International Business Machines Corporation

Christopher M Dennett

Roman Alexander Pletka

Andrew Dale Walls

Charles John Camp

Ioannis Koltsidas

Nikolas Ioannou

Sasa Tomic

Radu Ioan Stoica

Antonios Kornilios Kourtis

Shawn P Authement

Farnaz Toussi

Timothy J Fisher

Robert Edward Galbraith

Rivka Mayraz Matosevich

Constantine Gavrilov

Sergey Marenkov

Gowrisankar Radhakrishnan

Kevin E Sallese

Asaf Porat-Stoler

Donald J Ziebarth

Jonathan Fischer-Toubol

Afief Halumi

Kevin A Bosien

David Mullen

A method and system may reconstruct data in a smart storage array where upon detection of data inconsistency, an application of the system is notified and affected data strips are rebuilt. When an initiator detects stripe corruption, the initiator may report the strip corruption to storage. The storage may lock the strip for I/O operations. Initiators may determine recovery scenarios for rebuilding the data strips and send the scenarios to storage. At storage, initiator replies may be collected, and a rebuild option with the highest votes may be automatically determined for a reconstruction operation. Once the reconstruction operation is completed, the rebuilt stripe may be unlocked and data operations may recommence.

Reconstructing data in a smart storage array

A computer-implemented method, according to one embodiment, includes: receiving, at a storage drive, a portion of a write command. Metadata information is extracted from the received portion of the write command, and sequentially added to a metadata buffer. Parity information is extracted from the received portion of the write command, and adding to a parity buffer. The data in the received portion of the write command is stored in a memory in the storage drive. A determination is also made as to whether an open segment in the memory which corresponds to the received portion of the write command has been filled. In response to determining that the open segment has been filled, the parity buffer is updated with the metadata information included in the metadata buffer. The metadata information and parity information is also destaged from the respective buffers to a physical storage location in the memory.

Metadata hardening and parity accumulation for log-structured arrays

A computer-implemented method, according to one embodiment, includes: sequentially adding metadata information that has been extracted from a received write command to a metadata buffer, and adding parity information that has been extracted from the received write command to a parity buffer. The data corresponding to the received write command is also sent to memory. A determination is made as to whether an open segment in the memory which corresponds to the write command has been filled. In response to determining that the open segment has been filled, the parity buffer is updated with the metadata information included in the metadata buffer. Moreover, the metadata information is destaged from the metadata buffer and parity information is destaged from the parity buffer to a physical storage location in the memory.

Technology for handling page size mismatches when DPL-CLR is performed at multiple levels of a data storage system (for example, RAID level and flash card level). A 'corrective DPL' corrects only a portion of the data that would make up a page at the level at which the data is stored (that is, the 'initial DPL level'), and, after that, a partially corrected page of data is formed and stored in data storage, with the partially corrected page: (i) having a page size characteristic of the initial DPL; (ii) including the part of the data corrected by the corrective DPL; and (iii) further including other data. In some embodiments, the other data has a pattern that indicates that it is invalid, erroneous data, such that an error message will be returned if this portion of the data is attempted to be read.

Corrupt logical block addressing recovery scheme

Embodiments for optimizing resource consumption through partial parity information eviction in a storage system of a data storage environment. One or more cooperative Redundant Array of Independent Disks (RAID) parity computations are performed by evicting partial parity data from a RAID controller memory to a storage entity prior to a full stripes worth of data being monotonically written to the storage entity. The storage entity assembles the partial parity data from the one or more cooperative RAID parity computations into a single parity computation valid for the full stripes worth of data, thereby offloading parity computation to the storage entity to more efficiently utilize the RAID controller memory resources.

Log-structured array (LSA) partial parity eviction and reassembly

A technique for handling storage commands includes receiving, by an interface node of a data storage system, a first storage command. The interface node determines whether the first storage command is a head of queue (HOQ) command. In response to determining the first storage command is an HOQ command, the interface node increments a constrained command count and issues the first storage command to a first worker processor core for processing. In response to determining the first storage command is not an HOQ command, the interface node processes the first storage command as a non-HOQ command.

Techniques for storage command processing

A computer-implemented method, according to one embodiment, includes: receiving a write command to write data, the write command being received from a log structure array at a host location. The computer-implemented method also includes: extracting metadata information from the received write command; sequentially adding the extracted metadata information to a metadata buffer; extracting parity information from the received write command; adding the extracted parity information to a parity buffer; sending the data corresponding to the received write command to memory; determining whether an open segment in the memory which corresponds to the write command has been filled; updating the parity buffer with the metadata information included in the metadata buffer in response to determining that the open segment has been filled; and destaging the metadata information from the metadata buffer and parity information from the parity buffer to a physical storage location in the memory.

An interface receives a command corresponding to a non-volatile memory. The interface determines whether a bypass mode is enabled and whether the command is a medium-access command. A primary processing node processes the command in response to determining at least one of the following: that the bypass mode is disabled or that the command is not a medium-access command. A secondary processing node processes the command, in response to determining that the bypass mode is enabled and that the command is a medium-access command.

Firmware bypass for medium-access commands

Method and apparatus for redundant array of independent disks (RAID) recovery are disclosed. In one embodiment, a RAID controller schedules requests to rebuild failed drives based on the wear state of secondary drives and input/output (I/O) activity. The controller may be configured to assign higher scheduling priority to rebuild requests only when necessary, so as to reduce the time needed for the rebuild and to avoid affecting performance of the RAID system. In particular, the controller may give higher priority to rebuild requests if secondary drive failure is likely. In addition, the controller may determine when write-intensive periods occur, and assign lower priority to rebuild requests during such periods.

Growing community of inventors

Houston, TX, United States of America

Christopher M Dennett