Abstract:
A battery powered computer system determines when the system is not in use by monitoring various events associated with the operation of the system. The system preferably monitors the number of cache read misses and write operations, i.e., the cache hit rate, and reduces the system clock frequency when the cache hit rate rises above a certain level. When the cache hit rate is above a certain level, then it can be assumed that the processor is executing a tight loop, such as when the processor is waiting for a key to be pressed and then the frequency can be reduced without affecting system performance. Alternatively, the apparatus monitors the occurrence of memory page misses, I/O write cycles or other events to determine the level of activity of the computer system.
Abstract:
Die Erfindung betrifft ein Verfahren und eine Vorrichtung zur Bestimmung einer Laufzeit, welche von einer Funktion eines Steuerungsprogramms für eine Steuergeräteeinheit in einem Echtzeitsystem benötigt wird, ausgeführt auf einem Zielprozessor in einer Processor-in-the-loop (PIL) Simulation, wobei das Verfahren Erstellen oder Laden eines graphischen Entwicklungsmodells der Steuergeräteeinheit in eine Entwicklungsumgebung, wobei das graphische Entwicklungsmodell Funktionalität der Steuergeräteeinheit mittels Funktionsblöcken oder Funktionssymbolen im graphischen Entwicklungsmodell abbildet; Auswählen mindestens eines Funktionsblocks oder Funktionssymbols innerhalb des graphischen Entwicklungsmodells, insbesondere Auswählen eines Funktionsblocks oder Funktionssymbols über eine graphische Benutzeroberfläche; und automatisches Generieren des Steuerungsprogramms zur Ausführung auf dem Zielprozessor entsprechend dem graphischen Entwicklungsmodell, wobei das Steuerungsprogramm die Funktion umfasst, welche die Funktionalität des ausgewählten Funktionsblocks oder Funktionssymbols abbildet, umfasst. Ferner wird ein erster Laufzeitmesspunkt assoziiert mit dem Anfang und ein zweiter Laufzeitmesspunkt assoziiert mit dem Ende der Funktion im Steuerungsprogramm, in das Steuerungsprogramm und unmittelbar vor dem ersten Laufzeitmesspunkt der für eine Ausführung der Funktion wird der verwendete Cache des Zielprozessors in einen vorbestimmten Zustand versetzt und beim Ausführen des Steuerungsprograms auf dem Zielprozessor an dem ersten und zweiten Laufzeitmesspunkten Laufzeitwerte gemessen werden, aus denen die Laufzeit bestimmt wird.
Abstract:
Described herein are mechanisms for continuous automatic tuning of code regions for optimal hardware configurations for the code regions. One mechanism automatically tunes the tunable parameters for a demarcated code region by calculating metrics while executing the code region with different sets of tunable parameters and selecting one of the different sets based on the calculated metrics.
Abstract:
A method for configuring an asynchronous Disaster Recovery (DR) process over a storage system comprising a plurality of storage sites, the method comprising: receiving data indicative of the storage sites; calculating information dispersal parameters that enable dispersing slices of DR enabling data based on original data written to a primary storage site out of the storage sites between at least two DR storage sites out of the storage sites, wherein at least one of the DR storage sites is a remote storage site, wherein each of the slices of DR enabling data is smaller than the original data and wherein the DR enabling data is larger than the original data; and configuring the asynchronous DR process in accordance with the calculated information dispersal parameters.
Abstract:
Embodiments of apparatus, computer-implemented methods, systems, devices, and computer-readable media are described herein for tracking per-virtual machine ("VM") resource usage independent of a virtual machine monitor ("VMM"). In various embodiments, a first logic unit may associate one or more virtual central processing units ("vCPUs") operated by one or more physical processing units of a computing device with a first VM of a plurality of VMs operated by the computing device, and collect data about resources used by the one or more physical processing units to operate the one or more vCPUs associated with the first VM. In various embodiments, a second logic unit of the computing device may determine resource-usage by the first VM based on the collected data. In various embodiments, the first and second logic units may perform these functions independent of a VMM of the computing device.
Abstract:
A combination of hardware and software collect profile data for asynchronous events, at code region granularity. An exemplary embodiment is directed to collecting metrics for prefetching events, which are asynchronous in nature. Instructions that belong to a code region are identified using one of several alternative techniques, causing a profile bit to be set for the instruction, as a marker. Each line of a data block that is prefetched is similarly marked. Events corresponding to the profile data being collected and resulting from instructions within the code region are then identified. Each time that one of the different types of events is identified, a corresponding counter is incremented. Following execution of the instructions within the code region, the profile data accumulated in the counters are collected, and the counters are reset for use with a new code region.
Abstract:
A storage system in an embodiment of this invention comprises a non-volatile storage area for storing write data from a host, a cache area capable of temporarily storing the write data before storing the write data in the non-volatile storage area, and a controller that determines whether to store the write data in the cache area or to store the write data in the non-volatile storage area without storing the write data in the cache area, and stores the write data in the determined area.
Abstract:
A memory access monitoring method and device are disclosed, wherein, the memory access monitoring method includes: executing coarse-grained monitoring to local memory pages, if a hot page executed by coarse-grained monitoring exists in the local memory pages, then requesting the operating system to perform an optimized migration for the content of the hot page; if a half hot page executed by coarse-grained monitoring exists in the local memory pages, then initiating the fine-grained monitoring to the half hot page; executing the fine-grained monitoring to the half hot page, and if a hot area executed by fine-grained monitoring exists in the half hot page, then requesting the operating system to perform the optimized migration for the content of the hot area. The combination of coarse-grained monitoring and fine-grained monitoring is employed in the embodiment, so as to reduce the number of counters required by memory access monitoring, which can recognize the hot area which needs to be optimized cross nodes efficiently and improve the memory access optimization efficiency in non-uniform memory access(NUMA) architecture.
Abstract:
The claimed subject matter relates to systems and/or methodologies that facilitate intelligent distribution of backup information across storage locations in network-based backup architectures. A virtual layering of backup information across storage locations in the backup architecture can be implemented. Statistical models are utilized to dynamically re-allocate backup information among storage locations and/or layers to ensure availability of data, minimum latency upon restore, and minimum bandwidth utilization upon restore. In addition, heuristics or machine learning techniques can be applied to proactively detect failures or other changes in storage locations such that backup information can be reallocated accordingly prior to a failure.