Emc IP Holding Company LLC

Dell Products Inc.

Svetlana Kronrod

Xiangping Chen

Anton Kucherov

David Meiri

Vladimir Shveidel

Vamsi K Vankamamidi

Zvi Schneider

Michael P Wahl

Yuval Harduf

Leonid Ravich

David Bernard

Archana Parasnis

James H Shimer

An apparatus includes at least one processing device comprising a processor coupled to a memory, with the processing device being configured to maintain a synchronous replication input-output (IO) request list having a plurality of entries corresponding to respective synchronous replication IO requests, a given such entry identifying at least a sender component and one or more address locks held by the corresponding synchronous replication IO request. The processing device is further configured to detect a failure of a particular one of a plurality of sender components, to access the synchronous replication IO request list to identify one or more address locks held by at least one synchronous replication IO request previously sent by the failed sender component, and to release one or more address lock waiters that are waiting to obtain the one or more identified address locks. Other embodiments include methods and computer program products.

Storage system with efficient release of address lock waiters during synchronous replication

A method, computer program product, and computing system for receiving one or more IO requests on a storage system coupled to a cloud-based storage platform, wherein the cloud-based storage platform has a defined maximum IOPS rate; determining a current level of utilization of the defined maximum IOPS rate; and determining whether to queue the one or more IO requests for an aggregated write operation to the cloud-based storage platform based, at least in part, upon the current level of utilization of the defined maximum IOPS rate.

Storage management system and method

An apparatus includes at least one processing device comprising a processor coupled to a memory, with the processing device being configured to maintain a synchronous replication input-output (IO) request list having a plurality of entries corresponding to respective synchronous replication IO requests, a given such entry identifying at least a sender component and one or more associated component resources to be released responsive to a failure of the sender component. The processing device is further configured to detect a failure of a particular one of a plurality of sender components, to access the synchronous replication IO request list to determine one or more associated component resources to be released, to release the one or more associated component resources, and to update the synchronous replication IO request list by marking the one or more associated component resources as released. Other embodiments include methods and computer program products.

Storage system with efficient release of failed component resources during synchronous replication

Processing can be performed to persistently record, in a log, a write I/O that writes first data to a target logical address. The processing can include: allocating storage for a first page buffer (PB) located at offsets in a PB pool of non-volatile storage of the log; enqueuing a request to an aggregation queue to persistently store the first data to the first PB of the log, wherein the request identifies the offsets of the PB pool of non-volatile storage which correspond to the first PB; and integrating the request into the aggregation queue. Integrating can include: determining whether a contiguous segment of the offsets of the request is adjacent to a second contiguous segment of the aggregation queue; and responsive to determining the contiguous segment is adjacent to the second contiguous segment, merging the first and second contiguous segments and generating an aggregated continuous segment.

Coalescing logged operations

A method is provided for use in a storage system, the method comprising: receiving an I/O request at an R-node; generating a deadline for the I/O request; generating a C-node command based on the I/O request; transmitting the C-node command and the I/O request to a C-node; calculating, by the C-node, a first remaining time based on the deadline; detecting, by the C-node, whether the first remaining time meets a first threshold; when the first remaining time meets the first threshold, executing the I/O request and transmitting, from the C-node to the R-node, synchronous replication request that is associated with the C-node command; and when the first remaining time does not meet the first threshold, causing the storage system to stop performing synchronous replication and executing the C-node command.

Global deadline driven local synchronous replication I/O handling and recover

An aspect of performing rollback of a snapshot between a source storage system and a target storage system in a synchronous replication session includes reassigning a current replication source volume to a rollback source snapshot. The rollback source snapshot is generated for a consistency group that includes a plurality of volumes. An aspect also includes performing, for one or more snapshot trees maintained for the consistency group, a differential scan between a child of the rollback source snapshot and the current replication source volume, and calculating, from results of the differential scan, a dirty tree differential. For each difference identified in the dirty tree differential, an aspect further includes calculating a corresponding volume offset, and initiating a copy command for the current replication source volume and the rollback source snapshot. The copy command is translated to a remote metadata copy request in synchronous replication data transfer.

Snapshot rollback for synchronous replication

A first storage system in one illustrative embodiment is configured to participate in a replication process with a second storage system. The first storage system detects a replication failure condition or other condition requiring termination of a synchronous replication mode of the replication process, and responsive to the detected condition, captures a snapshot of source data that is subject to replication from the first storage system to the second storage system as part of the replication process. The first storage system terminates the synchronous replication mode of the replication process, initiates an asynchronous replication mode of the replication process, executes an asynchronous-to-synchronous transition cycle scan operation for the replication process utilizing the captured snapshot, and resumes the synchronous replication mode of the replication process responsive to successful completion of the asynchronous-to-synchronous transition cycle scan operation.

