Lags and setjmp
Super Bisquit
superbisquit at gmail.com
Sun Aug 7 19:19:39 UTC 2011
On Sun, Aug 7, 2011 at 11:19 AM, Super Bisquit <superbisquit at gmail.com>wrote:
> On 8/6/11, Super Bisquit <superbisquit at gmail.com> wrote:
> > On Sat, Aug 6, 2011 at 11:37 AM, Nathan Whitehorn
> > <nwhitehorn at freebsd.org>wrote:
> >
> >> On 08/05/11 10:47, Super Bisquit wrote:
> >>
> >>> The file /usr/src/sys/powerpc/powerpc/**setjmp.S has
> >>>
> >>> #ifdef __powerpc64__
> >>>
> >>> at line nine. Maybe this is affecting the system because:
> >>> the lag seems to occur on Xorg/Xserver with the cursor having to be
> >>> moved
> >>> before there is a response.
> >>> I'm wondering if setting the vale to powerpc instead of powerpc64 would
> >>> stop
> >>> this action.
> >>>
> >>>
> >> It wouldn't for the reason Justin said, and this file only applies to
> the
> >> kernel besides. I've also never experienced this bug you're referring
> to.
> >> Is
> >> X using longjmp/setjmp() internally? One thing we do not do is
> >> save/restore
> >> FP registers for long jumps. It's not required by the spec, but Linux
> >> does
> >> do it.
> >> -Nathan
> >>
> >> ______________________________**_________________
> >> freebsd-ppc at freebsd.org mailing list
> >> http://lists.freebsd.org/**mailman/listinfo/freebsd-ppc<
> http://lists.freebsd.org/mailman/listinfo/freebsd-ppc>
> >> To unsubscribe, send any mail to
> >> "freebsd-ppc-unsubscribe@**freebsd.org<
> freebsd-ppc-unsubscribe at freebsd.org>
> >> "
> >>
> >
> > How's it going?
> >
> > Anyway, I'm not sure. I'll restart X with a more verbose output and will
> > attach the file next reply.
> > I'm curious, what machines are you using for the 9.0 PowerPC ?
> >
>
>
> I did not find anything. This problem only occurs with the G4 systems.
> Unless someone else has the same equipment, it's just an "annoyance"
> bug for me.
>
Anyone with the following systems: iMac G4 800MHz nVidia NV11 /GeForce MX/MX
400, Quicksilver G4 2002 933MHz with Radeon 7500/RV200 QW, or a B&W G3
400MHz with ATI Rage 128?
The files included show a lag/hang when the pointer is moved during a
glxgears session. I've ran glxgears on FreeBSD/i386 using an IGP and did not
have the problem. Nathan Whitehorn mentioned that the problem may- forgive
my paraphrasing- be at stjmp and longjmp. Okay, then why does this problem
not occur with Debian or OpenBSD? Just curious if it is the driver and
FreeBSD or possible what Matthieu Herb stated. Has pixmap caused problems
before?
FreeBSD/x11 does not have enough people familiar with powerpc(64) to
understand the problem.
-------------- next part --------------
GLX 1.3 is not supported.
GLX_SGIX_fbconfig is supported.
The following fbconfigs meet the requirements. The first one will be used.
0x8e TrueColor 24 0 y . y . 8 8 8 0 24 0 0 0 0 0 0 0 y .
0xce DirectColor 24 0 y . y . 8 8 8 0 24 0 0 0 0 0 0 0 y .
0x92 TrueColor 24 0 y . y . 8 8 8 0 24 8 0 0 0 0 0 0 y .
0xd2 DirectColor 24 0 y . y . 8 8 8 0 24 8 0 0 0 0 0 0 y .
0x9e TrueColor 32 0 y . y . 8 8 8 8 24 0 0 0 0 0 0 0 y .
0xde DirectColor 32 0 y . y . 8 8 8 8 24 0 0 0 0 0 0 0 y .
0xa2 TrueColor 32 0 y . y . 8 8 8 8 24 8 0 0 0 0 0 0 y .
0xe2 DirectColor 32 0 y . y . 8 8 8 8 24 8 0 0 0 0 0 0 y .
