NFSD: add "NFSD DIRECT" and "NFSD DONTCACHE" IO modes
Subsystems (2)
v4 cover NFSD: add "NFSD DIRECT" and "NFSD DONTCACHE" IO modes
Hi,
Some workloads benefit from NFSD avoiding the page cache, particularly those with a working set that is significantly larger than available system memory. This patchset introduces _optional_ support to configure the use of O_DIRECT or DONTCACHE for NFSD's READ and WRITE support. The NFSD default to use page cache is left unchanged.
The performance win associated with using NFSD DIRECT was previously summarized here:
https://lore.kernel.org/linux-nfs/[email protected]/
This picture offers a nice summary of performance gains:
https://original.art/NFSD_direct_vs_buffered_IO.jpg
Very minor changes for this v4.
Thanks,
Mike
Changes since v3:
- Fix a copy-n-paste bug in nfsd_vfs_write:
s/nf_dio_read_offset_align/nf_dio_offset_align/
- Rename struct nfsd_dio_io to nfsd_read_dio.
Changes since v2:
- explored suggestion to use string based interface (e.g. "direct" instead of 3) but debugfs seems to only supports numeric values.
- shifted numeric values for debugfs interface from 0-2 to 1-3 and made 0 UNSPECIFIED (which is the default)
- if user specifies io_cache_read or io_cache_write mode other than 1, 2 or 3 (via debugfs) they will get an error message
- pass a data structure to nfsd_analyze_read_dio rather than so many in/out params
- improved comments as requested (e.g. "Must remove first start_extra_page from rqstp->rq_bvec" was reworked)
- use memmove instead of opencoded shift in nfsd_complete_misaligned_read_dio
- dropped the still very important "lib/iov_iter: remove piecewise bvec length checking in iov_iter_aligned_bvec" patch because it needs to be handled separately.
- various other changes to improve code
Mike Snitzer (5):
NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
NFSD: pass nfsd_file to nfsd_iter_read()
NFSD: add io_cache_read controls to debugfs interface
NFSD: add io_cache_write controls to debugfs interface
NFSD: issue READs using O_DIRECT even if IO is misaligned
fs/nfsd/debugfs.c | 102 +++++++++++++++++++ fs/nfsd/filecache.c | 32 ++++++ fs/nfsd/filecache.h | 4 + fs/nfsd/nfs4xdr.c | 8 +- fs/nfsd/nfsd.h | 10 ++ fs/nfsd/nfsfh.c | 4 + fs/nfsd/trace.h | 37 +++++++ fs/nfsd/vfs.c | 197 ++++++++++++++++++++++++++++++++++--- fs/nfsd/vfs.h | 2 +- include/linux/sunrpc/svc.h | 5 +- 10 files changed, 383 insertions(+), 18 deletions(-)
Signature · 1 line
2.44.0
PATCH v4 1/5 NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
Use STATX_DIOALIGN and STATX_DIO_READ_ALIGN to get and store DIO alignment attributes from underlying filesystem in associated nfsd_file. This is done when the nfsd_file is first opened for a regular file.
--- fs/nfsd/filecache.c | 32 ++++++++++++++++++++++++++++++++ fs/nfsd/filecache.h | 4 ++++ fs/nfsd/nfsfh.c | 4 ++++ 3 files changed, 40 insertions(+)
fs/nfsd/filecache.c +32 -0
@@ -231,6 +231,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,refcount_set (&nf->nf_ref,1 ); nf->nf_may = need; nf->nf_mark =NULL ; + nf->nf_dio_mem_align =0 ; + nf->nf_dio_offset_align =0 ; + nf->nf_dio_read_offset_align =0 ;return nf; }
@@ -1048,6 +1051,33 @@ nfsd_file_is_cached(struct inode *inode)return ret; } +static __be32 +nfsd_file_getattr (const struct svc_fh *fhp,struct nfsd_file *nf) +{ +struct inode *inode =file_inode (nf->nf_file); +struct kstat stat; +__be32 status; + +/* Currently only need to get DIO alignment info for regular files */ +if (!S_ISREG (inode->i_mode)) +return nfs_ok; + + status =fh_getattr (fhp, &stat); +if (status != nfs_ok) +return status; + +if (stat.result_mask &STATX_DIOALIGN ) { + nf->nf_dio_mem_align = stat.dio_mem_align; + nf->nf_dio_offset_align = stat.dio_offset_align; + } +if (stat.result_mask &STATX_DIO_READ_ALIGN ) + nf->nf_dio_read_offset_align = stat.dio_read_offset_align; +else + nf->nf_dio_read_offset_align = nf->nf_dio_offset_align; + +return status; +} + static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, struct svc_cred *cred,
@@ -1166,6 +1196,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, } status =nfserrno (ret);trace_nfsd_file_open (nf, status); +if (status == nfs_ok) + status =nfsd_file_getattr (fhp, nf); } }else status = nfserr_jukebox;
fs/nfsd/filecache.h +4 -0
@@ -54,6 +54,10 @@ struct nfsd_file {struct list_head nf_gc;struct rcu_head nf_rcu;ktime_t nf_birthtime; + +u32 nf_dio_mem_align; +u32 nf_dio_offset_align; +u32 nf_dio_read_offset_align; };int nfsd_file_cache_init (void );
fs/nfsd/nfsfh.c +4 -0
@@ -677,8 +677,12 @@ __be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat) .mnt = fhp->fh_export->ex_path.mnt, .dentry = fhp->fh_dentry, }; +struct inode *inode =d_inode (p.dentry);u32 request_mask =STATX_BASIC_STATS ; +if (S_ISREG (inode->i_mode)) + request_mask |= (STATX_DIOALIGN |STATX_DIO_READ_ALIGN ); +if (fhp->fh_maxsize ==NFS4_FHSIZE ) request_mask |= (STATX_BTIME |STATX_CHANGE_COOKIE );
Signature · 1 line
2.44.0
Jeff Layton
maintainerRe: [PATCH v4 1/5] NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
