pnfs/blocklayout: allocate separate pages for the layoutcommit payload
Instead of overflowing the XDR send buffer with our extent list allocate pages and pre-encode the layoutupdate payload into them. We optimistically allocate a single page use alloc_page and only switch to vmalloc when we have more extents outstanding. Currently there is only a single testcase (xfstests generic/113) which can reproduce large enough extent lists for this to occur. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
This commit is contained in:
parent
d4b18c3e00
commit
34dc93c2fc
|
@ -500,21 +500,16 @@ bl_return_range(struct pnfs_layout_hdr *lo,
|
||||||
err = ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end);
|
err = ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end);
|
||||||
}
|
}
|
||||||
|
|
||||||
static void
|
static int
|
||||||
bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr,
|
bl_prepare_layoutcommit(struct nfs4_layoutcommit_args *arg)
|
||||||
const struct nfs4_layoutcommit_args *arg)
|
|
||||||
{
|
{
|
||||||
dprintk("%s enter\n", __func__);
|
return ext_tree_prepare_commit(arg);
|
||||||
ext_tree_encode_commit(BLK_LO2EXT(lo), xdr);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
static void
|
static void
|
||||||
bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
|
bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
|
||||||
{
|
{
|
||||||
struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout;
|
ext_tree_mark_committed(&lcdata->args, lcdata->res.status);
|
||||||
|
|
||||||
dprintk("%s enter\n", __func__);
|
|
||||||
ext_tree_mark_committed(BLK_LO2EXT(lo), lcdata->res.status);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
static int
|
static int
|
||||||
|
@ -670,7 +665,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
|
||||||
.alloc_lseg = bl_alloc_lseg,
|
.alloc_lseg = bl_alloc_lseg,
|
||||||
.free_lseg = bl_free_lseg,
|
.free_lseg = bl_free_lseg,
|
||||||
.return_range = bl_return_range,
|
.return_range = bl_return_range,
|
||||||
.encode_layoutcommit = bl_encode_layoutcommit,
|
.prepare_layoutcommit = bl_prepare_layoutcommit,
|
||||||
.cleanup_layoutcommit = bl_cleanup_layoutcommit,
|
.cleanup_layoutcommit = bl_cleanup_layoutcommit,
|
||||||
.set_layoutdriver = bl_set_layoutdriver,
|
.set_layoutdriver = bl_set_layoutdriver,
|
||||||
.alloc_deviceid_node = bl_alloc_deviceid_node,
|
.alloc_deviceid_node = bl_alloc_deviceid_node,
|
||||||
|
|
|
@ -72,6 +72,9 @@ struct pnfs_block_extent {
|
||||||
unsigned int be_tag;
|
unsigned int be_tag;
|
||||||
};
|
};
|
||||||
|
|
||||||
|
/* on the wire size of the extent */
|
||||||
|
#define BL_EXTENT_SIZE (7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE)
|
||||||
|
|
||||||
struct pnfs_block_layout {
|
struct pnfs_block_layout {
|
||||||
struct pnfs_layout_hdr bl_layout;
|
struct pnfs_layout_hdr bl_layout;
|
||||||
struct rb_root bl_ext_rw;
|
struct rb_root bl_ext_rw;
|
||||||
|
@ -129,8 +132,7 @@ int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
|
||||||
sector_t len);
|
sector_t len);
|
||||||
bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
|
bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
|
||||||
struct pnfs_block_extent *ret, bool rw);
|
struct pnfs_block_extent *ret, bool rw);
|
||||||
int ext_tree_encode_commit(struct pnfs_block_layout *bl,
|
int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg);
|
||||||
struct xdr_stream *xdr);
|
void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status);
|
||||||
void ext_tree_mark_committed(struct pnfs_block_layout *bl, int status);
|
|
||||||
|
|
||||||
#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
|
#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
|
||||||
|
|
|
@ -462,32 +462,37 @@ out:
|
||||||
return err;
|
return err;
|
||||||
}
|
}
|
||||||
|
|
||||||
int
|
static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
|
||||||
ext_tree_encode_commit(struct pnfs_block_layout *bl, struct xdr_stream *xdr)
|
size_t buffer_size)
|
||||||
|
{
|
||||||
|
if (arg->layoutupdate_pages != &arg->layoutupdate_page) {
|
||||||
|
int nr_pages = DIV_ROUND_UP(buffer_size, PAGE_SIZE), i;
|
||||||
|
|
||||||
|
for (i = 0; i < nr_pages; i++)
|
||||||
|
put_page(arg->layoutupdate_pages[i]);
|
||||||
|
kfree(arg->layoutupdate_pages);
|
||||||
|
} else {
|
||||||
|
put_page(arg->layoutupdate_page);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
|
||||||
|
size_t buffer_size, size_t *count)
|
||||||
{
|
{
|
||||||
struct pnfs_block_extent *be;
|
struct pnfs_block_extent *be;
|
||||||
unsigned int count = 0;
|
|
||||||
__be32 *p, *xdr_start;
|
|
||||||
int ret = 0;
|
int ret = 0;
|
||||||
