERNEL); > + if (!da) > + return nfserrno(-ENOMEM); > + > + gdp->gd_device = da; > + > + da->version = 3; > + da->minor_version = 0; > + > + /* FIXME: Get from export? */ > + da->rsize = 4096; > + da->wsize = 4096; > + nfsd3_proc_fsinfo fills out its rsize/wsize with svc_max_payload(rqstp). I'd suggest doing the same here. > + rpc_ntop((struct sockaddr *)&rqstp->rq_daddr, > + addr, INET6_ADDRSTRLEN); > + if (rqstp->rq_daddr.ss_family == AF_INET) { > + struct sockaddr_in *sin; > + > + sin = (struct sockaddr_in *)&rqstp->rq_daddr; > + port = ntohs(sin->sin_port); > + snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp"); > + da->netaddr.netid_len = 3; > + } else { > + struct sockaddr_in6 *sin6; > + > + sin6 = (struct sockaddr_in6 *)&rqstp->rq_daddr; > + port = ntohs(sin6->sin6_port); > + snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp6"); > + da->netaddr.netid_len = 4; > + } > + > + da->netaddr.addr_len = > + snprintf(da->netaddr.addr, FF_ADDR_LEN + 1, > + "%s.%hhu.%hhu", addr, port >> 8, port & 0xff); > + > + da->tightly_coupled = false; > + > + return 0; > +} > + > +const struct nfsd4_layout_ops ff_layout_ops = { > + .notify_types = > + NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE, > + .proc_getdeviceinfo = nfsd4_ff_proc_getdeviceinfo, > + .encode_getdeviceinfo = nfsd4_ff_encode_getdeviceinfo, > + .proc_layoutget = nfsd4_ff_proc_layoutget, > + .encode_layoutget = nfsd4_ff_encode_layoutget, > +}; > +#endif /* CONFIG_NFSD_FLEXFILELAYOUT */ > diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c > new file mode 100644 > index 0000000..9d15ee0 > --- /dev/null > +++ b/fs/nfsd/flexfilelayoutxdr.c > @@ -0,0 +1,116 @@ > +/* > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> > + */ > +#include > +#include > +#include > + > +#include "nfsd.h" > +#include "flexfilelayoutxdr.h" > + > +#define NFSDDBG_FACILITY NFSDDBG_PNFS > + > +struct ff_idmap { > + char buf[11]; > + int len; > +}; > + > +__be32 > +nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, > + struct nfsd4_layoutget *lgp) > +{ > + struct pnfs_ff_layout *fl = lgp->lg_content; > + int len, mirror_len, ds_len, fh_len; > + __be32 *p; > + > + /* > + * Unlike nfsd4_encode_user, we know these will > + * always be stringified. > + */ > + struct ff_idmap uid; > + struct ff_idmap gid; > + > + fh_len = 4 + fl->fh.size; > + > + uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid)); > + gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid)); > + > + /* 8 + len for recording the length, name, and padding */ > + ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len + > + 8 + uid.len + 8 + gid.len; > + > + mirror_len = 4 + ds_len; > + > + /* The layout segment */ > + len = 20 + mirror_len; > + > + p = xdr_reserve_space(xdr, sizeof(__be32) + len); > + if (!p) > + return nfserr_toosmall; > + > + *p++ = cpu_to_be32(len); > + p = xdr_encode_hyper(p, 1); /* stripe unit of 1 */ > + > + *p++ = cpu_to_be32(1); /* single mirror */ > + *p++ = cpu_to_be32(1); /* single data server */ > + > + p = xdr_encode_opaque_fixed(p, &fl->deviceid, > + sizeof(struct nfsd4_deviceid)); > + > + *p++ = cpu_to_be32(1); /* efficiency */ > + > + *p++ = cpu_to_be32(fl->stateid.si_generation); > + p = xdr_encode_opaque_fixed(p, &fl->stateid.si_opaque, > + sizeof(stateid_opaque_t)); > + > + *p++ = cpu_to_be32(1); /* single file handle */ > + p = xdr_encode_opaque(p, fl->fh.data, fl->fh.size); > + > + p = xdr_encode_opaque(p, uid.buf, uid.len); > + p = xdr_encode_opaque(p, gid.buf, gid.len); > + > + *p++ = cpu_to_be32(fl->flags); > + *p++ = cpu_to_be32(0); /* No stats collect hint */ > + > + return 0; > +} > + > +__be32 > +nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, > + struct nfsd4_getdeviceinfo *gdp) > +{ > + struct pnfs_ff_device_addr *da = gdp->gd_device; > + int len; > + int ver_len; > + int addr_len; > + __be32 *p; > + > + /* len + padding for two strings */ > + addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; > + ver_len = 20; > + > + len = 4 + ver_len + 4 + addr_len; > + > + p = xdr_reserve_space(xdr, len + sizeof(__be32)); > + if (!p) > + return nfserr_resource; > + > + /* > + * Fill in the overall length and number of volumes at the beginning > + * of the layout. > + */ > + *p++ = cpu_to_be32(len); > + *p++ = cpu_to_be32(1); /* 1 netaddr */ > + p = xdr_encode_opaque(p, da->netaddr.netid, da->netaddr.netid_len); > + p = xdr_encode_opaque(p, da->netaddr.addr, da->netaddr.addr_len); > + > + *p++ = cpu_to_be32(1); /* 1 versions */ > + > + *p++ = cpu_to_be32(da->version); > + *p++ = cpu_to_be32(da->minor_version); > + *p++ = cpu_to_be32(da->rsize); > + *p++ = cpu_to_be32(da->wsize); > + *p++ = cpu_to_be32(da->tightly_coupled); > + > + return 0; > +} > diff --git a/fs/nfsd/flexfilelayoutxdr.h b/fs/nfsd/flexfilelayoutxdr.h > new file mode 100644 > index 0000000..40e6d1b > --- /dev/null > +++ b/fs/nfsd/flexfilelayoutxdr.h > @@ -0,0 +1,50 @@ > +/* > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> > + */ > +#ifndef _NFSD_FLEXFILELAYOUTXDR_H > +#define _NFSD_FLEXFILELAYOUTXDR_H 1 > + > +#include > +#include "xdr4.h" > + > +#define FF_FLAGS_NO_LAYOUTCOMMIT 1 > +#define FF_FLAGS_NO_IO_THRU_MDS 2 > +#define FF_FLAGS_NO_READ_IO 4 > + > +struct iomap; > +struct xdr_stream; > + > +#define FF_NETID_LEN (4) > +#define FF_ADDR_LEN (INET6_ADDRSTRLEN + 1) > +struct pnfs_ff_netaddr { > + char netid[FF_NETID_LEN + 1]; > + char addr[FF_ADDR_LEN + 1]; > + u32 netid_len; > + u32 addr_len; > +}; > + > +struct pnfs_ff_device_addr { > + struct pnfs_ff_netaddr netaddr; > + u32 version; > + u32 minor_version; > + u32 rsize; > + u32 wsize; > + bool tightly_coupled; > +}; > + > +struct pnfs_ff_layout { > + u32 flags; > + u32 stats_collect_hint; > + kuid_t uid; > + kgid_t gid; > + struct nfsd4_deviceid deviceid; > + stateid_t stateid; > + struct nfs_fh fh; > +}; > + > +__be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, > + struct nfsd4_getdeviceinfo *gdp); > +__be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, > + struct nfsd4_layoutget *lgp); > + > +#endif /* _NFSD_FLEXFILELAYOUTXDR_H */ > diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c > index 825c7bc..7cbd56a 100644 > --- a/fs/nfsd/nfs4layouts.c > +++ b/fs/nfsd/nfs4layouts.c > @@ -27,6 +27,9 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops; > static const struct lock_manager_operations nfsd4_layouts_lm_ops; > > const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > + [LAYOUT_FLEX_FILES] = &ff_layout_ops, > +#endif > #ifdef CONFIG_NFSD_BLOCKLAYOUT > [LAYOUT_BLOCK_VOLUME] = &bl_layout_ops, > #endif > @@ -122,7 +125,9 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, > > void nfsd4_setup_layout_type(struct svc_export *exp) > { > +#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT) > struct super_block *sb = exp->ex_path.mnt->mnt_sb; > +#endif > > if (!(exp->ex_flags & NFSEXP_PNFS)) > return; > @@ -145,6 +150,11 @@ void nfsd4_setup_layout_type(struct svc_export *exp) > sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops) > exp->ex_layout_type = LAYOUT_SCSI; > #endif > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > + // FIXME: How do we "export" this and how does it mingle with > + // the above types? > + exp->ex_layout_type = LAYOUT_FLEX_FILES; > +#endif > } > > static void > diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h > index e855677..0c2a716 100644 > --- a/fs/nfsd/pnfs.h > +++ b/fs/nfsd/pnfs.h > @@ -45,6 +45,9 @@ extern const struct nfsd4_layout_ops bl_layout_ops; > #ifdef CONFIG_NFSD_SCSILAYOUT > extern const struct nfsd4_layout_ops scsi_layout_ops; > #endif > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > +extern const struct nfsd4_layout_ops ff_layout_ops; > +#endif > > __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, > struct nfsd4_compound_state *cstate, stateid_t *stateid,
On Tue, 2016-05-24 at 22:09 -0700, Tom Haynes wrote: > Have a simple flex file server where the mds (NFSv4.1 or NFSv4.2) > is also the ds (NFSv3). I.e., the metadata and the data file are > the exact same file. > > This will allow testing of the flex file client. > > Simply add the "pnfs" export option to your export > in /etc/exports and mount from a client that supports > flex files. > > Signed-off-by: Tom Haynes <loghyr@primarydata.com> > --- > fs/nfsd/Makefile | 1 + > fs/nfsd/flexfilelayout.c | 148 ++++++++++++++++++++++++++++++++++++++++++++ > fs/nfsd/flexfilelayoutxdr.c | 116 ++++++++++++++++++++++++++++++++++ > fs/nfsd/flexfilelayoutxdr.h | 50 +++++++++++++++ > fs/nfsd/nfs4layouts.c | 10 +++ > fs/nfsd/pnfs.h | 3 + > 6 files changed, 328 insertions(+) > create mode 100644 fs/nfsd/flexfilelayout.c > create mode 100644 fs/nfsd/flexfilelayoutxdr.c > create mode 100644 fs/nfsd/flexfilelayoutxdr.h > > diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile > index 3ae5f3c..5f5d3a7 100644 > --- a/fs/nfsd/Makefile > +++ b/fs/nfsd/Makefile > @@ -20,3 +20,4 @@ nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ > nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o > nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o > nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o > +nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o > diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c > new file mode 100644 > index 0000000..d28b8a0 > --- /dev/null > +++ b/fs/nfsd/flexfilelayout.c > @@ -0,0 +1,148 @@ > +/* > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> > + * > + * The following implements a super-simple flex-file server > + * where the NFSv4.1 mds is also the ds. And the storage is > + * the same. I.e., writing to the mds via a NFSv4.1 WRITE > + * goes to the same location as the NFSv3 WRITE. > + */ > +#include > +#include > +#include > +#include > + > +#include > + > +#include > + > +#include "flexfilelayoutxdr.h" > +#include "pnfs.h" > + > +#define NFSDDBG_FACILITY NFSDDBG_PNFS > + > +static __be32 > +nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, > + struct nfsd4_layoutget *args) > +{ > + struct nfsd4_layout_seg *seg = &args->lg_seg; > + u32 block_size = (1 << inode->i_blkbits); > + u32 device_generation = 0; > + int error; > + > + struct pnfs_ff_layout *fl; > + > + if (seg->offset & (block_size - 1)) { > + dprintk("pnfsd: I/O misaligned\n"); > + goto out_layoutunavailable; > + } > + > + /* > + * The super simple flex file server has 1 mirror, 1 data server, > + * and 1 file handle. So instead of 4 