Einstein hogs too much CPU cycles on Linux 2.6.8

Anonyymi

Joined: 6 Jul 05

Posts: 17

Credit: 1270182

RAC: 0

First of all: top -

16 Oct 2005 8:14:32 UTC

Message 17291 in response to message 17290

(moderation:

)

First of all:

top - 10:55:40 up 1 day, 11:51,  4 users,  load average: 1.10, 1.19, 1.13
Tasks:  54 total,   1 running,  53 sleeping,   0 stopped,   0 zombie
Cpu(s):  0.9% us,  0.5% sy, 98.6% ni,  0.0% id,  0.0% wa,  0.0% hi,  0.0% si
Mem:    191820k total,   184220k used,     7600k free,    29324k buffers
Swap:   188960k total,     2816k used,   186144k free,    53776k cached

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
6837 root 16 0 42228 30m 2836 S 0.3 16.5 21:37.54 XFree86
64 root 20 -5 0 0 0 S 0.0 0.0 0:00.00 aio/0
4857 root 16 0 1600 544 476 S 0.0 0.3 0:00.04 apmd
4936 daemon 16 0 1804 680 576 S 0.0 0.4 0:00.00 atd
6752 anonyy 15 0 3664 1980 1232 S 0.0 1.0 0:00.15 bash
6857 anonyy 15 0 3832 2168 1360 S 0.0 1.1 0:00.70 bash
6924 anonyy 15 0 3640 1956 1228 S 0.0 1.0 0:00.07 bash
7330 anonyy 15 0 3764 2096 1360 S 0.0 1.1 0:00.65 bash
4865 boinc 16 0 4308 2668 1648 S 0.0 1.4 8:19.80 boinc_client
10296 anonyy 15 0 20868 12m 9.9m S 0.5 6.7 0:22.16 boincmgr
4918 root 18 0 1616 716 536 S 0.0 0.4 0:00.00 cardmgr
4939 root 15 0 1868 900 732 S 0.0 0.5 0:00.43 cron
4876 messageb 18 0 2212 948 804 S 0.0 0.5 0:00.00 dbus-daemon-1
4106 root 15 0 2464 888 752 S 0.0 0.5 0:00.00 dhclient
10297 boinc 34 19 18200 5756 1688 S 98.6 3.0 27:59.67 einstein_4.81_i
3 root 10 -5 0 0 0 S 0.0 0.0 0:02.09 events/0
6854 anonyy 16 0 5336 2832 2184 S 0.0 1.5 0:18.76 fvwm
5643 anonyy 16 0 4116 2260 1844 S 0.0 1.2 0:00.44 gconfd-2
4951 root 16 0 1596 508 436 S 0.0 0.3 0:00.00 getty
4952 root 16 0 1592 504 436 S 0.0 0.3 0:00.00 getty
4953 root 16 0 1592 504 436 S 0.0 0.3 0:00.00 getty
5006 root 16 0 1596 504 436 S 0.0 0.3 0:00.00 getty
5014 root 16 0 1592 504 436 S 0.0 0.3 0:00.00 getty
4885 root 18 0 2340 760 676 S 0.0 0.4 0:00.00 inetd
1 root 16 0 1600 540 472 S 0.0 0.3 0:03.72 init
3796 root 19 0 0 0 0 S 0.0 0.0 0:00.00 kIrDAd
1581 root 15 0 0 0 0 S 0.0 0.0 0:02.21 kapmd
23 root 10 -5 0 0 0 S 0.0 0.0 0:00.40 kblockd/0
3347 root 17 0 0 0 0 S 0.0 0.0 0:00.00 kgameportd
4 root 16 -5 0 0 0 S 0.0 0.0 0:00.05 khelper
2367 root 15 0 0 0 0 S 0.0 0.0 0:00.00 khubd
905 root 15 0 0 0 0 S 0.0 0.0 0:06.72 kjournald
4846 root 15 0 2472 1528 472 S 0.0 0.8 0:00.36 klogd
650 root 15 0 0 0 0 S 0.0 0.0 0:00.01 kseriod
2 root 34 19 0 0 0 S 0.0 0.0 0:00.01 ksoftirqd/0
63 root 15 0 0 0 0 S 0.0 0.0 0:01.64 kswapd0
5 root 20 -5 0 0 0 S 0.0 0.0 0:00.00 kthread
9840 lp 18 0 2576 940 800 S 0.0 0.5 0:00.00 lpd
6858 anonyy 16 0 114m 42m 20m S 0.0 22.5 19:36.55 mozilla-bin
7818 anonyy 15 0 2404 1160 876 S 0.0 0.6 0:00.31 nano
4933 root 16 0 4072 4072 3380 S 0.0 2.1 0:13.75 ntpd
2275 root 15 0 0 0 0 S 0.0 0.0 0:00.00 pccardd
2285 root 19 0 0 0 0 S 0.0 0.0 0:00.00 pccardd
61 root 15 0 0 0 0 S 0.0 0.0 0:01.69 pdflush
62 root 15 0 0 0 0 S 0.0 0.0 0:02.01 pdflush
4926 root 18 0 3612 1604 1324 S 0.0 0.8 0:00.00 sshd
6825 anonyy 17 0 3320 1556 984 S 0.0 0.8 0:00.03 startx
4825 root 16 0 2348 868 748 S 0.0 0.5 0:00.97 syslogd
10334 anonyy 16 0 2172 1068 836 R 0.2 0.6 0:01.81 top
947 root 11 -4 1588 472 404 S 0.0 0.2 0:00.37 udevd
6836 anonyy 17 0 2468 672 580 S 0.0 0.4 0:00.00 xinit
6856 anonyy 16 0 5956 3124 2156 S 0.0 1.6 0:09.21 xterm
6923 anonyy 16 0 5964 3144 2148 S 0.1 1.6 0:07.50 xterm
7329 anonyy 16 0 5932 3088 2156 S 0.0 1.6 0:10.29 xterm

