At the heart of many computer systems is the microprocessor or central processing unit (CPU) (referred to collectively as the “processor.”) The processor performs most of the actions responsible for application programs to function. The execution capabilities of the system are closely tied to the CPU: the faster the CPU can execute program instructions, the faster the system as a whole will execute.
Early processors executed instructions from relatively slow system memory, taking several clock cycles to execute a single instruction. They would read an instruction from memory, decode the instruction, perform the required activity, and write the result back to memory, all of which would take one or more clock cycles to accomplish.
As applications demanded more power from processors, internal and external cache memories were added to processors. A cache memory (hereinafter cache) is a section of very fast memory located within the processor or located external to the processor and closely coupled to the processor. Blocks of instructions or data are copied from the relatively slower system memory (DRAM) to the faster cache memory where they can be quickly accessed by the processor.
Cache memories can develop persistent errors over time, which degrade the operability and functionality of their associated CPU's. In such cases, physical removal and replacement of the failed or failing cache memory has been performed. Moreover, where the failing or failed cache memory is internal to the CPU, physical removal and replacement of the entire CPU module or chip has been performed. This removal process is generally performed by field personnel and results in greater system downtime.
Some computer systems use multiple CPUs concurrently. If a CPU fails during operation, it can cause severe problems for the applications that are running at the time of failure. Accordingly, it is desirable to determine how healthy each CPU is in order to remove unhealthy CPUs before they fail.
In one embodiment, a method for evaluating the status of a processor is provided. The method includes, for example, the steps of initializing and executing an operating system, de-allocating the processor from the available pool or system resources and performing a health-check on the processor while the operating system is executing.
The following includes definition of exemplary terms used throughout the disclosure. Both singular and plural forms of all terms fall within each meaning:
“Logic”, as used herein includes, but is not limited to, hardware, firmware, software and/or combinations of each to perform a function(s) or an action(s). For example, based on a desired application or needs, logic may include a software controlled microprocessor, discrete logic such as an application specific integrated circuit (ASIC), or other programmed logic device. Logic may also be fully embodied as software.
“Cache”, as used herein includes, but is not limited to, a buffer or a memory or section of a buffer or memory located within a processor (“CPU”) or located external to the processor and closely coupled to the processor.
“Cache element”, as used herein includes, but is not limited to, one or more sections or sub-units of a cache.
“CPU”, as used herein includes, but is not limited to, any device, structure or circuit that processes digital information including for example, data and instructions and other information. This term is also synonymous with processor and/or controller.
“Cache management logic”, as used herein includes, but is not limited to, any logic that can store, retrieve, and/or process data for exercising executive, administrative, and/or supervisory direction or control of caches or cache elements.
“During”, as used herein includes, but is not limited to, in or throughout the time or existence of; at some point in the entire time of; and/or in the course of.
Referring now to
A display 114 may be a Cathode Ray Tube, liquid crystal display or any other similar visual output device. An input device is also provided and serves as a user interface to the system. As will be described in more detail, input device may be a light sensitive panel for receiving commands from a user such as, for example, navigation of a cursor control input system. Input device interfaces with the computer system's I/O such as, for example, USB port 138. Alternatively, input device can interface with other I/O ports.
Secondary Bridge 118 is an I/O controller chipset. The secondary bridge 118 interfaces a variety of I/O or peripheral devices to CPU 102 and memory 108 via the host bridge 106. The host bridge 106 permits the CPU 102 to read data from or write data to system memory 108. Further, through host bridge 106, the CPU 102 can communicate with I/O devices on connected to the secondary bridge 118 and, and similarly, I/O devices can read data from and write data to system memory 108 via the secondary bridge 118 and host bridge 106. The host bridge 106 may have memory controller and arbiter logic (not specifically shown) to provide controlled and efficient access to system memory 108 by the various devices in computer system 100 such as CPU 102 and the various I/O devices. A suitable host bridge is, for example, a Memory Controller Hub such as the Intel® 875P Chipset described in the Intel® 82875P (MCH) Datasheet, which is hereby fully incorporated by reference.
Referring still to
The BIOS ROM 120 includes firmware that is executed by the CPU 102 and which provides low level functions, such as access to the mass storage devices connected to secondary bridge 118. The BIOS firmware also contains the instructions executed by CPU 102 to conduct System Management Interrupt (SMI) handling and Power-On-Self-Test (“POST”) 122. POST 102 is a subset of instructions contained with the BIOS ROM 102. During the boot up process, CPU 102 copies the BIOS to system memory 108 to permit faster access.