0x7e TrueColor 16 0 y . y . 5 6 5 0 16 0 0 0 0 0 0 0 y .
0xbe DirectColor 16 0 y . y . 5 6 5 0 16 0 0 0 0 0 0 0 y .
0x82 TrueColor 16 0 y . y . 5 6 5 0 16 8 0 0 0 0 0 0 y .
0xc2 DirectColor 16 0 y . y . 5 6 5 0 16 8 0 0 0 0 0 0 y .
0x6e TrueColor 8 0 y . y . 3 3 2 0 8 0 0 0 0 0 0 0 y .
0xae DirectColor 8 0 y . y . 3 3 2 0 8 0 0 0 0 0 0 0 y .
0x72 TrueColor 8 0 y . y . 3 3 2 0 8 8 0 0 0 0 0 0 y .
0xb2 DirectColor 8 0 y . y . 3 3 2 0 8 8 0 0 0 0 0 0 y .
0x8f TrueColor 24 0 y . y . 8 8 8 0 24 0 16 16 16 0 0 0 y .
0xcf DirectColor 24 0 y . y . 8 8 8 0 24 0 16 16 16 0 0 0 y .
0x93 TrueColor 24 0 y . y . 8 8 8 0 24 8 16 16 16 0 0 0 y .
0xd3 DirectColor 24 0 y . y . 8 8 8 0 24 8 16 16 16 0 0 0 y .
0x9f TrueColor 32 0 y . y . 8 8 8 8 24 0 16 16 16 16 0 0 y .
0xdf DirectColor 32 0 y . y . 8 8 8 8 24 0 16 16 16 16 0 0 y .
0xa3 TrueColor 32 0 y . y . 8 8 8 8 24 8 16 16 16 16 0 0 y .
0xe3 DirectColor 32 0 y . y . 8 8 8 8 24 8 16 16 16 16 0 0 y .
0x7f TrueColor 16 0 y . y . 5 6 5 0 16 0 16 16 16 0 0 0 y .
0xbf DirectColor 16 0 y . y . 5 6 5 0 16 0 16 16 16 0 0 0 y .
0x83 TrueColor 16 0 y . y . 5 6 5 0 16 8 16 16 16 0 0 0 y .
0xc3 DirectColor 16 0 y . y . 5 6 5 0 16 8 16 16 16 0 0 0 y .
0x6f TrueColor 8 0 y . y . 3 3 2 0 8 0 16 16 16 0 0 0 y .
0xaf DirectColor 8 0 y . y . 3 3 2 0 8 0 16 16 16 0 0 0 y .
0x73 TrueColor 8 0 y . y . 3 3 2 0 8 8 16 16 16 0 0 0 y .
0xb3 DirectColor 8 0 y . y . 3 3 2 0 8 8 16 16 16 0 0 0 y .
116 frames in 8.0 seconds = 14.500 FPS
65 frames in 5.0 seconds = 13.000 FPS
76 frames in 5.0 seconds = 15.200 FPS
74 frames in 5.0 seconds = 14.800 FPS
123 frames in 5.0 seconds = 24.600 FPS
16 frames in 10.0 seconds = 1.600 FPS
103 frames in 7.0 seconds = 14.714 FPS
59 frames in 5.0 seconds = 11.800 FPS
84 frames in 5.0 seconds = 16.800 FPS
-------------- next part --------------
146 frames in 27.4 seconds = 5.335 FPS
94 frames in 5.2 seconds = 18.058 FPS
76 frames in 5.0 seconds = 15.152 FPS
82 frames in 5.0 seconds = 16.376 FPS
52 frames in 8.2 seconds = 6.346 FPS
98 frames in 5.0 seconds = 19.519 FPS
104 frames in 5.0 seconds = 20.679 FPS
104 frames in 5.0 seconds = 20.775 FPS
168 frames in 5.1 seconds = 33.198 FPS
45 frames in 5.0 seconds = 8.965 FPS
110 frames in 5.1 seconds = 21.635 FPS
44 frames in 5.7 seconds = 7.785 FPS
89 frames in 5.2 seconds = 17.253 FPS
More information about the freebsd-ppc
mailing list