Abstract: A method includes, in a computing system that includes multiple compute nodes that run workloads and are connected by a network, establishing a dedicated Transport Control Protocol (TCP) connection over the network between a first compute node and a second compute node. Packets, which originate from one or more source workloads on the first compute node and are destined to one or more destination workloads on the second compute node, are identified and queued in the first compute node. The queued packets are aggregated in the first compute node into one or more TCP segments, and the TCP segments are sent over the dedicated TCP connection to the second compute node. In the second compute node, the TCP segments are received over the dedicated TCP connection, the packets are extracted from the received TCP segments, and the extracted packets are forwarded to the destination workloads.

Abstract: A method for storage includes storing multiple memory pages in a memory of a first compute node. Using a second compute node that communicates with the first compute node over a communication network, duplicate memory pages are identified among the memory pages stored in the memory of the first compute node by directly accessing the memory of the first compute node. One or more of the identified duplicate memory pages are evicted from the first compute node. The identification of duplicate pages is performed by a node selected responsive to available processing or bandwidth resources.

Abstract: A method includes, in a computing system in which one or more workloads access memory pages in a memory, defining multiple memory-page lists, and specifying for each memory-page list a respective different scanning period. Access frequencies, with which the memory pages are accessed, are estimated continually by periodically checking the memory pages on each memory-page list in accordance with the scanning period specified for that memory-page list, and re-assigning the memory pages to the memory-page lists based on the estimated access frequencies. One or more of the memory pages are evicted from the memory based on a history of assignments of the memory pages to the memory-page lists.

Abstract: A method includes storing data generated in a source node by sending write requests to multiple destination nodes. The destination nodes are requested to create snapshots of the data. The write requests are marked at the source node with marks that indicate to each destination node which of the write requests are pre-snapshot write requests that were issued before a snapshot request for a snapshot that the destination node is currently storing, and which of the write requests are post-snapshot write requests that were issued after the snapshot request for the snapshot that the destination node is currently storing. The snapshots are synchronized with one another at the destination nodes based on the marks.

Abstract: A computing method includes running, on a plurality of compute nodes, multiple workloads that access respective sets of memory pages. Respective bitmaps are calculated for at least some of the workloads, wherein (i) a bitmap of a workload is statistically indicative of a cardinality of the set of memory pages used by the workload, (ii) a union of two or more bitmaps is statistically indicative of the cardinality of a union of the sets of memory pages used by the two or more corresponding workloads, and (iii) an intersection of first and second bitmaps is statistically indicative of an overlap between respective first and second sets of memory pages used by the corresponding workloads. A decision is made to migrate a selected workload from a source compute node to a destination compute node, based on one or more of the bitmaps.

Abstract: A method includes running multiple processing tasks on multiple physical processing cores that support general-purpose registers and special-purpose registers. Respective usage levels, with which the processing tasks use the special-purpose registers, are estimated. The physical processing cores are assigned to the processing tasks based on the estimated usage levels of the special-purpose registers.

Abstract: A method includes, in a computing system that includes one or more compute nodes that run clients, defining memory chunks, each memory chunk including multiple memory pages accessed by a respective client. Respective similarity-preserving signatures are computed for one or more of the memory chunks. Based on the similarity-preserving signatures, an identification is made that first and second memory chunks differ in content in no more than a predefined number of memory pages with at least a predefined likelihood. Efficiency of access to the identified first and second memory chunks is improved.

Abstract: A method for data storage includes sending write commands to a first storage node, for storing data in a data volume on the first storage node. In response to a decision to create a copy of the data volume on a second storage node, (i) the write commands are sent both to the first storage node and to the second storage node, and (ii) a snapshot of the data volume is created and sent from the first storage node to the second storage node. The copy of the data volume is created by the second storage node based on the snapshot and on one or more of the write commands received at the second storage node.

Abstract: A method includes running in a computer a hypervisor that allocates physical memory pages of the computer to a Virtual Machine (VM). A guest Operating System (OS), a virtual memory and a virtual storage device run in the VM. The guest OS maps the allocated physical memory pages to respective virtual memory pages, retains virtual memory pages that are frequently-accessed by the VM in the virtual memory, and swaps-out virtual memory pages that are rarely-accessed by the VM to the virtual storage. In the hypervisor, one or more of the physical memory pages allocated to the VM are selected, and the corresponding virtual memory pages preventing from being swapped-out by the guest OS, by marking the corresponding virtual memory pages in the guest OS as accessed thus causing the guest OS to regard the corresponding virtual memory pages as frequently-accessed.

Abstract: A method includes running a Virtual Machine (VM) on a first compute node in a plurality of compute nodes that communicate with one another over a communication network. The VM is migrated from the first compute node to a second compute node in the plurality by generating, for memory pages accessed by the VM, page transfer state of one or more local memory pages that are accessed locally on the first compute node, and of one or more externalized memory pages whose access is not confined to the first node. Based on the page transfer state, the migrated VM is provided with access to the memory pages, including both the local and the externalized memory pages, on the second compute node.

Abstract: A method includes, in a plurality of compute nodes that communicate with one another over a communication network, running one or more Virtual Machines (VMs) that access storage blocks stored on non-volatile storage devices coupled to at least some of the compute nodes. One or more of the storage blocks accessed by a given VM, which runs on a first compute node, are cached in a volatile memory of a second compute node that is different from the first compute node. The cached storage blocks are served to the given VM.

Abstract: A method includes running on multiple compute nodes respective memory sharing agents that communicate with one another over a communication network. One or more local Virtual Machines (VMs), which access memory pages, run on a given compute node. Using the memory sharing agents, the memory pages that are accessed by the local VMs are stored on at least two of the compute nodes, and the stored memory pages are served to the local VMs.