Storage system with fast recovery and resumption of previously-terminated synchronous replication

A method for use in a storage system disclosed, comprising: transitioning the storage system into a first state, the first state including a state in which a source system performs synchronous replication to a target system; detecting a first event while the source system is in the first state; in response to the first event, transitioning the storage system from the first state into a second state, the second state being a state in which the source system performs asynchronous replication; detecting a second event while the storage system is in the second state, transitioning the source system from the second state into a third state, the third state including a state in which the source system performs both synchronous replication and asynchronous replication.

2-phase sync replication recovery to optimize recovery point objective (RPO)

In one aspect, automatic recovery of a synchronous replication session in response to an error is provided for a storage system that includes a source and target sites. During an active sync replication session in which a state machine indicates the system is operating in sync, an aspect includes monitoring input/output (IO) operations. Upon determining an occurrence of the error in which data has been persisted at the source site but not at the target site, an aspect includes discontinuing replication to the target site and transitioning the state machine from a sync state to a tripped state. Upon determining, during the tripped state, resources exist to conduct sync replication remote data transfer operations, transition the state machine to an async_to_sync state. The async_to_sync state causes the storage system to initiate a recovery operation to return the source and target sites to the sync state.

Highly resilient synchronous replication with automatic recovery

An aspect of performing on-demand remote snapshot creation for a synchronous replication session between a local system and a remote system of a storage system includes receiving a request for the remote snapshot on the remote system and identifying a current state of the synchronous replication session. The current state is one of a plurality of states. An aspect also includes implementing one or more actions with respect to the remote snapshot as a function of the current state. The actions are performed prior to transitioning from the current state to another state of the plurality of states.

On-demand remote snapshot creation for a synchronous replication session in automatic recovery

A method is provided for use in a storage system, comprising: identifying a first process that is arranged to execute a first type-1 node and a first type-2 node of the storage system, the first type-1 node being assigned a communication link for transmitting replication data to a target system, the first type-2 node being arranged to execute I/O requests associated with a first set of addresses in an address space; identifying a second process that is arranged to execute a second type-1 node and a second type-2 node of the storage system, the second type-1 node being not being assigned any communication link for transmitting replication data to a target system, the second type-2 node being arranged to execute I/O requests associated with a second set of addresses in the address space; and transferring at least one of the addresses in the first set to the second set.

Performance of replication system with small number of IP links available

An apparatus includes at least one processing device comprising a processor coupled to a memory, with the processing device being configured to maintain at least first and second journals for respective first and second different types of input-output requests, to move one or more entries between the first journal and the second journal under one or more specified conditions, to perform a clean-up operation for at least one of the first and second journals in conjunction with the moving of the one or more entries, and responsive to a failure occurring during the clean-up operation, to execute a contention resolution algorithm to resolve logical address range lock contentions between different entries of the first and second journals. The processing device illustratively comprises a storage controller of a storage system. The storage system may be, for example, a source storage system configured to carry out a synchronous replication process with a target storage system.

Storage system with coordinated recovery across multiple input-output journals of different types

A method is disclosed for use in a storage system including a source system that is coupled to a target system, the method comprising: detecting a rollback event that is associated with a source volume Vs; and performing a rollback of the source volume Vs in response to the rollback event, wherein performing the rollback of the source volume Vs includes: identifying a target snapset Sr to be rolled back to, the target snapset Sr having a creation time Tr; identifying a snapset recovery pair including a source snapset Sk and a target snapset Sk', the source snapset having a creation time Ts, and the target snapset having a creation time Tt, such that Tr&#x2264;Ts&#x2264;Tt; assigning the source volume Vs to the source snapset Sk; and update the source volume Vs based on a difference between the target snapset Sr and the target snapset Sk&#x2032;.

Automatic rollback to target for synchronous replication

An aspect of performing flow control of IO in a synchronous replication session between a local storage and a remote storage of a storage system includes tracking an amount of time an input/output (IO) request is processed at the remote storage including an amount of time the IO request is in transmit to and from the remote storage system. The amount of time indicates a remote latency value. An aspect also includes tracking an amount of time the IO request is processed at the local storage and calculating a difference between the remote latency value and the amount of time the IO request is processed at the local storage. The difference indicates a local latency value. An aspect further includes modifying an amount of IO requests admitted at the storage system as a function of the local latency value.

Flow control of input/output (IO) in a synchronous replication session

An aspect of performing input/output (IO) flow control in a storage system includes receiving an IO latency factor for each IO of a plurality of IOs in a workload. The IO latency factor specifies a priority level. An aspect also includes receiving a component latency factor, with respect to each of the IOs in the workload, for each component of a plurality of components in the storage system. The component latency factor indicates a degree to which the component is considered in assessing the workload. An aspect also includes applying, during processing of the workload, the IO latency factor and the component latency factor to each of the corresponding IOs; and determining an effective average latency of the plurality of IOs in the workload as a function of the applied IO latency factors and the applied component latency factors.

Growing community of inventors

Concord, MA, United States of America

Svetlana Kronrod