Efficient data transfer in remote mirroring connectivity on software-defined storage systems

Patent metadata

Field	Value
Publication number	US-10469288-B2
Application number	US-201615340091-A
Country	US
Kind code	B2
Filing date	Nov 1, 2016
Priority date	Nov 1, 2016
Publication date	Nov 5, 2019
Grant date	Nov 5, 2019

Abstract

Embodiments for network management in a Software-defined Storage (SDS) environment. Remote mirroring connectivity and data transfer is optimized in the SDS environment by establishing each of a plurality of nodes in a local storage array and a remote storage array as a gateway node. Data residing on a local gateway node is transferred directly to a remote gateway node owning the data, thereby avoiding interconnect data hops and improving datacenter network utilization.

First claim

The invention claimed is:

1. A method for network management in a Software-defined Storage (SDS) environment, by a processor, comprising:
configuring the SDS to implement a grid storage comprised of first multiple respective servers comprising a first plurality of nodes in a local storage array and second multiple respective servers comprising a second plurality of nodes at a remote storage array;
wherein data is distributed among the first and second plurality of nodes comprising the grid storage;
establishing each of the first plurality of nodes in the local storage array and the second plurality of nodes in the remote storage array as a gateway node;
wherein data residing on a local gateway node comprising any one node of the first plurality of nodes is transferred directly to a remote gateway node comprising any one node of the second plurality of nodes which owns the data, thereby avoiding interconnect data hops and improving datacenter network utilization; and
using, on the local gateway node, an agent having information of a data distribution within the remote storage array, the agent calculating, according to the data distribution, an expected location including which one of the plurality of nodes within the remote storage array the data is to be sent prior to sending the data;
wherein the calculating further includes identifying data rate limitations on ports of the first plurality of nodes, the data rate limitations including respective predetermined restrictions of bandwidth usage and an amount of the data to be sent from the local gateway node; and
wherein the local gateway node incorporates Heterogeneous System Architecture (HSA) functionality for the remote storage array.

2. The method of claim 1 , further including issuing, by a user, a request to define mirror connectivity between the local storage array and the remote storage array; and
exchanging, by each of the local storage array and the remote storage array, an Internet Protocol (IP) address with an associated port, and a module identification (ID).

3. The method of claim 2 , further including registering, by the local storage array and the remote storage array, a connection per IP address pair; wherein the connection is associated with the module ID of both the local storage array and the remote storage array.

4. The method of claim 1 , further including, upon receiving a request to transfer data, identifying, by a cache node, the local gateway node within the local storage array on which the data resides.

5. The method of claim 1 , further including periodically updating, by the agent, the information of the data distribution within the remote storage array including volume offsets and a slice table.

6. The method of claim 5 , further including using the information to identify the remote gateway node within the remote storage array owning the data.

7. A system for network management in a Software-defined Storage (SDS) environment, the system comprising:
one or more computers, each of the one or more computers having a processor, wherein the processor:
configures the SDS to implement a grid storage comprised of first multiple respective servers comprising a first plurality of nodes in a local storage array and second multiple respective servers comprising a second plurality of nodes at a remote storage array;
wherein data is distributed among the first and second plurality of nodes comprising the grid storage;
establishes each of the first plurality of nodes in the local storage array and the second plurality of nodes in the remote storage array as a gateway node;
wherein data residing on a local gateway node comprising any one node of the first plurality of nodes is transferred directly to a remote gateway node comprising any one node of the second plurality of nodes which owns the data, thereby avoiding interconnect data hops and improving datacenter network utilization; and
uses, on the local gateway node, an agent having information of a data distribution within the remote storage array, the agent calculating, according to the data distribution, an expected location including which one of the plurality of nodes within the remote storage array the data is to be sent prior to sending the data;
wherein the calculating further includes identifying data rate limitations on ports of the first plurality of nodes, the data rate limitations including respective predetermined restrictions of bandwidth usage and an amount of the data to be sent from the local gateway node; and
wherein the local gateway node incorporates Heterogeneous System Architecture (HSA) functionality for the remote storage array.

8. The system of claim 7 , wherein the processor issues, by a user, a request to define mirror connectivity between the local storage array and the remote storage array; and
exchanges, by each of the local storage array and the remote storage array, an Internet Protocol (IP) address with an associated port, and a module identification (ID).

9. The system of claim 8 , wherein the processor registers, by the local storage array and the remote storage array, a connection per IP address pair; wherein the connection is associated with the module ID of both the local storage array and the remote storage array.

10. The system of claim 7 , wherein the processor, upon receiving a request to transfer data, identifies, by a cache node, the local gateway node within the local storage array on which the data resides.

11. The system of claim 7 , wherein the processor periodically updates, by the agent, the information of the data distribution within the remote storage array including volume offsets and a slice table.

12. The system of claim 11 , wherein the processor uses the information to identify the remote gateway node within the remote storage array owning the data.

13. A computer program product for network management in a Software-defined Storage (SDS) environment, by a processor, the computer program product embodied on a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that configures the SDS to implement a grid storage comprised of first multiple respective servers comprising a first plurality of nodes in a local storage array and second multiple respective servers comprising a second plurality of nodes at a remote storage array;
wherein data is distributed among the first and second plurality of nodes comprising the grid storage;
an executable portion that establishes each of the first plurality of nodes in the local storage array and the second plurality of nodes in the remote storage array as a gateway node;
wherein data residing on a local gateway node comprising any one node of the first plurality of nodes is transferred directly to a remote gateway node comprising any one node of the second plurality of nodes which owns the data, thereby avoiding interconnect data hops and improving datacenter network utilization; and
an executable portion that uses, on the local gateway node, an agent having information of a data distribution within the remote storage array, the agent calculating, according to the data distribution, an expected location including which one of the plurality of nodes within the remote storage array the data is to be sent prior to sending the data;
wherein the calculating further includes identifying data rate limitations on ports of the first plurality of nodes, the data rate limitations including respective predetermined restrictions of bandwidth usage and an amount of the data to be sent from the local gateway node; and

Assignees

• IBM

Inventors

• Barzik Zah
• Chen Lior
• Glait Demian
• Kalaev Maxim
• Matosevich Rivka M

Classifications

• H04L45/64

  using an overlay routing layer · CPC title

• H04N21/2747

  Remote storage of video programmes received via the downstream path, e.g. from the server · CPC title

• H04L67/1097

  for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] · CPC title

• H04N21/4435

  Memory management (allocation of memory to service a request G06F9/5016; addressing or allocating within memory systems or architectures G06F12/02) · CPC title

• H04L49/356

  for storage area networks · CPC title