Abstract: Methods, apparatus and computer program products implement embodiments of the present invention that include defining, in a storage system including multiple storage devices, multiple redundant array of independent disks (RAID) configurations for data stored on the storage devices. A first one of the multiple RAID configurations is assigned to a first entry in a partition table having multiple entries, and a second one of the multiple RAID configurations is assigned to a second entry in the partition table, the second one of the multiple RAID configurations independent from the first one of the multiple RAID configurations.

Abstract: Methods, apparatus and computer program products for a distributed system include dividing logical volume data into data subsets, and defining at least one distributedly storage configuration for the logical volume. Metadata for the logical volume is written to a first set of first metadata tables, and the first set of first metadata tables is divided into metadata subsets having a one-to-one correspondence with the data subsets. The metadata subsets are distributed among the multiple digital information devices, and the metadata is copied from the first set of first metadata tables to a second set of corresponding second metadata tables in a one-to-one correspondence with the first metadata tables, and the second metadata tables are distributed among the multiple digital information devices.

Abstract: Methods, apparatus and computer program products implement embodiments of the present invention that enable digital information devices having respective storage devices and memories to distributedly store, for a logical volume, data and first and second parity values across corresponding regions of the storage devices. Freezers having a one-to-one correspondence with the storage devices are distributedly stored in the memories. Upon detecting, in a cache, updated data for one or more first regions on the storage devices, existing data from the one or more first regions, and additional data for parity calculations are retrieved from one or more corresponding second regions on the storage devices, and first and the second parity values are calculated using the updated data, the existing data and the additional data, and the updated data and the calculated first and second parity values are stored to the freezers.

Abstract: Methods, apparatus and computer program products for a distributed system include dividing logical volume data into data subsets, and defining at least one distributedly storage configuration for the logical volume. Metadata for the logical volume is written to a first set of first metadata tables, and the first set of first metadata tables is divided into metadata subsets having a one-to-one correspondence with the data subsets. The metadata subsets are distributed among the multiple digital information devices, and the metadata is copied from the first set of first metadata tables to a second set of corresponding second metadata tables in a one-to-one correspondence with the first metadata tables.

Abstract: Methods, apparatus and computer program products implement embodiments of the present invention that enable digital information devices having respective storage devices and memories to distributedly store, for a logical volume, data and first and second parity values across corresponding regions of the storage devices. Freezers having a one-to-one correspondence with the storage devices are distributedly stored in the memories. Upon detecting, in a cache, updated data for one or more first regions on the storage devices, existing data from the one or more first regions, and additional data for parity calculations are retrieved from one or more corresponding second regions on the storage devices, and first and the second parity values are calculated using the updated data, the existing data and the additional data. The updated data and the calculated first and second parity values are stored to the freezers, and then destaged from the freezers to the storage devices.

Abstract: Methods, apparatus and computer program products for a distributed system include dividing logical volume data into data subsets, and defining at least one distributedly storage configuration for the logical volume. Metadata for the logical volume is written to a first set of first metadata tables, and the first set of first metadata tables is divided into metadata subsets having a one-to-one correspondence with the data subsets. The metadata subsets are distributed among the multiple digital information devices, and the metadata is copied from the first set of first metadata tables to a second set of corresponding second metadata tables in a one-to-one correspondence with the first metadata tables. The second metadata tables are distributed among the multiple digital information devices, and upon modifying the metadata in a one of the first metadata tables while processing a storage request, the corresponding second metadata table is revised with the updated metadata.

Abstract: A method for in-band de-duplication, the method may include receiving by a hardware accelerator, a received packet of a first sequence of packets that conveys a first data chunk; applying a data chunk hash calculation process on the received packet while taking into account a hash calculation result obtained when applying the data chunk hash calculation process on a last packet of the first sequence that preceded the received packet; wherein the calculating of the first data chunk hash value is initiated before a completion of a reception of the entire first data chunk by the hardware accelerator.

Abstract: A method for hybrid RDMA, the method may include: (i) receiving, by a first computer, a packet that was sent over a network from a second computer; wherein the packet may include data and metadata; (ii) determining, in response to the metadata, whether the data should be (a) directly written to a first application memory of the first computer by a first hardware accelerator of the first computer; or (b) indirectly written to the first application memory; (iii) indirectly writing or indirectly writing in response to the determination.

Abstract: A method for facilitating direct memory access in a computing system in response to a request to transfer data is provided. The method comprises selecting a thread for transferring the data, wherein the thread executes on a processing core within the computing system; providing the thread with the request, wherein the request comprises information for carrying out a data transfer; and transferring the data according to the request. The method may further comprise: coordinating the request with a memory management unit, such that virtual addresses may be used to transfer data; invalidating a cache line associated with the source address or flushing a cache line associated with the destination address, if requested. Multiple threads can be selected to transfer data based on their proximity to the destination address.