Quoted 61 lines · Mike Snitzer
Use
STATX_DIOALIGNandSTATX_DIO_READ_ALIGNto get and store DIO alignment attributes from underlying filesystem in associatednfsd_file. This is done when thenfsd_fileis first opened for a regular file.Signed-off-by Mike Snitzer <[email protected]>--- fs/nfsd/filecache.c | 32 ++++++++++++++++++++++++++++++++ fs/nfsd/filecache.h | 4 ++++ fs/nfsd/nfsfh.c | 4 ++++ 3 files changed, 40 insertions(+)fs/nfsd/filecache.c +30
-0@@ -231,6 +231,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,refcount_set (&nf->nf_ref,1 ); nf->nf_may = need; nf->nf_mark =NULL ; + nf->nf_dio_mem_align =0 ; + nf->nf_dio_offset_align =0 ; + nf->nf_dio_read_offset_align =0 ;return nf; }@@ -1048,6 +1051,33 @@ nfsd_file_is_cached(struct inode *inode)return ret; } +static __be32 +nfsd_file_getattr (const struct svc_fh *fhp,struct nfsd_file *nf) +{ +struct inode *inode =file_inode (nf->nf_file); +struct kstat stat; +__be32 status; + +/* Currently only need to get DIO alignment info for regular files */ +if (!S_ISREG (inode->i_mode)) +return nfs_ok; + + status =fh_getattr (fhp, &stat); +if (status != nfs_ok) +return status; + +if (stat.result_mask &STATX_DIOALIGN ) { + nf->nf_dio_mem_align = stat.dio_mem_align; + nf->nf_dio_offset_align = stat.dio_offset_align; + } +if (stat.result_mask &STATX_DIO_READ_ALIGN ) + nf->nf_dio_read_offset_align = stat.dio_read_offset_align; +else + nf->nf_dio_read_offset_align = nf->nf_dio_offset_align; + +return status; +} + static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, struct svc_cred *cred,
fs/nfsd/filecache.c nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, · line 1200
Quoted 5 lines
fs/nfsd/filecache.c +2
-0@@ -1166,6 +1196,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, } status =nfserrno (ret);trace_nfsd_file_open (nf, status); +if (status == nfs_ok) + status =nfsd_file_getattr (fhp, nf);
Doing a getattr alongside every open could be expensive in some configurations (like reexported NFS). We may want to skip doing this getattr this if O_DIRECT isn't is use. Is that possible?
Quoted 35 lines
fs/nfsd/filecache.c +0
-0} }else status = nfserr_jukebox;fs/nfsd/filecache.h +4
-0@@ -54,6 +54,10 @@ struct nfsd_file {struct list_head nf_gc;struct rcu_head nf_rcu;ktime_t nf_birthtime; + +u32 nf_dio_mem_align; +u32 nf_dio_offset_align; +u32 nf_dio_read_offset_align; };int nfsd_file_cache_init (void );fs/nfsd/nfsfh.c +4
-0@@ -677,8 +677,12 @@ __be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat) .mnt = fhp->fh_export->ex_path.mnt, .dentry = fhp->fh_dentry, }; +struct inode *inode =d_inode (p.dentry);u32 request_mask =STATX_BASIC_STATS ; +if (S_ISREG (inode->i_mode)) + request_mask |= (STATX_DIOALIGN |STATX_DIO_READ_ALIGN ); +if (fhp->fh_maxsize ==NFS4_FHSIZE ) request_mask |= (STATX_BTIME |STATX_CHANGE_COOKIE );
Signature · 1 line
Jeff Layton <[email protected]>
Re: [PATCH v4 1/5] NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
Quoted 64 lines · Jeff Layton
Quoted 63 lines · Mike Snitzer
Use
STATX_DIOALIGNandSTATX_DIO_READ_ALIGNto get and store DIO alignment attributes from underlying filesystem in associatednfsd_file. This is done when thenfsd_fileis first opened for a regular file.Signed-off-by Mike Snitzer <[email protected]>--- fs/nfsd/filecache.c | 32 ++++++++++++++++++++++++++++++++ fs/nfsd/filecache.h | 4 ++++ fs/nfsd/nfsfh.c | 4 ++++ 3 files changed, 40 insertions(+)fs/nfsd/filecache.c +30
-0@@ -231,6 +231,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,refcount_set (&nf->nf_ref,1 ); nf->nf_may = need; nf->nf_mark =NULL ; + nf->nf_dio_mem_align =0 ; + nf->nf_dio_offset_align =0 ; + nf->nf_dio_read_offset_align =0 ;return nf; }@@ -1048,6 +1051,33 @@ nfsd_file_is_cached(struct inode *inode)return ret; } +static __be32 +nfsd_file_getattr (const struct svc_fh *fhp,struct nfsd_file *nf) +{ +struct inode *inode =file_inode (nf->nf_file); +struct kstat stat; +__be32 status; + +/* Currently only need to get DIO alignment info for regular files */ +if (!S_ISREG (inode->i_mode)) +return nfs_ok; + + status =fh_getattr (fhp, &stat); +if (status != nfs_ok) +return status; + +if (stat.result_mask &STATX_DIOALIGN ) { + nf->nf_dio_mem_align = stat.dio_mem_align; + nf->nf_dio_offset_align = stat.dio_offset_align; + } +if (stat.result_mask &STATX_DIO_READ_ALIGN ) + nf->nf_dio_read_offset_align = stat.dio_read_offset_align; +else + nf->nf_dio_read_offset_align = nf->nf_dio_offset_align; + +return status; +} + static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, struct svc_cred *cred,@@ -1166,6 +1196,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, } status =nfserrno (ret);
Quoted 8 lines
fs/nfsd/filecache.c nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, · line 1200
Quoted 3 lines
fs/nfsd/filecache.c +2
-0trace_nfsd_file_open (nf, status); +if (status == nfs_ok) + status =nfsd_file_getattr (fhp, nf);Doing a getattr alongside every open could be expensive in some configurations (like reexported NFS). We may want to skip doing this getattr this if
O_DIRECTisn't is use. Is that possible?
