| Message ID | 1410280853-3964-3-git-send-email-hch@lst.de (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 09/09/2014 12:40 PM, Christoph Hellwig wrote: > Like all block based filesystems, the pNFS block layout driver can't read > or write at a byte granularity and thus has to perform read-modify-write > cycles on writes smaller than this granularity. > > Add a flag so that the core NFS code always reads a whole page when > starting a smaller write, so that we can do it in the place where the VFS > expects it instead of doing in very deadlock prone way in the writeback > handler. > > Note that in theory we could do less than page size reads here for disks > that have a smaller sector size which are server by a server with a smaller Nit: This should read "served by a server" :) Anna > pnfs block size. But so far that doesn't seem like a worthwhile > optimization. > > Signed-off-by: Christoph Hellwig <hch@lst.de> > --- > fs/nfs/file.c | 7 +++++++ > fs/nfs/pnfs.h | 15 +++++++++++++++ > 2 files changed, 22 insertions(+) > > diff --git a/fs/nfs/file.c b/fs/nfs/file.c > index 524dd80..05ef7dc 100644 > --- a/fs/nfs/file.c > +++ b/fs/nfs/file.c > @@ -36,6 +36,7 @@ > #include "internal.h" > #include "iostat.h" > #include "fscache.h" > +#include "pnfs.h" > > #include "nfstrace.h" > > @@ -327,6 +328,12 @@ static int nfs_want_read_modify_write(struct file *file, struct page *page, > unsigned int offset = pos & (PAGE_CACHE_SIZE - 1); > unsigned int end = offset + len; > > + if (pnfs_ld_read_whole_page(file->f_mapping->host)) { > + if (!PageUptodate(page)) > + return 1; > + return 0; > + } > + > if ((file->f_mode & FMODE_READ) && /* open for read? */ > !PageUptodate(page) && /* Uptodate? */ > !PagePrivate(page) && /* i/o request already? */ > diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h > index 8835b5a..a4c530e 100644 > --- a/fs/nfs/pnfs.h > +++ b/fs/nfs/pnfs.h > @@ -72,6 +72,7 @@ enum layoutdriver_policy_flags { > /* Should the pNFS client commit and return the layout upon a setattr */ > PNFS_LAYOUTRET_ON_SETATTR = 1 << 0, > PNFS_LAYOUTRET_ON_ERROR = 1 << 1, > + PNFS_READ_WHOLE_PAGE = 1 << 2, > }; > > struct nfs4_deviceid_node; > @@ -370,6 +371,14 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode) > } > > static inline bool > +pnfs_ld_read_whole_page(struct inode *inode) > +{ > + if (!pnfs_enabled_sb(NFS_SERVER(inode))) > + return false; > + return NFS_SERVER(inode)->pnfs_curr_ld->flags & PNFS_READ_WHOLE_PAGE; > +} > + > +static inline bool > pnfs_layoutcommit_outstanding(struct inode *inode) > { > struct nfs_inode *nfsi = NFS_I(inode); > @@ -445,6 +454,12 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode) > } > > static inline bool > +pnfs_ld_read_whole_page(struct inode *inode) > +{ > + return false; > +} > + > +static inline bool > pnfs_roc(struct inode *ino) > { > return false; -- 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/nfs/file.c b/fs/nfs/file.c index 524dd80..05ef7dc 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -36,6 +36,7 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" +#include "pnfs.h" #include "nfstrace.h" @@ -327,6 +328,12 @@ static int nfs_want_read_modify_write(struct file *file, struct page *page, unsigned int offset = pos & (PAGE_CACHE_SIZE - 1); unsigned int end = offset + len; + if (pnfs_ld_read_whole_page(file->f_mapping->host)) { + if (!PageUptodate(page)) + return 1; + return 0; + } + if ((file->f_mode & FMODE_READ) && /* open for read? */ !PageUptodate(page) && /* Uptodate? */ !PagePrivate(page) && /* i/o request already? */ diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 8835b5a..a4c530e 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -72,6 +72,7 @@ enum layoutdriver_policy_flags { /* Should the pNFS client commit and return the layout upon a setattr */ PNFS_LAYOUTRET_ON_SETATTR = 1 << 0, PNFS_LAYOUTRET_ON_ERROR = 1 << 1, + PNFS_READ_WHOLE_PAGE = 1 << 2, }; struct nfs4_deviceid_node; @@ -370,6 +371,14 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode) } static inline bool +pnfs_ld_read_whole_page(struct inode *inode) +{ + if (!pnfs_enabled_sb(NFS_SERVER(inode))) + return false; + return NFS_SERVER(inode)->pnfs_curr_ld->flags & PNFS_READ_WHOLE_PAGE; +} + +static inline bool pnfs_layoutcommit_outstanding(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); @@ -445,6 +454,12 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode) } static inline bool +pnfs_ld_read_whole_page(struct inode *inode) +{ + return false; +} + +static inline bool pnfs_roc(struct inode *ino) { return false;
Like all block based filesystems, the pNFS block layout driver can't read or write at a byte granularity and thus has to perform read-modify-write cycles on writes smaller than this granularity. Add a flag so that the core NFS code always reads a whole page when starting a smaller write, so that we can do it in the place where the VFS expects it instead of doing in very deadlock prone way in the writeback handler. Note that in theory we could do less than page size reads here for disks that have a smaller sector size which are server by a server with a smaller pnfs block size. But so far that doesn't seem like a worthwhile optimization. Signed-off-by: Christoph Hellwig <hch@lst.de> --- fs/nfs/file.c | 7 +++++++ fs/nfs/pnfs.h | 15 +++++++++++++++ 2 files changed, 22 insertions(+)