I'm going over the write code carefully preparing for wave4, and came
across some code I traced to this patch.
Why is this needed? Why doesn't the pg_bsize check in
nfs_pageio_do_add_request() prevent this from ever being invoked?
Fred
On Sat, Feb 20, 2010 at 4:06 PM, Benny Halevy <[email protected]> wrote:
> We coalesce pages based on the strip size that may be bigger
> than the server can handle in one write (and even exceed the
> maximum RPC message size on the server)
>
> Signed-off-by: Benny Halevy <[email protected]>
> ---
> ?fs/nfs/nfs4proc.c ? ? ? | ? ?7 +++++++
> ?fs/nfs/write.c ? ? ? ? ?| ? ?8 ++++++++
> ?include/linux/nfs_xdr.h | ? ?1 +
> ?3 files changed, 16 insertions(+), 0 deletions(-)
>
> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
> index 8132a96..93b1963 100644
> --- a/fs/nfs/nfs4proc.c
> +++ b/fs/nfs/nfs4proc.c
> @@ -3180,6 +3180,13 @@ static int pnfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
> ? ? ? ?struct nfs_client *client = mds_svr->nfs_client;
> ? ? ? ?int status = task->tk_status >= 0 ? 0 : task->tk_status;
>
> + ? ? ? /* restore original count after retry? */
> + ? ? ? if (data->pdata.orig_count) {
> + ? ? ? ? ? ? ? dprintk("%s: restoring original count %u\n", __func__,
> + ? ? ? ? ? ? ? ? ? ? ? data->pdata.orig_count);
> + ? ? ? ? ? ? ? data->args.count = data->pdata.orig_count;
> + ? ? ? }
> +
> ? ? ? ?if (data->pdata.pnfsflags & PNFS_NO_RPC)
> ? ? ? ? ? ? ? ?return 0;
>
> diff --git a/fs/nfs/write.c b/fs/nfs/write.c
> index 90ce78e..fee6f00 100644
> --- a/fs/nfs/write.c
> +++ b/fs/nfs/write.c
> @@ -1108,6 +1108,14 @@ void nfs_write_prepare(struct rpc_task *task, void *calldata)
> ?#ifdef CONFIG_PNFS
> ? ? ? ?if (data->fldata.ds_nfs_client)
> ? ? ? ? ? ? ? ?clp = data->fldata.ds_nfs_client;
> + ? ? ? else if (data->args.count > NFS_SERVER(data->inode)->wsize) {
> + ? ? ? ? ? ? ? /* retrying via MDS? */
> + ? ? ? ? ? ? ? data->pdata.orig_count = data->args.count;
> + ? ? ? ? ? ? ? data->args.count = NFS_SERVER(data->inode)->wsize;
> + ? ? ? ? ? ? ? dprintk("%s: trimmed count %u to wsize %u\n", __func__,
> + ? ? ? ? ? ? ? ? ? ? ? data->pdata.orig_count, data->args.count);
> + ? ? ? } else
> + ? ? ? ? ? ? ? data->pdata.orig_count = 0;
> ?#endif /* CONFIG_PNFS */
>
> ? ? ? ?if (nfs4_setup_sequence(clp, &data->args.seq_args,
> diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
> index efc4ca0..13ccd48 100644
> --- a/include/linux/nfs_xdr.h
> +++ b/include/linux/nfs_xdr.h
> @@ -970,6 +970,7 @@ struct nfs_page;
> ?struct pnfs_call_data {
> ? ? ? ?struct pnfs_layout_segment *lseg;
> ? ? ? ?const struct rpc_call_ops *call_ops;
> + ? ? ? u32 ? ? ? ? ? ? ? ? ? ? orig_count; ? ? /* for retry via MDS */
> ? ? ? ?int ? ? ? ? ? ? ? ? ? ? pnfs_error;
> ? ? ? ?u8 ? ? ? ? ? ? ? ? ? ? ?pnfsflags;
> ? ? ? ?u8 ? ? ? ? ? ? ? ? ? ? ?how; ? ? ? ? ? ?/* for FLUSH_STABLE */
> --
> 1.6.4.4
>
> _______________________________________________
> pNFS mailing list
> [email protected]
> http://linux-nfs.org/cgi-bin/mailman/listinfo/pnfs
>
On 2011-01-20 07:20, Fred Isaman wrote:
> I'm going over the write code carefully preparing for wave4, and came
> across some code I traced to this patch.