The super I/O device 128 provides various inputs and output functions. For example, the super I/O device 128 may include a serial port and a parallel port (both not shown) for connecting peripheral devices that communicate over a serial line or a parallel pathway. Super I/O device 108 may also include a memory portion 130 in which various parameters can be stored and retrieved. These parameters may be system and user specified configuration information for the computer system such as, for example, a user-defined computer set-up or the identity of bay devices. The memory portion 130 in National Semiconductor's 97338VJG is a complementary metal oxide semiconductor (“CMOS”) memory portion. Memory portion 130, however, can be located elsewhere in the system.
Referring to
The first agent chip 202 is connected to a local memory 203 and a set of CPUs 204. The local memory 203 includes DIMMS and processor dependent hardware which is the hardware need to physically connect each the local memory 203 to the specific processors or agents used. In the embodiment shown in
Each CPU in set 204 is connected to a dedicated processor interface 205 on the first agent chip 202. Each processor interface 205 may be selectively turned “on” and “off” to isolate the connected CPU from the rest of the system.
Connected to the first agent branch through the crossbar 201 is a second agent branch. The second agent branch is essentially identical to the first agent branch. The second agent branch comprises a second agent chip 206 having a local memory 207. Like local memory 203 of the first agent chip 202, local memory 207 includes DIMMS and processor dependent hardware.
The second agent chip 206 is also shown having a second set 208 of CPUs connected thereto.
The embodiment shown in
Now referring to
A health-check refers generally, but is not limited to, the monitoring, managing, handling, storing, evaluating and/or repairing of CPUs including, for example, their cache elements and/or their corresponding cache element errors. Health-check logic can be divided up into different programs, routines, applications, software, firmware, circuitry and algorithms such that different parts of the health-check logic can be stored and run from various different locations within the computer system 100. For example, health-check logic may be included in the operating system 110. In other words, the implementation of the health-check logic can vary.
The health-check logic begins, while the operating system on the computer is executing, by de-allocating a CPU from the available pool of system resources (step 301). The selection process can be random or performed at some appropriate configurable frequency. The de-allocated CPU is then subjected to a health-check (step 302). A health-check generally refers to any type of testing done to determine whether the CPU is operating properly. If, following the health-check, the health-check logic determines that the CPU is healthy (i.e. performing properly), the CPU is re-allocated into the available pool of system resources (step 303).
Now referring to
After selecting a CPU for a health-check, the health-check logic de-allocates the CPU from the operating system and the available pool of system resources (step 401). The health-check logic may optionally de-allocate the dedicated processor interface 205, 209 corresponding to the selected CPU. Additionally, if the computer system 100 has a spare CPU that is available, the spare CPU may be logically inserted by the health-check logic for the de-allocated CPU if there is a need to maintain a constant number of CPUs in the available pool of system resources during the health-check.
After de-allocating the selected CPU from the pool of system resources, the health-check logic obtains control over the de-allocated CPU. A health-check is then performed on the de-allocated CPU (step 402). The health-check begins by having the health-check logic read the CPU error logs. The health-check logic reads all errors contained in the CPU error logs. These include but is not limited to, for example, errors caused by an illegal snoop response, parity bit errors, hard fails, unexpected delays, read errors, write errors, ECC errors, cache data errors, cache tag errors, and bus errors. Sometimes, the cause of the error is based on the cache element itself mishandling information or operating improperly when called upon to store/recall information. These types of errors are referred to generally as cache element errors or cache errors. The read error logs are stored in a memory and are then cleared from the CPU. After having the CPU's error logs cleared, the health-check logic tests the CPU.
The testing may be done by starting the CPU BIST (Built-In Self-Test) engines or by having the health-check logic run worst-case tests on the CPU. If the CPU BIST engines are used, the health-check logic programmatically starts the BIST engine. Generally, the CPU BIST engines are only started during a system boot-up. However, since the CPU has been de-allocated, the health-check logic may start the CPU BIST engines while the computer system 100 is up and running its operating system. Alternatively, the health-check logic runs designed tests or worst-case tests to determine if the CPU is operating properly. The type of test run may vary and may be generic or specially designed for the specific CPU.
