Writing and reading data in tape media

• US 9,025,261 B1
• Filed: 11/18/2013
• Issued: 05/05/2015
• Est. Priority Date: 11/18/2013
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hasegawa, Tohru, Oishi, Yutaka
• Primary Examiner(s): Mercedes, Dismery
• Application Number:
  US14/082,565
• Publication Number:
  US 20150138665A1
• Time in Patent Office: 533 Days
• Field of Search: None
• US Class Current: 360/8
• CPC Class Codes: G11B 15/442 Control thereof
• CPC Class Codes: G11B 20/00007 Time or data compression or expansion audio compression based on psychoacoustics G10L19/00; data processing for reproducing audio data at different playback speeds G10L21/04; video compression H04N19/00; data compression per se H03M7/30

Abstract

A mechanism is provided for determining storage device speed based on a ratio of data compression. A bandwidth (B) is identified between a storage device accessing storage medium and a host application requesting access to data on the storage medium. A host side transfer rate is identified, where the host side transfer rate (HSTR) is a rate of data transfer between the host application and the storage device. For each data set in a set of data sets of a record, a ratio of data compression (R) is identified for the data set; a compression considered host side transfer rate (CCHSTR) is determined; and the storage device speed is set to the compression considered host side transfer rate (CCHSTR) for transmitting the data set to the host application.

Claims

1. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:

identify a bandwidth (B) between a storage device accessing storage medium and a host application requesting access to data on the storage medium;

identify a host side transfer rate, wherein the host side transfer rate (HSTR) is a rate of data transferred between the host application and the storage device; and

for each data set in a set of data sets of a record;

identify a ratio of data compression (R) for the data set;

determine a compression considered host side transfer rate (CCHSTR), wherein the compression considered host side transfer rate (CCHSTR) is determined utilizing;

CCHSTR=max (B, HSTR/R); and

set a storage device speed to the compression considered host side transfer rate (CCHSTR) for transmitting the data set to the host application.

2. The computer program product of claim 1, wherein the ratio of data compression (R) for the data set is determined by the computer readable program further causing the computing device to:

compare a data length of the data set before compression to a data length of the data set after compression during a writing of the record to the storage medium, wherein the comparison forms the ratio of data compression (R) for the data set.

3. The computer program product of claim 1, wherein the computer readable program further causes the computing device to:

for each data set in the set of data sets of a record;

determine whether the data set is the first data set of the record; and

responsive to the data set being the first data set of the record, transmit the data set to the host application at the compression considered host side transfer rate (CCHSTR).

4. The computer program product of claim 3, wherein the computer readable program further causes the computing device to:

responsive to the data set failing to be the first data set of the record, determine whether a rate of transfer by a hard disk (Th) associated with the host application is greater than the highest rate of transfer of data that cannot be compressed on the storage medium (Tt) divided by the ratio of data compression (R) for the data set using;

Th>

Tt/R; and

responsive to Th being greater than Tt/R, transmit the data set to the host application at the compression considered host side transfer rate (CCHSTR).

5. The computer program product of claim 4, wherein the computer readable program further causes the computing device to:

responsive to Th being less than or equal to Tt/R, determine whether a maximum time of seeking of data on the hard disk associated with the host application (Sh) when added to a capacity (volume) of data associated with a particular data set (Cd) divided by the rate of transfer by the hard disk (Th) is greater than a maximum time of seeking of data by the storage device reading the tape medium (St) using;

Sh+(Cd/Th)>

St;

responsive to Sh+(Cd/Th) being less than or equal to St, transmit the data set to the host application at the compression considered host side transfer rate (CCHSTR); and

responsive to Sh+(Cd/Th) being greater than St, read out a next data set and repeat the process.

6. The computer program product of claim 1, wherein the computer readable program further causes the computing device to:

determine whether the record being read is written over a plurality of data sets;

responsive to the record being read being written over the plurality of data sets, identify an average of the ratios of data compression for the plurality of data sets (A) over which the record is written; and

utilize the identified average of the ratios of data compression for the plurality of data sets (A) for transmitting the plurality of data sets to the host application.

7. The computer program product of claim 6, wherein the average of the ratios of data compression for the plurality of data sets is increased when data is added to the record using:

A=(L*O+La*R)/(L+La)

where A is the average of ratios of data compression for the plurality of data sets, L is a size (length) of the record, O is a previous average of ratios of data compression for the plurality of data sets, R is a ratio of data compression (R) of the data that is being added, and La is a size (length) of the data that is being added.

