man: update recordsize max size info

Reflect openzfs@f2330bd
change in our man pages and add some context.

Wording is primarily copy-pasted from code comments.

Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by:  Tino Reichardt <[email protected]>
Signed-off-by: George Melikov <[email protected]>
Closes openzfs#16581

Author: gmelikov

man/man4/zfs.4

@@ -1607,6 +1607,11 @@ 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.
+.Pp
+Note that it is still limited by default to
+.Ar 1 MiB
+on x86_32, because Linux's
+3/1 memory split doesn't leave much room for 16M chunks.
 .
 .It Sy zfs_allow_redacted_dataset_mount Ns = Ns Sy 0 Ns | Ns 1 Pq int
 Allow datasets received with redacted send/receive to be mounted.

man/man7/zfsprops.7

@@ -1463,11 +1463,22 @@ and less than or equal to
 If the
 .Sy large_blocks
 feature is enabled on the pool, the size may be up to
-.Ar 1 MiB .
+.Ar 16 MiB .
 See
 .Xr zpool-features 7
 for details on ZFS feature flags.
 .Pp
+However, blocks larger than
+.Ar 1 MiB
+can have an impact on i/o latency (e.g. tying up a spinning disk for
+~300ms), and also potentially on the memory allocator.
+.Pp
+Note that maximum size is still limited by default to
+.Ar 1 MiB
+on x86_32, see
+.Sy zfs_max_recordsize
+module parameter.
+.Pp
 Changing the file system's
 .Sy recordsize
 affects only files created afterward; existing files are unaffected.