Abstract: To generate a checkpoint for a virtual machine (VM), first, while the VM is still running, a copy-on-write (COW) disk file is created pointing to a parent disk file that the VM is using. Next, the VM is stopped, the VM's memory is marked COW, the device state of the VM is saved to memory, the VM is switched to use the COW disk file, and the VM begins running again for substantially the remainder of the checkpoint generation. Next, the device state that was stored in memory and the unmodified VM memory pages are saved to a checkpoint file. Also, a copy may be made of the parent disk file for retention as part of the checkpoint, or the original parent disk file may be retained as part of the checkpoint. If a copy of the parent disk file was made, then the COW disk file may be committed to the original parent disk file.

Abstract: Techniques for using commit coalescing when performing micro-journal-based transaction logging are provided. In one embodiment a computer system can maintain, in a volatile memory, a globally ascending identifier, a first list of free micro-journals, and a second list of in-flight micro-journals. The computer system can further receive a transaction comprising a plurality of modifications to data or metadata stored in the byte-addressable persistent memory, select a micro-journal from the first list, obtain a lock on the globally ascending identifier, write a current value of the globally ascending identifier as a journal commit identifier into a header of the micro-journal, and write journal entries into the micro-journal corresponding to the plurality of modifications included in the transaction. The computer system can then commit the micro-journal to the byte-addressable persistent memory, increment the current value of the globally ascending identifier, and release the lock.

Abstract: A module for rewriting application code as a failure-atomic transaction is disclosed. An application delineates a code fragment that is to become a failure-atomic transaction by writing a tx_begin( ) and tx_end( ) functions into its code. A module detects the tx_begin( ) and tx_end( ) functions and rewrites the code fragment as a failure-atomic transaction. The rewritten code is then available to be executed by the application. The rewritten code stores values and locations of stores to persistent memory locations so that the transaction can be either undone or redone in the case of an application error or a power failure. If the transaction is an undo type of transaction, the application can be rolled back to a state prior to the failure. If the transaction is a redo type of transaction, the application can be advanced to a correct state after the error.

Abstract: Disclosed are embodiments for running an application on a local processor when the application is dependent on pages not locally present but contained in a remote host. The system is informed that the pages on which the application depends are locally present. While running, the application encounters a cache miss and a cache line satisfying the miss from the remote host is obtained and provided to the application. Alternatively, the page containing the cache line satisfying the miss is obtained and the portion of the page not including the cache line is stored locally while the cache line is provided to the application. The cache miss is discovered by monitoring coherence events on a coherence interconnect connected to the local processor. In some embodiments, the cache misses are tracked and provide a way to predict a set of pages to be pre-fetched in anticipation of the next cache misses.

Abstract: A module for rewriting application code as a failure-atomic transaction is disclosed. An application delineates a code fragment that is to become a failure-atomic transaction by writing a tx_begin( ) and tx_end( ) functions into its code. A module detects the tx_begin( ) and tx_end( ) functions and rewrites the code fragment as a failure-atomic transaction. The rewritten code is then available to be executed by the application. The rewritten code stores values and locations of stores to persistent memory locations so that the transaction can be either undone or redone in the case of an application error or a power failure. If the transaction is an undo type of transaction, the application can be rolled back to a state prior to the failure. If the transaction is a redo type of transaction, the application can be advanced to a correct state after the error.

Abstract: Described herein is a method for tracking changes to memory locations made by an application. In one embodiment, the application decides to start tracking and sends a list of virtual memory pages to be tracked to an operating system via an interface. The operating system converts the list of virtual memory pages to a list of physical addresses and sends the list of physical addresses to a hardware unit which performs the tracking by detecting write backs on a coherence interconnect coupled to the hardware unit. After the application ends tracking, the application requests a list of dirty cache lines. In response to the request, the operating system obtains the list of dirty cache lines from the hardware unit and adds the list to a buffer that the application can read. In other embodiments, the operating system can perform the tracking without the application making the request.

