[petsc-users] sources of floating point randomness in JFNK in serial

I'm running multiple iterations of newtonls with an MFFD/JFNK nonlinear solver where I give it the sparsity. PC asm, KSP gmres, with SNESSetLagJacobian -2 (compute once and then frozen jacobian). I'm seeing slight (<1%) but nonzero differences in residuals from run to run. I'm wondering where randomness might enter here -- does the jacobian coloring use a random seed?