Good point, yes, should be easy enough. Will depend on the debugfs knobs, so will tack a patch on at the end.
Thanks,
Mike
Re: [PATCH v4 1/5] NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
Quoted 74 lines · Mike Snitzer
Quoted 64 lines · Jeff Layton
Quoted 63 lines · Mike Snitzer
Use
STATX_DIOALIGNandSTATX_DIO_READ_ALIGNto get and store DIO alignment attributes from underlying filesystem in associatednfsd_file. This is done when thenfsd_fileis first opened for a regular file.Signed-off-by Mike Snitzer <[email protected]>--- fs/nfsd/filecache.c | 32 ++++++++++++++++++++++++++++++++ fs/nfsd/filecache.h | 4 ++++ fs/nfsd/nfsfh.c | 4 ++++ 3 files changed, 40 insertions(+)fs/nfsd/filecache.c +30
-0@@ -231,6 +231,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,refcount_set (&nf->nf_ref,1 ); nf->nf_may = need; nf->nf_mark =NULL ; + nf->nf_dio_mem_align =0 ; + nf->nf_dio_offset_align =0 ; + nf->nf_dio_read_offset_align =0 ;return nf; }@@ -1048,6 +1051,33 @@ nfsd_file_is_cached(struct inode *inode)return ret; } +static __be32 +nfsd_file_getattr (const struct svc_fh *fhp,struct nfsd_file *nf) +{ +struct inode *inode =file_inode (nf->nf_file); +struct kstat stat; +__be32 status; + +/* Currently only need to get DIO alignment info for regular files */ +if (!S_ISREG (inode->i_mode)) +return nfs_ok; + + status =fh_getattr (fhp, &stat); +if (status != nfs_ok) +return status; + +if (stat.result_mask &STATX_DIOALIGN ) { + nf->nf_dio_mem_align = stat.dio_mem_align; + nf->nf_dio_offset_align = stat.dio_offset_align; + } +if (stat.result_mask &STATX_DIO_READ_ALIGN ) + nf->nf_dio_read_offset_align = stat.dio_read_offset_align; +else + nf->nf_dio_read_offset_align = nf->nf_dio_offset_align; + +return status; +} + static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, struct svc_cred *cred,@@ -1166,6 +1196,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, } status =nfserrno (ret);Quoted 8 lines
fs/nfsd/filecache.c nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, · line 1200
Quoted 3 lines
fs/nfsd/filecache.c +2
-0trace_nfsd_file_open (nf, status); +if (status == nfs_ok) + status =nfsd_file_getattr (fhp, nf);Doing a getattr alongside every open could be expensive in some configurations (like reexported NFS). We may want to skip doing this getattr this if
O_DIRECTisn't is use. Is that possible?
Quoted 2 lines
Good point, yes, should be easy enough. Will depend on the debugfs knobs, so will tack a patch on at the end.
What is the best way to check for NFSD reexporting NFS?
I've done stuff like that as a side-effect of setting/checking a particular flag, e.g. commit 5cca2483b9fd ("nfsd: disallow file locking and delegations for NFSv4 reexport")
But not immediately seeing a more generic way to do the check...
