Supercharge message exchanger
View Patent ↗A system with a first random access memory (RAM), a second RAM, a first processor coupled to the first RAM and a second processor coupled to the second RAM. The first RAM is configured to store input/output (I/O) completions from at least two engines. The second RAM is also configured to store I/O completions from at least two engines. When all engines are active, the system writes I/O completions from the engines to the first and second RAMs. The first processor processes I/O completions stored in the first RAM. The second processor processes I/O completions stored in the second RAM.
1. A storage network interface comprising:
a first protocol engine coupled to transmit and receive data from a first port on a storage network;
a second protocol engine coupled to transmit and receive data from a second port;
first and second physically distinct processors having coordination connections therebetween and coupled to the first and second protocol engines for controlling a transfer of data through the first and second ports; and
a random access memory (RAM) communicatively coupled to the first and second protocol engines and the first and second processors for storing I/O completion notices from the first and second protocol engines as a first step in the transfer of data, the I/O completion notices being accessible by either the first processor or the second processor;
wherein the first and second processors are configured to read the I/O completion notices from the RAM as a second step in the transfer of data through the first and second ports.
2. The storage network interface as recited in claim 1 , the coordination connections comprising doorbell registers for enabling communications between the first and second processors.
3. The storage network interface as recited in claim 1 , the coordination connections allowing for exchanging messages that enable communications between the first and second processors.
4. The storage network interface as recited in claim 3 , wherein a message sent by the first processor notifies the second processor that an Input/Output (I/O) operation has completed and to prepare for a next processing stage.
5. The storage network interface as recited in claim 1 , wherein the second port comprises a host bus interface for connecting to a host computer.
6. The storage network interface as recited in claim 1 , wherein the first and second protocol engines provide for Direct Memory Access (DMA) data transfer without involvement of a host processor.
7. The storage network interface as recited in claim 1 located on a single chip.
8. A host bus adapter (HBA) comprising the storage network interface of claim 1 .
9. A server comprising the host bus adapter (HBA) of claim 8 .
10. A storage area network (SAN) comprising the server of claim 9 .
11. A method for providing a storage network interface, comprising:
transmitting and receiving data from a first port on a storage network using a first protocol engine;
transmitting and receiving data from a second port using a second protocol engine;
coordinating operations between first and second physically distinct processors using coordination connections between the first and second processors, the operations including controlling a transfer of data through the first and second ports;
storing I/O completion notices from the first and second protocol engines in a random access memory (RAM) as a first step in the transfer of data, the RAM being communicatively coupled to the first and second protocol engines and the first and second processors, the I/O completion notices being accessible by either the first processor or the second processor ; and
reading the I/O completion notices from the RAM by the first and second processors as a second step in the transfer of data through the first and second ports.
12. The method as recited in claim 11 , further comprising utilizing doorbell registers to coordinate the operations between the first and second processors.
13. The method as recited in claim 11 , further comprising exchanging messages to coordinate the operations between the first and second processors.
14. The method as recited in claim 13 , further comprising sending a message from the first processor to notify the second processor that an Input/Output (I/O) operation has completed and to prepare for a next processing stage.
15. The method as recited in claim 11 , wherein the second port comprises a host bus interface for connecting to a host computer.
16. The method as recited in claim 11 , wherein the first and second protocol engines provide for Direct Memory Access (DMA) data transfer without involvement of a host processor.