allocs, do 1 for now. > + * Zero it out for the stateid - don't want junk in there! > + */ > + error = -ENOMEM; > + fl = kzalloc(sizeof(*fl), GFP_KERNEL); > + if (!fl) > + goto out_error; > + args->lg_content = fl; > + > + /* > + * Avoid layout commit, try to force the I/O to the DS, > + * and for fun, cause all IOMODE_RW layout segments to > + * effectively be WRITE only. > + */ > + fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS | > + FF_FLAGS_NO_READ_IO; > + > + fl->uid = inode->i_uid; > + fl->gid = inode->i_gid; > + > + error = nfsd4_set_deviceid(&fl->deviceid, fhp, device_generation); > + if (error) > + goto out_error; > + > + fl->fh.size = fhp->fh_handle.fh_size; > + memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size); > + > + /* Give whole file layout segments */ > + seg->offset = 0; > + seg->length = NFS4_MAX_UINT64; > + > + dprintk("GET: 0x%llx:0x%llx %d\n", seg->offset, seg->length, > + seg->iomode); > + return 0; > + > +out_error: > + kfree(fl); > + seg->length = 0; > + return nfserrno(error); > +out_layoutunavailable: > + seg->length = 0; > + return nfserr_layoutunavailable; > +} > + > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > +static __be32 > +nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, > + struct svc_rqst *rqstp, > + struct nfs4_client *clp, > + struct nfsd4_getdeviceinfo *gdp) > +{ > + struct pnfs_ff_device_addr *da; > + > + u16 port; > + char addr[INET6_ADDRSTRLEN]; > + > + if (sb->s_bdev != sb->s_bdev->bd_contains) > + return nfserr_inval; > + > + da = kzalloc(sizeof(struct pnfs_ff_device_addr), GFP_KERNEL); > + if (!da) > + return nfserrno(-ENOMEM); > + > + gdp->gd_device = da; > + > + da->version = 3; > + da->minor_version = 0; > + > + /* FIXME: Get from export? */ > + da->rsize = 4096; > + da->wsize = 4096; > + > + rpc_ntop((struct sockaddr *)&rqstp->rq_daddr, > + addr, INET6_ADDRSTRLEN); > + if (rqstp->rq_daddr.ss_family == AF_INET) { > + struct sockaddr_in *sin; > + > + sin = (struct sockaddr_in *)&rqstp->rq_daddr; > + port = ntohs(sin->sin_port); > + snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp"); > + da->netaddr.netid_len = 3; > + } else { > + struct sockaddr_in6 *sin6; > + > + sin6 = (struct sockaddr_in6 *)&rqstp->rq_daddr; > + port = ntohs(sin6->sin6_port); > + snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp6"); > + da->netaddr.netid_len = 4; > + } > + > + da->netaddr.addr_len = > + snprintf(da->netaddr.addr, FF_ADDR_LEN + 1, > + "%s.%hhu.%hhu", addr, port >> 8, port & 0xff); > + > + da->tightly_coupled = false; > + > + return 0; > +} > + > +const struct nfsd4_layout_ops ff_layout_ops = { > + .notify_types = > + NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE, > + .proc_getdeviceinfo = nfsd4_ff_proc_getdeviceinfo, > + .encode_getdeviceinfo = nfsd4_ff_encode_getdeviceinfo, > + .proc_layoutget = nfsd4_ff_proc_layoutget, > + .encode_layoutget = nfsd4_ff_encode_layoutget, > +}; > +#endif /* CONFIG_NFSD_FLEXFILELAYOUT */ > diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c > new file mode 100644 > index 0000000..9d15ee0 > --- /dev/null > +++ b/fs/nfsd/flexfilelayoutxdr.c > @@ -0,0 +1,116 @@ > +/* > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> > + */ > +#include > +#include > +#include > + > +#include "nfsd.h" > +#include "flexfilelayoutxdr.h" > + > +#define NFSDDBG_FACILITY NFSDDBG_PNFS > + > +struct ff_idmap { > + char buf[11]; > + int len; > +}; > + > +__be32 > +nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, > + struct nfsd4_layoutget *lgp) > +{ > + struct pnfs_ff_layout *fl = lgp->lg_content; > + int len, mirror_len, ds_len, fh_len; > + __be32 *p; > + > + /* > + * Unlike nfsd4_encode_user, we know these will > + * always be stringified. > + */ > + struct ff_idmap uid; > + struct ff_idmap gid; > + > + fh_len = 4 + fl->fh.size; > + > + uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid)); > + gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid)); > + > + /* 8 + len for recording the length, name, and padding */ > + ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len + > + 8 + uid.len + 8 + gid.len; > + > + mirror_len = 4 + ds_len; > + > + /* The layout segment */ > + len = 20 + mirror_len; > + > + p = xdr_reserve_space(xdr, sizeof(__be32) + len); > + if (!p) > + return nfserr_toosmall; > + > + *p++ = cpu_to_be32(len); > + p = xdr_encode_hyper(p, 1); /* stripe unit of 1 */ > + > + *p++ = cpu_to_be32(1); /* single mirror */ > + *p++ = cpu_to_be32(1); /* single data server */ > + > + p = xdr_encode_opaque_fixed(p, &fl->deviceid, > + sizeof(struct nfsd4_deviceid)); > + > + *p++ = cpu_to_be32(1); /* efficiency */ > + > + *p++ = cpu_to_be32(fl->stateid.si_generation); > + p = xdr_encode_opaque_fixed(p, &fl->stateid.si_opaque, > + sizeof(stateid_opaque_t)); > + > + *p++ = cpu_to_be32(1); /* single file handle */ > + p = xdr_encode_opaque(p, fl->fh.data, fl->fh.size); > + > + p = xdr_encode_opaque(p, uid.buf, uid.len); > + p = xdr_encode_opaque(p, gid.buf, gid.len); > + > + *p++ = cpu_to_be32(fl->flags); > + *p++ = cpu_to_be32(0); /* No stats collect hint */ > + > + return 0; > +} > + > +__be32 > +nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, > + struct nfsd4_getdeviceinfo *gdp) > +{ > + struct pnfs_ff_device_addr *da = gdp->gd_device; > + int len; > + int ver_len; > + int addr_len; > + __be32 *p; > + > + /* len + padding for two strings */ > + addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; > + ver_len = 20; > + > + len = 4 + ver_len + 4 + addr_len; > + > + p = xdr_reserve_space(xdr, len + sizeof(__be32)); > + if (!p) > + return nfserr_resource; > + > + /* > + * Fill in the overall length and number of volumes at the beginning > + * of the layout. > + */ > + *p++ = cpu_to_be32(len); > + *p++ = cpu_to_be32(1); /* 1 netaddr */ > + p = xdr_encode_opaque(p, da->netaddr.netid, da->netaddr.netid_len); > + p = xdr_encode_opaque(p, da->netaddr.addr, da->netaddr.addr_len); > + > + *p++ = cpu_to_be32(1); /* 1 versions */ > + > + *p++ = cpu_to_be32(da->version); > + *p++ = cpu_to_be32(da->minor_version); > + *p++ = cpu_to_be32(da->rsize); > + *p++ = cpu_to_be32(da->wsize); > + *p++ = cpu_to_be32(da->tightly_coupled); > + > + return 0; > +} > diff --git a/fs/nfsd/flexfilelayoutxdr.h b/fs/nfsd/flexfilelayoutxdr.h > new file mode 100644 > index 0000000..40e6d1b > --- /dev/null > +++ b/fs/nfsd/flexfilelayoutxdr.h > @@ -0,0 +1,50 @@ > +/* > + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> > + */ > +#ifndef _NFSD_FLEXFILELAYOUTXDR_H > +#define _NFSD_FLEXFILELAYOUTXDR_H 1 > + > +#include > +#include "xdr4.h" > + > +#define FF_FLAGS_NO_LAYOUTCOMMIT 1 > +#define FF_FLAGS_NO_IO_THRU_MDS 2 > +#define FF_FLAGS_NO_READ_IO 4 > + > +struct iomap; > +struct xdr_stream; > + > +#define FF_NETID_LEN (4) > +#define FF_ADDR_LEN (INET6_ADDRSTRLEN + 1) > +struct pnfs_ff_netaddr { > + char netid[FF_NETID_LEN + 1]; > + char addr[FF_ADDR_LEN + 1]; > + u32 netid_len; > + u32 addr_len; > +}; > + > +struct pnfs_ff_device_addr { > + struct pnfs_ff_netaddr netaddr; > + u32 version; > + u32 minor_version; > + u32 rsize; > + u32 wsize; > + bool tightly_coupled; > +}; > + > +struct pnfs_ff_layout { > + u32 flags; > + u32 stats_collect_hint; > + kuid_t uid; > + kgid_t gid; > + struct nfsd4_deviceid deviceid; > + stateid_t stateid; > + struct nfs_fh fh; > +}; > + > +__be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, > + struct nfsd4_getdeviceinfo *gdp); > +__be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, > + struct nfsd4_layoutget *lgp); > + > +#endif /* _NFSD_FLEXFILELAYOUTXDR_H */ > diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c > index 825c7bc..7cbd56a 100644 > --- a/fs/nfsd/nfs4layouts.c > +++ b/fs/nfsd/nfs4layouts.c > @@ -27,6 +27,9 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops; > static const struct lock_manager_operations nfsd4_layouts_lm_ops; > > const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > + [LAYOUT_FLEX_FILES] = &ff_layout_ops, > +#endif > #ifdef CONFIG_NFSD_BLOCKLAYOUT > [LAYOUT_BLOCK_VOLUME] = &bl_layout_ops, > #endif > @@ -122,7 +125,9 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, > > void nfsd4_setup_layout_type(struct svc_export *exp) > { > +#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT) > struct super_block *sb = exp->ex_path.mnt->mnt_sb; > +#endif > > if (!(exp->ex_flags & NFSEXP_PNFS)) > return; > @@ -145,6 +150,11 @@ void nfsd4_setup_layout_type(struct svc_export *exp) > sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops) > exp->ex_layout_type = LAYOUT_SCSI; > #endif > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > + // FIXME: How do we "export" this and how does it mingle with > + // the above types? > + exp->ex_layout_type = LAYOUT_FLEX_FILES; > +#endif > } > Maybe it's time to start thinking about how to support multiple layout types per export? It doesn't look like it would be that hard. I think we could convert ex_layout_type into a bitmap that shows which types are supported. The harder work looks to be on the client. You'd need some heuristic to choose when you get back multiple layout types and fix that to work properly. > static void > diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h > index e855677..0c2a716 100644 > --- a/fs/nfsd/pnfs.h > +++ b/fs/nfsd/pnfs.h > @@ -45,6 +45,9 @@ extern const struct nfsd4_layout_ops bl_layout_ops; > #ifdef CONFIG_NFSD_SCSILAYOUT > extern const struct nfsd4_layout_ops scsi_layout_ops; > #endif > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > +extern const struct nfsd4_layout_ops ff_layout_ops; > +#endif > > __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, > struct nfsd4_compound_state *cstate, stateid_t *stateid,
