Patent Application
20070073947
The present invention relates to computer systems; more particularly, the present invention relates to computer system interaction with storage devices.
Serial attached storage protocols, such as serial ATA (SATA) and serial Small Computer System Interface (SCSI) (SAS) are becoming more prevalent for connecting storage devices to a computer system. In computer systems implementing such serial storage devices, one storage device in the system may communicate with others. For example, a device requesting data (referred to as the initiator device) may receive data from a target device.
Typically, communication between the devices may occur after an identification sequence and the establishing of connections between the devices. In a typical SAS serial SCSI (SSP) target controller when write data is transferred from a receive buffer to the target device and data corruption detected (uncorrectable memory error etc), the target device will send a bad response frame to the initiator device. Upon receiving the bad response frame, the initiator device retries to transmit the entire I/O write command. For large I/O transactions (e.g., 2 GB-4 GB), having to re-transmit the entire data write command is time consuming and impracticable.
The invention is illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements, and in which:
A mechanism for handling uncorrectable write data errors is described. In the following detailed description of the present invention numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the present invention.
Reference in the specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. The appearances of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment.
In a further embodiment, a chipset 107 is also coupled to interface 105. Chipset 107 includes a memory control hub (MCH) 110. MCH 110 may include a memory controller 112 that is coupled to a main system memory 115. Main system memory 115 stores data and sequences of instructions that are executed by CPU 102 or any other device included in system 100. In one embodiment, main system memory 115 includes dynamic random access memory (DRAM); however, main system memory 115 may be implemented using other memory types. Additional devices may also be coupled to interface 105, such as multiple CPUs and/or multiple system memories.
MCH 110 is coupled to an input/output control hub (ICH) 140 via a hub interface. ICH 140 provides an interface to input/output (I/O) devices within computer system 100. ICH 140 may support standard I/O operations on I/O busses such as peripheral component interconnect (PCI), accelerated graphics port (AGP), universal serial bus (USB), low pin count (LPC) bus, or any other kind of I/O bus (not shown).
According to one embodiment, ICH 140 includes a host bus adapter (HBA) 144. HBA 144 serves as a controller implemented to control access to one or more hard storage devices 150. In such an embodiment, HBA 144 operates as a serial attached SCSI (SAS) device coupled to one or more additional SAS devices. In a further embodiment, hard disk drive 150 is a serial SCSI (SSP) drive. However in other embodiments, storage device 150 may be implemented using other serial protocols.
As discussed above communication may occur between SAS devices upon establishing a connection between an initiator device such as HBA 144 and target device such as hard drive 150. As previously discussed, HBA 144 as the initiator device may be coupled to multiple serial drive devices via different ports.
Whenever write data is to be transferred between an initiator device and a target device an uncorrectable data error may occur. Specifically, when data is to be transferred from a receive buffer at the SSP target controller to the SAS target device and data corruption detected, the target controller will send a bad response frame to the initiator device.
In many instances the write command may indicate that the amount of data to be transferred to the target device from the initiator device (e.g., 3 MB) may be greater than the data size that can be handled by the target device at one time (e.g., 1.5 MB). Thus, the write data is to be transferred in two or more segments. Consequently, at time t3, the initiator port receives a transfer ready (XFER_RDY (A)) signal indicating that the target port is ready to receive a first segment of data from the initiator port. Following an Ack to the target port at time t4, the initiator transfers the first segment of data at time t5. At time t6, the data is forwarded from the target port to the SAS target device, followed by Acks from the target port to the initiator port at time t7.
At time t8, the initiator port receives another transfer ready (XFER_RDY (B)) signal indicating that the target port is ready to receive the second segment of data from the initiator port. Following an Ack at time t9, the initiator transfers the second segment of data at time t10. At time till, the data is forwarded from the target port to the SAS target device.
However, this time data corruption is detected while the data is transferred from the target port to the target device. After Acks transmitted from the target port to the initiator port at time t12, a Bad Response frame is transmitted to the initiator port from the target port at time t13 indicating an uncorrectable error is detected.
Following an Ack at t14, a FW error handling routine is executed. In response, the initiator port typically proceeds to execute the entire write command from the beginning of the sequence at t1. Thus, both the first segment and second segment of data is to be transferred although an error occurred only in the transfer of the second segment. As discussed above, having to re-transmit the entire data write command is very time consuming.
According to one embodiment, a transport layer retry mechanism is implemented to eliminate the FW process of having to retransmit an entire write command when an error occurred at a data segment after previous segments have been successfully transferred. In such an embodiment, both the initiator port and the target port are configured to support transport layer retry. Further, the initiator port includes a control module to facilitate the transport layer retry mechanism. In one embodiment, the control module includes control bits that are used to enable transport layer retry if a data transmission error occurs.
Subsequently, the initiator port retransmits all of the write data for XFER_RDY (B). From times t14-t19, the process for transmitting the second segment of data from the initiator port to the target port and the target device is implemented. Therefore, the time of having to resend the first segment of data has been saved.
Whereas many alterations and modifications of the present invention will no doubt become apparent to a person of ordinary skill in the art after having read the foregoing description, it is to be understood that any particular embodiment shown and described by way of illustration is in no way intended to be considered limiting. Therefore, references to details of various embodiments are not intended to limit the scope of the claims, which in themselves recite only those features regarded as essential to the invention.
