专利汇可以提供Method and apparatus for arbitrating for serial bus access专利检索,专利查询,专利分析的服务。并且In a highly available storage system, an enclosure includes first and second power supplies, and first and second controller boards. Each of the first and second controller boards includes first and second serial bus controllers. First and second serial buses are coupled to both of the first and second serial bus controllers on each of the first and second controller boards. The first serial bus is coupled to the first power supply, while the second serial bus coupled to the second power supply. The first and second serial buses are used for exchanging enclosure management and environmental information between the first and second power supplies and the first and second controller boards. The first and second serial buses are coupled to isolation switches so that redundant modules can operate if a serial bus controller fails.,下面是Method and apparatus for arbitrating for serial bus access专利的具体信息内容。
We claim:
This application is a continuation-in-part application claiming priority to application Ser. No. 10/608,635 filed Jun. 27, 2003, now U.S. Pat. No. 7,154,723.
The present invention relates generally to storage systems, and more particularly to a highly available serial bus architecture useful for enclosure management.
Today's networked computing environments are used in businesses for generating and storing large amounts of critical data. For example, banks, insurance companies, and manufacturing companies generate and store critical data related to their business and to their customers. It is therefore very important that the storage systems used for storing the critical data are highly reliable. “High Availability” storage systems employ various means for optimizing the reliability of storage systems.
High Availability systems are generally designed such that single points of failure are avoided. One means for avoiding single points of failure is to provide redundant components. For example, two processors may be provided such that if one fails, the other can assume the role of the first processor as well as its own. However, redundancy is costly and can be an inefficient use of resources.
Furthermore, when designing Highly Available systems, the failure of a component in the system can cause redundant parts of the system to fail as well. Special care must be taken to ensure that component failures do not cause cascading failures.
What is needed is a High Availability storage system that employs mechanisms for avoiding single points of failure efficiently and effectively.
In accordance one aspect of the invention, apparatus is provided including an enclosure including first and second power supplies. The enclosure also includes first and second controller boards. Each of the first and second controller boards includes first and second serial bus controllers. First and second serial buses are coupled to both of the first and second serial bus controllers on each of the first and second controller boards. The first serial bus is coupled to the first power supply, while the second serial bus coupled to the second power supply. The first and second serial buses are used for exchanging enclosure management and environmental information between the first and second power supplies and the first and second controller boards. The first and second power supplies share status information between each other, and status information related to the first power supply can be read from the second power supply via the serial bus to which the second power supply is coupled. According to a further aspect, each of the first and second power supplies includes first and second blowers, and status related to the first and second blowers is shared between the first and second power supplies. The status related to the first and second blowers in the first power supply can be read from the second power supply via the serial bus to which the second power supply is coupled. High availability is thereby maintained even though each power supply is coupled to only one serial bus.
According to another aspect of the invention, a system includes a first module including first and second serial bus controllers. A first serial bus is coupled to the first and second serial bus controllers. A second serial bus is also coupled to the first and second serial bus controllers. A second module is coupled to the first and second serial buses. First and second isolation switches on the first module are coupled to the first and second serial buses respectively. Logic on the first module causes the first and second isolation switches to open when either the first or second serial bus controller suffers a fault, such that the serial buses are isolated from the second module.
In accordance with an implementation, the logic includes a watchdog timer coupled to the first and second serial bus controllers for monitoring the first and second serial bus controllers to ascertain whether the first or second serial bus controller suffers a fault. A flip flop is coupled to the watchdog timer. The clock input of the flip-flop is driven by the watchdog timer such that when the watchdog timer ascertains that either the first or second serial bus controller has suffered a fault, the clock input of the flip-flop is asserted, causing an output of the flip-flop to be asserted. The output of the flip-flop coupled to the first and second isolation switches such that when the output of the flip-flop is asserted the first and second isolation switches open.
Furthering this aspect of the invention, the system includes third and fourth serial bus controllers on the second module. A third serial bus is coupled to the third and fourth serial bus controllers and to the first isolation switches. A fourth serial bus is also coupled to the third and fourth serial bus controllers and to the second isolation switches, such that when the logic on the first module causes the first and second isolation switches to open, the third and fourth serial buses remain functional. Moreover, third and fourth isolation switches on the second module are coupled to the third and fourth serial buses respectively. The output of the third and fourth isolation switches are coupled to outputs of the first and second isolation switches. Logic on the second module causes the third and fourth isolation switches to open when either the third or fourth serial bus controller suffers a fault, such that the first and second serial buses remain functional. The logic on the second module can be implemented with the watchdog timer and flip-flop as is done on the first module.
In accordance with another aspect of the invention, multiple serial controllers arbitrate for control of a serial bus. The arbitration utilizes redundant control lines, advantageously providing a highly available arbitration mechanism.
In order to facilitate a fuller understanding of the present invention, reference is now made to the appended drawings. These drawings should not be construed as limiting the present invention, but are intended to be exemplary only.
Referring to
In
In
Furthermore, the power supplies 32a,b are capable of exchanging status information between each other via status lines 40. For example, referring to
Though each power supply 32a,b is coupled to only a single I2C bus, high availability is maintained—that is, single points of failure are avoided. For example, if the I2C bus 38a fails, the power supply 32a is capable of collecting status information from the power supply 32b via the status lines 40. So for example if one blower fails in power supply 32a, the other power supply 32b can detect this via the blower sensor inputs 52 from the power supply 32a. The power supply 32b then causes the remaining blowers 46 to speed up. The enclosure 14 thereby remains fully functional. As a further example, the blower assembly 44 may receive a blower speed input 54 indicating that the blowers 46 should increase speed. The system advantageously minimizes the extent to which signals must be routed by utilizing the serial bus in combination with the sharing of status signals between power supplies.
