This patchset converts NFS with fscache non-direct READ IO paths to
use the netfs API with a non-invasive approach. The existing NFS pgio
layer does not need extensive changes, and is the best way so far I've
found to address Trond's concerns about modifying the IO path [1] as
well as only enabling netfs when fscache is configured and enabled [2].
I have not attempted performance comparisions to address Chuck
Lever's concern [3] because we are not converting the non-fscache
enabled NFS IO paths to netfs.
The main patch to be reviewed is patch #3 which converts nfs_read_folio
and nfs_readahead.
Changes since v4 (all PATCH3)
- Remove more #ifdefs, replace with stub functions (Jeff Layton)[6]
- Use refcount for last RPC marker (Jeff Layton)[6]
The patches are fairly stable as evidenced with xfstests generic with
various servers, both with and without fscache enabled:
hammerspace(pNFS flexfiles): vers=4.2,fsc; vers=4.2
NetApp(pNFS filelayout): vers=4.1,fsc; vers=4.0,fsc
RHEL8: vers=3,fsc; vers=3
No major issues outstanding. Even the previous issue with the
"Subreq overread" was not reproducible with this set.
The known issues are as follows:
1. Unit test setting rsize < readahead does not properly read from
fscache but re-reads data from the NFS server
* This will be fixed with another linux-cachefs [4] patch to resolve
"Stop read optimisation when folio removed from pagecache"
* Daire Byrne also verified the patch fixes his issue as well
2. "Cache volume key already in use" after xfstest runs
* xfstests (hammerspace with vers=4.2,fsc) shows the following on the
console after some tests:
"NFS: Cache volume key already in use (nfs,4.1,2,c50,cfe0100a,3,,,8000,100000,100000,bb8,ea60,7530,ea60,1)"
* This may be fixed with another patch [4] that is in progress
The patchset is based on 6.0-rc3 and has been pushed to github at:
https://github.com/DaveWysochanskiRH/kernel/commits/nfs-fscache-netfs
[1] https://lore.kernel.org/linux-nfs/[email protected]/
[2] https://lore.kernel.org/linux-nfs/[email protected]/
[3] https://marc.info/?l=linux-nfs&m=160597917525083&w=4
[4] https://www.mail-archive.com/[email protected]/msg03043.html
[5] https://marc.info/?l=linux-nfs&m=165962662200679&w=4
[6] https://marc.info/?l=linux-nfs&m=166204800323762&w=4
Dave Wysochanski (3):
NFS: Rename readpage_async_filler to nfs_pageio_add_page
NFS: Configure support for netfs when NFS fscache is configured
NFS: Convert buffered read paths to use netfs when fscache is enabled
fs/nfs/Kconfig | 1 +
fs/nfs/delegation.c | 2 +-
fs/nfs/dir.c | 2 +-
fs/nfs/fscache.c | 256 ++++++++++++++++++++++++---------------
fs/nfs/fscache.h | 102 ++++++++++------
fs/nfs/inode.c | 8 +-
fs/nfs/internal.h | 11 +-
fs/nfs/pagelist.c | 12 ++
fs/nfs/pnfs.c | 12 +-
fs/nfs/read.c | 110 ++++++++---------
fs/nfs/write.c | 2 +-
include/linux/nfs_fs.h | 34 ++++--
include/linux/nfs_page.h | 3 +
include/linux/nfs_xdr.h | 3 +
14 files changed, 341 insertions(+), 217 deletions(-)
--
2.31.1
Rename readpage_async_filler to nfs_pageio_add_page to
better reflect what this function does (add a page to
the nfs_pageio_descriptor), and simplify arguments to
this function by removing struct nfs_readdesc.