After the testing procedure is completed, the CPU's error logs are again read by the health-check logic to determine if any error occurred during testing (step 403). Testing may be considered completed after a predetermined amount of time or after the test program reports that it is completed. If after reading the CPU's error logs following testing there are no errors in the CPU's error logs, the health-check logic assumes that the CPU is healthy and subsequently reports and records that a health-check has been performed on the CPU and that the CPU is operating properly. The CPU is then re-allocated and returned to the available pool of system resources (step 403).
However, if errors are found in the error logs of the CPU following testing, the health-check logic concludes that the CPU is not performing properly (a faulty CPU). The health-check logic reports that errors were found. Furthermore, the health-check logic reports the error codes found in the error logs and which cache elements incurred the error and thus need to be replaced. The health-check logic may then attempt to repair the cache elements within the CPU that caused the errors (step 405). The repair process is described in further detail below with respect to
The health-check logic then determines if the cache element repair performed successfully (step 406). As described in further detail with respect to
Referring to
Within each cache area 502, 503, 504, 505 are at least two subsets of elements. For example,
As such, the CPU 501 begins with a number of data cache elements 506 that have passed the wafer test and are currently used by the CPU. In other words, the data cache elements 506 that passed the wafer test are initially presumed to be operating properly and are thus initially used or allocated by the CPU 501. Similarly, the CPU 501 begins with a number of spare or non-allocated cache elements 507 that have passed the wafer test and are initially not used, but are available to be swapped in for data cache elements 306 that become faulty.
Also included in the CPU 501 is core logic 512. The CPU 501 may be connected to additional memory through an interface. The interface allows the CPU 501 to communicate with and share information with other memory in the computer system 100.
When the CPU contains errors following health-check testing, the health-check logic may attempt to repair the specific cache elements which are causing the errors (faulty cache elements). Essentially, the health-check logic may “swap in” a spare cache element (non-allocated cache element) for a faulty cache element. “Swapping in” refers generally to the reconfiguration and re-allocation within the computer system 100 and its memory such that the computer system 100 recognizes and utilizes a spare (or swapped in) component in place of the faulty (or de-allocated) component, and no longer utilizes the faulty (or de-allocated) component. The “swapping in” process for cache elements may be accomplished, for example, by using associative addressing. More specifically, each spare cache element has an associative addressing register and a valid bit associated with it. To repair a faulty cache element, the address of the faulty cache element is entered into the associative address register on one of the spare cache elements, and the valid bit is turned on. The hardware may then automatically access the replaced element rather than the original cache element.
Referring to
The repair process then determines whether a spare (non-allocated) cache element is available to be swapped in for the fault cache element (step 602). In making this determination, the logic may utilize any spare cache element 507 that is available. In other words, there is no predetermined or pre-allocated spare cache element 507 for a particular cache element 506. Any available spare cache element 507 may be swapped in for any cache element 506 that becomes faulty. If a spare cache element is available, the spare cache element is swapped in for the faulty cache element (step 603). A spare cache element may be swapped in for a previously swapped in spare cache element that has become faulty. Hereinafter, such swapping refers to any process by which the spare cache element is mapped for having data stored therein or read therefrom in place of the faulty cache element. In one embodiment, this can be accomplished by de-allocating the faulty cache element and allocating the spare cache element in its place.
Once the spare cache element has been swapped in for the faulty cache element, the cache configuration is updated in a memory at step 604. Once updated, the repair process reports that the cache element repair was successful (step 605) and returns (step 606) to step 406.
If, however, it is determined at step 602 that a spare cache element is not available, the repair process reports that the cache element repair was unsuccessful (step 607) and returns (step 606) to step 406.
The repair process may be performed while the operating system in the computer is executing. Since the CPU is de-allocated, no applications running on the operating system will be affected by the cache element repair process. Alternatively, the repair process may be performed during a system reboot. In that case, once the repair process determines that a spare cache element is available (step 602), a system reboot is scheduled and generated. During the reboot procedure, the remaining steps (603-606) may be carried out and the repaired CPU may be re-allocated to the available pool of system resources following system reboot.