Abstract: Disclosed is a technique in which an application can record changes it makes to physical memory. In the technique, the application specifies a virtual memory region which is converted to a plurality of cache lines, each of which is monitored for changes by a device connected to a coherence interconnect coupled to the processor caches. The application sends a start signal to start the logging process and an end signal to stop the process. During the logging process, when a change occurs to one of the cache lines, an undo entry corresponding to the change is created and entered into a transaction log residing in persistent memory. The transaction log containing the undo entries makes the set of changes recorded in the transaction log atomic. If a failure occurs, the recorded changes can be undone as if they never occurred.

Abstract: Described herein is a method for tracking changes made by an application. Embodiments include determining, by a processor, a write-back of a cache line from a hardware unit associated with a socket of a plurality of sockets to a page table entry of a page table in a memory location associated with the processor. Embodiments include adding, by the processor, the cache line to a list of dirty cache lines. Embodiments include, for each respective cache line in the list of dirty cache lines, identifying, by the processor, a memory location associated with a respective socket of the plurality of sockets corresponding to the respective cache line and updating, by the processor, an entry of a page table replica at the memory location based on the respective cache line.

Abstract: Exemplary methods, apparatuses, and systems include a distributed memory agent within a first node intercepting an operating system request to open a file from an application running on the first node. The request includes a file identifier, which the distributed memory agent transmits to a remote memory manager. The distributed memory agent receives, from the remote memory manager, a memory location within a second node for the file identifier and information to establish a remote direct memory access channel between the first node and the second node. In response to the request to open the file, the distributed memory agent establishes the remote direct memory access channel between the first node and the second node. The remote direct memory access channel allows the first node to read directly from or write directly to the memory location within the second node while bypassing an operating system of the second node.

Abstract: Techniques for virtualizing NVDIMM WPQ flushing with minimal overhead are provided. In one set of embodiments, a hypervisor of a computer system can allocate a virtual flush hint address (FHA) for a virtual machine (VM), where the virtual flush hint address is associated with one or more physical FHAs corresponding to one or more physical memory controllers of the computer system. The hypervisor can further determine whether one or more physical NVDIMMs of the computer system support WPQ flushing. If so, the hypervisor can write protect a guest physical address (GPA) to host physical address (HPA) mapping for the virtual FHA in the page tables of the computer system, thereby enabling the hypervisor to trap VM writes to the virtual FHA and propagate those write to the physical FHAs of the system.

Abstract: Techniques for implementing high availability for persistent memory are provided. In one embodiment, a first computer system can detect an alternating current (AC) power loss/cycle event and, in response to the event, can save data in a persistent memory of the first computer system to a memory or storage device that is remote from the first computer system and is accessible by a second computer system. The first computer system can then generate a signal for the second computer system subsequently to initiating or completing the save process, thereby allowing the second computer system to restore the saved data from the memory or storage device into its own persistent memory.

Abstract: Techniques for implementing OS/hypervisor-based persistent memory are provided. In one embodiment, an OS or hypervisor running on a computer system can allocate a portion of the volatile memory of the computer system as a persistent memory allocation. The OS/hypervisor can further receive a signal from the computer system's BIOS indicating an AC power loss or cycle event and, in response to the signal, can save data in the persistent memory allocation to a nonvolatile backing store. Then, upon restoration of AC power to the computer system, the OS/hypervisor can restore the saved data from the nonvolatile backing store to the persistent memory allocation.

Abstract: Disclosed are embodiments for migrating a virtual machine (VM) from a source host to a destination host while the virtual machine is running on the destination host. The system includes an RDMA facility connected between the source and destination hosts and a device coupled to a local memory, the local memory being responsible for memory pages of the VM instead of the source host. The device is configured to copy pages of the VM to the destination host and to maintain correct operation of the VM by monitoring coherence events, such as a cache miss, caused by the virtual machine running on the destination host. The device services these cache misses using the RDMA facility and copies the cache line satisfying the cache miss to the CPU running the VM. The device also tracks the cache misses to create an access pattern that it uses to predict future cache misses.