8. The computer program product of claim 6, wherein the average of the ratios of data compression for the plurality of data sets is decreased when data is deleted from the record using:

A=(L*O−

Ld*R)/(L−

Ld)

where A is the average of ratios of data compression for the plurality of data sets, L is a size (length) of the record, O is a previous average of ratios of data compression for the plurality of data sets, R is a ratio of data compression (R) of the data that is being added, and Ld is a size (length) of the data that is being deleted.

9. The computer program product of claim 1, wherein the computer readable program further causes the computing device to:

determine whether the record has changed either through adding of data and/or deletion of data thereby breaking the record into one or more portions;

responsive to the record changing, identify for each portion of the one or more portions of the record a wrap of a head (start) of the portion (Ws), a lpos of the head (start) of the portion (Ps), a wrap of a tail (end) of the portion (We), and the lpos of the tail (end) of the portion (Pe);

utilize the identified values, determining whether one or more access times between the one or more portions of the record exceed a predetermined record access time threshold; and

responsive to one or more access times between the one or more portions of the record exceeding the predetermined record access time threshold, mark the record for reclamation.

10. The computer program product of claim 1, wherein the computer readable program further causes the computing device to:

determine whether one or more records have changed either through adding of data and/or deletion of data;

responsive to one or more records changing, determine whether a difference between a sum of areas Zt for all records written to the tape medium and a sum of areas Ze for all records deleted from the tape medium exceeds a predetermined tape medium reclamation threshold; and

responsive to the difference between the sum of areas Zt for all records written to the tape medium and the sum of areas Ze for all records deleted from the tape medium exceeding the predetermined tape medium reclamation threshold, mark the storage medium as a whole for reclamation.

11. A method, in a data processing system, for determining storage device speed based on a ratio of data compression, the method comprising:

identifying a bandwidth (B) between a storage device accessing storage medium and a host application requesting access to data on the storage medium;

identifying a host side transfer rate, wherein the host side transfer rate (HSTR) is a rate of data transferred between the host application and the storage device; and

for each data set in a set of data sets of a record;

identifying the ratio of data compression (R) for the data set;

determining a compression considered host side transfer rate (CCHSTR), wherein the compression considered host side transfer rate (CCHSTR) is determined utilizing;

CCHSTR=max (B, HSTR/R); and

setting the storage device speed to the compression considered host side transfer rate (CCHSTR) for transmitting the data set to the host application.

12. The method of claim 11, wherein the ratio of data compression (R) for the data set is determined by the method comprising:

comparing a data length of the data set before compression to a data length of the data set after compression during writing of the record to the storage medium, wherein the comparison forms the ratio of data compression (R) for the data set.

13. The method of claim 11, further comprising:

for each data set in the set of data sets of a record;

determining whether the data set is the first data set of the record;

responsive to the data set being the first data set of the record, transmitting the data set to the host application at the compression considered host side transfer rate (CCHSTR);

responsive to the data set failing to be the first data set of the record, determining whether a rate of transfer by a hard disk (Th) associated with the host application is greater than the highest rate of transfer of data that cannot be compressed on the storage medium (Tt) divided by the ratio of data compression (R) for the data set using;

Th>

Tt/R,

responsive to Th being greater than Tt/R, transmitting the data set to the host application at the compression considered host side transfer rate (CCHSTR);

responsive to Th being less than or equal to Tt/R, determining whether a maximum time of seeking of data on the hard disk associated with the host application (Sh) when added to a capacity (volume) of data associated with a particular data set (Cd) divided by the rate of transfer by the hard disk (Th) is greater than a maximum time of seeking of data by the storage device reading the tape medium (St) using;

Sh+(Cd/Th)>

St;

responsive to Sh+(Cd/Th) being less than or equal to St, transmitting the data set to the host application at the compression considered host side transfer rate (CCHSTR); and

responsive to Sh+(Cd/Th) being greater than St, reading out a next data set and repeating the process.

14. The method of claim 11, further comprising:

determining whether the record being read is written over a plurality of data sets;

responsive to the record being read being written over the plurality of data sets, identifying an average of the ratios of data compression for the plurality of data sets (A) over which the record is written; and

utilizing the identified average of the ratios of data compression for the plurality of data sets (A) for transmitting the plurality of data sets to the host application, wherein the average of the ratios of data compression for the plurality of data sets is increased when data is added to the record using;

A=(L*O+La*R)/(L+La)

where A is the average of ratios of data compression for the plurality of data sets, L is a size (length) of the record, O is a previous average of ratios of data compression for the plurality of data sets, R is a ratio of data compression (R) of the data that is being added, and La is a size (length) of the data that is being added and wherein the average of the ratios of data compression for the plurality of data sets is decreased when data is deleted from the record using;

A=(L*O−

Ld*R)/(L−

Ld)

where A is the average of ratios of data compression for the plurality of data sets, L is a size (length) of the record, O is a previous average of ratios of data compression for the plurality of data sets, R is a ratio of data compression (R) of the data that is being added, and Ld is a size (length) of the data that is being deleted.