> On May 25, 2016, at 5:30 AM, Jeff Layton <jlayton@poochiereds.net> wrote: > > On Tue, 2016-05-24 at 22:09 -0700, Tom Haynes wrote: >> >> void nfsd4_setup_layout_type(struct svc_export *exp) >> { >> +#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT) >> struct super_block *sb = exp->ex_path.mnt->mnt_sb; >> +#endif >> >> if (!(exp->ex_flags & NFSEXP_PNFS)) >> return; >> @@ -145,6 +150,11 @@ void nfsd4_setup_layout_type(struct svc_export *exp) >> sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops) >> exp->ex_layout_type = LAYOUT_SCSI; >> #endif >> +#ifdef CONFIG_NFSD_FLEXFILELAYOUT >> + // FIXME: How do we "export" this and how does it mingle with >> + // the above types? >> + exp->ex_layout_type = LAYOUT_FLEX_FILES; >> +#endif >> } >> > > Maybe it's time to start thinking about how to support multiple layout types per export? It doesn't look like it would be that hard. I think we could convert ex_layout_type into a bitmap that shows which types are supported. > > The harder work looks to be on the client. You'd need some heuristic to choose when you get back multiple layout types and fix that to work properly. In thinking about it, if we rearrange the code to be: void nfsd4_setup_layout_type(struct svc_export *exp) { #if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT) struct super_block *sb = exp->ex_path.mnt->mnt_sb; #endif if (!(exp->ex_flags & NFSEXP_PNFS)) return; /* * If flex file is configured, use it by default. Otherwise * check if the file system supports exporting a block-like layout. * If the block device supports reservations prefer the SCSI layout, * otherwise advertise the block layout. */ #ifdef CONFIG_NFSD_FLEXFILELAYOUT // FIXME: How do we "export" this and how does it mingle with // the above types? exp->ex_layout_type = LAYOUT_FLEX_FILES; #endif #ifdef CONFIG_NFSD_BLOCKLAYOUT /* overwrite flex file layout selection if needed */ if (sb->s_export_op->get_uuid && sb->s_export_op->map_blocks && sb->s_export_op->commit_blocks) exp->ex_layout_type = LAYOUT_BLOCK_VOLUME; #endif #ifdef CONFIG_NFSD_SCSILAYOUT /* overwrite block layout selection if needed */ if (sb->s_export_op->map_blocks && sb->s_export_op->commit_blocks && sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops) exp->ex_layout_type = LAYOUT_SCSI; #endif } We get what seems natural. -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Nice! A few comments below: > + * where the NFSv4.1 mds is also the ds. And the storage is > + * the same. I.e., writing to the mds via a NFSv4.1 WRITE > + * goes to the same location as the NFSv3 WRITE. > + */ > +#include <linux/exportfs.h> > +#include <linux/genhd.h> > +#include <linux/pr.h> I don't think you need any of the three headers above. > +static __be32 > +nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, > + struct nfsd4_layoutget *args) > +{ > + struct nfsd4_layout_seg *seg = &args->lg_seg; > + u32 block_size = (1 << inode->i_blkbits); > + u32 device_generation = 0; > + int error; > + > + struct pnfs_ff_layout *fl; > + > + if (seg->offset & (block_size - 1)) { > + dprintk("pnfsd: I/O misaligned\n"); > + goto out_layoutunavailable; > + } Do we really care about aligned I/O for flexfiles layouts? > + * effectively be WRITE only. > + */ > + fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS | > + FF_FLAGS_NO_READ_IO; > + > + fl->uid = inode->i_uid; > + fl->gid = inode->i_gid; Maybe I need to actually read the latest draft, but what's the story about these on the wire uids/gids? > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT I don't think you need this - the whole file is conditional on this symbol. > + if (sb->s_bdev != sb->s_bdev->bd_contains) > + return nfserr_inval; Shouldn't be needed. > +#include <linux/exportfs.h> probably not needed. > +struct iomap; no needed. > void nfsd4_setup_layout_type(struct svc_export *exp) > { > +#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT) > struct super_block *sb = exp->ex_path.mnt->mnt_sb; > +#endif > > if (!(exp->ex_flags & NFSEXP_PNFS)) > return; > @@ -145,6 +150,11 @@ void nfsd4_setup_layout_type(struct svc_export *exp) > sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops) > exp->ex_layout_type = LAYOUT_SCSI; > #endif > +#ifdef CONFIG_NFSD_FLEXFILELAYOUT > + // FIXME: How do we "export" this and how does it mingle with > + // the above types? > + exp->ex_layout_type = LAYOUT_FLEX_FILES; > +#endif As pointed out by Jeff we'll probably need a bitmap of supported layouts here. Something like unsigned long ex_layout_types; ... if (supported) ex_layout_types |= (1 << LAYOUT_XXX) probably best done as a separate preparation patch. The other issue is that the Linux client is currently confused when more than a single layout type is supported - we'll need some sort of runtime option to chose the layout(s) supported. -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Wed, May 25, 2016 at 08:30:44AM -0400, Jeff Layton wrote: > Maybe it's time to start thinking about how to support multiple layout > types per export? It looks like nobody would want this flex file code in production. The only users will be testers and developers. And the scsi layout is really just a replacement for the block layout, nobody should be supporting both of those at once either. Would it be too much of a burden just to make flexfiles and developers build their own kernels? > It doesn't look like it would be that hard. I think > we could convert ex_layout_type into a bitmap that shows which types > are supported. ex_layout_type is only used internally, the only external interface is an export flag, so we'd need some new interface. --b. > The harder work looks to be on the client. You'd need some heuristic to choose when you get back multiple layout types and fix that to work properly. -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Wed, 2016-05-25 at 13:42 -0400, J. Bruce Fields wrote: > On Wed, May 25, 2016 at 08:30:44AM -0400, Jeff Layton wrote: > > > > Maybe it's time to start thinking about how to support multiple layout > > types per export? > It looks like nobody would want this flex file code in production. The > only users will be testers and developers. > > And the scsi layout is really just a replacement for the block layout, > nobody should be supporting both of those at once either. > Well...unless you have a mix of clients that just support block and some that support scsi. Is that plausible? > Would it be too much of a burden just to make flexfiles and developers > build their own kernels? > > > It doesn't look like it would be that hard. I think > > we could convert ex_layout_type into a bitmap that shows which types > > are supported. > ex_layout_type is only used internally, the only external interface is > an export flag, so we'd need some new interface. > I was thinking that with the "pnfs" export option you'd just enable any layouts that the fs supports. So here, you could theoretically allow nfsd to offer up block, scsi and flexfiles layouts given the right fs, and leave the decision of the layout type to actually use up to the client.
> On May 25, 2016, at 8:15 AM, Christoph Hellwig <hch@lst.de> wrote: > > >> + * effectively be WRITE only. >> + */ >> + fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS | >> + FF_FLAGS_NO_READ_IO; >> + >> + fl->uid = inode->i_uid; >> + fl->gid = inode->i_gid; > > Maybe I need to actually read the latest draft, but what's the story > about these on the wire uids/gids? > Since NFSv3 does not grok stateids, this allows us to control access to the file. The mode is adjusted such that the owner has read/write and the group has read access: loghyr:~ loghyr$ ls -la foo -rw-r----- 1 loghyr staff 0 May 25 22:27 foo When the mds decides to fence off access for the IOMODE_RW segment, it changes the uid (monotonically increasing reduces the chance of resetting to some older value). When it wants to fence off the IOMODE_READ segment, it changes the gid. So the code above, should really be something like: if (seg->iomode == IOMODE_READ) fl->uid = inode->i_uid + 11; else fl->uid = inode->i_uid; fl->gid = inode->i_gid; This prevents some client from using the IOMODE_READ segment to do writes. (I think Jeff just fixed that recently in the client.) As this patchset neither has fencing nor a remote DS, the synthetic uid/gid works because the file modes have already determined if access is to be granted. There are “issues” in that the mode bits may not be 0640. -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Wed, May 25, 2016 at 05:57:29PM -0400, Jeff Layton wrote: > On Wed, 2016-05-25 at 13:42 -0400, J. Bruce Fields wrote: > > On Wed, May 25, 2016 at 08:30:44AM -0400, Jeff Layton wrote: > > > > > > Maybe it's time to start thinking about how to support multiple layout > > > types per export? > > It looks like nobody would want this flex file code in production. The > > only users will be testers and developers. > > > > And the scsi layout is really just a replacement for the block layout, > > nobody should be supporting both of those at once either. > > > > Well...unless you have a mix of clients that just support block and > some that support scsi. Is that plausible? Maybe so. I don't think it would be useful to support, though. (I'd rather people skipped straight to scsi. And block never got much use, so I don't think that should be hard. But if you're really stuck with some block clients, I suspect you may as well use block for all of them--the scsi clients could probably do block layout too, and I think you only get all the advantages of the scsi layout if all your clients are using it.) > > Would it be too much of a burden just to make flexfiles and developers > > build their own kernels? > > > > > It doesn't look like it would be that hard. I think > > > we could convert ex_layout_type into a bitmap that shows which types > > > are supported. > > ex_layout_type is only used internally, the only external interface is > > an export flag, so we'd need some new interface. > > > > I was thinking that with the "pnfs" export option you'd just enable any > layouts that the fs supports. So here, you could theoretically allow > nfsd to offer up block, scsi and flexfiles layouts given the right fs, > and leave the decision of the layout type to actually use up to the > client. OK. In this particular case that seems less interesting than just the ability to turn flexfiles on and off from user space, so testers can enable it without having to build a new kernel. Hopefully we can figure out how to make this useful in production some day, and then maybe the multiple-layout support becomes more interesting. --b. -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 3ae5f3c..5f5d3a7 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -20,3 +20,4 @@ nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o +nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c new file mode 100644 index 0000000..d28b8a0 --- /dev/null +++ b/fs/nfsd/flexfilelayout.c @@ -0,0 +1,148 @@ +/* + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> + * + * The following implements a super-simple flex-file