Commit Graph

6 Commits

Author SHA1 Message Date
Ronnie Sahlberg
864bf81c56 TESTS: Test that WRITESAME10/16 unmap can handle big number of logical blocks when unmapping.
If  BLockLimits->MaxWriteSameLength is 0 (no limit) or >=256
then verify that both WRITESAME10 and WRITESAME16 can unmap with a
number of blocks == 2 byte field.
If not, then verify that a 256 block unmap results in INVALID FIELD IN CDB

If  BLockLimits->MaxWriteSameLength is 0 (no limit) or >=65536
then verify that WRITESAME16 can unmap with a
number of blocks == 3 byte field.
If not, then verify that a 65536 block unmap results in INVALID FIELD IN CDB

From discussions on linux-scsi there are devices that support WRITESAME16
but where the implementation only looks at the low 2 bytes of the 4 bytes for
num-blocks in the CDB.
This added test aims to find and flag such devices.
2013-05-15 19:50:41 -07:00
Ronnie Sahlberg
8c22f8d986 TESTS: UNMAP/WRITESAME10/16 Check LBPRZ before we read the unmapped blocks and verify they are blank. 2013-05-15 17:10:20 -07:00
Ronnie Sahlberg
dd46f3acf0 TESTS: Keep the LogicalBlockProvisioning VPD around after we read it during
test startup.
2013-05-14 20:25:42 -07:00
Lee Duncan
990af4a427 Added printf format checking to logging function.
This also required changing the logging of "" at the
start of each test to appeal the otherwise-friendly
compiler.
2013-02-13 18:04:51 -08:00
Ronnie Sahlberg
aefa88b724 TESTS: Add tests that WRITESAME10/16 UNMAP will unmap until end of the device when number-of-blocks is set to 0 2013-01-27 10:32:00 -08:00
Ronnie Sahlberg
f8298d013c TESTS: Add WRITESAME10 tests to the new testsuite 2013-01-26 09:05:02 -08:00