Abstract: Disclosed is a method for performing write-back operations to maintain coherence of remote memories in a memory pool. When a local application makes a request for a page of memory that is in the memory pool but not local, a device obtains the page through its RDMA facility and thereafter keeps track of the page for any changes made by the application to the page by storing the page locally and monitoring cache coherency events of cache lines that make up the page. If a requested page become dirty, then periodically the dirty cache lines of the dirty page are written back to the remote memory from which the pages were obtained. In addition, all dirty cache lines are written back when the local memory storing the page becomes full or the application closes a region containing the page.

Abstract: A virtual machine running on a source host is live migrated to a destination host. The source host includes a first processing node with a first processing hardware and a first memory, and a second processing node with a second processing hardware and a second memory. While the virtual machine is running on the first processing hardware, the second processing hardware tracks cache lines of the first processing hardware that become dirty as a result of write operations performed on one or more memory pages of the virtual machine. The dirty cache lines are copied to the destination host in units of a cache line or groups of cache lines.

Abstract: A device is connected via a coherence interconnect to a CPU with a cache. The device monitors cache coherence events via the coherence interconnect, where the cache coherence events relate to the cache of the CPU. The device also includes a buffer that can contain representations, such as addresses, of cache lines. If a coherence event occurs on the coherence interconnect indicating that a cache line in the CPU's cache is dirty, then the device is configured to add an entry to the buffer to record the dirty cache line.

Abstract: Disclosed are embodiments for running an application on a local processor when the application is dependent on pages not locally present but contained in a remote host. The system is informed that the pages on which the application depends are locally present. While running, the application encounters a cache miss and a cache line satisfying the miss from the remote host is obtained and provided to the application. Alternatively, the page containing the cache line satisfying the miss is obtained and the portion of the page not including the cache line is stored locally while the cache line is provided to the application. The cache miss is discovered by monitoring coherence events on a coherence interconnect connected to the local processor. In some embodiments, the cache misses are tracked and provide a way to predict a set of pages to be pre-fetched in anticipation of the next cache misses.

Abstract: A provisioning server automatically configures a virtual machine (VM) according to user specifications and then deploys the VM on a physical host. The user may either choose from a list of pre-configured, ready-to-deploy VMs, or he may select which hardware, operating system and application(s) he would like the VM to have. The provisioning server then configures the VM accordingly, if the desired configuration is available, or it applies heuristics to configure a VM that best matches the user's request if it isn't. The invention also includes mechanisms for monitoring the status of VMs and hosts, for migrating VMs between hosts, and for creating a network of VMs.

Abstract: Techniques for using micro-journals to ensure crash consistency of a transactional application are provided. In one embodiment, a computer system can receive a transaction associated with the transactional application, where the transaction includes a plurality of modifications to data or metadata of the transactional application. The computer system can further select a free micro-journal from a pool of micro-journals, where the pool of micro-journals are stored in a byte-addressable persistent memory of the computer system, and where each micro-journal in the pool is configured to record journal entries for a single transaction at a time. The computer system can then write journal entries into the micro-journal corresponding to the plurality of modifications included in the transaction and commit the journal entries to the byte-addressable persistent memory.

Abstract: Techniques for using commit coalescing when performing micro-journal-based transaction logging are provided. In one embodiment a computer system can maintain, in a volatile memory, a globally ascending identifier, a first list of free micro-journals, and a second list of in-flight micro-journals. The computer system can further receive a transaction comprising a plurality of modifications to data or metadata stored in the byte-addressable persistent memory, select a micro-journal from the first list, obtain a lock on the globally ascending identifier, write a current value of the globally ascending identifier as a journal commit identifier into a header of the micro-journal, and write journal entries into the micro-journal corresponding to the plurality of modifications included in the transaction. The computer system can then commit the micro-journal to the byte-addressable persistent memory, increment the current value of the globally ascending identifier, and release the lock.