Reducing data using a plurality of compression operations in a virtual tape library

Patent metadata

Field	Value
Publication number	US-11487430-B2
Application number	US-201815923372-A
Country	US
Kind code	B2
Filing date	Mar 16, 2018
Priority date	Mar 16, 2018
Publication date	Nov 1, 2022
Grant date	Nov 1, 2022

Abstract

Embodiments are provided for reducing data using a plurality of compression operations in a computing storage environment. A speed of data writing to a virtual tape device and an availability of one or more processor devices for the virtual tape device may be monitored. One or more requests may be received for writing data to the virtual tape device. Data to be written to the virtual tape device, corresponding to a selected number of the one or more requests for writing the data, may be compressed according to both the speed of data writing to the virtual tape device and the availability of one or more processor devices for the virtual tape device. The compressed data may be stored in the virtual tape device in record units. Non-compressed data may be compressed in the virtual tape device at a subsequent period of time (e.g., future time period).

First claim

What is claimed is:

1. A method, by a processor, for reducing data using a plurality of compression operations in a computing storage environment, comprising:
monitoring both a speed of data writing to a virtual tape device and an availability of one or more processor devices for the virtual tape device;
receiving a write request to write data to the virtual tape device, wherein the data corresponding to the write request is divided into a plurality of records;
for all of the plurality of records intended to be stored as compressed records on the virtual tape device via a predetermination prior to the write request, compressing, as the plurality of records of the write request are successively received in real-time as a data stream and written to the virtual tape device, a first number of the plurality of records while withholding any compression, as the plurality of records of the write request are successively received in real-time as the data stream and written to the virtual tape device, of a second number of the plurality of records, wherein the compression and withholding of compression is performed according to both the speed of data writing to the virtual tape device and the availability of one or more processor devices for the virtual tape device;
storing the first number of records of the data corresponding to the write request interleaved with the second number of records of the data corresponding to the write request in the virtual tape device, wherein, during the writing of all of the plurality of records intended to be stored as compressed records to the virtual tape device, the data is selectively compressed for each of N records of the plurality of records during a given interval of time thereby interleaving compressed records with non-compressed records within the data corresponding to the write request, wherein N is a positive integer of a predetermined value which is increased and decreased for the given interval of time by determining performance information inclusive of whether the speed of data writing to the virtual tape device is greater than a user-specified minimally acceptable writing speed and the availability of one or more processor devices for the virtual tape device is greater than a user-specified minimally acceptable availability of the one or more processor devices, and wherein N, corresponding to the first number of records of the data stored as the compressed records, is automatically determined in real-time at each given interval of time by computing the performance information subsequent to a sleep period between each given interval of time; and
compressing non-compressed data of the plurality of records intended to be stored as compressed records upon completing the writing the data to the virtual tape device when an amount of Input/Output (I/O) operations to and from the virtual tape device is below a threshold value and according to the availability of one or more processor devices for the virtual tape device, wherein the compressing of the non-compressed data is performed such that a capacity used by the virtual tape device subsequent to compressing the non-compressed data is equivalent to a capacity which would have been used by the virtual storage device were all the plurality of records had been compressed while initially performing the writing to the virtual tape device by performing a post-processing operation on each of the second number of the plurality of records subsequent to the compressing upon completion of the writing.

2. The method of claim 1 , further including adding an indicator to indicate that the data is compressed in a record header region of a corresponding record.

3. The method of claim 1 , further including:
detecting the non-compressed data that is stored in one of the plurality of records of the virtual tape device; and
compressing the detected non-compressed data according to both the speed of data writing to the virtual tape device and the availability of one or more processor devices for the virtual tape device.

4. The method according to claim 3 , further including creating a hole in one of the plurality of records by compressing the detected non-compressed data and converting the virtual tape device to a sparse file.

5. The method according to claim 1 , further including:
receiving one or more requests for reading data from the virtual tape device;
determining whether the data is compressed and stored in records corresponding to the one or more requests for reading data;
decompressing the compressed data in the records for the data that is determined to be compressed and stored; and
sending the decompressed data to a requester.

6. A system, for reducing data using a plurality of compression operations in a computing storage environment, comprising:
one or more processors with executable instructions that when executed cause the system to:
monitor both a speed of data writing to a virtual tape device and an availability of one or more processor devices for the virtual tape device;
receive a write request to write data to the virtual tape device, wherein the data corresponding to the write request is divided into a plurality of records;
for all of the plurality of records intended to be stored as compressed records on the virtual tape device via a predetermination prior to the write request, compress, as the plurality of records of the write request are successively received in real-time as a data stream and written to the virtual tape device, a first number of the plurality of records while withholding any compression, as the plurality of records of the write request are successively received in real-time as the data stream and written to the virtual tape device, of a second number of the plurality of records, wherein the compression and withholding of compression is performed according to both the speed of data writing to the virtual tape device and the availability of one or more processor devices for the virtual tape device;
store the first number of records of the data corresponding to the write request interleaved with the second number of records of the data corresponding to the write request in the virtual tape device, wherein, during the writing of all of the plurality of records intended to be stored as compressed records to the virtual tape device, the data is selectively compressed for each of N records of the plurality of records during a given interval of time thereby interleaving compressed records with non-compressed records within the data corresponding to the write request, wherein N is a positive integer of a predetermined value which is increased and decreased for the given interval of time by determining performance information inclusive of whether the speed of data writing to the virtual tape device is greater than a user-specified minimally acceptable writing speed and the availability of one or more processor devices for the virtual tape device is greater than a user-specified minimally acceptable availability of the one or more processor devices, and wherein N, corresponding to the first number of records of the data stored as the compressed records, is automatically determined in real-time at each given interval of time by computing the performance information subsequent to a sleep period between each given interval of time; and
compress non-compressed data of the plurality of records intended to be stored as compressed records upon completing the writing the data to the virtual tape device when an amount of Input/Output (I/O) operations to and from the virtual tape device is below a threshold value and according to the availability of one or more processor devices for the virtual tape device, wherein the compressing of the non-compressed data is performed such that a capacity used by the virtual tape

Assignees

• IBM

Inventors

• Tsuda Takahiro
• Masuda Koichi
• Matsui Sosuke
• Nohta Takeshi
• Mitsuma Shinsuke
• Kawamura Kousei

Classifications

• G06F3/0661

  Format or protocol conversion arrangements · CPC title

• G06F3/0686

  Libraries, e.g. tape libraries, jukebox · CPC title

• G11C2207/102

  Compression or decompression of data before storage · CPC title

• G06F3/0659

  Command handling arrangements, e.g. command buffers, queues, command scheduling · CPC title

• G06F3/0608 Primary

  Saving storage space on storage systems · CPC title