Hi Guys ,
I have a doubt on MDTS value of NVMe.
There are 2 scenarios:
Scenario1: I have formatted my drive to the LBA format of extended LBA i.e 512 bytes of Data size followed by 8 bytes of Metadata. So totally the LBA is 520 bytes. So,if my host tries to write with a block size of 512 bytes then the write is failing which is as expected because of the LBA size mismatch. [ Note: MDTS value for this drive is : 512 ]
Scenario 2: I have another drive which has been again formatted with the extended LBA i.e 512 bytes data size followed by 8bytes of Metadata. So, if my host issues a write with a block size of 512 bytes then this is PASSING [ Note: MDTS value in this drive is 8KB].
I dont understand this.. How does the write succeeded if the host writes with a blocksize of 512 bytes though the device is formatted with 520 bytes ??? Can somebody throw some light on this ??? i am using the "dd" command to write [eg. dd if=/dev/zero of=/dev/nvme2n1 count=1 oflag=direct ]
I have a doubt on MDTS value of NVMe.
There are 2 scenarios:
Scenario1: I have formatted my drive to the LBA format of extended LBA i.e 512 bytes of Data size followed by 8 bytes of Metadata. So totally the LBA is 520 bytes. So,if my host tries to write with a block size of 512 bytes then the write is failing which is as expected because of the LBA size mismatch. [ Note: MDTS value for this drive is : 512 ]
Scenario 2: I have another drive which has been again formatted with the extended LBA i.e 512 bytes data size followed by 8bytes of Metadata. So, if my host issues a write with a block size of 512 bytes then this is PASSING [ Note: MDTS value in this drive is 8KB].
I dont understand this.. How does the write succeeded if the host writes with a blocksize of 512 bytes though the device is formatted with 520 bytes ??? Can somebody throw some light on this ??? i am using the "dd" command to write [eg. dd if=/dev/zero of=/dev/nvme2n1 count=1 oflag=direct ]
Last edited: