Forming consistency groups using self-describing record sets for remote data duplexing

Claim 2

In a system providing remote data shadowing for disaster recovery purposes, the system including a primary site having a primary processor running a primary data mover and applications generating record updates, the primary processor coupled to a primary storage subsystem having storage devices for storing the record updates according to write I/O operations issued by the primary processor to the primary storage subsystem, the primary site further including a common system timer for synchronizing time dependent operations in the primary site, the system further including a secondary site having a secondary processor communicating with the primary processor, and a secondary storage subsystem for storing copies of the record updates in sequence consistent order, a method for shadowing the record updates in sequence consistent order comprising steps of: (a) time stamping each write I/O operation in the primary storage subsystem; (b) capturing record set information for the record updates from the primary storage subsystem; (c) reading into the primary data mover the record updates and the record set information to form record sets; (d) prefixing each of the record sets with a header to create self describing record sets, the self describing record sets to be used by the secondary processor to re-create a sequence of the write I/O operations at the secondary site; (e) transmitting the self describing record sets to the secondary processor in time interval groups according to predetermined time intervals; (f) forming consistency groups from the time interval groups of the self describing record sets, the record updates being ordered within the consistency groups based upon time sequences of the write I/O operations issued to the primary storage subsystem; and (g) shadowing the record updates of each consistency group to the secondary storage subsystem in a sequence consistent order.

Claim 3

The method according to claim 1 wherein the record sets are transmitted to the secondary processor asynchronously.

Claim 4

The method according to claim 1 wherein the step (f) is performed at the secondary site.

Claim 5

The method according to claim 1 wherein the step (e) further includes determining at the secondary site whether each received self describing record set is complete.

Claim 6

The method according to claim 4 wherein the step (e) further includes requesting the primary site to re-transmit any missing record updates if the primary site determined a received self describing record set is incomplete.

Claim 7

The method according to claim 1 further comprising a step (h) determining at the secondary site whether each time interval group is complete.

Claim 8

The method according to claim 6 wherein the step (h) further includes requesting the primary site to re-send a missing record set if the secondary site determined that the time interval group was incomplete.

Claim 9

The method according to claim 1 wherein the step (b) identifies, in the record set information, a physical location on the primary storage devices where each record update is stored.

Claim 10

The method according to claim 8 wherein the step (b) identifies, in the record set information, a sequence and time of update of each record update stored to the primary storage devices within the session.

Claim 11

The method according to claim 1 wherein the step (d) identifies, in the prefix header, an interval group number for the session and sequence within group for each record update referred to therein.

Claim 12

A remote data shadowing system including a primary site and a secondary site, the secondary site asynchronously shadowing record updates of the primary site in real time for disaster recovery purposes, the record updates generated by applications running at the primary site, the primary site comprising: a sysplex timer; a primary processor running the applications generating the record updates and issuing a corresponding write I/O operation for each record update, the primary processor having a primary data mover therein; a plurality of primary storage controllers directed to store the record updates, the plurality of primary storage controllers executing the issued write I/O operation for each record update; and a plurality of primary storage devices receiving and storing the record updates therein according to the corresponding write I/O operations, wherein the primary processor and each write I/O are time-stamped by the primary processor, as synchronized by the sysplex timer, such that write I/O operations are accurately sequence ordered relative to each other, the primary data mover collecting sets of record updates and combining each record set information as provided by each one of the plurality of primary storage controllers with the corresponding record update, each record set information including a relative sequence and time of each corresponding write I/O operation, the primary data mover collecting record updates into time interval groups and inserting a prefix header to each time interval group, wherein the prefix header includes information identifying the record updates included in each time interval group, each record set information and prefix header combined for creating self describing record sets, the self describing record sets being transmitted to the secondary site, wherein the self describing record sets provide information adequate for the secondary site to shadow the record updates therein in sequence consistent order without further communications from the primary site.

Claim 13

A remote data shadowing system including a primary site and a secondary site, the secondary site asynchronously shadowing record updates of the primary site in real time for disaster recovery purposes, the record updates generated by applications running at the primary site, the primary site comprising: a sysplex timer; a primary processor running the applications generating the record updates and issuing a corresponding write I/O operation for each record update, the primary processor having a primary data mover therein; a plurality of primary storage controllers directed to store the record updates, the plurality of primary storage controllers executing the issued write I/O operation for each record update; and a plurality of primary storage devices receiving and storing the record updates therein according to the corresponding write I/O operations, wherein the primary processor and each write I/O are time-stamped by the primary processor, as synchronized by the sysplex timer, such that write I/O operations are accurately sequence ordered relative to each other, the primary data mover collecting sets of record updates and combining each record set information as provided by each one of the plurality of primary storage controllers with the corresponding record update, each record set information including a relative sequence and time of each corresponding write I/O operation, the primary data mover collecting record updates into time interval groups and inserting a prefix header to each time interval group, wherein the prefix header includes information identifying the record updates included in each time interval group, each record set information and prefix header combined for creating self describing record sets, the self describing record sets being transmitted to the secondary site, wherein the self describing record sets provide information adequate for the secondary site to shadow the record updates therein in sequence consistent order without further communications from the primary site.