15. The method of claim 11, further comprising;

determining whether the record has changed either through adding of data and/or deletion of data thereby breaking the record into one or more portions;

responsive to the record changing, identifying for each portion of the one or more portions of the record a wrap of a head (start) of the portion (Ws), a lpos of the head (start) of the portion (Ps), a wrap of a tail (end) of the portion (We), and the lpos of the tail (end) of the portion (Pe);

utilizing the identified values, determining whether one or more access times between the one or more portions of the record exceed a predetermined record access time threshold; and

responsive to one or more access times between the one or more portions of the record exceeding the predetermined record access time threshold, marking the record for reclamation.

16. The method of claim 11, further comprising:

determining whether one or more records have changed either through adding of data and/or deletion of data;

responsive to one or more records changing, determining whether a difference between a sum of areas Zt for all records written to the tape medium and a sum of areas Ze for all records deleted from the tape medium exceeds a predetermined tape medium reclamation threshold; and

responsive to the difference between the sum of areas Zt for all records written to the tape medium and the sum of areas Ze for all records deleted from the tape medium exceeding the predetermined tape medium reclamation threshold, marking the storage medium as a whole for reclamation.

17. An apparatus comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to;

identify a bandwidth (B) between a storage device accessing storage medium and a host application requesting access to data on the storage medium;

identify a host side transfer rate, wherein the host side transfer rate (HSTR) is a rate of data transferred between the host application and the storage device; and

for each data set in a set of data sets of a record;

identify a ratio of data compression (R) for the data set;

determine a compression considered host side transfer rate (CCHSTR), wherein the compression considered host side transfer rate (CCHSTR) is determined utilizing;

CCHSTR=max (B, HSTR/R); and

set a storage device speed to the compression considered host side transfer rate (CCHSTR) for transmitting the data set to the host application.

18. The apparatus of claim 17, wherein the ratio of data compression (R) for the data set is determined by the instructions further causing the processor to:

compare a data length of the data set before compression to a data length of the data set after compression during a writing of the record to the storage medium, wherein the comparison forms the ratio of data compression (R) for the data set.

19. The apparatus of claim 17, wherein the instructions further cause the processor to:

for each data set in the set of data sets of a record;

determine whether the data set is the first data set of the record;

responsive to the data set being the first data set of the record, transmit the data set to the host application at the compression considered host side transfer rate (CCHSTR);

responsive to the data set failing to be the first data set of the record, determine whether a rate of transfer by a hard disk (Th) associated with the host application is greater than the highest rate of transfer of data that cannot be compressed on the storage medium (Tt) divided by the ratio of data compression (R) for the data set using;

Th>

Tt/R; and

responsive to Th being greater than Tt/R, transmit the data set to the host application at the compression considered host side transfer rate (CCHSTR);

responsive to Th being less than or equal to Tt/R, determine whether a maximum time of seeking of data on the hard disk associated with the host application (Sh) when added to a capacity (volume) of data associated with a particular data set (Cd) divided by the rate of transfer by the hard disk (Th) is greater than a maximum time of seeking of data by the storage device reading the tape medium (St) using;

Sh+(Cd/Th)>

St;

responsive to Sh+(Cd/Th) being less than or equal to St, transmit the data set to the host application at the compression considered host side transfer rate (CCHSTR); and

responsive to Sh+(Cd/Th) being greater than St, read out a next data set and repeat the process.

20. The apparatus of claim 17, wherein the instruction further cause the processor to:

determine whether the record being read is written over a plurality of data sets;

responsive to the record being read being written over the plurality of data sets, identify an average of the ratios of data compression for the plurality of data sets (A) over which the record is written; and

utilize the identified average of the ratios of data compression for the plurality of data sets (A) for transmitting the plurality of data sets to the host application, wherein the average of the ratios of data compression for the plurality of data sets is increased when data is added to the record using;

A=(L*O+La*R)/(L+La)

where A is the average of ratios of data compression for the plurality of data sets, L is a size (length) of the record, O is a previous average of ratios of data compression for the plurality of data sets, R is a ratio of data compression (R) of the data that is being added, and La is a size (length) of the data that is being added and wherein the average of the ratios of data compression for the plurality of data sets is decreased when data is deleted from the record using;

A=(L*O−

Ld*R)/(L−

Ld)

where A is the average of ratios of data compression for the plurality of data sets, L is a size (length) of the record, O is a previous average of ratios of data compression for the plurality of data sets, R is a ratio of data compression (R) of the data that is being added, and Ld is a size (length) of the data that is being deleted.