Thanks,
Mike
Jeff Layton
maintainerRe: [PATCH v4 1/5] NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
Quoted 78 lines · Mike Snitzer
Quoted 74 lines · Mike Snitzer
Quoted 64 lines · Jeff Layton
Quoted 63 lines · Mike Snitzer
Use
STATX_DIOALIGNandSTATX_DIO_READ_ALIGNto get and store DIO alignment attributes from underlying filesystem in associatednfsd_file. This is done when thenfsd_fileis first opened for a regular file.Signed-off-by Mike Snitzer <[email protected]>--- fs/nfsd/filecache.c | 32 ++++++++++++++++++++++++++++++++ fs/nfsd/filecache.h | 4 ++++ fs/nfsd/nfsfh.c | 4 ++++ 3 files changed, 40 insertions(+)fs/nfsd/filecache.c +30
-0@@ -231,6 +231,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,refcount_set (&nf->nf_ref,1 ); nf->nf_may = need; nf->nf_mark =NULL ; + nf->nf_dio_mem_align =0 ; + nf->nf_dio_offset_align =0 ; + nf->nf_dio_read_offset_align =0 ;return nf; }@@ -1048,6 +1051,33 @@ nfsd_file_is_cached(struct inode *inode)return ret; } +static __be32 +nfsd_file_getattr (const struct svc_fh *fhp,struct nfsd_file *nf) +{ +struct inode *inode =file_inode (nf->nf_file); +struct kstat stat; +__be32 status; + +/* Currently only need to get DIO alignment info for regular files */ +if (!S_ISREG (inode->i_mode)) +return nfs_ok; + + status =fh_getattr (fhp, &stat); +if (status != nfs_ok) +return status; + +if (stat.result_mask &STATX_DIOALIGN ) { + nf->nf_dio_mem_align = stat.dio_mem_align; + nf->nf_dio_offset_align = stat.dio_offset_align; + } +if (stat.result_mask &STATX_DIO_READ_ALIGN ) + nf->nf_dio_read_offset_align = stat.dio_read_offset_align; +else + nf->nf_dio_read_offset_align = nf->nf_dio_offset_align; + +return status; +} + static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, struct svc_cred *cred,@@ -1166,6 +1196,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, } status =nfserrno (ret);Quoted 8 lines
fs/nfsd/filecache.c nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, · line 1200
Quoted 3 lines
fs/nfsd/filecache.c +2
-0trace_nfsd_file_open (nf, status); +if (status == nfs_ok) + status =nfsd_file_getattr (fhp, nf);Doing a getattr alongside every open could be expensive in some configurations (like reexported NFS). We may want to skip doing this getattr this if
O_DIRECTisn't is use. Is that possible?Quoted 2 lines
Good point, yes, should be easy enough. Will depend on the debugfs knobs, so will tack a patch on at the end.
Quoted 8 lines
What is the best way to check for NFSD reexporting NFS?
I've done stuff like that as a side-effect of setting/checking a particular flag, e.g. commit
5cca2483b9fd("nfsd: disallow file locking and delegations for NFSv4 reexport")But not immediately seeing a more generic way to do the check...
I don't think there is a reliable method, and we probably wouldn't want to just limit this to NFS. Other filesystems might have similar limitations (e.g. Ceph or Lustre).
I'd probably just base this on whether support is enabled in debugfs. If it is, then do the getattr. If that slows down reexports then we can figure out what to do then. If and when we get to converting this to an export option, we may need to do something more elaborate, but I wouldn't bother for now.
Signature · 1 line
Jeff Layton <[email protected]>
Re: [PATCH v4 1/5] NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
Quoted 92 lines · Jeff Layton
Quoted 78 lines · Mike Snitzer
Quoted 74 lines · Mike Snitzer
Quoted 64 lines · Jeff Layton
Quoted 63 lines · Mike Snitzer
Use
STATX_DIOALIGNandSTATX_DIO_READ_ALIGNto get and store DIO alignment attributes from underlying filesystem in associatednfsd_file. This is done when thenfsd_fileis first opened for a regular file.Signed-off-by Mike Snitzer <[email protected]>--- fs/nfsd/filecache.c | 32 ++++++++++++++++++++++++++++++++ fs/nfsd/filecache.h | 4 ++++ fs/nfsd/nfsfh.c | 4 ++++ 3 files changed, 40 insertions(+)fs/nfsd/filecache.c +30
-0@@ -231,6 +231,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,refcount_set (&nf->nf_ref,1 ); nf->nf_may = need; nf->nf_mark =NULL ; + nf->nf_dio_mem_align =0 ; + nf->nf_dio_offset_align =0 ; + nf->nf_dio_read_offset_align =0 ;return nf; }@@ -1048,6 +1051,33 @@ nfsd_file_is_cached(struct inode *inode)return ret; } +static __be32 +nfsd_file_getattr (const struct svc_fh *fhp,struct nfsd_file *nf) +{ +struct inode *inode =file_inode (nf->nf_file); +struct kstat stat; +__be32 status; + +/* Currently only need to get DIO alignment info for regular files */ +if (!S_ISREG (inode->i_mode)) +return nfs_ok; + + status =fh_getattr (fhp, &stat); +if (status != nfs_ok) +return status; + +if (stat.result_mask &STATX_DIOALIGN ) { + nf->nf_dio_mem_align = stat.dio_mem_align; + nf->nf_dio_offset_align = stat.dio_offset_align; + } +if (stat.result_mask &STATX_DIO_READ_ALIGN ) + nf->nf_dio_read_offset_align = stat.dio_read_offset_align; +else + nf->nf_dio_read_offset_align = nf->nf_dio_offset_align; + +return status; +} + static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, struct svc_cred *cred,@@ -1166,6 +1196,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, } status =nfserrno (ret);Quoted 8 lines
fs/nfsd/filecache.c nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net, · line 1200
Quoted 3 lines
fs/nfsd/filecache.c +2
-0trace_nfsd_file_open (nf, status); +if (status == nfs_ok) + status =nfsd_file_getattr (fhp, nf);Doing a getattr alongside every open could be expensive in some configurations (like reexported NFS). We may want to skip doing this getattr this if
O_DIRECTisn't is use. Is that possible?Quoted 2 lines
Good point, yes, should be easy enough. Will depend on the debugfs knobs, so will tack a patch on at the end.
Quoted 8 lines
What is the best way to check for NFSD reexporting NFS?
I've done stuff like that as a side-effect of setting/checking a particular flag, e.g. commit
5cca2483b9fd("nfsd: disallow file locking and delegations for NFSv4 reexport")But not immediately seeing a more generic way to do the check...
I don't think there is a reliable method, and we probably wouldn't want to just limit this to NFS. Other filesystems might have similar limitations (e.g. Ceph or Lustre).
