SUNRPC: switchable buffer allocation
Add RPC client transport switch support for replacing buffer management
on a per-transport basis.
In the current IPv4 socket transport implementation, RPC buffers are
allocated as needed for each RPC message that is sent. Some transport
implementations may choose to use pre-allocated buffers for encoding,
sending, receiving, and unmarshalling RPC messages, however. For
transports capable of direct data placement, the buffers can be carved
out of a pre-registered area of memory rather than from a slab cache.
Test-plan:
Millions of fsx operations. Performance characterization with "sio" and
"iozone". Use oprofile and other tools to look for significant regression
in CPU utilization.
Signed-off-by: Chuck Lever <cel@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 94b0afa..8b25629 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -52,8 +52,6 @@
* RPC call state
*/
struct rpc_message tk_msg; /* RPC call info */
- __u32 * tk_buffer; /* XDR buffer */
- size_t tk_bufsize;
__u8 tk_garb_retry;
__u8 tk_cred_retry;
@@ -268,6 +266,7 @@
void rpc_wake_up_status(struct rpc_wait_queue *, int);
void rpc_delay(struct rpc_task *, unsigned long);
void * rpc_malloc(struct rpc_task *, size_t);
+void rpc_free(struct rpc_task *);
int rpciod_up(void);
void rpciod_down(void);
void rpciod_wake_up(void);