Signed-off-by: Dave Wysochanski <[email protected]>
---
fs/nfs/read.c | 60 +++++++++++++++++++++++++--------------------------
1 file changed, 30 insertions(+), 30 deletions(-)
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 8ae2c8d1219d..525e82ea9a9e 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -127,11 +127,6 @@ static void nfs_readpage_release(struct nfs_page *req, int error)
nfs_release_request(req);
}
-struct nfs_readdesc {
- struct nfs_pageio_descriptor pgio;
- struct nfs_open_context *ctx;
-};
-
static void nfs_page_group_set_uptodate(struct nfs_page *req)
{
if (nfs_page_group_sync_on_bit(req, PG_UPTODATE))
@@ -153,7 +148,8 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
/* note: regions of the page not covered by a
- * request are zeroed in readpage_async_filler */
+ * request are zeroed in nfs_pageio_add_page
+ */
if (bytes > hdr->good_bytes) {
/* nothing in this request was good, so zero
* the full extent of the request */
@@ -281,8 +277,10 @@ static void nfs_readpage_result(struct rpc_task *task,
nfs_readpage_retry(task, hdr);
}
-static int
-readpage_async_filler(struct nfs_readdesc *desc, struct page *page)
+int
+nfs_pageio_add_page(struct nfs_pageio_descriptor *pgio,
+ struct nfs_open_context *ctx,
+ struct page *page)
{
struct inode *inode = page_file_mapping(page)->host;
unsigned int rsize = NFS_SERVER(inode)->rsize;
@@ -302,15 +300,15 @@ readpage_async_filler(struct nfs_readdesc *desc, struct page *page)
goto out_unlock;
}
- new = nfs_create_request(desc->ctx, page, 0, aligned_len);
+ new = nfs_create_request(ctx, page, 0, aligned_len);
if (IS_ERR(new))
goto out_error;
if (len < PAGE_SIZE)
zero_user_segment(page, len, PAGE_SIZE);
- if (!nfs_pageio_add_request(&desc->pgio, new)) {
+ if (!nfs_pageio_add_request(pgio, new)) {
nfs_list_remove_request(new);
- error = desc->pgio.pg_error;
+ error = pgio->pg_error;
nfs_readpage_release(new, error);
goto out;
}
@@ -332,7 +330,8 @@ readpage_async_filler(struct nfs_readdesc *desc, struct page *page)
int nfs_read_folio(struct file *file, struct folio *folio)
{
struct page *page = &folio->page;
- struct nfs_readdesc desc;
+ struct nfs_pageio_descriptor pgio;
+ struct nfs_open_context *ctx;
struct inode *inode = page_file_mapping(page)->host;
int ret;
@@ -358,29 +357,29 @@ int nfs_read_folio(struct file *file, struct folio *folio)
if (file == NULL) {
ret = -EBADF;
- desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
- if (desc.ctx == NULL)
+ ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
+ if (ctx == NULL)
goto out_unlock;
} else
- desc.ctx = get_nfs_open_context(nfs_file_open_context(file));
+ ctx = get_nfs_open_context(nfs_file_open_context(file));
- xchg(&desc.ctx->error, 0);
- nfs_pageio_init_read(&desc.pgio, inode, false,
+ xchg(&ctx->error, 0);
+ nfs_pageio_init_read(&pgio, inode, false,
&nfs_async_read_completion_ops);
- ret = readpage_async_filler(&desc, page);
+ ret = nfs_pageio_add_page(&pgio, ctx, page);
if (ret)
goto out;
- nfs_pageio_complete_read(&desc.pgio);
- ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0;
+ nfs_pageio_complete_read(&pgio);
+ ret = pgio.pg_error < 0 ? pgio.pg_error : 0;
if (!ret) {
ret = wait_on_page_locked_killable(page);
if (!PageUptodate(page) && !ret)
- ret = xchg(&desc.ctx->error, 0);
+ ret = xchg(&ctx->error, 0);
}
out:
- put_nfs_open_context(desc.ctx);
+ put_nfs_open_context(ctx);
trace_nfs_aop_readpage_done(inode, page, ret);
return ret;
out_unlock:
@@ -391,9 +390,10 @@ int nfs_read_folio(struct file *file, struct folio *folio)
void nfs_readahead(struct readahead_control *ractl)
{
+ struct nfs_pageio_descriptor pgio;
+ struct nfs_open_context *ctx;
unsigned int nr_pages = readahead_count(ractl);
struct file *file = ractl->file;
- struct nfs_readdesc desc;
struct inode *inode = ractl->mapping->host;
struct page *page;
int ret;
@@ -407,25 +407,25 @@ void nfs_readahead(struct readahead_control *ractl)
if (file == NULL) {
ret = -EBADF;
- desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
- if (desc.ctx == NULL)
+ ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
+ if (ctx == NULL)
goto out;
} else
- desc.ctx = get_nfs_open_context(nfs_file_open_context(file));
+ ctx = get_nfs_open_context(nfs_file_open_context(file));
- nfs_pageio_init_read(&desc.pgio, inode, false,
+ nfs_pageio_init_read(&pgio, inode, false,
&nfs_async_read_completion_ops);
while ((page = readahead_page(ractl)) != NULL) {
- ret = readpage_async_filler(&desc, page);
+ ret = nfs_pageio_add_page(&pgio, ctx, page);
put_page(page);
if (ret)
break;
}
- nfs_pageio_complete_read(&desc.pgio);
+ nfs_pageio_complete_read(&pgio);
- put_nfs_open_context(desc.ctx);
+ put_nfs_open_context(ctx);
out:
trace_nfs_aop_readahead_done(inode, nr_pages, ret);
}
--
2.31.1