diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-22 12:55:50 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-22 12:55:50 -0700 |
commit | 7e0338c0de18c50f09aea1fbef45110cf7d64a3c (patch) | |
tree | 30a935c1f6eee7125a9fbb802a33292b1f7268fa /fs/nfsd/vfs.c | |
parent | df36b439c5fedefe013d4449cb6a50d15e2f4d70 (diff) | |
parent | 47fcb03fefee2501e79176932a4184fc24d6f8ec (diff) | |
download | linux-7e0338c0de18c50f09aea1fbef45110cf7d64a3c.tar.bz2 |
Merge branch 'for-2.6.31' of git://fieldses.org/git/linux-nfsd
* 'for-2.6.31' of git://fieldses.org/git/linux-nfsd: (60 commits)
SUNRPC: Fix the TCP server's send buffer accounting
nfsd41: Backchannel: minorversion support for the back channel
nfsd41: Backchannel: cleanup nfs4.0 callback encode routines
nfsd41: Remove ip address collision detection case
nfsd: optimise the starting of zero threads when none are running.
nfsd: don't take nfsd_mutex twice when setting number of threads.
nfsd41: sanity check client drc maxreqs
nfsd41: move channel attributes from nfsd4_session to a nfsd4_channel_attr struct
NFS: kill off complicated macro 'PROC'
sunrpc: potential memory leak in function rdma_read_xdr
nfsd: minor nfsd_vfs_write cleanup
nfsd: Pull write-gathering code out of nfsd_vfs_write
nfsd: track last inode only in use_wgather case
sunrpc: align cache_clean work's timer
nfsd: Use write gathering only with NFSv2
NFSv4: kill off complicated macro 'PROC'
NFSv4: do exact check about attribute specified
knfsd: remove unreported filehandle stats counters
knfsd: fix reply cache memory corruption
knfsd: reply cache cleanups
...
Diffstat (limited to 'fs/nfsd/vfs.c')
-rw-r--r-- | fs/nfsd/vfs.c | 93 |
1 files changed, 50 insertions, 43 deletions
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 99f835753596..4145083dcf88 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -966,6 +966,43 @@ static void kill_suid(struct dentry *dentry) mutex_unlock(&dentry->d_inode->i_mutex); } +/* + * Gathered writes: If another process is currently writing to the file, + * there's a high chance this is another nfsd (triggered by a bulk write + * from a client's biod). Rather than syncing the file with each write + * request, we sleep for 10 msec. + * + * I don't know if this roughly approximates C. Juszak's idea of + * gathered writes, but it's a nice and simple solution (IMHO), and it + * seems to work:-) + * + * Note: we do this only in the NFSv2 case, since v3 and higher have a + * better tool (separate unstable writes and commits) for solving this + * problem. + */ +static int wait_for_concurrent_writes(struct file *file) +{ + struct inode *inode = file->f_path.dentry->d_inode; + static ino_t last_ino; + static dev_t last_dev; + int err = 0; + + if (atomic_read(&inode->i_writecount) > 1 + || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) { + dprintk("nfsd: write defer %d\n", task_pid_nr(current)); + msleep(10); + dprintk("nfsd: write resume %d\n", task_pid_nr(current)); + } + + if (inode->i_state & I_DIRTY) { + dprintk("nfsd: write sync %d\n", task_pid_nr(current)); + err = nfsd_sync(file); + } + last_ino = inode->i_ino; + last_dev = inode->i_sb->s_dev; + return err; +} + static __be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, struct kvec *vec, int vlen, @@ -978,6 +1015,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, __be32 err = 0; int host_err; int stable = *stablep; + int use_wgather; #ifdef MSNFS err = nfserr_perm; @@ -996,9 +1034,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, * - the sync export option has been set, or * - the client requested O_SYNC behavior (NFSv3 feature). * - The file system doesn't support fsync(). - * When gathered writes have been configured for this volume, + * When NFSv2 gathered writes have been configured for this volume, * flushing the data to disk is handled separately below. */ + use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp); if (!file->f_op->fsync) {/* COMMIT3 cannot work */ stable = 2; @@ -1007,7 +1046,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (!EX_ISSYNC(exp)) stable = 0; - if (stable && !EX_WGATHER(exp)) { + if (stable && !use_wgather) { spin_lock(&file->f_lock); file->f_flags |= O_SYNC; spin_unlock(&file->f_lock); @@ -1017,52 +1056,20 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, oldfs = get_fs(); set_fs(KERNEL_DS); host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset); set_fs(oldfs); - if (host_err >= 0) { - *cnt = host_err; - nfsdstats.io_write += host_err; - fsnotify_modify(file->f_path.dentry); - } + if (host_err < 0) + goto out_nfserr; + *cnt = host_err; + nfsdstats.io_write += host_err; + fsnotify_modify(file->f_path.dentry); /* clear setuid/setgid flag after write */ - if (host_err >= 0 && (inode->i_mode & (S_ISUID | S_ISGID))) + if (inode->i_mode & (S_ISUID | S_ISGID)) kill_suid(dentry); - if (host_err >= 0 && stable) { - static ino_t last_ino; - static dev_t last_dev; - - /* - * Gathered writes: If another process is currently - * writing to the file, there's a high chance - * this is another nfsd (triggered by a bulk write - * from a client's biod). Rather than syncing the - * file with each write request, we sleep for 10 msec. - * - * I don't know if this roughly approximates - * C. Juszak's idea of gathered writes, but it's a - * nice and simple solution (IMHO), and it seems to - * work:-) - */ - if (EX_WGATHER(exp)) { - if (atomic_read(&inode->i_writecount) > 1 - || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) { - dprintk("nfsd: write defer %d\n", task_pid_nr(current)); - msleep(10); - dprintk("nfsd: write resume %d\n", task_pid_nr(current)); - } - - if (inode->i_state & I_DIRTY) { - dprintk("nfsd: write sync %d\n", task_pid_nr(current)); - host_err=nfsd_sync(file); - } -#if 0 - wake_up(&inode->i_wait); -#endif - } - last_ino = inode->i_ino; - last_dev = inode->i_sb->s_dev; - } + if (stable && use_wgather) + host_err = wait_for_concurrent_writes(file); +out_nfserr: dprintk("nfsd: write complete host_err=%d\n", host_err); if (host_err >= 0) err = 0; |