In accordance with another aspect of the invention as can be seen in
As shown, each I2C controller 36a,b on each LCC 22a,b is coupled to a watchdog circuit 62. When the I2C controllers 36a,b are operating properly, they each provide a heartbeat signal 64a,b which is monitored by the watchdog circuit 62. If either I2C controller 36a,b malfunctions, it will cease to provide the heartbeat signal 64a,b. If, for example, the watchdog circuit 62 detects the absence of a heartbeat signal 64a,b from either controller 36a,b respectively on the LCC 22a, it causes the isolation switches 60 to open, thereby isolating the I2C buses 55a,b on the LCC 22a from the I2C buses 38a,b on the midplane 34 and other LCC 22b.
In
More particularly, referring to
In accordance with a further aspect of the invention, the isolation switches 60 may be opened in response to a board Reset. There may be failure modes which would cause one of the I2C buses on an LCC 22a,b to malfunction exterior to one of the controllers 36a,b. In this case, the heartbeat signals may still operate. So, it is desirable to provide a further mechanism for isolating the I2C buses 38a,b. As seen in
One skilled in the art will realize that the asynchronous logic example shown in
Further in accordance with the principles of the invention, as seen in
In accordance with a further aspect of the invention, one LCC can isolate its peer LCC from the I2C buses. For example, if LCC 22a senses, either via the I2C bus 38a,b or by other means, that its peer LCC 22b is malfunctioning, the LCC 22a can send a command via the I2C bus 38a,b to cause either controller 36a,b on the LCC 22b to cause the isolation switches 60 to open, thus isolating the LCC 22b from the buses 38a,b. More particularly, referring to
Referring back to
It should be noted that, when the system is fully operational, both LCCs 22a and 22b are capable of driving the I2C buses 38a and 38b. Thus, in accordance with another aspect of the invention, a bus arbitration mechanism is provided. In
Referring to
More particularly, the following parameters are defined:
Referring to the flow diagram of
If a controller 36a fails to gain access to the bus, then during its next attempt it will drive the control lines for a longer period of time related to the parameter “r”. This prevents bus starvation for lower designated controllers.
Referring back to step 110, if the controller checks the control lines I 00a and finds that they are low, then another device is probably using the I2C bus 38a. The controller 36a then proceeds to monitor the control signals 100a until a timeout has passed (step 120). The timeout is preferably at least as long as a maximum I2C bus cycle. If the control lines 100a go high by the end of the timeout period, the controller 36a proceeds back through the arbitration phases. If the control lines 100a do not both go high by the end of the timeout period, the controller 36a then checks to see if they are both low (step 122). If so, the bus has malfunctioned and an error state must be entered (step 124). If one control line 100a is high, then the controller 36a reports a failure of the other control line 100a (step 126) and uses the high control line 100a to proceed through the arbitration steps 110-118. The dual control signals 100a thereby provide high availability for the arbitration mechanism.
The present invention is not to be limited in scope by the specific embodiments described herein. Indeed, various modifications of the present invention, in addition to those described herein, will be apparent to those of ordinary skill in the art from the foregoing description and accompanying drawings. Thus, such modifications are intended to fall within the scope of the invention. Further, although aspects of the present invention have been described herein in the context of a particular implementation in a particular environment for a particular purpose, those of ordinary skill in the art will recognize that its usefulness is not limited thereto and that the present invention can be beneficially implemented in any number of environments for any number of purposes. For example, though the invention has been described in terms of a storage system, it is clear that the invention can be employed in any type of system wherein a highly available serial bus architecture would be useful—for example, computer systems.
标题 | 发布/更新时间 | 阅读量 |
---|---|---|
一种防误操作开关机构 | 2021-10-29 | 2 |
接地电气隔离开关 | 2023-03-29 | 1 |
高压隔离开关合闸到位的检测装置与方法 | 2021-08-10 | 2 |
轨道交通直流隔离开关 | 2022-08-15 | 1 |
一种基于WSN的变电站监控系统 | 2021-04-07 | 2 |
手车式高压断路器用水平插接隔离开关 | 2021-07-03 | 1 |
车检背景更新电路、车检雷达和车检系统 | 2020-05-31 | 1 |
机车车顶的整备机器人、作业装置及系统 | 2020-10-19 | 1 |
一种家庭电路电流监控器 | 2021-01-01 | 0 |
서지 프리 자동복구형 누전차단기 | 2020-10-07 | 0 |
高效检索全球专利专利汇是专利免费检索,专利查询,专利分析-国家发明专利查询检索分析平台,是提供专利分析,专利查询,专利检索等数据服务功能的知识产权数据服务商。
我们的产品包含105个国家的1.26亿组数据,免费查、免费专利分析。
专利汇分析报告产品可以对行业情报数据进行梳理分析,涉及维度包括行业专利基本状况分析、地域分析、技术分析、发明人分析、申请人分析、专利权人分析、失效分析、核心专利分析、法律分析、研发重点分析、企业专利处境分析、技术处境分析、专利寿命分析、企业定位分析、引证分析等超过60个分析角度,系统通过AI智能系统对图表进行解读,只需1分钟,一键生成行业专利分析报告。