Re: [PATCH 0/4] 2.6.21-rc7 NFS writes: fix a series of issues

[Trond Myklebust]

On Tue, 2007-04-17 at 23:07 -0500, Florin Iucha wrote:
> When 'big-copy' hangs, if I switch to a different console and run
> 'lsof', '[u]mount', or use shell completion on a network mount then that
> process goes into D state.  I cannot umount the network shares nor
> stop autofs.  I cannot do a clean reboot, I have to ssh
> in and "echo s > /proc/sysrq-trigger; echo u > /proc/sysrq-trigger;
> echo b > /proc/sysrq-trigger" .

What happens if you issue "echo 0 >/proc/sys/sunrpc/rpc_debug"?

> I am not mounting anything using CIFS, but I could give it a try.
> 
> I could transfer 75 GB without hiccup with 2.6.19 using NFS4 and CIFS,
> and with 2.6.20 using CIFS.  2.6.20 works fine under reasonably light
> load, with gnome sessions logging in and out several times a day.

How about NFSv3? I'd like to eliminate any issues with NFSv4 state.

I've also attached a little patch that I used in order to debug the list
consistency issues. Could you try it on top of the 4 I sent last night?

Cheers
  Trond


> --- Begin Message ---
> Adds consistency checks for nfs_page list operations
>
> Signed-off-by: Trond Myklebust <Trond.Myklebust@xxxxxxxxxx>
> ---
>
>  fs/nfs/write.c           |    8 ++++++--
>  include/linux/nfs_page.h |    3 +++
>  2 files changed, 9 insertions(+), 2 deletions(-)
>
> diff --git a/fs/nfs/write.c b/fs/nfs/write.c
> index cadbf3c..9be626d 100644
> --- a/fs/nfs/write.c
> +++ b/fs/nfs/write.c
> @@ -194,6 +194,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
>  	nfs_grow_file(page, offset, count);
>  	/* Set the PG_uptodate flag? */
>  	nfs_mark_uptodate(page, offset, count);
> +	WARN_ON(test_bit(PG_NEED_COMMIT,&(req)->wb_flags));
>  	nfs_unlock_request(req);
>  	return 0;
>  }
> @@ -459,6 +460,7 @@ nfs_mark_request_commit(struct nfs_page *req)
>  	struct inode *inode = req->wb_context->dentry->d_inode;
>  	struct nfs_inode *nfsi = NFS_I(inode);
>  
> +	WARN_ON(nfs_dirty_request(req));
>  	spin_lock(&nfsi->req_lock);
>  	nfs_list_add_request(req, &nfsi->commit);
>  	nfsi->ncommit++;
> @@ -552,7 +554,7 @@ static void nfs_cancel_commit_list(struct list_head *head)
>  		req = nfs_list_entry(head->next);
>  		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
>  		nfs_list_remove_request(req);
> -		clear_bit(PG_NEED_COMMIT, &(req)->wb_flags);
> +		WARN_ON(!test_and_clear_bit(PG_NEED_COMMIT,&(req)->wb_flags));
>  		nfs_inode_remove_request(req);
>  		nfs_unlock_request(req);
>  	}
> @@ -1033,6 +1035,7 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata)
>  
>  		if (nfs_write_need_commit(data)) {
>  			memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf));
> +			set_bit(PG_NEED_COMMIT,&(req)->wb_flags);
>  			nfs_mark_request_commit(req);
>  			nfs_end_page_writeback(page);
>  			dprintk(" marked for commit\n");
> @@ -1206,6 +1209,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how)
>  		nfs_list_remove_request(req);
>  		nfs_mark_request_commit(req);
>  		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
> +		WARN_ON(!test_and_clear_bit(PG_NEED_COMMIT,&(req)->wb_flags));
>  		nfs_clear_page_writeback(req);
>  	}
>  	return -ENOMEM;
> @@ -1229,7 +1233,7 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
>  	while (!list_empty(&data->pages)) {
>  		req = nfs_list_entry(data->pages.next);
>  		nfs_list_remove_request(req);
> -		clear_bit(PG_NEED_COMMIT, &(req)->wb_flags);
> +		WARN_ON(!test_and_clear_bit(PG_NEED_COMMIT,&(req)->wb_flags));
>  		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
>  
>  		dprintk("NFS: commit (%s/%Ld %d@%Ld)",
> diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
> index 41afab6..75c2d34 100644
> --- a/include/linux/nfs_page.h
> +++ b/include/linux/nfs_page.h
> @@ -116,6 +116,9 @@ nfs_lock_request(struct nfs_page *req)
>  static inline void
>  nfs_list_add_request(struct nfs_page *req, struct list_head *head)
>  {
> +	BUG_ON(!list_empty(&req->wb_list));
> +	BUG_ON(req->wb_list_head != NULL);
> +
>  	list_add_tail(&req->wb_list, head);
>  	req->wb_list_head = head;
>  }
>
> --- End Message ---