staging: lustre: clio: revise readahead to support 16MB IO

Read ahead currently doesn't handle 16MB RPC packets correctly
by assuming the packets are a default size instead of querying
the size. This work adjust the read ahead policy to issue
read ahead RPC by the underlying RPC size.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Signed-off-by: Gu Zheng <gzheng@ddn.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-7990
Reviewed-on: http://review.whamcloud.com/19368Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Li Xi <lixi@ddn.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: James Simmons <jsimmons@infradead.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/staging/lustre/lustre/include/cl_object.h

@@ -1452,8 +1452,10 @@ struct cl_read_ahead {
 	 * cra_end is included.
 	 */
 	pgoff_t cra_end;
+	/* optimal RPC size for this read, by pages */
+	unsigned long cra_rpc_size;
 	/*
-	 * Release routine. If readahead holds resources underneath, this
+	 * Release callback. If readahead holds resources underneath, this
 	 * function should be called to release it.
 	 */
 	void (*cra_release)(const struct lu_env *env, void *cbdata);

drivers/staging/lustre/lustre/ldlm/ldlm_lib.c

@@ -351,13 +351,11 @@ int client_obd_setup(struct obd_device *obddev, struct lustre_cfg *lcfg)
 	cli->cl_supp_cksum_types = OBD_CKSUM_CRC32;
 	atomic_set(&cli->cl_resends, OSC_DEFAULT_RESENDS);
 
-	/* This value may be reduced at connect time in
-	 * ptlrpc_connect_interpret() . We initialize it to only
-	 * 1MB until we know what the performance looks like.
-	 * In the future this should likely be increased. LU-1431
+	/*
+	 * Set it to possible maximum size. It may be reduced by ocd_brw_size
+	 * from OFD after connecting.
 	 */
-	cli->cl_max_pages_per_rpc = min_t(int, PTLRPC_MAX_BRW_PAGES,
-					  LNET_MTU >> PAGE_SHIFT);
+	cli->cl_max_pages_per_rpc = PTLRPC_MAX_BRW_PAGES;
 
 	/*
 	 * set cl_chunkbits default value to PAGE_CACHE_SHIFT,

drivers/staging/lustre/lustre/llite/llite_internal.h

@@ -281,10 +281,8 @@ static inline struct ll_inode_info *ll_i2info(struct inode *inode)
 	return container_of(inode, struct ll_inode_info, lli_vfs_inode);
 }
 
-/* default to about 40meg of readahead on a given system.  That much tied
- * up in 512k readahead requests serviced at 40ms each is about 1GB/s.
- */
-#define SBI_DEFAULT_READAHEAD_MAX (40UL << (20 - PAGE_SHIFT))
+/* default to about 64M of readahead on a given system. */
+#define SBI_DEFAULT_READAHEAD_MAX	(64UL << (20 - PAGE_SHIFT))
 
 /* default to read-ahead full files smaller than 2MB on the second read */
 #define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_SHIFT))
@@ -321,6 +319,9 @@ struct ll_ra_info {
 struct ra_io_arg {
 	unsigned long ria_start;  /* start offset of read-ahead*/
 	unsigned long ria_end;    /* end offset of read-ahead*/
+	unsigned long ria_reserved; /* reserved pages for read-ahead */
+	unsigned long ria_end_min;  /* minimum end to cover current read */
+	bool ria_eof;		    /* reach end of file */
 	/* If stride read pattern is detected, ria_stoff means where
 	 * stride read is started. Note: for normal read-ahead, the
 	 * value here is meaningless, and also it will not be accessed
@@ -550,6 +551,11 @@ struct ll_readahead_state {
 	 * PTLRPC_MAX_BRW_PAGES chunks up to ->ra_max_pages.
 	 */
 	unsigned long   ras_window_start, ras_window_len;
+	/*
+	 * Optimal RPC size. It decides how many pages will be sent
+	 * for each read-ahead.
+	 */
+	unsigned long	ras_rpc_size;
 	/*
 	 * Where next read-ahead should start at. This lies within read-ahead
 	 * window. Read-ahead window is read in pieces rather than at once

drivers/staging/lustre/lustre/osc/osc_io.c

@@ -99,6 +99,7 @@ static int osc_io_read_ahead(const struct lu_env *env,
 			ldlm_lock_decref(&lockh, dlmlock->l_req_mode);
 		}
 
+		ra->cra_rpc_size = osc_cli(osc)->cl_max_pages_per_rpc;
 		ra->cra_end = cl_index(osc2cl(osc),
 				       dlmlock->l_policy_data.l_extent.end);
 		ra->cra_release = osc_read_ahead_release;
@@ -138,7 +139,7 @@ static int osc_io_submit(const struct lu_env *env,
 
 	LASSERT(qin->pl_nr > 0);
 
-	CDEBUG(D_CACHE, "%d %d\n", qin->pl_nr, crt);
+	CDEBUG(D_CACHE | D_READA, "%d %d\n", qin->pl_nr, crt);
 
 	osc = cl2osc(ios->cis_obj);
 	cli = osc_cli(osc);