|
|
||||||
dprintk("%s enter\n", __func__);
|
|
||||||
|
|
||||||
xdr_start = xdr_reserve_space(xdr, 8);
|
|
||||||
if (!xdr_start)
|
|
||||||
return -ENOSPC;
|
|
||||||
|
|
||||||
spin_lock(&bl->bl_ext_lock);
|
spin_lock(&bl->bl_ext_lock);
|
||||||
for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
|
for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
|
||||||
if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
|
if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
|
||||||
be->be_tag != EXTENT_WRITTEN)
|
be->be_tag != EXTENT_WRITTEN)
|
||||||
continue;
|
continue;
|
||||||
|
|
||||||
p = xdr_reserve_space(xdr, 7 * sizeof(__be32) +
|
(*count)++;
|
||||||
NFS4_DEVICEID4_SIZE);
|
if (*count * BL_EXTENT_SIZE > buffer_size) {
|
||||||
if (!p) {
|
/* keep counting.. */
|
||||||
printk("%s: out of space for extent list\n", __func__);
|
|
||||||
ret = -ENOSPC;
|
ret = -ENOSPC;
|
||||||
break;
|
continue;
|
||||||
}
|
}
|
||||||
|
|
||||||
p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
|
p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
|
||||||
|
@ -498,25 +503,80 @@ ext_tree_encode_commit(struct pnfs_block_layout *bl, struct xdr_stream *xdr)
|
||||||
*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
|
*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
|
||||||
|
|
||||||
be->be_tag = EXTENT_COMMITTING;
|
be->be_tag = EXTENT_COMMITTING;
|
||||||
count++;
|
|
||||||
}
|
}
|
||||||
spin_unlock(&bl->bl_ext_lock);
|
spin_unlock(&bl->bl_ext_lock);
|
||||||
|
|
||||||
xdr_start[0] = cpu_to_be32((xdr->p - xdr_start - 1) * 4);
|
|
||||||
xdr_start[1] = cpu_to_be32(count);
|
|
||||||
|
|
||||||
dprintk("%s found %i ranges\n", __func__, count);
|
|
||||||
return ret;
|
return ret;
|
||||||
}
|
}
|
||||||
|
|
||||||
void
|
int
|
||||||
ext_tree_mark_committed(struct pnfs_block_layout *bl, int status)
|
ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
|
||||||
{
|
{
|
||||||
|
struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout);
|
||||||
|
size_t count = 0, buffer_size = PAGE_SIZE;
|
||||||
|
__be32 *start_p;
|
||||||
|
int ret;
|
||||||
|
|
||||||
|
dprintk("%s enter\n", __func__);
|
||||||
|
|
||||||
|
arg->layoutupdate_page = alloc_page(GFP_NOFS);
|
||||||
|
if (!arg->layoutupdate_page)
|
||||||
|
return -ENOMEM;
|
||||||
|
start_p = page_address(arg->layoutupdate_page);
|
||||||
|
arg->layoutupdate_pages = &arg->layoutupdate_page;
|
||||||
|
|
||||||
|
retry:
|
||||||
|
ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count);
|
||||||
|
if (unlikely(ret)) {
|
||||||
|
ext_tree_free_commitdata(arg, buffer_size);
|
||||||
|
|
||||||
|
buffer_size = sizeof(__be32) + BL_EXTENT_SIZE * count;
|
||||||
|
count = 0;
|
||||||
|
|
||||||
|
arg->layoutupdate_pages =
|
||||||
|
kcalloc(DIV_ROUND_UP(buffer_size, PAGE_SIZE),
|
||||||
|
sizeof(struct page *), GFP_NOFS);
|
||||||
|
if (!arg->layoutupdate_pages)
|
||||||
|
return -ENOMEM;
|
||||||
|
|
||||||
|
start_p = __vmalloc(buffer_size, GFP_NOFS, PAGE_KERNEL);
|
||||||
|
if (!start_p) {
|
||||||
|
kfree(arg->layoutupdate_pages);
|
||||||
|
return -ENOMEM;
|
||||||
|
}
|
||||||
|
|
||||||
|
goto retry;
|
||||||
|
}
|
||||||
|
|
||||||
|
*start_p = cpu_to_be32(count);
|
||||||
|
arg->layoutupdate_len = sizeof(__be32) + BL_EXTENT_SIZE * count;
|
||||||
|
|
||||||
|
if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) {
|
||||||
|
__be32 *p = start_p;
|
||||||
|
int i = 0;
|
||||||
|
|
||||||
|
for (p = start_p;
|
||||||
|
p < start_p + arg->layoutupdate_len;
|
||||||
|
p += PAGE_SIZE) {
|
||||||
|
arg->layoutupdate_pages[i++] = vmalloc_to_page(p);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
dprintk("%s found %zu ranges\n", __func__, count);
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
void
|
||||||
|
ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status)
|
||||||
|
{
|
||||||
|
struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout);
|
||||||
struct rb_root *root = &bl->bl_ext_rw;
|
struct rb_root *root = &bl->bl_ext_rw;
|
||||||
struct pnfs_block_extent *be;
|
struct pnfs_block_extent *be;
|
||||||
|
|
||||||
dprintk("%s status %d\n", __func__, status);
|
dprintk("%s status %d\n", __func__, status);
|
||||||
|
|
||||||
|
ext_tree_free_commitdata(arg, arg->layoutupdate_len);
|
||||||
|
|
||||||
spin_lock(&bl->bl_ext_lock);
|
spin_lock(&bl->bl_ext_lock);
|
||||||
for (be = ext_tree_first(root); be; be = ext_tree_next(be)) {
|
for (be = ext_tree_first(root); be; be = ext_tree_next(be)) {
|
||||||
if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
|
if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
|
||||||
|
|
Loading…
Reference in New Issue