Multi-partition networking device and method therefor
View Patent ↗A multi-partition networking device comprising a primary partition running on a first set of hardware resources and a secondary partition running on a further set of hardware resources. The multi-partition networking device is arranged to operate in a first operating state, whereby the first set of hardware resources are in an active state and the primary partition is arranged to process network traffic, and the further set of hardware resources are in a standby state. The multi-partition networking device is further arranged to transition to a second operating state upon detection of a suspicious condition within the primary partition, whereby the further set of hardware resources are transitioned from a standby state to an active state, and to transition to a third operating state upon detection of a failure condition within the primary partition, whereby processing of network traffic is transferred to the secondary partition.
1. A multi-partition networking device comprising at least one primary partition running on a first set of hardware resources and at least one secondary partition running on at least one further set of hardware resources; wherein the multi-partition networking device is arranged to:
operate in a first operating state, whereby the first set of hardware resources are in an active state and the primary partition is arranged to process network traffic and the at least one further set of hardware resources are in a standby state;
transition to a second operating state upon detection of a suspicious condition within the primary partition, whereby the at least one further set of hardware resources are transitioned from a standby state to an active state;
transition to a third operating state upon detection of a failure condition within the primary partition, whereby processing of network traffic is transferred to the secondary partition; and
the multi-partition networking device further comprising;
a management module, the management module arranged to detect the occurrence of at least one suspicious condition within the primary partition, and to cause the multi-partition networking device to transition to the second operating state upon detection of the at least one suspicious condition within the primary partition; and
a network sub-module arranged to:
detect when an occupancy level for at least one buffer pool for received network traffic exceeds a threshold; and
output to the management module a buffer pool threshold exceeded indication, upon detection of an occupancy level for the at least one buffer pool exceeding the threshold.
2. The multi-partition networking device of claim 1 , wherein the management module is further arranged to detect the occurrence of at least one failure condition within the primary partition, and to cause the multi-partition networking device to transition to the third operating state, upon detection of the at least one failure condition within the primary partition.
3. The multi-partition networking device of claim 1 , wherein the management module is further arranged to cause the multi-partition networking device to transition to the first operating state, upon detection of a resume condition.
4. The multi-partition networking device of claim 1 , wherein a suspicious condition comprises at least one from a group comprising at least one of:
an occupancy level of at least one buffer pool for received network traffic exceeding a threshold level;
inactivity within at least one transmission queue;
inactivity within at least one task queue;
a watchdog timer expiration; and
an indication of a hardware resource going out of normal state.
5. The multi-partition networking device of claim 1 , wherein a failure condition comprises at least one from a group comprising at least one of:
a watchdog timer expiration;
an indication of a hardware failure; and
an indication of a non-correctable ECC fault.
6. The multi-partition networking device of claim 1 , wherein transitioning the at least one further set of hardware resources from a standby state to an active state comprises loading a current context for the primary partition into the secondary partition.
7. The multi-partition networking device of claim 1 , wherein transitioning the at least one further set of hardware resources from a standby state to an active state comprises powering up at least a part of the at least one further set of hardware resources.
8. The multi-partition networking device of claim 1 implemented within an integrated circuit device comprising at least one die within a single integrated circuit package.
9. The multi-partition networking device of claim 2 , wherein the management module is further arranged to cause the multi-partition networking device to transition to the first operating state, upon detection of a resume condition.
10. The multi-partition networking device of claim 2 , wherein multi-partition networking device comprises at least one network sub-module arranged to:
detect when an occupancy level for at least one buffer pool for received network traffic exceeds a threshold; and
output to the management module a buffer pool threshold exceeded indication, upon detection of an occupancy level for the at least one buffer pool exceeding the threshold.
11. The multi-partition networking device of claim 3 , wherein multi-partition networking device comprises at least one network sub-module arranged to:
detect when an occupancy level for at least one buffer pool for received network traffic exceeds a threshold; and
output to the management module a buffer pool threshold exceeded indication, upon detection of an occupancy level for the at least one buffer pool exceeding the threshold.
12. A method of managing a multi-partition networking system comprising at least one primary partition running on a first set of hardware resources and at least one secondary partition running on at least one further set of hardware resources; the method comprising:
configuring the multi-partition networking system to operate in a first operating state, whereby the first set of hardware resources are in an active state and the primary partition is arranged to process network traffic and the at least one further set of hardware resources are in a standby state;
causing the multi-partition networking system to transition to a second operating state upon detection of a suspicious condition within the primary partition, whereby the at least one further set of hardware resources are transitioned from a standby state to an active state;
causing the multi-partition networking system to transition to a third operating state upon detection of a failure condition within the primary partition, whereby processing of network traffic is transferred to the secondary partition; and
detecting when an occupancy level for at least one buffer pool for received network traffic exceeds a threshold; and
determining the occurrence of the suspicious condition within the primary partition upon detection of an occupancy level for the at least one buffer pool exceeding the threshold.
13. A non-transitory computer program product having executable program code stored therein for managing a multi-partition networking system comprising at least one primary partition running on a first set of hardware resources and at least one secondary partition running on at least one further set of hardware resources, the program code operable for:
configuring the multi-partition networking system to operate in a first operating state, whereby the first set of hardware resources are in an active state and the primary partition is arranged to process network traffic and the at least one further set of hardware resources are in a standby state;
causing the multi-partition networking system to transition to a second operating state upon detection of a suspicious condition within the primary partition, whereby the at least one further set of hardware resources are transitioned from a standby state to an active state;
causing the multi-partition networking system to transition to a third operating state upon detection of a failure condition within the primary partition, whereby processing of network traffic is transferred to the secondary partition;
detecting when an occupancy level for at least one buffer pool for received network traffic exceeds a threshold; and
determining the occurrence of the suspicious condition within the primary partition upon detection of an occupancy level for the at least one buffer pool exceeding the threshold.
14. The non-transitory computer program product of claim 13 , wherein the non-transitory computer program product comprises at least one from a group including: a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a Read Only Memory, ROM, a Programmable Read Only Memory, PROM, an Erasable Programmable Read Only Memory, EPROM, an Electrically Erasable Programmable Read Only Memory, EEPROM, and a Flash memory.