On 7/11/19 10:49 AM, user...@yahoo.com wrote: > On 7/4/19 1:07 PM, user...@yahoo.com wrote: >> Correction: The CPU of the Wallstreet is 266 MHz, not 292 MHz. > > Update: > > Please see attached "all.tar.xz", which contains the following files: > > "x11perf -all" tests: > > 1) x11perf_8_fbdev.txt : Debian 8.11, mach64 removed > 2) x11perf_8_mach64.txt : Debian 8.11, mach64 installed > 3) x11perf_sid_fbdev.txt : Debian sid, mach64 removed > 4) x11perf_sid_mach64.txt : Debian sid, mach64 installed > 5) x11perfcomp.txt : comparison of the above four tests > > "/var/log/Xorg.0.log" files: > > 6) Xorg_8_fbdev.log : Xorg log file for test (1) > 7) Xorg_8_mach64.log : Xorg log file for test (2) > 8) Xorg_sid_fbdev.log : Xorg log file for test (3) > 9) Xorg_sid_mach64.log : Xorg log file for test (4) > > "glxgears" (from mesa-utils) tests: > > 10) glxgears.txt > ...
I added two tests. Please see the attached "update.tar.xz", which contains the following six files: "x11perf -all" tests: 11) x11perf_sid_fbdev-1.txt : Debian sid, mach64 removed, multiuser 12) x11perf_sid_mach64-1.txt : Debian sid, mach64 installed, multiuser 13) x11perfcomp_sid.txt : comparison of 3), 4), 11) and 12) "/var/log/Xorg.0.log" files: 14) Xorg_sid_fbdev-1.log : Xorg log file for 11) 15) Xorg_sid_mach64-1.log : Xorg log file for 12) serial console log: 16) console_log.txt : console log file for 11) and 12) The G3 Wallstreet test system was booted multiuser into Debian sid using the kernel 4.19.56-debian-pmac. After the system was up, I logged in at the serial console and ran "/etc/init.d/wdm stop" to stop X. At that point, I ran "xinit &" and the x11perf tests. A quick look at the x11perfcomp_sid.txt file seems to show that it doesn't make much difference whether running in single user mode or multiuser mode. For tests 11) and 12), there were no dbus errors in the respective Xorg.log files (this may not have affected the earlier tests much, anyway, since the dbus errors happened only once every ten seconds). The "ps auxw" output (at the end of the serial console log) is interesting. It shows the following (while I'm logged in as a non-privileged user at the console and as root at the serial console): a) The total VSZ of all processes on the system is about 2.6 GB. b) The total RSS of all processes on the system is about 738 MB. That suggests that some swapping will have to occur in multiuser mode with a full Xfce desktop running, since the system has only 512 MB memory. c) Just the X server by itself is using 58 MB memory (RSS): root 891 14.6 11.6 149056 58472 tty7 Ssl+ 13:37 0:13 /usr/lib/xorg/Xorg d) The systemd processes (including dbus) are using 53 MB (RSS). e) The Xfce-related processes are using about 260 MB. f) Between systemd, X, and a minimal desktop such as Xfce, it appears that any system with less than about 58+53+260 = 371 MB memory would experience fairly severe swapping trying to run a modern X11 desktop. If the trend continues, only emulators running on modern hardware will be able to do a decent job running powerpc distributions. I realize the bloat problem is not directly related to this bug report. I'll backup the partitions I've been using for Debian 8.11 and sid in case any further testing is needed. If not, this bug report is complete. Eventually, Michel's patch should make it to Debian sid (I'll ask about that on the Debian powerpc mailing list), and when a new version is available, I'll be happy to test it. I'm still wondering whether this is a problem: (II) FBDEV(0): hardware: OFfb ATY,RageLT (video memory: 3072kB) If the FBDEV driver is being told by the kernel that the video memory is 3072 K, when it should be reported as 4096 K, how does that affect the x11perf results for FBDEV? Meanwhile, I'll be removing systemd and seeing if earlier versions of Xorg and Xfce can be used on (or compiled for) Debian sid. Thanks to all who have helped with this issue. -Stan Johnson user...@yahoo.com
update.tar.xz
Description: Binary data