Quoted 5 lines
I'd probably just base this on whether support is enabled in debugfs. If it is, then do the getattr. If that slows down reexports then we can figure out what to do then. If and when we get to converting this to an export option, we may need to do something more elaborate, but I wouldn't bother for now.
Fwiw, I would expect that re-exports would prefer to utilize the NFS server's page cache.
Signature · 1 line
Chuck Lever
PATCH v4 2/5 NFSD: pass nfsd_file to nfsd_iter_read()
In reply to Mike SnitzerPrepares for nfsd_iter_read() to use DIO alignment stored in nfsd_file.
--- fs/nfsd/nfs4xdr.c | 8 ++++---- fs/nfsd/vfs.c | 7 ++++--- fs/nfsd/vfs.h | 2 +- 3 files changed, 9 insertions(+), 8 deletions(-)
fs/nfsd/nfs4xdr.c +4 -4
@@ -4465,7 +4465,7 @@ static __be32 nfsd4_encode_splice_read(static __be32 nfsd4_encode_readv (struct nfsd4_compoundres *resp,struct nfsd4_read *read, -struct file *file,unsigned long maxcount) +unsigned long maxcount) {struct xdr_stream *xdr = resp->xdr;unsigned int base = xdr->buf->page_len & ~PAGE_MASK ;
@@ -4476,7 +4476,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,if (xdr_reserve_space_vec (xdr, maxcount) <0 )return nfserr_resource; - nfserr =nfsd_iter_read (resp->rqstp, read->rd_fhp, file, + nfserr =nfsd_iter_read (resp->rqstp, read->rd_fhp, read->rd_nf, read->rd_offset, &maxcount, base, &read->rd_eof); read->rd_length = maxcount;
@@ -4523,7 +4523,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,if (file->f_op->splice_read && splice_ok) nfserr =nfsd4_encode_splice_read (resp, read, file, maxcount);else - nfserr =nfsd4_encode_readv (resp, read, file, maxcount); + nfserr =nfsd4_encode_readv (resp, read, maxcount);if (nfserr) {xdr_truncate_encode (xdr, eof_offset);return nfserr;
@@ -5419,7 +5419,7 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,if (file->f_op->splice_read && splice_ok) nfserr =nfsd4_encode_splice_read (resp, read, file, maxcount);else - nfserr =nfsd4_encode_readv (resp, read, file, maxcount); + nfserr =nfsd4_encode_readv (resp, read, maxcount);if (nfserr)return nfserr;
fs/nfsd/vfs.c +4 -3
@@ -1075,7 +1075,7 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,* nfsd_iter_read - Perform a VFS read using an iterator * @rqstp: RPC transaction context * @fhp: file handle of file to be read -* @file: opened struct file of file to be read +* @nf: opened struct nfsd_file of file to be read * @offset: starting byte offset * @count: IN: requested number of bytes; OUT: number of bytes read * @base: offset in first page of read buffer
@@ -1088,9 +1088,10 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,* returned. */ __be32 nfsd_iter_read (struct svc_rqst *rqstp,struct svc_fh *fhp, -struct file *file,loff_t offset,unsigned long *count, +struct nfsd_file *nf,loff_t offset,unsigned long *count,unsigned int base,u32 *eof) { +struct file *file = nf->nf_file;unsigned long v, total;struct iov_iter iter;struct kiocb kiocb;
@@ -1312,7 +1313,7 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,if (file->f_op->splice_read &&nfsd_read_splice_ok (rqstp)) err =nfsd_splice_read (rqstp, fhp, file, offset, count, eof);else - err =nfsd_iter_read (rqstp, fhp, file, offset, count,0 , eof); + err =nfsd_iter_read (rqstp, fhp, nf, offset, count,0 , eof);nfsd_file_put (nf);trace_nfsd_read_done (rqstp, fhp, offset, *count);
fs/nfsd/vfs.h +1 -1
@@ -121,7 +121,7 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,unsigned long *count, u32 *eof);__be32 nfsd_iter_read (struct svc_rqst *rqstp,struct svc_fh *fhp, -struct file *file,loff_t offset, +struct nfsd_file *nf,loff_t offset,unsigned long *count,unsigned int base,u32 *eof);bool nfsd_read_splice_ok (struct svc_rqst *rqstp);
Signature · 1 line
2.44.0
PATCH v4 3/5 NFSD: add io_cache_read controls to debugfs interface
In reply to Mike SnitzerAdd 'io_cache_read' to NFSD's debugfs interface so that: Any data read by NFSD will either be:
- cached using page cache (NFSD_IO_BUFFERED=1)
- cached but removed from the page cache upon completion (NFSD_IO_DONTCACHE=2).
- not cached (NFSD_IO_DIRECT=3)
io_cache_read may be set by writing to:
/sys/kernel/debug/nfsd/io_cache_read
If NFSD_IO_DONTCACHE is specified using 2, FOP_DONTCACHE must be advertised as supported by the underlying filesystem (e.g. XFS), otherwise all IO flagged with RWF_DONTCACHE will fail with -EOPNOTSUPP.
If NFSD_IO_DIRECT is specified using 3, the IO must be aligned relative to the underlying block device's logical_block_size. Also the memory buffer used to store the read must be aligned relative to the underlying block device's dma_alignment.
