US 11,144,416 B2Granted

Device fault processing method, apparatus, and system

AssigneeHuawei Technologies Co., Ltd.

InventorsHuixiong Zhu, Wei Liu

Life of this patent

Estimating the term…

Loading patent…

Abstract

A device fault processing method is used to perform fault processing on a peripheral component interconnect express device. The method includes: obtaining, by the controller, first device fault information after detecting that the device is faulty, where the first device fault information is used to indicate that the device is faulty, the first device fault information includes a first value of a fault processing state parameter of the device, and the first value indicates that the device is in a soft reset state; and performing, by the controller, hot reset processing on the device, so as to implement fault processing on the peripheral component interconnect express device without manual intervention in plugging out and plugging in or resetting a pluggable unit in which the peripheral component interconnect express device is located and without manual resetting on a computer system.

Claims17

Dependent claims

A device fault processing method performed by a controller, wherein the device is a peripheral component interconnect express device, comprising:

obtaining first device fault information, wherein the first device fault information is used to indicate that the device is faulty, the first device fault information comprises a first value of a fault processing state parameter of the device, and the first value indicates that the device is in a soft reset state;
performing hot reset processing on the device based on the first value;
and after the performing of the hot reset processing on the device, the method further comprises:
obtaining second device fault information, wherein the second device fault information is used to indicate that the device is faulty, the second device fault information comprises a second value of the fault processing state parameter of the device, and the second value indicates that the device is in a hard reset state;
and
performing cold reset processing on the device based on the second value,
the performing of the cold reset processing on the device comprising:
sending a power-off instruction to a resetter, wherein the power-off instruction is used to instruct the resetter to power off the device;
and
after detecting that the device is powered off, sending a power-on instruction to the resetter, wherein the power-on instruction is used to instruct the resetter to power on the device.

7 more elements

A device fault processing apparatus configured to perform fault processing on a peripheral component interconnect express device, comprising:

a memory configured to store instructions;
and
a processor coupled to the memory and configured to execute the instructions to:
obtain first device fault information, wherein the first device fault information is used to indicate that the device is faulty, the first device fault information comprises a first value of a fault processing state parameter of the device, and the first value indicates that the device is in a soft reset state;
send a first reset instruction to a resetter to instruct the resetter to perform hot reset processing on the device based on the first value, and, in response to an indication that the device is faulty, modify a connection parameter of the device to obtain a modified connection parameter of the device, wherein the connection parameter of the device indicates a state of connection between the device and an upstream communications device of the device, and the modified connection parameter of the device indicates that the device and the upstream communications device of the device are not connected.

2 more elements

A device fault processing system, comprising:

a device fault processing apparatus and a resetter connected to the device fault processing apparatus, the device fault processing apparatus configured to perform fault processing on a peripheral component interconnect express device;
the device fault processing apparatus is further configured to:
after obtaining first device fault information, send a first reset instruction to the resetter based on a first value that is of a fault processing state parameter of the device and that is comprised in the first device fault information to instruct the resetter to perform hot reset processing on the device, wherein the first device fault information is used to indicate that the device is faulty, and the first value of the fault processing state parameter of the device indicates that the device is in a soft reset state;
and
the resetter is configured to perform the hot reset processing on the device after receiving the first reset instruction,
wherein the resetter comprises a reset monitoring chip and a hot reset control module, and the reset monitoring chip is connected to the hot reset control module;
the reset monitoring chip is configured to send a reset signal to the hot reset control module after receiving the first reset instruction;
and
the hot reset control module is configured to send a reset notification to the device after receiving the reset signal, to instruct the device to perform the hot reset processing.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/903,483Filed 17 Jun 2020 · continuation
Priority: CN 201711452816.828 Dec 2017
Published: US 2020/0310933 A11 Oct 2020
Granted: 12 Oct 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G06F 11/2221
Using arrangements specific to the hardware being tested: to test input/output devices or peripheral units
G06F 1/24
Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00: resetting means
G06F 11/0751
Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of…
G06F 11/0775
Error or fault reporting or storing: content or structure details of the error report, e.g. specific table structure, specific error fields