Checkpointing a set of stream computing data

Abstract

Disclosed aspects relate to checkpointing a set of stream computing data with respect to a stream computing environment having a set of windowed stream operators including both a first windowed stream operator and a second windowed stream operator. It may be identified that the first windowed stream operator has a first subset of the set of stream computing data. It may be identified that the second windowed stream operator has the first subset of the set of stream computing data. It may be determined to checkpoint the first subset of the set of stream computing data without a redundant checkpoint related to the first and second windowed stream operators. The set of stream computing data may be checkpointed without the redundant checkpoint of the first subset of the set of stream computing data.

What is claimed is: 
     
         1 . A system for checkpointing a set of stream computing data with respect to a stream computing environment having a set of windowed stream operators including both a first windowed stream operator and a second windowed stream operator, the system comprising:
 a memory configured to store executable instructions; and   a processor communicatively coupled to the memory and configured to execute the executable instructions to:   identify in real time, with respect to the stream computing environment, that the first windowed stream operator has a first subset of the set of stream computing data, wherein the first windowed stream operator includes a filter operator associated with a common window that stores incoming tuples prior to filtering;   identify, with respect to the stream computing environment, that the second windowed stream operator has the first subset of the set of stream computing data, wherein the second windowed stream operator includes a sort operator associated with the common window that stores incoming tuples prior to sorting, the common window shared by both the first and second windowed stream operators;   determine, based on both the first and second windowed stream operators having the first subset of the set of stream computing data, to checkpoint the first subset of the set of stream computing data without a redundant checkpoint related to the first and second windowed stream operators;   checkpoint, with respect to the stream computing environment, the set of stream computing data without the redundant checkpoint of the first subset of the set of stream computing data related to the first and second windowed stream operators;   detect a first throughput factor for the first windowed stream operator, the first throughput factor including an indication of the rate at which data is processed by the first windowed stream operator;   detect a second throughput factor for the second windowed stream operator, the second throughput factor including an indication of the rate at which data is processed by the second windowed stream operator;   compare the first and second throughput factors for the first and second windowed stream operators;   determine that the first throughput factor exceeds the second throughput factor;   in response to determining that the first throughput factor exceeds the second throughput factor, checkpoint, with respect to the stream computing environment, the set of stream computing data using the first windowed stream operator to checkpoint the first subset of the set of stream computing data and prevent, with respect to the stream computing environment, the second windowed stream operator from checkpointing the first subset of the set of stream computing data;   wherein the processor is further configured to:   identify, with respect to the stream computing environment, that the first windowed stream operator has a second subset of the set of stream computing data;   identify, with respect to the stream computing environment, that the second windowed stream operator has a third subset of the set of stream computing data;   checkpoint, with respect to the stream computing environment, the set of stream computing data using the first windowed stream operator to checkpoint the second subset of the set of stream computing data; and   checkpoint, with respect to the stream computing environment, the set of stream computing data using the second windowed stream operator to checkpoint the third subset of the set of stream computing data.