Electrical computers and digital processing systems: multicomput – Network-to-computer interfacing
Reexamination Certificate
1999-03-09
2004-05-04
Jean, Frantz B. (Department: 2155)
Electrical computers and digital processing systems: multicomput
Network-to-computer interfacing
C713S300000, C713S323000
Reexamination Certificate
active
06732190
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to the field of managing power consumption in a computer system. More specifically, the present invention relates to the management of power consumption by a network interface device (also referred to as network interface card or NIC for short).
2. Background Information
Today, most computer systems are equipped with power management features. Their constituting components are power management enabled, i.e. they include provisions through which a power management enabled operating system may put some or all of these components into low-to-no function power saving modes when the components' services are not needed. The components are brought back to the full function normal power consumption mode of operation when their services are needed again. Examples of these computer systems include ACPI compliant systems equipped with Window 95 or later (available from Microsoft Corp. of Redmond, Wash.). ACPI compliant means compliance with the Advanced Power and Configuration Interface specification, revision 1.0 or later, available from Intel Corp. of Santa Clara, Calif., a co-developer of the specification, and assignee of the present application.
Today, many computer systems are also equipped with NICs to enable the computer systems to be connectable to local, wide area or global networks, such as the Internet, via links to networking devices such as hubs or switches. For power management equipped computer systems, these NICs are equipped to operate in at least a full function normal power consumption mode, or a low function power saving consumption mode (selectably entered in response to instructions from the operating systems). Under the low function power saving consumption mode, a NIC would monitor the link for packets directed to the “host” computer system (i.e. the computer system on which the NIC is installed), where the “host” computer system should be awakened to process the packets. This low function power saving consumption mode of operation is referred to as the “packet filtering” mode of operation.
Many NICs support only one speed of operation. Thus, the link is operated at the same speed regardless of whether the NIC is operating in the full function or packet filtering mode. Historically, this was not a problem, as the power required to sustain such packet filtering mode of operation (i.e. with the link being operated at the same speed as in the full function mode of operation), was well within the power available from the interconnecting system bus under a power saving mode of operation. For example, a Ethernet NIC typically requires only 0.5 watts to operate a link in the packet filtering mode at 100 Mbps, which is well within the 1.2 watts available from an interconnecting PCI bus under a power saving mode of operation. However, with the advent of higher operating speeds for networking links, this has become a problem; as many of these NICs that support only the higher ones of these operating speeds require more power to operate in the packet filtering mode than the power available from the interconnecting buses operating under a power saving mode, e.g., in the case of a gigabit Ethernet NIC interconnected to a PCI bus. As a result, these NICs and other interconnected components cannot be placed into the low function power saving mode of operation.
This problem exists also in NICs that support multiple speeds of operation, even though the multiple speeds include the lower speeds that in and of themselves would have required power that is within the power available from the interconnecting buses. The reason is because the actual full function operating speed is dynamically negotiated between the NIC and the interconnecting hub/switch. Often times, it is the higher speeds that are selected. Once the higher speeds are negotiated, these prior art NICs operate the links at the negotiated speeds, regardless of whether they are operating in the full function mode of operation or in the packet filtering mode of operation. Thus, upon establishing one of these higher power requirement operating speeds, these multi-speed NICs are no different from the single high speed NICs, as far as power management is concerned.
Thus, an improved NIC power management technique, without some of these disadvantages of the prior art, is desired.
SUMMARY OF THE INVENTION
A notification is received for a NIC operating a link to a hub/switch in a normal mode of operation at one operating speed to enter a packet filtering mode of operation. In response, a lower power consuming operating speed is re-negotiated with the hub/switch for the NIC to operate the link in the packet filtering mode.
REFERENCES:
patent: 4680781 (1987-07-01), Amundson et al.
patent: 5371734 (1994-12-01), Fischer
patent: 6065121 (2000-05-01), Hobson et al.
patent: 6243821 (2001-06-01), Reneris
patent: 6272642 (2001-08-01), Pole, II et al.
Williams Steven D.
Zinaty Amir
Blakely , Sokoloff, Taylor & Zafman LLP
Jean Frantz B.
LandOfFree
Method and apparatus for conserving power consumed by a... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for conserving power consumed by a..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for conserving power consumed by a... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3229926