Enhance vdev layer to maintain logical and physical block sizes

cmd/zpool/zpool_main.c

@@ -1294,12 +1294,13 @@ print_status_config(zpool_handle_t *zhp, const char *name, nvlist_t *nv,
     int namewidth, int depth, boolean_t isspare)
 {
 	nvlist_t **child;
-	uint_t c, children;
+	uint_t c, vsc, children;
 	pool_scan_stat_t *ps = NULL;
 	vdev_stat_t *vs;
 	char rbuf[6], wbuf[6], cbuf[6];
 	char *vname;
 	uint64_t notpresent;
+	uint64_t ashift;
 	spare_cbdata_t cb;
 	char *state;
 
@@ -1308,7 +1309,7 @@ print_status_config(zpool_handle_t *zhp, const char *name, nvlist_t *nv,
 		children = 0;
 
 	verify(nvlist_lookup_uint64_array(nv, ZPOOL_CONFIG_VDEV_STATS,
-	    (uint64_t **)&vs, &c) == 0);
+	    (uint64_t **)&vs, &vsc) == 0);
 
 	state = zpool_state_to_name(vs->vs_state, vs->vs_aux);
 	if (isspare) {
@@ -1361,6 +1362,10 @@ print_status_config(zpool_handle_t *zhp, const char *name, nvlist_t *nv,
 			(void) printf(gettext("unsupported feature(s)"));
 			break;
 
+		case VDEV_AUX_ASHIFT_TOO_BIG:
+			(void) printf(gettext("unsupported minimum blocksize"));
+			break;
+
 		case VDEV_AUX_SPARED:
 			verify(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID,
 			    &cb.cb_guid) == 0);
@@ -1403,6 +1408,12 @@ print_status_config(zpool_handle_t *zhp, const char *name, nvlist_t *nv,
 			(void) printf(gettext("corrupted data"));
 			break;
 		}
+	} else if (children == 0 && !isspare &&
+	    VDEV_STAT_VALID(vs_physical_ashift, vsc) &&
+	    vs->vs_configured_ashift < vs->vs_physical_ashift) {
+		(void) printf(
+		    gettext("  block size: %dB configured, %dB native"),
+		    1 << vs->vs_configured_ashift, 1 << vs->vs_physical_ashift);
 	}
 
 	(void) nvlist_lookup_uint64_array(nv, ZPOOL_CONFIG_SCAN_STATS,
@@ -4322,6 +4333,15 @@ status_callback(zpool_handle_t *zhp, void *data)
 		    "'zpool clear'.\n"));
 		break;
 
+	case ZPOOL_STATUS_NON_NATIVE_ASHIFT:
+		(void) printf(gettext("status: One or more devices are "
+		    "configured to use a non-native block size.\n"
+		    "\tExpect reduced performance.\n"));
+		(void) printf(gettext("action: Replace affected devices with "
+		    "devices that support the\n\tconfigured block size, or "
+		    "migrate data to a properly configured\n\tpool.\n"));
+		break;
+
 	default:
 		/*
 		 * The remaining errors can't actually be generated, yet.

include/libzfs.h

@@ -328,6 +328,7 @@ typedef enum {
 	ZPOOL_STATUS_RESILVERING,	/* device being resilvered */
 	ZPOOL_STATUS_OFFLINE_DEV,	/* device online */
 	ZPOOL_STATUS_REMOVED_DEV,	/* removed device */
+	ZPOOL_STATUS_NON_NATIVE_ASHIFT,	/* (e.g. 512e dev with ashift of 9) */
 
 	/*
 	 * Finally, the following indicates a healthy pool.

