A recent compression discussion I saw involved how do compressors fare on uncompressible input? For example, suppose you wanted to add compression to all your outbound network traffic. What would happen if there was mixed compressible traffic along with the uncomressible kind? A common case would be sending HTML along with JPEG.
Good compressors can't squeeze any more out of a JPEG, but they can back off fast and go faster. Snappy was designed to do this, and even implementations of gzip do it too. It greatly reduces the fear of CPU overhead to always on compression. I wonder how Zstd handles such cases?
Known techniques. JPEG uses Huffman coding for entropy coding, you can replace that with arithmetic coding. This requires knowing the format details, though.
Good compressors can't squeeze any more out of a JPEG, but they can back off fast and go faster. Snappy was designed to do this, and even implementations of gzip do it too. It greatly reduces the fear of CPU overhead to always on compression. I wonder how Zstd handles such cases?
*Ignoring security altogether