I/O devices work normally. I'm very pleased. Possible solution was (besides changing the network access interval from 0.01 to 0.1 and disk access interval from 60 to 300) was that I changed "Do work while on running on batteries" to yes". I guess it is possible that Boinc was trying to find out whether I'm on batteries. I'm using apmd. acpi is installed (and disabled), but it doesn't work because it says "BIOS is from '97 and too old" at boot time. In principle it should work because the manual says that the machine supports ACPI. I haven't bothered tweaking it because I'm afraid I might fry my machine if something goes wrong.

Quote:

Hda3 shows all the I/O activity, whats on that? If hda5 is swap then your system has very little swap activity and most of that is writes.

hda3 has my Debian system.

Quote:

Thats it then. You said BOINC was complaining about network problems, could be its tying up the CPU in constant retries. Try disabling the network until you know you have a good connection and BOINC needs to communicate with the server:

boinc_cmd -set_network_mode never
boinc_cmd -set_network_mode always

See if that fixes it. If it does you could try running BoincMgr to check what BOINC is doing and change the network settings. If you start if after BOINC is running, it'll just connect.

Tried that but it didn't help. Strangely, when I start Boincmgr I get this:

connect: Toiminto on nyt käynnissä
init_poll: get_socket_error(): 111

"Toiminto on nyt käynnissä" means something like "now running".

Then I get a lot of these:

(boincmgr:10249): Pango-WARNING **: Invalid UTF-8 string passed to pango_layout_set_text()

Quote:

Also check your preferences for "write to disk at most every __ seconds". Its part of the general preferences in "your account" on the E@H web site. That setting controls how often BOINC and the Einstein application write checkpoints. Although the default setting of 60 seconds is OK, I like to reduce the overhead from checkpointing and set it to 300 seconds.

I did this.

Quote:

Theres a new version of BOINC almost ready, when its released you should install it. Normally I'd recommend running the development version, but this one doesn't handle dropped network connections very well. Maybe the opposite of what you're seeing now, it doesn't retry file transfers and doesn't tell you why its not retrying.

I'll take a look when it's released.

Quote:

But what do you mean by the jerky HDD?

At first I thought I'm going to have a HDD failure. It sounded like a FDD reading the same cylinder of a bad disk over and over again. But then I realized that it was the same jerkiness as with keyboard and mouse. It was just pausing for very short intervals. When I stopped Einstein the HDD returned to normal.

As far as I'm concerned, this thread may go to sleep. Thank you very much Walt and others for your input.

Einstein hogs too much CPU cycles on Linux 2.6.8

Forums › Problems and Bug Reports

First of all: top -

Comment viewing options

Forums › Problems and Bug Reports