Emc IP Holding Company LLC

Emc Corporation

Subin George

Arieh Don

Vinay G Rao

Deepak Vokaliga

Michael E Specht

Sanjib Mallick

Anestis Panidis

Kevin Loehfelm

Weiqun Li

Michael J Scharland

Benjamin W Yoder

Jaeyoo Jung

Scott Rowlands

Xiali He

Maneesh Pusalkar

Svetlana Sokolova

Violet S Beckett

John S Copley

William Alan Hatstat

Manickavasaham M Senguden

Mavvureddypatty Senguden Manickavasaham

G Vinay Rao

Shwetha Handral Sridhara

Techniques for transmitting data may comprise: receiving a first data transfer rate indicating a communication rate at which a first entity communicates with a second entity over a communications fabric; receiving a second data transfer rate indicating a communication rate at which the second entity communicates with the first entity over the communications fabric; and performing first processing to send first data from the first entity to the second entity over the communications fabric, said first processing including: determining whether the first data transfer rate is greater than the second data transfer rate; and responsive to determining the first data transfer rate is greater than the second transfer rate, performing second processing by the first entity that controls and limits, in accordance with the second data transfer rate, a rate at which the first data is transmitted from the first entity to the second entity.

Data transmission techniques between systems having different communication speeds

Combinations of host ports and storage ports (e.g., I-T pairs) on a storage network that are zoned but not masked may be determined, without accessing a switch or network administrator. Heartbeat communications (heartbeats) may be transmitted from host systems to each storage device of a storage system of which the host system is aware, along the one or more I/O paths of which the host is aware to the storage port of the I/O path. The storage devices may include one or more nominal devices defined for I-T pairs for which I/O connectivity has not been defined for any storage devices. The storage system may maintain a master heartbeat (heartbeat) table that may include a plurality of entries, each entry corresponding to a combination of a host port, storage port and storage device, and storing a time stamp value for a most recent heartbeat received for the combination.

Determining zoned but inactive I/O paths

An illustrative embodiment includes a host device configured to communicate over a network with a storage system comprising a plurality of storage devices. The host device comprises a set of input-output queues and a multi-path input-output driver configured to select input-output operations from the set of input-output queues for delivery to the storage system over the network. The multi-path input-output driver is further configured to determine fabric identifiers for respective ones of a plurality of paths from the host device to the storage system, and to select particular ones of the paths for delivery of the input-output operations to the storage system based at least in part on the fabric identifiers. The fabric identifiers may be determined for the respective paths, for example, based at least in part on responses to a predetermined command sent over the paths by the multi-path input-output driver.

Host device with multi-path layer implementing path selection based at least in part on fabric identifiers

In response to a target port group state query from a host, the storage arrays that present a replicated volume to the host aggregate port group state of the storage arrays into a single logical target port group state that is provided to the host. The storage array that receives the query from the host may prompt other storage arrays to provide target port group state and combine the responses from all storage arrays. Port IDs may be translated into unique port IDs so that the logical target port group state does not include repeated port IDs.

Aggregating ALUA statuses from multiple arrays

Techniques for performing data migration may include: receiving host information regarding hosts registered on a source data storage system; issuing registration commands from a host to a target data storage system; determining, at the target data storage system in accordance with the registration commands, a host registration table including a corresponding entry for the host, the corresponding entry denoting a host name for the host and initiators of the host that sent the registration commands; and determining a masking view for the host on the target data storage system, the masking view including an initiator group of the initiators of the host that sent the registration commands to the target data storage system, wherein the masking view is used by the target data storage system to determine whether to service received I/O operations.

Data migration techniques

An apparatus comprises a host device configured to communicate over a network with a storage system comprising a plurality of storage devices. The host device comprises a multi-path input-output driver configured to schedule input-output operations for delivery to the storage system over the network. The multi-path input-output driver is further configured to measure latencies of respective ones of a plurality of paths from the host device to the storage system, to schedule particular ones of the input-output operations for delivery to the storage system over particular ones of the paths based at least in part on the measured latencies, and to control transmission of the particular input-output operations over the particular paths in accordance with the scheduling. The scheduling additionally or alternatively takes into account other measured parameters such as measured latencies of respective ones of a plurality of storage volumes of the storage system and/or measured payload size per operation metrics for each of at least a subset of the plurality of paths.

Host device with multi-path scheduling based at least in part on measured parameters

An apparatus in one embodiment comprises a host device configured to communicate over a network with a storage system comprising a plurality of storage devices. The host device comprises a set of input-output queues and a multi-path input-output driver configured to select input-output operations from the set of input-output queues for delivery to the storage system over the network. The multi-path input-output driver is further configured to generate a command comprising a cluster identifier of a cluster that includes the first host device and at least a second host device, and to send the command to the storage system over the network. The command is configured for utilization by the storage system to verify that the second host device is part of the same cluster as the first host device. The command may further comprise a group identifier for utilization by the storage system to identify the first host device of the cluster having the cluster identifier.