server + * where the NFSv4.1 mds is also the ds. And the storage is + * the same. I.e., writing to the mds via a NFSv4.1 WRITE + * goes to the same location as the NFSv3 WRITE. + */ +#include <linux/exportfs.h> +#include <linux/genhd.h> +#include <linux/slab.h> +#include <linux/pr.h> + +#include <linux/nfsd/debug.h> + +#include <linux/sunrpc/addr.h> + +#include "flexfilelayoutxdr.h" +#include "pnfs.h" + +#define NFSDDBG_FACILITY NFSDDBG_PNFS + +static __be32 +nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, + struct nfsd4_layoutget *args) +{ + struct nfsd4_layout_seg *seg = &args->lg_seg; + u32 block_size = (1 << inode->i_blkbits); + u32 device_generation = 0; + int error; + + struct pnfs_ff_layout *fl; + + if (seg->offset & (block_size - 1)) { + dprintk("pnfsd: I/O misaligned\n"); + goto out_layoutunavailable; + } + + /* + * The super simple flex file server has 1 mirror, 1 data server, + * and 1 file handle. So instead of 4 allocs, do 1 for now. + * Zero it out for the stateid - don't want junk in there! + */ + error = -ENOMEM; + fl = kzalloc(sizeof(*fl), GFP_KERNEL); + if (!fl) + goto out_error; + args->lg_content = fl; + + /* + * Avoid layout commit, try to force the I/O to the DS, + * and for fun, cause all IOMODE_RW layout segments to + * effectively be WRITE only. + */ + fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS | + FF_FLAGS_NO_READ_IO; + + fl->uid = inode->i_uid; + fl->gid = inode->i_gid; + + error = nfsd4_set_deviceid(&fl->deviceid, fhp, device_generation); + if (error) + goto out_error; + + fl->fh.size = fhp->fh_handle.fh_size; + memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size); + + /* Give whole file layout segments */ + seg->offset = 0; + seg->length = NFS4_MAX_UINT64; + + dprintk("GET: 0x%llx:0x%llx %d\n", seg->offset, seg->length, + seg->iomode); + return 0; + +out_error: + kfree(fl); + seg->length = 0; + return nfserrno(error); +out_layoutunavailable: + seg->length = 0; + return nfserr_layoutunavailable; +} + +#ifdef CONFIG_NFSD_FLEXFILELAYOUT +static __be32 +nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, + struct svc_rqst *rqstp, + struct nfs4_client *clp, + struct nfsd4_getdeviceinfo *gdp) +{ + struct pnfs_ff_device_addr *da; + + u16 port; + char addr[INET6_ADDRSTRLEN]; + + if (sb->s_bdev != sb->s_bdev->bd_contains) + return nfserr_inval; + + da = kzalloc(sizeof(struct pnfs_ff_device_addr), GFP_KERNEL); + if (!da) + return nfserrno(-ENOMEM); + + gdp->gd_device = da; + + da->version = 3; + da->minor_version = 0; + + /* FIXME: Get from export? */ + da->rsize = 4096; + da->wsize = 4096; + + rpc_ntop((struct sockaddr *)&rqstp->rq_daddr, + addr, INET6_ADDRSTRLEN); + if (rqstp->rq_daddr.ss_family == AF_INET) { + struct sockaddr_in *sin; + + sin = (struct sockaddr_in *)&rqstp->rq_daddr; + port = ntohs(sin->sin_port); + snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp"); + da->netaddr.netid_len = 3; + } else { + struct sockaddr_in6 *sin6; + + sin6 = (struct sockaddr_in6 *)&rqstp->rq_daddr; + port = ntohs(sin6->sin6_port); + snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp6"); + da->netaddr.netid_len = 4; + } + + da->netaddr.addr_len = + snprintf(da->netaddr.addr, FF_ADDR_LEN + 1, + "%s.%hhu.%hhu", addr, port >> 8, port & 0xff); + + da->tightly_coupled = false; + + return 0; +} + +const struct nfsd4_layout_ops ff_layout_ops = { + .notify_types = + NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE, + .proc_getdeviceinfo = nfsd4_ff_proc_getdeviceinfo, + .encode_getdeviceinfo = nfsd4_ff_encode_getdeviceinfo, + .proc_layoutget = nfsd4_ff_proc_layoutget, + .encode_layoutget = nfsd4_ff_encode_layoutget, +}; +#endif /* CONFIG_NFSD_FLEXFILELAYOUT */ diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c new file mode 100644 index 0000000..9d15ee0 --- /dev/null +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -0,0 +1,116 @@ +/* + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> + */ +#include <linux/sunrpc/svc.h> +#include <linux/exportfs.h> +#include <linux/nfs4.h> + +#include "nfsd.h" +#include "flexfilelayoutxdr.h" + +#define NFSDDBG_FACILITY NFSDDBG_PNFS + +struct ff_idmap { + char buf[11]; + int len; +}; + +__be32 +nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, + struct nfsd4_layoutget *lgp) +{ + struct pnfs_ff_layout *fl = lgp->lg_content; + int len, mirror_len, ds_len, fh_len; + __be32 *p; + + /* + * Unlike nfsd4_encode_user, we know these will + * always be stringified. + */ + struct ff_idmap uid; + struct ff_idmap gid; + + fh_len = 4 + fl->fh.size; + + uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid)); + gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid)); + + /* 8 + len for recording the length, name, and padding */ + ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len + + 8 + uid.len + 8 + gid.len; + + mirror_len = 4 + ds_len; + + /* The layout segment */ + len = 20 + mirror_len; + + p = xdr_reserve_space(xdr, sizeof(__be32) + len); + if (!p) + return nfserr_toosmall; + + *p++ = cpu_to_be32(len); + p = xdr_encode_hyper(p, 1); /* stripe unit of 1 */ + + *p++ = cpu_to_be32(1); /* single mirror */ + *p++ = cpu_to_be32(1); /* single data server */ + + p = xdr_encode_opaque_fixed(p, &fl->deviceid, + sizeof(struct