Wisconsin Alumni Research Foundation

Emc Corporation

University of Washington

Michael Mansfield Swift

Mark Donald Hill

Arkaprava Basu

Ari Juels

Kevin Bowers

David Allen Wood

Michael Roger Marty

Abhishek Rajimwale

Brian N Bershad

Benjamin Tillman Farley

Andrea C Arpaci-Dusseau

Remzi H Arpaci-Dusseau

Sujay Yadalam Sudarshan

Jayaram Bobba

Venkatanathan Varadarajan

Haris Volos

Thomas Ristenpart

Hank Levy

Swaminathan Sundararaman

Sriram Subramanian

Luke Yen

Jayneel Gandhi

Kevin E Moore

An I/O memory management unit operates to provide hardware moderated restrictions on access to internal I/O device addresses of I/O devices eliminating the interposition of the operating system in such data transfers. As well as providing read/write permissions, the I/O memory management unit can perform address translation for virtualization and may be the combined with the functions of an IOMMU for managing physical addresses.

Storage I/O management unit for solid-state drives

The translation of virtual guest addresses to host physical addresses in a virtualized computer system provides a compound page table that may simultaneously support nested-paging and shadow-paging for different memory regions. Memory regions with stable address mapping, for example, holding program code, may be treated using shadow-paging while memory regions with dynamic address mapping, for example, variable storage, may be treated using nested-paging thereby obtaining the benefits of both techniques.

Efficient memory management system for computers supporting virtual machines

A memory management unit for I/O devices uses page table entries to translate virtual addresses to physical addresses. The page table entries include removal rules allowing the I/O memory management unit to delete page table entries without CPU involvement significantly reducing the CPU overhead involved in virtualized I/O data transactions.

I/O memory management unit providing self invalidated mapping

A computer system using virtual memory provides hybrid memory access either through a conventional translation between virtual memory and physical memory using a page table possibly with a translation lookaside buffer, or a high-speed translation using a fixed offset value between virtual memory and physical memory. Selection between these modes of access may be encoded into the address space of virtual memory eliminating the need for a separate tagging operation of specific memory addresses.

Virtual memory management system with reduced latency

A method includes the step of running a set of instances on at least one cloud for a first time interval, each of the instances comprising a bundle of virtualized resources. The method also includes the step of evaluating one or more performance characteristics of each of the instances in the set of instances over the first time interval. The method further includes the step of determining a first subset of the set of instances to maintain for a second time interval and a second subset of the set of instances to terminate for the second time interval responsive to the evaluating step. The steps are performed by at least one processing device comprising a processor coupled to a memory.

Determining instances to maintain on at least one cloud responsive to an evaluation of performance characteristics

In general, techniques are described for enabling a restartable file system. A computing device comprising a processor that executes an operating system may implement the techniques. The processor executes kernel and file system functions of the operating system to perform an operation, where both types of functions call each other to perform the operation. The operating system stores data identifying those of the kernel functions that called the file system functions. In response to determining that one of the file system functions that was called has failed, the operating system accesses the data to identify one of the kernel functions that most recently called one of the file system functions, and returns control to the identified one of the kernel functions without executing any of the file system functions called after the identified one of the kernel functions and prior to the one of the file system functions that failed.

Providing restartable file systems within computing devices

A coherence controller in hardware of an apparatus in an example detects conflicts on coherence requests through direct, non-broadcast employment of signatures that: summarize read-sets and write-sets of memory transactions; and provide false positives but no false negatives for the conflicts on the coherence requests. The signatures comprise fixed-size representations of a substantially arbitrary set of addresses for the read-sets and the write-sets of the memory transactions.

Non-broadcast signature-based transactional memory

A solution to the problem of maintaining application integrity when device drivers fail. This solution employs a new mechanism, the shadow driver, which is an operating system (OS) kernel agent that monitors communication between the OS kernel and the device driver it 'shadows.' When a device driver error occurs, the shadow driver acts in place of the failed device driver, intercepting and responding to calls from the OS kernel and the device driver during cleanup, unloading, reloading, and re-initialization of the failed device driver. Applications and the OS kernel are thus isolated from the failure. An initial embodiment was developed for use with the Linux&#x2122; OS and was tested with a dozen device drivers. Results demonstrate that shadow drivers successfully mask device driver failures from applications, impose minimal performance overhead, require no changes to existing applications and device drivers, and can be implemented with relatively little code.

Recovering device drivers

Growing community of inventors

Madison, WI, United States of America

Michael Mansfield Swift