While the present invention has been illustrated by the description of embodiments thereof, and while the embodiments have been described in considerable detail, it is not the intention of the applicants to restrict or in any way limit the scope of the appended claims to such detail. Additional advantages and modifications will readily appear to those skilled in the art. For example, the number of spare cache elements, spare CPUs, and the definition of a faulty cache or memory can be changed. Therefore, the inventive concept, in its broader aspects, is not limited to the specific details, the representative apparatus, and illustrative examples shown and described. Accordingly, departures may be made from such details without departing from the spirit or scope of the applicant's general inventive concept.
This application claims priority from U.S. Provisional application Ser. No. 60/654,273 filed on Feb. 18, 2005. This application is also related to the following US patent applications: “Systems and Methods for CPU Repair”, Ser. No. 60/254,741, filed Feb. 18, 2005, and Ser. No. 60/654,741, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,259, filed Feb. 18, 2005, and Ser. No. 60/654,259, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,255, filed Feb. 18, 2005, and Ser. No. 60/654,255, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,272, filed Feb. 18, 2005, and Ser. No. 60/654,272, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,256, filed Feb. 18, 2005, and Ser. No. 60/654,256, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,740, filed Feb. 18, 2005, and Ser. No. 60/654,740, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,739, filed Feb. 18, 2005, and Ser. No. 60/254,739, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,258, filed Feb. 18, 2005, and Ser. No. 60/654,258, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,744, filed Feb. 18, 2005, and Ser. No. 60/654,744, filed Feb. 18, 2005 having the same title; “Systems and Methods for CPU Repair”, Ser. No. 60/254,743, filed Feb. 18, 2005, and Ser. No. 60/654,743, filed Feb. 18, 2005 having the same title; and “Methods and Systems for Conducting Processor Health-Checks”, Ser. No. 60/254,203, filed Feb. 18, 2005, and Ser. No. 60/654,603, filed Feb. 18, 2005 having the same title; which are fully incorporated herein by reference.
Number | Name | Date | Kind |
---|---|---|---|
4684885 | Chapman et al. | Aug 1987 | A |
5649090 | Edwards | Jul 1997 | A |
5954435 | Yoshida | Sep 1999 | A |
5961653 | Kalter | Oct 1999 | A |
6006311 | Arimilli | Dec 1999 | A |
6181614 | Aipperspach | Jan 2001 | B1 |
6363506 | Karri et al. | Mar 2002 | B1 |
6425094 | Drogichen et al. | Jul 2002 | B1 |
6516429 | Bossen | Feb 2003 | B1 |
6651182 | Chang et al. | Nov 2003 | B1 |
6654707 | Wynn et al. | Nov 2003 | B2 |
6708294 | Nakao | Mar 2004 | B1 |
6789048 | Arndt | Sep 2004 | B2 |
6922798 | Nemani | Jul 2005 | B2 |
6954851 | Natu | Oct 2005 | B2 |
6973604 | Davis | Dec 2005 | B2 |
6985826 | Pomaranski et al. | Jan 2006 | B2 |
7007210 | Fields, Jr. | Feb 2006 | B2 |
7047466 | Meaney | May 2006 | B2 |
7058782 | Henderson | Jun 2006 | B2 |
7117388 | Arimilli et al. | Oct 2006 | B2 |
7134057 | Kaushik | Nov 2006 | B1 |
7155637 | Jarboe, Jr. | Dec 2006 | B2 |
7155645 | Korhonen | Dec 2006 | B1 |
7321986 | Ash | Jan 2008 | B2 |
7350119 | Zuraski Jr. | Mar 2008 | B1 |
7409600 | Azevedo | Aug 2008 | B2 |
7415644 | Bower, III | Aug 2008 | B2 |
7418367 | Pomaranski et al. | Aug 2008 | B2 |
20030074598 | Bossen et al. | Apr 2003 | A1 |
20030212884 | Lee | Nov 2003 | A1 |
20040133826 | Zhu | Jul 2004 | A1 |
20040143776 | Cox | Jul 2004 | A1 |
20040221193 | Armstrong | Nov 2004 | A1 |
20050096875 | Pomaranski et al. | May 2005 | A1 |
20060080572 | Fong | Apr 2006 | A1 |
20060248394 | McGowan | Nov 2006 | A1 |
20080235454 | Duron | Sep 2008 | A1 |
20080263394 | Tanabe | Oct 2008 | A1 |
Number | Date | Country | |
---|---|---|---|
20060230307 A1 | Oct 2006 | US |
Number | Date | Country | |
---|---|---|---|
60654273 | Feb 2005 | US |