bug#46722: test-map-into fails

[Basil L. Contovounesios]

Stefan Monnier <monnier@iro.umontreal.ca> writes:

> This kind of code is supposed to be fully deterministic, so it's quite
> worrisome.  It sounds/smells like memory corruption or some other bug in
> the memory management.
>
> If you could come up with a reasonably simple code (in the sense that it
> doesn't take too long to run) to reproduce this problem with a high
> probability, maybe we can start adding some tracing to try and figure
> out what's going on.
>
> IOW, try and write a loop that runs the problematic code a couple
> hundred times, so that one of those should fail.  Then try and cut down
> the code as much as possible, verifying along the way that the problem
> didn't disappear.

Here's the simplest repro I could find:

  ;;; foo.el -*- lexical-binding: t -*-
  (require 'map)
  (map-into () '(hash-table))
  ;;; foo.el ends here

followed by:

  emacs -Q -batch -f batch-byte-compile foo.el
  while emacs -Q -batch -l foo.elc; do :; done

which barfs the attached after a few seconds.

The same happens with:

  (map-into () '(hash-table :test eq))
  (map-into () '(hash-table :test eql))
  (map-into () '(hash-table :test equal))

but not with:

  (map-into () 'hash-table)

so maybe the heisenbug lies with cl-defmethod's treatment of 'head'?

Let me know if you'd like me to run anything else.

Thanks,

-- 
Basil

backtrace.el
Description: application/emacs-lisp