From 9eafa8cc521b489f205bf7b0634c99e34e046606 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 20 Mar 2006 13:44:33 -0500 Subject: NFS: support EIOCBQUEUED return in direct write path For async iocb's, the NFS direct write path now returns EIOCBQUEUED, and calls aio_complete when all the requested writes are finished. The synchronous part of the NFS direct write path behaves exactly as it was before. Shared mapped NFS files will have some coherency difficulties when accessed concurrently with aio+dio. Will need to explore how this is handled in the local file system case. Test plan: aio-stress with "-O". OraSim. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'fs/nfs/direct.c') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 9d57a299824..df86e526702 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -441,8 +441,10 @@ static void nfs_direct_write_result(struct rpc_task *task, void *calldata) else atomic_set(&dreq->error, status); - if (unlikely(atomic_dec_and_test(&dreq->complete))) + if (unlikely(atomic_dec_and_test(&dreq->complete))) { + nfs_end_data_update(data->inode); nfs_direct_complete(dreq); + } } static const struct rpc_call_ops nfs_write_direct_ops = { @@ -548,8 +550,6 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz result = nfs_direct_wait(dreq); rpc_clnt_sigunmask(clnt, &oldset); - nfs_end_data_update(inode); - return result; } @@ -655,10 +655,6 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, size_t file->f_dentry->d_name.name, (unsigned long) count, (long long) pos); - retval = -EINVAL; - if (!is_sync_kiocb(iocb)) - goto out; - retval = generic_write_checks(file, &pos, &count, 0); if (retval) goto out; @@ -688,8 +684,18 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, size_t retval = nfs_direct_write(iocb, (unsigned long) buf, count, pos, pages, page_count); + + /* + * XXX: nfs_end_data_update() already ensures this file's + * cached data is subsequently invalidated. Do we really + * need to call invalidate_inode_pages2() again here? + * + * For aio writes, this invalidation will almost certainly + * occur before the writes complete. Kind of racey. + */ if (mapping->nrpages) invalidate_inode_pages2(mapping); + if (retval > 0) iocb->ki_pos = pos + retval; -- cgit v1.2.3-18-g5258