>
> Why is this needed? Why doesn't the pg_bsize check in
> nfs_pageio_do_add_request() prevent this from ever being invoked?
Apparently this got squashed in too early.
It's actually needed only after
"pnfs: Introduce pnfs_call_done and io done callbacks"
which is post pnfs-submit.
Benny
>
> Fred
>
> On Sat, Feb 20, 2010 at 4:06 PM, Benny Halevy <[email protected]> wrote:
>> We coalesce pages based on the strip size that may be bigger
>> than the server can handle in one write (and even exceed the
>> maximum RPC message size on the server)
>>
>> Signed-off-by: Benny Halevy <[email protected]>
>> ---
>> fs/nfs/nfs4proc.c | 7 +++++++
>> fs/nfs/write.c | 8 ++++++++
>> include/linux/nfs_xdr.h | 1 +
>> 3 files changed, 16 insertions(+), 0 deletions(-)
>>
>> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
>> index 8132a96..93b1963 100644
>> --- a/fs/nfs/nfs4proc.c
>> +++ b/fs/nfs/nfs4proc.c
>> @@ -3180,6 +3180,13 @@ static int pnfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
>> struct nfs_client *client = mds_svr->nfs_client;
>> int status = task->tk_status >= 0 ? 0 : task->tk_status;
>>
>> + /* restore original count after retry? */
>> + if (data->pdata.orig_count) {
>> + dprintk("%s: restoring original count %u\n", __func__,
>> + data->pdata.orig_count);
>> + data->args.count = data->pdata.orig_count;
>> + }
>> +
>> if (data->pdata.pnfsflags & PNFS_NO_RPC)
>> return 0;
>>
>> diff --git a/fs/nfs/write.c b/fs/nfs/write.c
>> index 90ce78e..fee6f00 100644
>> --- a/fs/nfs/write.c
>> +++ b/fs/nfs/write.c
>> @@ -1108,6 +1108,14 @@ void nfs_write_prepare(struct rpc_task *task, void *calldata)
>> #ifdef CONFIG_PNFS
>> if (data->fldata.ds_nfs_client)
>> clp = data->fldata.ds_nfs_client;
>> + else if (data->args.count > NFS_SERVER(data->inode)->wsize) {
>> + /* retrying via MDS? */
>> + data->pdata.orig_count = data->args.count;
>> + data->args.count = NFS_SERVER(data->inode)->wsize;
>> + dprintk("%s: trimmed count %u to wsize %u\n", __func__,
>> + data->pdata.orig_count, data->args.count);
>> + } else
>> + data->pdata.orig_count = 0;
>> #endif /* CONFIG_PNFS */
>>
>> if (nfs4_setup_sequence(clp, &data->args.seq_args,
>> diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
>> index efc4ca0..13ccd48 100644
>> --- a/include/linux/nfs_xdr.h
>> +++ b/include/linux/nfs_xdr.h
>> @@ -970,6 +970,7 @@ struct nfs_page;
>> struct pnfs_call_data {
>> struct pnfs_layout_segment *lseg;
>> const struct rpc_call_ops *call_ops;
>> + u32 orig_count; /* for retry via MDS */
>> int pnfs_error;
>> u8 pnfsflags;
>> u8 how; /* for FLUSH_STABLE */
>> --
>> 1.6.4.4
>>
>> _______________________________________________
>> pNFS mailing list
>> [email protected]
>> http://linux-nfs.org/cgi-bin/mailman/listinfo/pnfs
>>