Abstract: A method includes receiving, by a storage device and from a host device, a set of protocol parameters initialized by the host device. The set of protocol parameters are used to facilitate data transfer between the host device and the storage device. The method also includes determining that a threshold value associated with the data transfer between the host device and the storage device has been satisfied. The method further includes, in response to determining that the threshold value has been satisfied, sending, by the storage device and to the host device, the set of protocol parameters that were received from the host device.

Abstract: In general, techniques are described for stream management in storage devices. A storage device comprising a memory device and a processor may be configured to perform the techniques. The processor may detect a stream collision in which a host device writes a first version of a logical block (LB) to a first stream, and writes a second version of the same LB to a second stream. The processors may compare a first blockset sequence number (BSN) associated with a first collection of physical blocks referenced by the first stream to a second BSN associated with a second collection of physical blocks referenced by the second stream. Based on the comparison of the first BSN to the second BSN, the processor may write, to the mem device, the second version of the LB to the first stream.

Abstract: In general, techniques are described for stream management in storage devices. A storage device comprising a memory device and a processor may be configured to perform the techniques. The processor may detect a stream collision in which a host device writes a first version of a logical block (LB) to a first stream, and writes a second version of the same LB to a second stream. The processors may compare a first blockset sequence number (BSN) associated with a first collection of physical blocks referenced by the first stream to a second BSN associated with a second collection of physical blocks referenced by the second stream. Based on the comparison of the first BSN to the second BSN, the processor may write, to the mem device, the second version of the LB to the first stream.

Abstract: A method includes receiving, by a storage device and from a host device, a set of protocol parameters initialized by the host device. The set of protocol parameters are used to facilitate data transfer between the host device and the storage device. The method also includes determining that a threshold value associated with the data transfer between the host device and the storage device has been satisfied. The method further includes, in response to determining that the threshold value has been satisfied, sending, by the storage device and to the host device, the set of protocol parameters that were received from the host device.

Abstract: Salvaging event trace information in power loss interruption (PLI) scenarios, for use in solid-state drive (SSD) and hard disk drive (HDD) storage devices. If volatile state information that is salvaged after an inadvertent power loss were to include event trace information, then such information can provide a valuable debug resource. Event trace information from volatile memory is copied to a second memory upon a power on which is in response to a PLI event. A corrupt state of context reconstruction data stored on non-volatile memory is detected, and an indication of the corrupt state is set. The event trace information is passed to the host if requested based on the indication.

Abstract: In general, techniques of this disclosure describe usage monitoring of data partitions within a data storage device, such as a data storage device that implements elastic capacity. Techniques may be performed by a host device and a controller of a storage device, where the host device causes the controller to perform the techniques described herein. In general, the controller may create a data partition in the data storage device based on a maximum exposed logical size for the data partition, a maximum allocated logical capacity for the data partition, and an allocated physical capacity for the data partition. The controller may write one or more blocks of data to the data partition. The controller may also send an indication representative of physical space used in the data partition to a host device based on the written one or more blocks of data.

Abstract: Salvaging event trace information in power loss interruption (PLI) scenarios, for use in solid-state drive (SSD) and hard disk drive (HDD) storage devices. If volatile state information that is salvaged after an inadvertent power loss were to include event trace information, then such information can provide a valuable debug resource. Event trace information from volatile memory is copied to a second memory upon a power on which is in response to a PLI event. A corrupt state of context reconstruction data stored on non-volatile memory is detected, and an indication of the corrupt state is set. The event trace information is passed to the host if requested based on the indication.

Abstract: Multiple disk access commands such as XOR commands are broken down into their constituent read and write parts and, if in LBA sequence, coalesced into pipes. These XOR read and write commands are then provided to the RPO algorithm of the HDD for scheduling along with data reads and writes. The actual XOR buffer operation is also scheduled by the RPO algorithm, advantageously to occur during a seek for another read or write.

Abstract: An RPO algorithm in a HDD coalesces LBA-sequential XOR commands in pipes, and passes the pipes to a lower level execution engine. The execution engine executes XOR reads and write separately to optimize performance using head and/or cylinder skew information to approach the nominal disk data rate.

Abstract: Commands in a queue in a hard disk drive (HDD) are selected based on a benefit of providing either an optimized throughput or an optimized number of commands per second execution, as opposed to a simple shortest access time first (SATF) selection method.