--- fs/nfsd/debugfs.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++ fs/nfsd/nfsd.h | 9 ++++++++ fs/nfsd/vfs.c | 16 +++++++++++++ 3 files changed, 83 insertions(+)
fs/nfsd/debugfs.c +58 -0
@@ -27,11 +27,66 @@ static int nfsd_dsr_get(void *data, u64 *val)static int nfsd_dsr_set (void *data,u64 val) { nfsd_disable_splice_read = (val >0 ) ? true : false; +if (!nfsd_disable_splice_read) { +/* +* Cannot use NFSD_IO_DONTCACHE or NFSD_IO_DIRECT +* if splice_read is enabled. +*/ + nfsd_io_cache_read =NFSD_IO_BUFFERED ; + }return 0 ; }DEFINE_DEBUGFS_ATTRIBUTE (nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set,"%llu\n" ); +/* +* /sys/kernel/debug/nfsd/io_cache_read +* +* Contents: +* %1: NFS READ will use buffered IO +* %2: NFS READ will use dontcache (buffered IO w/ dropbehind) +* %3: NFS READ will use direct IO +* +* The default value of this setting is zero (UNSPECIFIED). +* This setting takes immediate effect for all NFS versions, +* all exports, and in all NFSD net namespaces. +*/ + +static int nfsd_io_cache_read_get (void *data,u64 *val) +{ + *val = nfsd_io_cache_read; +return 0 ; +} + +static int nfsd_io_cache_read_set (void *data,u64 val) +{ +int ret =0 ; + +switch (val) { +case NFSD_IO_BUFFERED : + nfsd_io_cache_read =NFSD_IO_BUFFERED ; +break ; +case NFSD_IO_DONTCACHE : +case NFSD_IO_DIRECT : +/* +* Must disable splice_read when enabling +* NFSD_IO_DONTCACHE or NFSD_IO_DIRECT. +*/ + nfsd_disable_splice_read = true; + nfsd_io_cache_read = val; +break ; +default : + nfsd_io_cache_read =NFSD_IO_UNSPECIFIED ; + ret = -EINVAL ; +break ; + } + +return ret; +} + +DEFINE_DEBUGFS_ATTRIBUTE (nfsd_io_cache_read_fops, nfsd_io_cache_read_get, + nfsd_io_cache_read_set,"%llu\n" ); +void nfsd_debugfs_exit (void ) {debugfs_remove_recursive (nfsd_top_dir);
@@ -44,4 +99,7 @@ void nfsd_debugfs_init(void)debugfs_create_file ("disable-splice-read" ,S_IWUSR |S_IRUGO , nfsd_top_dir,NULL , &nfsd_dsr_fops); + +debugfs_create_file ("io_cache_read" ,S_IWUSR |S_IRUGO , + nfsd_top_dir,NULL , &nfsd_io_cache_read_fops); }
fs/nfsd/nfsd.h +9 -0
@@ -153,6 +153,15 @@ static inline void nfsd_debugfs_exit(void) {}extern bool nfsd_disable_splice_read__read_mostly ; +enum { +NFSD_IO_UNSPECIFIED =0 , +NFSD_IO_BUFFERED , +NFSD_IO_DONTCACHE , +NFSD_IO_DIRECT , +}; + +extern u64 nfsd_io_cache_read__read_mostly ; +extern int nfsd_max_blksize;static inline int nfsd_v4client (struct svc_rqst *rq)
fs/nfsd/vfs.c +16 -0
@@ -49,6 +49,7 @@#define NFSDDBG_FACILITY NFSDDBG_FILEOPbool nfsd_disable_splice_read__read_mostly ; +u64 nfsd_io_cache_read__read_mostly ;/** * nfserrno - Map Linux errnos to NFS errnos
@@ -1115,6 +1116,21 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,trace_nfsd_read_vector (rqstp, fhp, offset, *count);iov_iter_bvec (&iter,ITER_DEST , rqstp->rq_bvec, v, *count); + +switch (nsfd_io_cache_read) { +case NFSD_IO_DIRECT : +if (nf->nf_dio_mem_align && nf->nf_dio_read_offset_align && +iov_iter_is_aligned (&iter, nf->nf_dio_mem_align -1 , + nf->nf_dio_read_offset_align -1 )) + kiocb.ki_flags =IOCB_DIRECT ; +break ; +case NFSD_IO_DONTCACHE : + kiocb.ki_flags =IOCB_DONTCACHE ; +break ; +case NFSD_IO_BUFFERED : +break ; + } + host_err =vfs_iocb_iter_read (file, &kiocb, &iter);return nfsd_finish_read (rqstp, fhp, file, offset, count, eof, host_err); }
Signature · 1 line
2.44.0
PATCH v4 4/5 NFSD: add io_cache_write controls to debugfs interface
In reply to Mike SnitzerAdd 'io_cache_write' to NFSD's debugfs interface so that: Any data written by NFSD will either be:
- cached using page cache (NFSD_IO_BUFFERED=1)
- cached but removed from the page cache upon completion (NFSD_IO_DONTCACHE=2).
- not cached (NFSD_IO_DIRECT=3)
io_cache_write may be set by writing to:
/sys/kernel/debug/nfsd/io_cache_write
If NFSD_IO_DONTCACHE is specified using 2, FOP_DONTCACHE must be advertised as supported by the underlying filesystem (e.g. XFS), otherwise all IO flagged with RWF_DONTCACHE will fail with -EOPNOTSUPP.
If NFSD_IO_DIRECT is specified using 3, the IO must be aligned relative to the underlying block device's logical_block_size. Also the memory buffer used to store the WRITE payload must be aligned relative to the underlying block device's dma_alignment.
--- fs/nfsd/debugfs.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ fs/nfsd/nfsd.h | 1 + fs/nfsd/vfs.c | 18 ++++++++++++++++++ 3 files changed, 63 insertions(+)
fs/nfsd/debugfs.c +44 -0
@@ -87,6 +87,47 @@ static int nfsd_io_cache_read_set(void *data, u64 val)DEFINE_DEBUGFS_ATTRIBUTE (nfsd_io_cache_read_fops, nfsd_io_cache_read_get, nfsd_io_cache_read_set,"%llu\n" ); +/* +* /sys/kernel/debug/nfsd/io_cache_write +* +* Contents: +* %1: NFS WRITE will use buffered IO +* %2: NFS WRITE will use dontcache (buffered IO w/ dropbehind) +* %3: NFS WRITE will use direct IO +* +* The default value of this setting is zero (UNSPECIFIED). +* This setting takes immediate effect for all NFS versions, +* all exports, and in all NFSD net namespaces. +*/ + +static int nfsd_io_cache_write_get (void *data,u64 *val) +{ + *val = nfsd_io_cache_write; +return 0 ; +} + +static int nfsd_io_cache_write_set (void *data,u64 val) +{ +int ret =0 ; + +switch (val) { +case NFSD_IO_BUFFERED : +case NFSD_IO_DONTCACHE : +case NFSD_IO_DIRECT : + nfsd_io_cache_write = val; +break ; +default : + nfsd_io_cache_write =NFSD_IO_UNSPECIFIED ; + ret = -EINVAL ; +break ; + } + +return ret; +} + +DEFINE_DEBUGFS_ATTRIBUTE (nfsd_io_cache_write_fops, nfsd_io_cache_write_get, + nfsd_io_cache_write_set,"%llu\n" ); +void nfsd_debugfs_exit (void ) {debugfs_remove_recursive (nfsd_top_dir);
@@ -102,4 +143,7 @@ void nfsd_debugfs_init(void)debugfs_create_file ("io_cache_read" ,S_IWUSR |S_IRUGO , nfsd_top_dir,NULL , &nfsd_io_cache_read_fops); + +debugfs_create_file ("io_cache_write" ,S_IWUSR |S_IRUGO , + nfsd_top_dir,NULL , &nfsd_io_cache_write_fops); }
fs/nfsd/nfsd.h +1 -0
@@ -161,6 +161,7 @@ enum { };extern u64 nfsd_io_cache_read__read_mostly ; +extern u64 nfsd_io_cache_write__read_mostly ;extern int nfsd_max_blksize;
fs/nfsd/vfs.c +18 -0
@@ -50,6 +50,7 @@bool nfsd_disable_splice_read__read_mostly ;u64 nfsd_io_cache_read__read_mostly ; +u64 nfsd_io_cache_write__read_mostly ;/** * nfserrno - Map Linux errnos to NFS errnos
@@ -1237,6 +1238,23 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, nvecs =xdr_buf_to_bvec (rqstp->rq_bvec, rqstp->rq_maxpages, payload);iov_iter_bvec (&iter,ITER_SOURCE , rqstp->rq_bvec, nvecs, *cnt); + +switch (nfsd_io_cache_write) { +case NFSD_IO_DIRECT : +/* direct I/O must be aligned to device logical sector size */ +if (nf->nf_dio_mem_align && nf->nf_dio_offset_align && + (((offset | *cnt) & (nf->nf_dio_offset_align-1 )) ==0 ) && +iov_iter_is_aligned (&iter, nf->nf_dio_mem_align -1 , + nf->nf_dio_offset_align -1 )) + kiocb.ki_flags =IOCB_DIRECT ; +break ; +case NFSD_IO_DONTCACHE : + kiocb.ki_flags =IOCB_DONTCACHE ; +break ; +case NFSD_IO_BUFFERED : +break ; + } + since =READ_ONCE (file->f_wb_err);if (verf)nfsd_copy_write_verifier (verf, nn);
Signature · 1 line
2.44.0
PATCH v4 5/5 NFSD: issue READs using O_DIRECT even if IO is misaligned
In reply to Mike SnitzerIf NFSD_IO_DIRECT is used, expand any misaligned READ to the next DIO-aligned block (on either end of the READ). The expanded READ is verified to have proper offset/len (logical_block_size) and dma_alignment checking.
Must allocate and use a bounce-buffer page (called 'start_extra_page') if/when expanding the misaligned READ requires reading extra partial page at the start of the READ so that its DIO-aligned. Otherwise that extra page at the start will make its way back to the NFS client and corruption will occur. As found, and then this fix of using an extra page verified, using the 'dt' utility:
dt of=/mnt/share1/dt_a.test passes=1 bs=47008 count=2 \
iotype=sequential pattern=iot onerr=abort oncerr=abort
see: https://github.com/RobinTMiller/dt.git
Any misaligned READ that is less than 32K won't be expanded to be DIO-aligned (this heuristic just avoids excess work, like allocating start_extra_page, for smaller IO that can generally already perform well using buffered IO).
