International Business Machines Corporation

Cisco Technology, Inc.

Actona Technologies Ltd.

Globalfoundries Inc.

Idan Zach

Nir Naaman

Avraham Harpaz

Etai Lev-Ran

Vita Bortnikov

Zvi Cahana

Etai Lev Ran

Shahar Glixman

Israel Cidon

Daniel Kaminsky

Israel Ben Shaul

Danit Ben Kiki

Itzhack Goldberg

Gidon Gershinsky

Israel Zvi Ben-Shaul

Shriram Rajagopalan

Guy Laden

Alexey Roytman

Benjamin Mandler

Eliezer Dekel

Alexander Krits

Bruno Wassermann

Michal Malka

A method and a system for checking permissions compatibility between a configuration management system and an orchestration system of a computing cluster are disclosed. The method comprises: identifying a request to approve a change in at least one file of the computing cluster. Retrieving from a repository of the configuration management system an identity of a user for performing the change. Acquiring a denial response or an approval response received in response to a query provisioned to the orchestration system, the query is for rights to change the at least one file using the identity of the user. In response to the approval response, entering the approval response, into the configuration management system for confirming the checking permissions compatibility is approved. In response to the denial received, sending a message to the configuration management system, the message is indicative that the checking permissions compatibility is not approved.

Method and system for checking permissions compatibility between a configuration management system and an orchestration system of a computing cluster

Examples of techniques for selectively providing mTLS using alternative server names are described herein. An example system includes a processor to generate an alternative server name in response to detecting a legacy indicator. The processor is to also associate the alternative server name with an address of a pod. The processor is to further configure a proxy associated with the pod to selectively provide mutual transport layer security (mTLS) based on the alternative server name.

Selectively providing mutual transport layer security using alternative server names

An example system and method includes a processor to receive an image ID corresponding to a container image of a container to be run. The processor is to also send the image ID to a registry. The processor is also to receive an image metadata corresponding to the image ID from the registry. The processor is to store the image metadata on a local file system. The processor is to generate a container comprising an application. The processor is to execute the application using the image metadata.

Container application execution using image metadata

In some examples, a system for managing distributed data can include a processor to detect an update notification from a client device to update a managing server, the update notification indicating that a remote server node is unavailable. The processor can also generate a comparison value by comparing a first time stamp to a second time stamp, wherein the first time stamp corresponds to a time at which the system receives the update notification from the client device and the second time stamp corresponds to a time the remote server node transmits a set of renewal data. Furthermore, the processor can determine that the comparison value indicates the remote server node is unavailable and remove the remote server node from the managing server.

Distributed data management

Embodiments of the present invention may provide techniques by which missed interactions with display advertising may be reduced or recovered. For example, in an embodiment of the present invention, a computer-implemented method for processing computer input may comprise displaying on a display screen at least one background application and a foreground item frame, removing display of the foreground item frame, and after removing display of the foreground item frame, detecting user input in the location where the foreground item frame was displayed.

Recovering missed display advertising

Embodiments of the present invention provide a means for managing portable Internet Protocol (IP) addresses and virtual machine persistent storage. The invention includes defining a set of available portable IP addresses. When a request for a portable IP address is received from a first virtual machine (VM), a first portable IP address is assigned to the first VM. The assignment of the first portable IP address to the first VM extends for a predetermined amount of time and requires a lease renewal to extend the assignment.

Management of clustered and replicated systems in dynamic computing environments

An example system includes a plurality of containers associated with a plurality of tenants. The plurality of containers are to execute code in isolation for the associated plurality of tenants. The system also include a container daemon communicatively coupled to the plurality of containers via an internal proxy. The container daemon is to provide a service to the plurality of containers. The internal proxy is to receive a daemon access policy. The internal proxy is to further intercept a daemon command from a container. The internal proxy is to detect that the container is allowed access to the container daemon based on the daemon access policy. The internal proxy is to also generate a modified daemon command and forward the modified daemon command to the container daemon.

Providing containers access to container daemon in multi-tenant environment

A method for enabling access to a data resource, which is held on a file server () on a first local area network (LAN) (), by a client () on a second LAN (). A proxy receiver () on the second LAN () intercepts a request for the data resource submitted by the client () and transmits a message via a wide area network (WAN) () to a proxy transmitter () on the first LAN (), requesting the data resource. The proxy transmitter () retrieves a replica of the data resource from the file server () and conveys the replica of the data resource over the WAN () to the proxy receiver (), which serves the replica of the data resource from the proxy receiver () to the client () over the second LAN ().

