NFSv4/flexfiles: Write path updates for striped layouts

Updates write path to calculate and use dss_id to direct IO to the
appropriate stripe DS.

Signed-off-by: Jonathan Curley <jcurley@purestorage.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index d4620fc414d8f2c165147b9441886494bf81637c..ba222c54b102bba493573cba7a7296cf342a7ff9 100644 (file)
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -605,6 +605,14 @@ ff_layout_free_lseg(struct pnfs_layout_segment *lseg)
        _ff_layout_free_lseg(fls);
 }
 
+static u32 calc_commit_idx(struct pnfs_layout_segment *lseg,
+                          u32 mirror_idx, u32 dss_id)
+{
+       struct nfs4_ff_layout_segment *flseg = FF_LAYOUT_LSEG(lseg);
+
+       return (mirror_idx * flseg->mirror_array[0]->dss_count) + dss_id;
+}
+
 static u32 calc_mirror_idx_from_commit(struct pnfs_layout_segment *lseg,
                                       u32 commit_index)
 {
@@ -1009,7 +1017,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
        struct nfs4_ff_layout_mirror *mirror;
        struct nfs_pgio_mirror *pgm;
        struct nfs4_pnfs_ds *ds;
-       u32 i;
+       u32 i, dss_id;
 
 retry:
        pnfs_generic_pg_check_layout(pgio, req);
@@ -1034,7 +1042,12 @@ retry:
 
        for (i = 0; i < pgio->pg_mirror_count; i++) {
                mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
-               ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, 0, true);
+               dss_id = nfs4_ff_layout_calc_dss_id(
+                       FF_LAYOUT_LSEG(pgio->pg_lseg)->stripe_unit,
+                       mirror->dss_count,
+                       req_offset(req));
+               ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror,
+                                              dss_id, true);
                if (IS_ERR(ds)) {
                        if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
                                goto out_mds;
@@ -1044,7 +1057,7 @@ retry:
                        goto retry;
                }
                pgm = &pgio->pg_mirrors[i];
-               pgm->pg_bsize = mirror->dss[0].mirror_ds->ds_versions[0].wsize;
+               pgm->pg_bsize = mirror->dss[dss_id].mirror_ds->ds_versions[0].wsize;
        }
 
        if (NFS_SERVER(pgio->pg_inode)->flags &
@@ -1117,7 +1130,7 @@ static const struct nfs_pageio_ops ff_layout_pg_read_ops = {
 
 static const struct nfs_pageio_ops ff_layout_pg_write_ops = {
        .pg_init = ff_layout_pg_init_write,
-       .pg_test = pnfs_generic_pg_test,
+       .pg_test = ff_layout_pg_test,
        .pg_doio = pnfs_generic_pg_writepages,
        .pg_get_mirror_count = ff_layout_pg_get_mirror_count_write,
        .pg_cleanup = pnfs_generic_pg_cleanup,
@@ -2051,25 +2064,30 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
        int vers;
        struct nfs_fh *fh;
        u32 idx = hdr->pgio_mirror_idx;
+       u32 dss_id;
        bool ds_fatal_error = false;
 
        mirror = FF_LAYOUT_COMP(lseg, idx);
-       ds = nfs4_ff_layout_prepare_ds(lseg, mirror, 0, true);
+       dss_id = nfs4_ff_layout_calc_dss_id(
+               FF_LAYOUT_LSEG(lseg)->stripe_unit,
+               mirror->dss_count,
+               offset);
+       ds = nfs4_ff_layout_prepare_ds(lseg, mirror, dss_id, true);
        if (IS_ERR(ds)) {
                ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
                goto out_failed;
        }
 
        ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
-                                                  hdr->inode, 0);
+                                                  hdr->inode, dss_id);
        if (IS_ERR(ds_clnt))
                goto out_failed;
 
-       ds_cred = ff_layout_get_ds_cred(mirror, &lseg->pls_range, hdr->cred, 0);
+       ds_cred = ff_layout_get_ds_cred(mirror, &lseg->pls_range, hdr->cred, dss_id);
        if (!ds_cred)
                goto out_failed;
 
-       vers = nfs4_ff_layout_ds_version(mirror, 0);
+       vers = nfs4_ff_layout_ds_version(mirror, dss_id);
 
        dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d vers %d\n",
                __func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
@@ -2079,12 +2097,12 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
        hdr->pgio_done_cb = ff_layout_write_done_cb;
        refcount_inc(&ds->ds_clp->cl_count);
        hdr->ds_clp = ds->ds_clp;
-       hdr->ds_commit_idx = idx;
-       fh = nfs4_ff_layout_select_ds_fh(mirror, 0);
+       hdr->ds_commit_idx = calc_commit_idx(lseg, idx, dss_id);
+       fh = nfs4_ff_layout_select_ds_fh(mirror, dss_id);
        if (fh)
                hdr->args.fh = fh;
 
-       nfs4_ff_layout_select_ds_stateid(mirror, 0, &hdr->args.stateid);
+       nfs4_ff_layout_select_ds_stateid(mirror, dss_id, &hdr->args.stateid);
 
        /*
         * Note that if we ever decide to split across DSes,
@@ -2093,7 +2111,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
        hdr->args.offset = offset;
 
        /* Start IO accounting for local write */
-       localio = ff_local_open_fh(lseg, idx, 0, ds->ds_clp, ds_cred, fh,
+       localio = ff_local_open_fh(lseg, idx, dss_id, ds->ds_clp, ds_cred, fh,
                                   FMODE_READ|FMODE_WRITE);
        if (localio) {
                hdr->task.tk_start = ktime_get();