Host device with multi-path layer configured to provide cluster identification information to storage system

Techniques for migrating data of a logical device from a source to a target system may include: obtaining a map indicating unused data portions of a logical device; issuing read commands from the target system to the source system to only read data from the source copy of the logical device for logical addresses that are not marked in the map as unused data portions; receiving the read data at the target system; writing the read data to second logical addresses of the target copy of the logical device on the target system; and marking logical addresses indicated by the map as corresponding to the unused data portions. The source system may also determine whether all data of a received read request that reads data from the logical device is included in an unused data portion and if so, return no read data and a specialized error condition.

Efficient data transmission techniques

Connectivity loss on a storage network may be reliably determined. For one or more host ports connected to a storage system, the frequency with which status communications are received from the host port may be determined. Status communications from a host port then may be monitored to determine if a predefined number of status communications within a predefined period of time have not been received. If so, it may be determined whether a change in storage system permissions concerning use of ports potentially caused the one or more status communications to not be received. If not, it may be determined whether one or more communications associated with a change in configuration of a switch have been received, in which case a predefined amount of time may be allowed to pass to allow the switch change communications to complete; after which status communications from the host port may again be monitored.

Determining causes of connectivity loss on a storage system

A data storage system migrates a device between a storage array and a cloud gateway based on monitored conditions such as access frequency. More particularly, both a logical volume and the associated data are migrated. The unique device ID (e.g. and without limitation the WWN or WWID) is maintained after migration so the migration is transparent to the host application. The device is deleted from the migration source after being moved to the migration target, thereby releasing resources such as memory, storage, processor cycles and bandwidth at the migration source. A multi-path IO driver in the host computer coordinates with a tiering program in the storage array and a monitoring program in the cloud gateway to manage migration of the logical volume.

Seamless data migration to the cloud

Described are techniques for maintaining and using registration and reservation information in an active-active configuration that provides automated data replication of a logical device. Various commands may be issued from one or more hosts to read and modify registration and reservation information in the active-active configuration. Processing is performed to service the various commands and provide a host or client with a consolidated logical view of a data storage system including the logical device where the host is allowed to issue I/Os over multiple paths to the logical device. Depending on the command, such processing may include replicating or mirroring reservation state information between two data storage systems each including a different device configured as the logical device.

Managing registration and reservation information in an active-active configuration

A method and apparatus for identifying process use on storage array resources is provided. A first process (e.g. an IO driver such as an MPIO driver) on each host collects process information of application processes running on that host. The process/device information is forwarded to the storage array where it is added to a process correlation data structure and correlated with assigned devices of the storage array. The host name that provided the process information is also added to the process correlation data structure. A name of the application is also correlated to the process name in the process correlation data structure. The date the device was last used is periodically updated in the process correlation data structure. The process correlation data structure may then be used to identify devices that have not recently been used and to identify the host, application, and process that uses the devices.

Method and apparatus for identifying process use on storage array resources

In one aspect, a method includes receiving, at a storage array, a command to a virtual volume from a host, extracting a virtual volume index from the command; reading a table using the virtual volume index to determine the logical unit where the virtual volume is stored and executing the command at the logical unit with the virtual volume. The command is one of a read command to read data from the virtual volume or a write command to write data to the virtual volume.

Accessing a virtual volume on a storage array

A computer-implemented method is disclosed to enhance command burst tolerance in a SCSI system. The method starts with receiving an initiator timeout value at a SCSI target, where the SCSI target is communicatively coupled with a SCSI initiator through a set of communication links, and where the initiator timeout value is associated with a timeout duration after which the SCSI initiator times out if receiving no response from the SCSI target after sending a SCSI command. After receiving the initiator timeout value, the SCSI target determines how long a SCSI command has been pending to be processed at the SCSI target. The SCSI target then returns a response for the SCSI command to the SCSI initiator within the timeout duration associated with the initiator timeout value even if the SCSI command is pending to be processed at the SCSI target.

Method and apparatus for enhancing command burst tolerance

Masking information may be automatically determined for a host after zoning between the host and data storage system is complete. Processing may include the host sending host registration commands from host initiators. From registration information provided with the host registration commands, an initiator group may be determined for the masking view as including the initiators identified as belonging to the host. A port group may be determined as those target ports at which the host registration commands are received. A default storage group with a default device may be created. A masking view for the host may be created that includes the initiator group, the target port group and the default storage group whereby the masking view indicates that the first device is accessible or exposed, through each target port of the target port group, to each initiator of the initiator group.

Growing community of inventors

Framingham, MA, United States of America

Subin George