nfsd4_deviceid)); + + *p++ = cpu_to_be32(1); /* efficiency */ + + *p++ = cpu_to_be32(fl->stateid.si_generation); + p = xdr_encode_opaque_fixed(p, &fl->stateid.si_opaque, + sizeof(stateid_opaque_t)); + + *p++ = cpu_to_be32(1); /* single file handle */ + p = xdr_encode_opaque(p, fl->fh.data, fl->fh.size); + + p = xdr_encode_opaque(p, uid.buf, uid.len); + p = xdr_encode_opaque(p, gid.buf, gid.len); + + *p++ = cpu_to_be32(fl->flags); + *p++ = cpu_to_be32(0); /* No stats collect hint */ + + return 0; +} + +__be32 +nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, + struct nfsd4_getdeviceinfo *gdp) +{ + struct pnfs_ff_device_addr *da = gdp->gd_device; + int len; + int ver_len; + int addr_len; + __be32 *p; + + /* len + padding for two strings */ + addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; + ver_len = 20; + + len = 4 + ver_len + 4 + addr_len; + + p = xdr_reserve_space(xdr, len + sizeof(__be32)); + if (!p) + return nfserr_resource; + + /* + * Fill in the overall length and number of volumes at the beginning + * of the layout. + */ + *p++ = cpu_to_be32(len); + *p++ = cpu_to_be32(1); /* 1 netaddr */ + p = xdr_encode_opaque(p, da->netaddr.netid, da->netaddr.netid_len); + p = xdr_encode_opaque(p, da->netaddr.addr, da->netaddr.addr_len); + + *p++ = cpu_to_be32(1); /* 1 versions */ + + *p++ = cpu_to_be32(da->version); + *p++ = cpu_to_be32(da->minor_version); + *p++ = cpu_to_be32(da->rsize); + *p++ = cpu_to_be32(da->wsize); + *p++ = cpu_to_be32(da->tightly_coupled); + + return 0; +} diff --git a/fs/nfsd/flexfilelayoutxdr.h b/fs/nfsd/flexfilelayoutxdr.h new file mode 100644 index 0000000..40e6d1b --- /dev/null +++ b/fs/nfsd/flexfilelayoutxdr.h @@ -0,0 +1,50 @@ +/* + * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com> + */ +#ifndef _NFSD_FLEXFILELAYOUTXDR_H +#define _NFSD_FLEXFILELAYOUTXDR_H 1 + +#include <linux/inet.h> +#include "xdr4.h" + +#define FF_FLAGS_NO_LAYOUTCOMMIT 1 +#define FF_FLAGS_NO_IO_THRU_MDS 2 +#define FF_FLAGS_NO_READ_IO 4 + +struct iomap; +struct xdr_stream; + +#define FF_NETID_LEN (4) +#define FF_ADDR_LEN (INET6_ADDRSTRLEN + 1) +struct pnfs_ff_netaddr { + char netid[FF_NETID_LEN + 1]; + char addr[FF_ADDR_LEN + 1]; + u32 netid_len; + u32 addr_len; +}; + +struct pnfs_ff_device_addr { + struct pnfs_ff_netaddr netaddr; + u32 version; + u32 minor_version; + u32 rsize; + u32 wsize; + bool tightly_coupled; +}; + +struct pnfs_ff_layout { + u32 flags; + u32 stats_collect_hint; + kuid_t uid; + kgid_t gid; + struct nfsd4_deviceid deviceid; + stateid_t stateid; + struct nfs_fh fh; +}; + +__be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, + struct nfsd4_getdeviceinfo *gdp); +__be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, + struct nfsd4_layoutget *lgp); + +#endif /* _NFSD_FLEXFILELAYOUTXDR_H */ diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 825c7bc..7cbd56a 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -27,6 +27,9 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops; static const struct lock_manager_operations nfsd4_layouts_lm_ops; const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { +#ifdef CONFIG_NFSD_FLEXFILELAYOUT + [LAYOUT_FLEX_FILES] = &ff_layout_ops, +#endif #ifdef CONFIG_NFSD_BLOCKLAYOUT [LAYOUT_BLOCK_VOLUME] = &bl_layout_ops, #endif @@ -122,7 +125,9 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, void nfsd4_setup_layout_type(struct svc_export *exp) { +#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT) struct super_block *sb = exp->ex_path.mnt->mnt_sb; +#endif if (!(exp->ex_flags & NFSEXP_PNFS)) return; @@ -145,6 +150,11 @@ void nfsd4_setup_layout_type(struct svc_export *exp) sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops) exp->ex_layout_type = LAYOUT_SCSI; #endif +#ifdef CONFIG_NFSD_FLEXFILELAYOUT + // FIXME: How do we "export" this and how does it mingle with + // the above types? + exp->ex_layout_type = LAYOUT_FLEX_FILES; +#endif } static void diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h index e855677..0c2a716 100644 --- a/fs/nfsd/pnfs.h +++ b/fs/nfsd/pnfs.h @@ -45,6 +45,9 @@ extern const struct nfsd4_layout_ops bl_layout_ops; #ifdef CONFIG_NFSD_SCSILAYOUT extern const struct nfsd4_layout_ops scsi_layout_ops; #endif +#ifdef CONFIG_NFSD_FLEXFILELAYOUT +extern const struct nfsd4_layout_ops ff_layout_ops; +#endif __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid,
Have a simple flex file server where the mds (NFSv4.1 or NFSv4.2) is also the ds (NFSv3). I.e., the metadata and the data file are the exact same file. This will allow testing of the flex file client. Simply add the "pnfs" export option to your export in /etc/exports and mount from a client that supports flex files. Signed-off-by: Tom Haynes <loghyr@primarydata.com> --- fs/nfsd/Makefile | 1 + fs/nfsd/flexfilelayout.c | 148 ++++++++++++++++++++++++++++++++++++++++++++ fs/nfsd/flexfilelayoutxdr.c | 116 ++++++++++++++++++++++++++++++++++ fs/nfsd/flexfilelayoutxdr.h | 50 +++++++++++++++ fs/nfsd/nfs4layouts.c | 10 +++ fs/nfsd/pnfs.h | 3 + 6 files changed, 328 insertions(+) create mode 100644 fs/nfsd/flexfilelayout.c create mode 100644 fs/nfsd/flexfilelayoutxdr.c create mode 100644 fs/nfsd/flexfilelayoutxdr.h