histogram of file sizes, and how many files are in that size range.

filesize_histogram

find . -type f -print0 | xargs -0 ls -l | awk '{ n=int(log($5)/log(2)); if (n<10) { n=10; } size[n]++ } END { for (i in size) printf("%d %d\n", 2^i, size[i]) }' | sort -n | awk 'function human(x) { x[1]/=1024; if (x[1]>=1024) { x[2]++; human(x) } } { a[1]=$1; a[2]=0; human(a); printf("%3d%s: %6d\n", a[1],substr("kMGTEPYZ",a[2]+1,1),$2) }'

--e.g.
--  1k: 270448
--  2k:  72548
--  4k:  74510
--  8k:  62799
-- 16k:  36386
-- 32k:  74070
-- 64k:  21528
--128k:  30624
--256k:  25892
--512k:  83264
--1M: 140595
--2M:  23716
--4M:  14846
--8M:   4843