Claim 14

The remote data shadowing system according to claim 11 wherein the primary data mover forms time interval groups by establishing a session with all primary storage controllers identified to participate in remote data shadowing.

Claim 15

The remote data shadowing system according to claim 12 wherein the primary data mover collects record set information from all the identified primary storage controllers.

Claim 16

The remote data shadowing system according to claim 13 wherein the primary processor transmits the self describing records to the secondary site.

Claim 17

The remote data shadowing system according to claim 14 wherein the secondary site forms consistency groups from the transmitted self describing records.

Claim 18

The remote data shadowing system according to claim 13 wherein the primary data mover forms consistency groups from the self describing records.

Claim 19

The remote data shadowing system according to claim 13 wherein the primary data mover creates a state table journaling record updates and cross referencing a storage location of each record update on the primary system and the secondary system.

Claim 20

The remote data shadowing system according to claim 13 wherein the plurality of primary storage devices are direct access storage devices (DASDs).

Claim 21

The remote data shadowing system according to claim 18 wherein each record set information comprises: a primary device address; a cylinder number and head number (CCHH); a record update sequence number; a write I/O type; a search argument; a sector number; and a record update time.

Claim 22

The remote data shadowing system according to claim 18 wherein the prefix header comprises: a total data length; an operational time stamp; a time interval group number; and a records read time.

Claim 23

An asynchronous remote data duplexing system providing storage based, real time data shadowing, including a primary site running applications generating record updates and having a secondary site, remote from the primary site, the secondary site shadowing the record updates and providing disaster recovery for the primary site, the asynchronous remote data duplexing system comprising: a sysplex timer for synchronizing time dependent processes in the primary site; a primary processor at the primary site for running the applications and issuing write I/O operations for corresponding record updates, the primary processor having a primary data mover therein; a plurality of primary storage controllers receiving the a write I/O operation for each record update, each primary storage controller write I/O operation synchronized to the sysplex timer by the primary processor; a plurality of primary storage devices storing the record updates therein according to the corresponding write I/O operation, wherein the primary data mover collects record set information from the plurality of primary storage controllers for each record update and appends a prefix header to a predetermined grouped of record set informations, the prefix header and predetermined record set information groups forming self describing record sets, each record set information including a primary device address, a cylinder number and head number (CCHH), a record update sequence number, a write I/O type, a search argument, a sector number, and a record update time, and wherein the prefix header includes a total data length, an operational time stamp, a time interval group number, and a records read time; a secondary processor at the secondary site having a secondary data mover, the secondary data mover receiving the self describing record sets from the primary site; a plurality of secondary storage controllers coupled to the secondary processor; and a plurality of secondary storage devices storing the record updates, wherein the secondary data mover determines whether the transmitted self describing record sets are complete and forms consistency groups from the self describing record sets and provides the record updates from each consistency group to the plurality of secondary storage controllers for writing to the plurality of secondary storage devices in an order consistent with a sequence that the record updates were written to the plurality of primary storage devices.

Claim 24

An asynchronous remote data duplexing system providing storage based, real time data shadowing, including a primary site running applications generating record updates and having a secondary site, remote from the primary site, the secondary site shadowing the record updates and providing disaster recovery for the primary site, the asynchronous remote data duplexing system comprising: a sysplex timer for synchronizing time dependent processes in the primary site; a primary processor at the primary site for running the applications and issuing write I/O operations for corresponding record updates, the primary processor having a primary data mover therein; a plurality of primary storage controllers receiving the a write I/O operation for each record update, each primary storage controller write I/O operation synchronized to the sysplex timer by the primary processor; a plurality of primary storage devices storing the record updates therein according to the corresponding write I/O operation, wherein the primary data mover collects record set information from the plurality of primary storage controllers for each record update and appends a prefix header to a predetermined grouped of record set informations, the prefix header and predetermined record set information groups forming self describing record sets, each record set information including a primary device address, a cylinder number and head number (CCHH), a record update sequence number, a write I/O type, a search argument, a sector number, and a record update time, and wherein the prefix header includes a total data length, an operational time stamp, a time interval group number, and a records read time; a secondary processor at the secondary site having a secondary data mover, the secondary data mover receiving the self describing record sets from the primary site; a plurality of secondary storage controllers coupled to the secondary processor; and a plurality of secondary storage devices storing the record updates, wherein the secondary data mover determines whether the transmitted self describing record sets are complete and forms consistency groups from the self describing record sets and provides the record updates from each consistency group to the plurality of secondary storage controllers for writing to the plurality of secondary storage devices in an order consistent with a sequence that the record updates were written to the plurality of primary storage devices.