Virtual file-sharing network

A method comprising using at least one hardware processor for managing persistent messaging data in a volatile memory, writing the persistent messaging data to a first section of a Fast Persistent Memory (FPM), responsive to the first section of the FPM approaching a full state, offloading the persistent messaging data from the first section of the FPM to a hard disk device (HDD), and erasing the persistent messaging data from the first section of the FPM, recording, in a second section of the FPM, an identifier of said offloading, responsive to receiving a request to erase or modify at least some of the persistent messaging data in the HDD, updating the identifier of the offloading in the second section of the FPM while leaving the persistent messaging data in the HDD intact, and responsive to a server failure, selectively reading at least some of the persistent messaging data from the HDD to the volatile memory, wherein the selective reading is based on the identifier of the offloading in the second section of the FPM.

Persistent messaging mechanism

A method comprising managing persistent messaging data in a volatile memory of a primary instance of a multi-node server, wherein the persistent messaging data is stored in a Hard Disk Device (HDD) and a Fast Persistent Memory (FPM) of the primary instance, repeatedly replicating the persistent messaging data to a corresponding HDD and a corresponding FPM of at least one standby instance of the multi-node server, repeatedly copying the persistent messaging data stored in the FPM or the HDD of the at least one standby instance to a Recovery Memory Region (RMR) in a volatile memory of the at least one standby instance, and responsive to a failure of the primary instance, initiating a failover procedure by the standby instance, wherein the failover procedure comprises reading at least some of the persistent messaging data from the RMR in lieu of the HDD of the at least one standby instance.

A computer-implemented method, a computerized system and a product for providing a cluster of replicated servers. The method performed by a computerized server in a cluster of servers, wherein the cluster of servers are executing replicated instances of an application, wherein the replicated instances are configured to perform the same processing of the same input, comprising: detecting a message loss in the server; electively determining a responsive action to the message loss; and notifying the cluster of servers of the responsive action determined by the server, whereby other servers of the cluster of servers are able to mimic operation of the server by simulating the responsive action.

Selective message loss handling in a cluster of replicated servers

A method for server replication in a network environment is provided. The primary server provides a first service to a client. If the first service involves interaction with a non-deterministic data source, the primary server performs the interaction and provides information about the interaction to a secondary server that is a replica of the primary server. The secondary server uses the information about the interaction to synchronize the secondary server with the primary server.

Replication in a network environment

A group communication service maintains synchronization limiting the group to the processing entities that receive a plurality of source message streams from sources outside the group and transmit delivery message streams to destinations that are outside the group. Synchronization of message ordering and other state synchronization directives are communicated from a leader exclusively to other group members. Once having declared themselves to be synchronized and active by a reply protocol message, which is an opaque object and is interpreted by an application layer, the processing entities independently process the source message streams in accordance with the order specified in the directives, without requiring additional sequencing information from another processing entity.

Group communication system achieving efficient total order and state synchronization in a multi-tier environment

Approaches are disclosed for lock optimization and lock prediction for reducing the number of client-server messages involved in working with server-based resources. First one or more lock requests for first one or more locks on a remote data resource that is linked by a slow communication link are received. Based on the first one or more lock requests, a sequence of lock requests for locks on the remote data resource is determined. A first message that includes the sequence of lock requests is sent. A second message is received. The second message includes second one or more locks on the remote data resource, where the second one or more locks correspond to second one or more lock requests of the sequence of lock requests. A particular lock of the second one or more locks is granted in response to receiving a particular lock request for the particular lock on the remote data resource.

Lock optimization and lock prediction approaches for reducing client-server messages

A method for communication in a computing environment is provided. The method comprises transmitting a first data packet to one or more receiving units in a first set; receiving one or more acknowledgement messages (ACKs) from one or more receiving units in a second set, wherein the second set is a subset of the first set; removing the first data packet from a queue, in response to receiving at least one ACK from N receiving units within a time threshold; and re-transmitting the first data packet to the first set, in response to failing to receive at least one ACK from N receiving units within the time threshold.

Growing community of inventors

Givat Ela, Israel

Idan Zach