Default zfs_max_recordsize to 16M

Increase the default allowed maximum recordsize from 1M to 16M.
As described in the zfs(4) man page, there are significant costs
which need to be considered before using very large blocks.
However, there are scenarios where they make good sense and
it should no longer be necessary to artificially restrict their
use behind a module option.

Note that for 32-bit platforms we continue to leave this
restriction in place due to the limited virtual address space
available (256-512MB).  On these systems only a handful
of blocks could be cached at any one time severely impacting
performance and potentially stability.

Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: Alexander Motin <[email protected]>
Signed-off-by: Rich Ercolani <[email protected]>
Closes #12830
Closes #13302

man/man4/zfs.4

@@ -1469,15 +1469,15 @@ feature uses to estimate incoming log blocks.
 .It Sy zfs_max_logsm_summary_length Ns = Ns Sy 10 Pq ulong
 Maximum number of rows allowed in the summary of the spacemap log.
 .
-.It Sy zfs_max_recordsize Ns = Ns Sy 1048576 Po 1MB Pc Pq int
+.It Sy zfs_max_recordsize Ns = Ns Sy 16777216 Po 16MB Pc Pq int
 We currently support block sizes from
 .Em 512B No to Em 16MB .
 The benefits of larger blocks, and thus larger I/O,
 need to be weighed against the cost of COWing a giant block to modify one byte.
 Additionally, very large blocks can have an impact on I/O latency,
 and also potentially on the memory allocator.
-Therefore, we do not allow the recordsize to be set larger than this tunable.
-Larger blocks can be created by changing it,
+Therefore, we formerly forbade creating blocks larger than 1M.
+Larger blocks could be created by changing it,
 and pools with larger blocks can always be imported and used,
 regardless of this setting.
 .

module/zfs/dsl_dataset.c

@@ -73,12 +73,19 @@
  * The SPA supports block sizes up to 16MB.  However, very large blocks
  * can have an impact on i/o latency (e.g. tying up a spinning disk for
  * ~300ms), and also potentially on the memory allocator.  Therefore,
- * we do not allow the recordsize to be set larger than zfs_max_recordsize
- * (default 1MB).  Larger blocks can be created by changing this tunable,
- * and pools with larger blocks can always be imported and used, regardless
- * of this setting.
+ * we did not allow the recordsize to be set larger than zfs_max_recordsize
+ * (former default: 1MB).  Larger blocks could be created by changing this
+ * tunable, and pools with larger blocks could always be imported and used,
+ * regardless of this setting.
+ *
+ * We do, however, still limit it by default to 1M on x86_32, because Linux's
+ * 3/1 memory split doesn't leave much room for 16M chunks.
  */
-int zfs_max_recordsize = 1 * 1024 * 1024;
+#ifdef _ILP32
+int zfs_max_recordsize =  1 * 1024 * 1024;
+#else
+int zfs_max_recordsize = 16 * 1024 * 1024;
+#endif
 static int zfs_allow_redacted_dataset_mount = 0;
 
 #define	SWITCH64(x, y) \
@@ -4964,13 +4971,7 @@ dsl_dataset_oldest_snapshot(spa_t *spa, uint64_t head_ds, uint64_t min_txg,
 	return (0);
 }
 
-#if defined(_LP64)
-#define	RECORDSIZE_PERM ZMOD_RW
-#else
-/* Limited to 1M on 32-bit platforms due to lack of virtual address space */
-#define	RECORDSIZE_PERM ZMOD_RD
-#endif
-ZFS_MODULE_PARAM(zfs, zfs_, max_recordsize, INT, RECORDSIZE_PERM,
+ZFS_MODULE_PARAM(zfs, zfs_, max_recordsize, INT, ZMOD_RW,
 	"Max allowed record size");
 
 ZFS_MODULE_PARAM(zfs, zfs_, allow_redacted_dataset_mount, INT, ZMOD_RW,

module/zfs/zio.c

@@ -166,15 +166,6 @@ zio_init(void)
 		cflags = (zio_exclude_metadata || size > zio_buf_debug_limit) ?
 		    KMC_NODEBUG : 0;
 
-#if defined(_ILP32) && defined(_KERNEL)
-		/*
-		 * Cache size limited to 1M on 32-bit platforms until ARC
-		 * buffers no longer require virtual address space.
-		 */
-		if (size > zfs_max_recordsize)
-			break;
-#endif
-
 		while (!ISP2(p2))
 			p2 &= p2 - 1;
 

tests/zfs-tests/tests/functional/alloc_class/alloc_class_011_neg.ksh

@@ -35,7 +35,7 @@ log_must disk_setup
 log_must zpool create $TESTPOOL raidz $ZPOOL_DISKS special mirror \
 	$CLASS_DISK0 $CLASS_DISK1
 
-for value in 256 1025 2097152
+for value in 256 1025 33554432
 do
 	log_mustnot zfs set special_small_blocks=$value $TESTPOOL
 done

tests/zfs-tests/tests/functional/cli_root/zfs_create/zfs_create_008_neg.ksh

@@ -56,7 +56,7 @@ set -A args "ab" "-?" "-cV" "-Vc" "-c -V" "c" "V" "--c" "-e" "-s" \
     "-blah" "-cV 12k" "-s -cV 1P" "-sc" "-Vs 5g" "-o" "--o" "-O" "--O" \
     "-o QuOta=none" "-o quota=non" "-o quota=abcd" "-o quota=0" "-o quota=" \
     "-o ResErVaTi0n=none" "-o reserV=none" "-o reservation=abcd" "-o reserv=" \
-    "-o recorDSize=64k" "-o recordsize=2048K" "-o recordsize=2M" \
+    "-o recorDSize=64k" "-o recordsize=32768K" "-o recordsize=32M" \
     "-o recordsize=256" "-o recsize=" "-o recsize=zero" "-o recordsize=0" \
     "-o mountPoint=/tmp/tmpfile$$" "-o mountpoint=non0" "-o mountpoint=" \
     "-o mountpoint=LEGACY" "-o mounpoint=none" \

tests/zfs-tests/tests/functional/cli_root/zfs_set/zfs_set_001_neg.ksh

@@ -78,7 +78,7 @@ while (( i < ${#dataset[@]} )); do
 		(( j += 1 ))
 	done
 	# Additional recordsize
-	set_n_check_prop "2048K" "recordsize" "${dataset[i]}" false
+	set_n_check_prop "32768K" "recordsize" "${dataset[i]}" false
 	set_n_check_prop "128B" "recordsize" "${dataset[i]}" false
 	(( i += 1 ))
 done

tests/zfs-tests/tests/functional/cli_root/zpool_create/zpool_create_023_neg.ksh

@@ -52,7 +52,7 @@ log_onexit cleanup
 
 set -A args "QuOta=none" "quota=non" "quota=abcd" "quota=0" "quota=" \
     "ResErVaTi0n=none" "reserV=none" "reservation=abcd" "reserv=" \
-    "recorDSize=64k" "recordsize=2M" "recordsize=2048K" \
+    "recorDSize=64k" "recordsize=32M" "recordsize=32768K" \
     "recordsize=256" "recsize=" "recsize=zero" "recordsize=0" \
     "mountPoint=/tmp/tmpfile$$" "mountpoint=non0" "mountpoint=" \
     "mountpoint=LEGACY" "mounpoint=none" \