mdadm: Add --write-zeros option for Create

Add the --write-zeros option for Create which will send a write zeros
request to all the disks before assembling the array. After zeroing
the array, the disks will be in a known clean state and the initial
sync may be skipped.

Writing zeroes is best used when there is a hardware offload method
to zero the data. But even still, zeroing can take several minutes on
a large device. Because of this, all disks are zeroed in parallel using
their own forked process and a message is printed to the user. The main
process will proceed only after all the zeroing processes have completed
successfully.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Kinga Tanska <kinga.tanska@linux.intel.com>
Reviewed-by: Xiao Ni <xni@redhat.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Jes Sorensen <jes@trained-monkey.org>

1 files changed, 9 insertions, 0 deletions

diff --git a/mdadm.c b/mdadm.c
index 57e8e6f..4685ad6 100644
--- a/mdadm.c
+++ b/mdadm.c
@@ -590,6 +590,10 @@ int main(int argc, char *argv[])
 			s.assume_clean = 1;
 			continue;
 
+		case O(CREATE, WriteZeroes):
+			s.write_zeroes = 1;
+			continue;
+
 		case O(GROW,'n'):
 		case O(CREATE,'n'):
 		case O(BUILD,'n'): /* number of raid disks */
@@ -1251,6 +1255,11 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	if (s.write_zeroes && !s.assume_clean) {
+		pr_info("Disk zeroing requested, setting --assume-clean to skip resync\n");
+		s.assume_clean = 1;
+	}
+
 	if (!mode && devs_found) {
 		mode = MISC;
 		devmode = 'Q';