Also add nfsd_read_vector_dio trace event. This combination of trace events is useful:
echo 1 > /sys/kernel/tracing/events/nfsd/nfsd_read_vector/enable echo 1 > /sys/kernel/tracing/events/nfsd/nfsd_read_vector_dio/enable echo 1 > /sys/kernel/tracing/events/nfsd/nfsd_read_io_done/enable echo 1 > /sys/kernel/tracing/events/xfs/xfs_file_direct_read/enable
Which for this dd command:
dd if=/mnt/share1/test of=/dev/null bs=47008 count=2 iflag=direct
Results in:
nfsd-16580 [001] ..... 5672.403130: nfsd_read_vector_dio: xid=0x5ccf019c fh_hash=0xe4dadb60 offset=0 len=47008 start=0+0 end=47104-96 nfsd-16580 [001] ..... 5672.403131: nfsd_read_vector: xid=0x5ccf019c fh_hash=0xe4dadb60 offset=0 len=47104 nfsd-16580 [001] ..... 5672.403134: xfs_file_direct_read: dev 253:0 ino 0x1c2388c1 disize 0x16f40 pos 0x0 bytecount 0xb800 nfsd-16580 [001] ..... 5672.404380: nfsd_read_io_done: xid=0x5ccf019c fh_hash=0xe4dadb60 offset=0 len=47008
nfsd-16580 [001] ..... 5672.404672: nfsd_read_vector_dio: xid=0x5dcf019c fh_hash=0xe4dadb60 offset=47008 len=47008 start=46592+416 end=94208-192 nfsd-16580 [001] ..... 5672.404672: nfsd_read_vector: xid=0x5dcf019c fh_hash=0xe4dadb60 offset=46592 len=47616 nfsd-16580 [001] ..... 5672.404673: xfs_file_direct_read: dev 253:0 ino 0x1c2388c1 disize 0x16f40 pos 0xb600 bytecount 0xba00 nfsd-16580 [001] ..... 5672.405771: nfsd_read_io_done: xid=0x5dcf019c fh_hash=0xe4dadb60 offset=47008 len=47008
--- fs/nfsd/trace.h | 37 ++++++++ fs/nfsd/vfs.c | 180 ++++++++++++++++++++++++++++++++----- include/linux/sunrpc/svc.h | 5 +- 3 files changed, 200 insertions(+), 22 deletions(-)
fs/nfsd/trace.h +37 -0
@@ -473,6 +473,43 @@ DEFINE_NFSD_IO_EVENT(write_done);DEFINE_NFSD_IO_EVENT (commit_start);DEFINE_NFSD_IO_EVENT (commit_done); +TRACE_EVENT (nfsd_read_vector_dio, + TP_PROTO(struct svc_rqst *rqstp, + struct svc_fh *fhp, + u64 offset, + u32 len, + loff_t start, + loff_t start_extra, + loff_t end, + loff_t end_extra), +TP_ARGS (rqstp, fhp, offset, len, start, start_extra, end, end_extra), +TP_STRUCT__entry ( + __field(u32, xid) + __field(u32, fh_hash) + __field(u64, offset) + __field(u32, len) + __field(loff_t, start) + __field(loff_t, start_extra) + __field(loff_t, end) +__field (loff_t, end_extra) + ), +TP_fast_assign ( + __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle); + __entry->offset = offset; + __entry->len = len; + __entry->start = start; + __entry->start_extra = start_extra; + __entry->end = end; + __entry->end_extra = end_extra; + ), +TP_printk ("xid=0x%08x fh_hash=0x%08x offset=%llu len=%u start=%llu+%llu end=%llu-%llu" , + __entry->xid, __entry->fh_hash, + __entry->offset, __entry->len, + __entry->start, __entry->start_extra, + __entry->end, __entry->end_extra) +); + DECLARE_EVENT_CLASS(nfsd_err_class, TP_PROTO(struct svc_rqst *rqstp, struct svc_fh *fhp,
fs/nfsd/vfs.c +159 -21
216 lines not on this page · raw message
include/linux/sunrpc/svc.h +4 -1
@@ -163,10 +163,13 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp);* pages, one for the request, and one for the reply. * nfsd_splice_actor() might need an extra page when a READ payload * is not page-aligned. +* nfsd_iter_read() might need two extra pages when a READ payload +* is not DIO-aligned -- but nfsd_iter_read() and nfsd_splice_actor() +* are mutually exclusive (so reuse page reserved for nfsd_splice_actor). */ static inline unsigned long svc_serv_maxpages (const struct svc_serv *serv) { -return DIV_ROUND_UP (serv->sv_max_mesg,PAGE_SIZE ) +2 +1 ; +return DIV_ROUND_UP (serv->sv_max_mesg,PAGE_SIZE ) +2 +1 +1 ; }/*
Signature · 1 line
2.44.0
[PATCH v4 6/5] NFSD: filecache: only get DIO alignment attrs if NFSD_IO_DIRECT enabled modes
In reply to Mike SnitzerAvoids needless extra fh_getattr() unless NFSD_IO_DIRECT enabled.
--- fs/nfsd/filecache.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
fs/nfsd/filecache.c +6 -2
@@ -1058,8 +1058,12 @@ nfsd_file_getattr(const struct svc_fh *fhp, struct nfsd_file *nf)struct kstat stat;__be32 status; -/* Currently only need to get DIO alignment info for regular files */ -if (!S_ISREG (inode->i_mode)) +/* Currently only need to get DIO alignment info for regular files +* IFF NFSD_IO_DIRECT is enabled for nfsd_io_cache_{read,write}. +*/ +if (!S_ISREG (inode->i_mode) || + (nfsd_io_cache_read !=NFSD_IO_DIRECT && + nfsd_io_cache_write !=NFSD_IO_DIRECT ))return nfs_ok; status =fh_getattr (fhp, &stat);
Signature · 1 line
2.43.5