Dynamically sized redundant write buffer with sector-based tracking

A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to:

• detect an operation to read data from a cache, wherein the cache is divided into a plurality of channels and further divided into a plurality of sets addressed via set values;
• determine that an attempt to read the data from a first cache line in the cache failed, wherein the first cache line is accessed via a first channel;
• in response to the determination, select a second cache line for reading a redundant copy of the data, wherein the second cache line is accessed via a second channel and selected because the first and second cache lines have a same set value on different channels;
• and
• read the redundant copy of the data from the second cache line in the cache.

A system comprising:

• a plurality of memory components;
• and
• a processing device, operatively coupled with the plurality of memory components, to:
• detect an operation to read data from a cache, wherein the cache is divided into a plurality of channels and further divided into a plurality of sets addressed via set values;
• determine that an attempt to read the data from a first cache line in the cache failed, wherein the first cache line is accessed via a first channel;
• in response to the determination, select a second cache line for reading a redundant copy of the data, wherein the second cache line is accessed via a second channel and selected because the first and second cache lines have a same set value on different channels;
• and
• read the redundant copy of the data from the second cache line in the cache, wherein reading the redundant copy of the data includes parsing the same set value on the second channel for a way marked as a redundant write buffer and locating a metadata entry for the redundant write buffer that references a location of the attempted read of the first cache line.