Abstract: A method, system and computer program product is disclosed for scheduling data packets in a multi-processor system comprising a plurality of processor units and a multitude of multicast groups. The method comprises associating one of the processor units with each of the multicast groups, receiving a multitude of data packets from the multicast groups, and scheduling all of the data packets received from each of the multicast groups for processing by the one of the processor units associated with said each of the multicast groups. In one embodiment, scheduling is based on affinity of both transmit and received processing for multiple connections to a processor unit. In another embodiment, a system call is provided for transmitting the same data over multiple sockets. Additional system calls may be used for building multicast group socket lists.

Abstract: Mechanisms are provided to improve efficiency of systems operating on internet protocol (IP) over Infiniband (IB) networks. One mechanism includes multicasting a first ARP request from a source node, the first ARP request including an IP address of a source port of the source node, and performing load-balancing of host traffic across a plurality of ports of a plurality of nodes by sending a reply from a destination node corresponding to the IP address included in the first ARP request, the reply being sent over the source port to the source node.

Abstract: A method for accessing a memory space allocated to a virtual machine, the method includes: receiving a request from the virtual machine to generate, for another virtual machine, a memory credential associated with a certain memory space allocated to the virtual machine; generating, in response to the request, a cryptographically signed credential; sending the cryptographically signed credential to the other virtual machine; receiving from the other virtual machine an access request to access at least one memory entry within the certain memory space; and accessing the at least one memory entry, if the access request complies with the memory credential.

Abstract: Methods, systems, and physical computer-readable storage medium are provided to improve efficiency of systems operating on internet protocol (IP) over Infiniband (IB) networks. In an embodiment, by way of example only, a method is provided for implementing redundancy for IB networks. The method includes detecting a failure at a first source port of a source node having a plurality of source ports, selecting a new source port, sending an address resolution protocol (ARP) message to one or more other nodes in communication with the source node including an IP address of the source node and IB address of the new source port of the source node, and re-balancing host traffic.

Abstract: Methods, apparatus and computer program products implement embodiments of the present invention that include identifying non-destaged first data in a write cache. Upon detecting second data in a master read cache, the second data is copied the second data to one or more backup read caches, and the second data is pinned to the master and the backup read caches. Using the first data stored in the write cache and the second data stored in the master read cache, one or more parity values are calculated, and the first data and the one or more parity values are destaged.

Abstract: Methods, apparatus and computer program products implement embodiments of the present invention that include defining, in a storage system including receiving, by a processor, metadata describing a first cache configured as a master cache having non-destaged data, and defining, using the received metadata, a second cache configured as a backup cache for the master cache. Subsequent to defining the second cache, the non-destaged data is retrieved from the first cache, and the non-destaged data is stored to the second cache.

Abstract: Methods, apparatus and computer program products implement embodiments of the present invention that include defining, in a storage system including receiving, by a storage system, a storage request, and identifying, based on the storage request, one or more storage management units. For each of the storage management units, a master partition table having multiple master entries and one or more backup partition tables is identified, each of the backup partition tables having backup entries in a one-to-one-correspondence with the master entries. The storage request is performed, and upon the storage request being performed, any changes to essential metadata in the one or more master partition tables are identified, and the identified changes are stored to the essential metadata in the one or more backup partition tables.

Abstract: Methods, apparatus and computer program products implement embodiments of the present invention that enable digital information devices having respective storage devices and memories to distributedly store, for a logical volume, data and first and second parity values across corresponding regions of the storage devices. Freezers having a one-to-one correspondence with the storage devices are distributedly stored in the memories. Upon detecting, in a cache, updated data for one or more first regions on the storage devices, existing data from the one or more first regions, and additional data for parity calculations are retrieved from one or more corresponding second regions on the storage devices, and first and the second parity values are calculated using the updated data, the existing data and the additional data. The updated data and the calculated first and second parity values are stored to the freezers, and then destaged from the freezers to the storage devices.

Abstract: Method embodiments are provided to improve efficiency of systems operating on internet protocol (IP) over Infiniband (IB) networks. In an embodiment, by way of example only, a method is provided for implementing redundancy for IB networks. The method includes detecting a failure at a first source port of a source node having a plurality of source ports, selecting a new source port, sending an address resolution protocol (ARP) message to one or more other nodes in communication with the source node including an IP address of the source node and IB address of the new source port of the source node, and re-balancing host traffic.

Abstract: To improve efficiency of systems operating on internet protocol (IP) over Infiniband (IB) networks, mechanisms are provided for operating a system including a plurality of nodes, each connected to at least one IB switch. A determination is made whether an IP address of a node is included in a first level of a global ARP cache. An IP over IB GUID corresponding to the IP address of the node is identified. A determination is made whether an entry in a second level of the global ARP cache includes the identified IP over IB GUID of the node, and corresponding the IP over IB GUID of the node to IB address information of the node.

Abstract: To improve efficiency of systems operating on internet protocol (IP) over Infiniband (IB) networks, mechanisms are provided for operating a system including a plurality of nodes, each connected to at least one IB switch. A determination is made whether an IP address of a node is included in a first level of a global ARP cache. An IP over IB GUID corresponding to the IP address of the node is identified. A determination is made whether an entry in a second level of the global ARP cache includes the identified IP over IB GUID of the node, and corresponding the IP over IB GUID of the node to IB address information of the node.