Unified indirection in a multi-device hybrid storage unit

#The present disclosure relates to a multi-device platform. In particular, the present disclosure relates, by way of non-limiting example, to a multi-device platform formed of a plurality of flash storage devices and magnetic storage devices.

#Magnetic storage devices such as Hard Disk Drives (HDDs) are capable of providing a large storage capacity with low cost. However, because the HDD uses a read/write head attached to a mechanical arm to read or write data, the performance of the HDD is limited in terms of latency and access performance. Especially when the accessed file is fragmented and written across multiple sections of the magnetic disks or in the case of multiple initiators accessing the same device. Furthermore, in a HDD using shingle-written magnetic recording (SMR) technique, response time is dependent on internal operations such as garbage collection (GC). The amount of GC may vary significantly according to the availability of indirection memory. For example, when the indirection memory is almost full, the HDD requires GC. In particular, the HDD may need to perform defragmentation to reorder the writes to free up indirection memory. The latency variation caused by the decrease of indirection memory can significantly impact the performance of the service, and thereby impact the user experience.

#Flash storage devices such as Solid States Drives (SSDs) are capable of providing low latency access performance. Because the memory cells of the SSD can be accessed simultaneously, the speed at which the SSDs read or write data can be much higher than the HDDs, even if the accessed file is fragmented and written sporadically across multiple cells. However, the SSD is considerably more expensive than the HDD in terms of cost per storage capacity.

#The present disclosure is illustrated by way of example, and not by way of limitation in the figures of the accompanying drawings in which like reference numerals are used to refer to similar elements.

#FIG. 1 is a block diagram illustrating an example system of a data center using a plurality of multi-device platforms according to the techniques described herein.

#FIG. 2A is a block diagram illustrating an example logical structure of a device unit representing a multi-device platform.

#The present disclosure relates to systems and methods for implementing multi-device platforms. In particular, the systems and methods for transferring a data item with the multi-device platform and managing data placement among physical storage devices of the multi-device platform are described below. While the systems, methods of the present disclosure are described in the context of particular system architecture that uses flash storage devices and magnetic storage devices, it should be understood that the systems and methods can be applied to other architectures and organizations of hardware.

#FIG. 1 is a block diagram illustrating an example system 100 of a data center using a plurality of multi-device platforms according to the techniques described herein. As depicted, in one embodiment, the system 100 may include a network interface layer 102, a server 104, an application layer 106, a file system 108, a Host Bus Adapter (HBA)/Controller 110, and a multi-device storage layer 112. In some embodiments, the multi-device storage layer 112 may include a data storage system having multiple device units 130a . . . 130z, each device unit represents an individual multi-device platform. In this present disclosure, the multi-device platform may also be referred to as the device unit. In FIG. 1 and the remaining figures, a letter after a reference number, e.g., “130a,” represents a reference to the element having that particular reference number. A reference number in the text without a following letter, e.g., “130,” represents a general reference to instances of the element bearing that reference number. It should be recognized that the present disclosure is not limited to this configuration and a variety of different system environments and configurations can be employed. Other embodiments may include additional or fewer components.

#The network interface layer 102 is configured to connect the system 100 to a network and/or other systems (not shown). For example, network interface layer 102 may enable communication through one or more of the Internet, cable networks, wired or wireless networks using a variety of different communication protocols such as Transmission Control Protocol/Internet Protocol (TCP/IP), Hypertext Transfer Protocol (HTTP), Hypertext Transfer Protocol Secure (HTTPS), Simple Mail Transfer Protocol (SMTP), etc. In some embodiments, the network interface layer 102 may include a transceiver for sending and receiving signals using WiFi Bluetooth® or cellular communications for wireless communication. The network interface layer 102 may be coupled to other components of the system 100 (e.g., device units 130 of the multi-device storage layer 112) for distribution and/or retrieval of data files and/or media objects stored in the device units 130.