include/linux/blkdev_compat.h

@@ -416,15 +416,21 @@ bio_set_flags_failfast(struct block_device *bdev, int *flags)
  * the logical block size interface and then the older hard sector size.
  */
 #ifdef HAVE_BDEV_PHYSICAL_BLOCK_SIZE
-# define vdev_bdev_block_size(bdev)	bdev_physical_block_size(bdev)
+# define vdev_bdev_physical_block_size(bdev)	bdev_physical_block_size(bdev)
 #else
 # ifdef HAVE_BDEV_LOGICAL_BLOCK_SIZE
-#  define vdev_bdev_block_size(bdev)	bdev_logical_block_size(bdev)
+#  define vdev_bdev_physical_block_size(bdev)	bdev_logical_block_size(bdev)
 # else
-#  define vdev_bdev_block_size(bdev)	bdev_hardsect_size(bdev)
+#  define vdev_bdev_physical_block_size(bdev)	bdev_hardsect_size(bdev)
 # endif /* HAVE_BDEV_LOGICAL_BLOCK_SIZE */
 #endif /* HAVE_BDEV_PHYSICAL_BLOCK_SIZE */
 
+#ifdef HAVE_BDEV_LOGICAL_BLOCK_SIZE
+# define vdev_bdev_logical_block_size(bdev)	bdev_logical_block_size(bdev)
+#else
+# define vdev_bdev_logical_block_size(bdev)	bdev_hardsect_size(bdev)
+#endif /* HAVE_BDEV_LOGICAL_BLOCK_SIZE */
+
 /*
  * 2.6.37 API change
  * The WRITE_FLUSH, WRITE_FUA, and WRITE_FLUSH_FUA flags have been

include/sys/fs/zfs.h

@@ -613,7 +613,8 @@ typedef enum vdev_aux {
 	VDEV_AUX_IO_FAILURE,	/* experienced I/O failure		*/
 	VDEV_AUX_BAD_LOG,	/* cannot read log chain(s)		*/
 	VDEV_AUX_EXTERNAL,	/* external diagnosis			*/
-	VDEV_AUX_SPLIT_POOL	/* vdev was split off into another pool	*/
+	VDEV_AUX_SPLIT_POOL,	/* vdev was split off into another pool	*/
+	VDEV_AUX_ASHIFT_TOO_BIG /* vdev's min block size is too large   */
 } vdev_aux_t;
 
 /*
@@ -707,8 +708,19 @@ typedef struct vdev_stat {
 	uint64_t	vs_self_healed;		/* self-healed bytes	*/
 	uint64_t	vs_scan_removing;	/* removing?	*/
 	uint64_t	vs_scan_processed;	/* scan processed bytes	*/
+	uint64_t	vs_configured_ashift;	/* TLV vdev_ashift      */
+	uint64_t	vs_logical_ashift;	/* vdev_logical_ashift  */
+	uint64_t	vs_physical_ashift;	/* vdev_physical_ashift */
 } vdev_stat_t;
 
+#ifndef        offsetof
+#define        offsetof(s, m)          ((size_t)(&(((s *)0)->m)))
+#endif
+
+#define VDEV_STAT_VALID(field, uint64_t_field_count) \
+    ((uint64_t_field_count * sizeof(uint64_t)) >= \
+     (offsetof(vdev_stat_t, field) + sizeof(((vdev_stat_t *)NULL)->field)))
+
 /*
  * DDT statistics.  Note: all fields should be 64-bit because this
  * is passed between kernel and userland as an nvlist uint64 array.

include/sys/metaslab.h

@@ -72,6 +72,7 @@ extern uint64_t metaslab_class_get_alloc(metaslab_class_t *mc);
 extern uint64_t metaslab_class_get_space(metaslab_class_t *mc);
 extern uint64_t metaslab_class_get_dspace(metaslab_class_t *mc);
 extern uint64_t metaslab_class_get_deferred(metaslab_class_t *mc);
+extern uint64_t metaslab_class_get_minblocksize(metaslab_class_t *mc);
 
 extern metaslab_group_t *metaslab_group_create(metaslab_class_t *mc,
     vdev_t *vd);

include/sys/metaslab_impl.h

@@ -49,6 +49,7 @@ struct metaslab_class {
 	uint64_t		mc_deferred;	/* total deferred frees */
 	uint64_t		mc_space;	/* total space (alloc + free) */
 	uint64_t		mc_dspace;	/* total deflated space */
+	uint64_t		mc_minblocksize;
 	kmutex_t		mc_fastwrite_lock;
 };
 

include/sys/spa.h

@@ -91,6 +91,17 @@ struct dsl_pool;
 
