Re: profiling emacs-23.1 vs emacs-22.3

[Kenichi Handa <handa@m17n.org>]

In article <200908260633.n7Q6XRXi018187@godzilla.ics.uci.edu>, Dan Nicolaescu <dann@ics.uci.edu> writes:

> Some CJK charsets are necessary to create the default
> fontset.  I think it's possible to avoid loading unnecessary
> charsets for creating the default fontset.  I'll work on it.

> Can the data in the default fontset be in the dumped image in pure
> memory?  To not have to create it every time on start up and GC it
> should be a win.

Is it possible to put the whole char-table in pure space,
then modify some part at running time?

> So, (3) is still 13% slower than (1), but I think it's a
> necessary cost for having the full Unicode support.  And
> usually the slowness of GC doesn't direclty affect the total
> execution time.

> It does, see the profiling data that I sent.  The problem with GC is
> that it will flush all the caches if there's too much memory to walk
> over.  And the slowdown in GC speed is directly related to the big
> increase in the number of GCable objects.

If most of the execution is spent by GC, shouldn't such a
task run with bigger gc-cons-threshold?

But, I tried your test case of indent-region with different
gc-cons-threshold (gct), and the result shows that GC is not
the main culprit of the slowness.

emacs-22 (gct=400000):	16 to 17 sec
emacs-22 (gct=10000000):16 to 17 sec
trunk (gct=400000):	20 to 21 sec
trunk (gct=10000000):	19 to 20 sec

---
Kenichi Handa
handa@m17n.org