Spindel Ljungmark

I have done some experiments here to see if it's worth replacing our current VCDIFF based updater for squashfs , and the best I end up with is an order...

mean uncompressed inside squashfs file is 22k large The filesystems are root filesystems for ARM, designed to fit in a 128MiB partition. I'm continuing some testing to get more numbers...


I've done more comparisions on various block sizes of squashfs + casync. Here are all the deltas that are in "acceptable" size (

Worth noting is that when blocksize is < 8K or similar, the storage area for the blocks on disk is larger than the storage area of the individiual block files...

Squashfs doesn't compress files individually. It compresses blocks, a block can contain many files due to tail packing. Side note: That's why you see worse deltas between similar filesystems on...

That was an experiment, I'm trying to get this query up to at least _approximate_ the time it takes on a normal table with a brin index. Perhaps the question...

The data table is approximately 25 gigs uncompressed, compresses down to a rather respectable 3-5 gigabytes in size. This is a small subset of 1 year data, 2000 sensors of...

Well, we are (in live) already disk IO bound, and hitting massive slowdowns there, because a single seek will blow much of the dcache, etc. However, the current "comparision" for...

So, testing shows that for my workload: - Order by the most common selector when inserting (itemid,clock) rather than the natural insert order (clock, itemid) Causes the difference between extra...