 #define	SPA_BLOCKSIZES		(SPA_MAXBLOCKSHIFT - SPA_MINBLOCKSHIFT + 1)
 
+/*
+ * Maximum supported logical ashift.
+ *
+ * The current 8k allocation block size limit is due to the 8k
+ * aligned/sized operations performed by vdev_probe() on
+ * vdev_label->vl_pad2.  Using another "safe region" for these tests
+ * would allow the limit to be raised to 16k, at the expense of
+ * only having 8 available uberblocks in the label area.
+ */
+#define	SPA_MAXASHIFT		13
+
 /*
  * Size of block to hold the configuration data (a packed nvlist)
  */

include/sys/vdev.h

@@ -76,6 +76,7 @@ extern void vdev_rele(vdev_t *);
 extern int vdev_metaslab_init(vdev_t *vd, uint64_t txg);
 extern void vdev_metaslab_fini(vdev_t *vd);
 extern void vdev_metaslab_set_size(vdev_t *);
+extern void vdev_ashift_optimize(vdev_t *);
 extern void vdev_expand(vdev_t *vd, uint64_t txg);
 extern void vdev_split(vdev_t *vd);
 extern void vdev_deadman(vdev_t *vd);

include/sys/vdev_impl.h

@@ -58,7 +58,7 @@ typedef struct vdev_cache_entry vdev_cache_entry_t;
  * Virtual device operations
  */
 typedef int	vdev_open_func_t(vdev_t *vd, uint64_t *size, uint64_t *max_size,
-    uint64_t *ashift);
+    uint64_t *logical_ashift, uint64_t *physical_ashift);
 typedef void	vdev_close_func_t(vdev_t *vd);
 typedef uint64_t vdev_asize_func_t(vdev_t *vd, uint64_t psize);
 typedef int	vdev_io_start_func_t(zio_t *zio);
@@ -131,6 +131,24 @@ struct vdev {
 	uint64_t	vdev_min_asize;	/* min acceptable asize		*/
 	uint64_t	vdev_max_asize;	/* max acceptable asize		*/
 	uint64_t	vdev_ashift;	/* block alignment shift	*/
+	/*
+	 * Logical block alignment shift
+	 *
+	 * The smallest sized/aligned I/O supported by the device.
+	 */
+	uint64_t        vdev_logical_ashift;
+	/*
+	 * Physical block alignment shift
+	 *
+	 * The device supports logical I/Os with vdev_logical_ashift
+	 * size/alignment, but optimum performance will be achieved by
+	 * aligning/sizing requests to vdev_physical_ashift.  Smaller
+	 * requests may be inflated or incur device level read-modify-write
+	 * operations.
+	 *
+	 * May be 0 to indicate no preference (i.e. use vdev_logical_ashift).
+         */
+	uint64_t        vdev_physical_ashift;
 	uint64_t	vdev_state;	/* see VDEV_STATE_* #defines	*/
 	uint64_t	vdev_prevstate;	/* used when reopening a vdev	*/
 	vdev_ops_t	*vdev_ops;	/* vdev operations		*/

include/sys/zio_compress.h

@@ -83,7 +83,7 @@ extern int lz4_decompress(void *src, void *dst, size_t s_len, size_t d_len,
  * Compress and decompress data if necessary.
  */
 extern size_t zio_compress_data(enum zio_compress c, void *src, void *dst,
-    size_t s_len);
+    size_t s_len, size_t minblocksize);
 extern int zio_decompress_data(enum zio_compress c, void *src, void *dst,
     size_t s_len, size_t d_len);