Created attachment 505334 [details] High temperature of cpu at idle Description of problem: High temperature on AMD E-350 as seen on Gnome 3. It looks like Version-Release number of selected component (if applicable): 2.6.38.8-32.fc15.x86_64 How reproducible: Always Steps to Reproduce: 1. Simply start the system 2. 3. Actual results: Abnormal high temperature on cpu Expected results: Idle should be in the range of 30 Celsius Additional info: Smolt profile: http://www.smolts.org/client/show/pub_c3a5a04c-c58f-4138-8166-9fb8576ffc18
Is cpufreq enabled on that machine?
$ lsmod | grep cpufreq cpufreq_ondemand 9466 2 freq_table 3963 2 cpufreq_ondemand,powernow_k8 It looks like cpufreq is enabled. I first thought it was a service when I realized I looked at cpuspeed. Is there another command to see cpufreq status?
(In reply to comment #2) > It looks like cpufreq is enabled. I first thought it was a service when I > realized I looked at cpuspeed. Is there another command to see cpufreq status? $ grep "" /sys/devices/system/cpu/cpu0/cpufreq/* And: $ sudo modprobe cpufreq_stats $ grep "" /sys/devices/system/cpu/cpu0/cpufreq/stats/*
$ grep "" /sys/devices/system/cpu/cpu0/cpufreq/* /sys/devices/system/cpu/cpu0/cpufreq/affected_cpus:0 /sys/devices/system/cpu/cpu0/cpufreq/bios_limit:1600000 /sys/devices/system/cpu/cpu0/cpufreq/cpb:0 grep: /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq: Permission denied /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_max_freq:1600000 /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_min_freq:800000 /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_transition_latency:1000 /sys/devices/system/cpu/cpu0/cpufreq/related_cpus:0 /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies:1600000 1280000 800000 /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_governors:ondemand userspace performance /sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq:1600000 /sys/devices/system/cpu/cpu0/cpufreq/scaling_driver:powernow-k8 /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:ondemand /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq:1600000 /sys/devices/system/cpu/cpu0/cpufreq/scaling_min_freq:800000 /sys/devices/system/cpu/cpu0/cpufreq/scaling_setspeed:<unsupported> $ grep "" /sys/devices/system/cpu/cpu0/cpufreq/stats/* /sys/devices/system/cpu/cpu0/cpufreq/stats/time_in_state:1600000 116 /sys/devices/system/cpu/cpu0/cpufreq/stats/time_in_state:1280000 8 /sys/devices/system/cpu/cpu0/cpufreq/stats/time_in_state:800000 1993 /sys/devices/system/cpu/cpu0/cpufreq/stats/total_trans:60 /sys/devices/system/cpu/cpu0/cpufreq/stats/trans_table: From : To /sys/devices/system/cpu/cpu0/cpufreq/stats/trans_table: : 1600000 1280000 800000 /sys/devices/system/cpu/cpu0/cpufreq/stats/trans_table: 1600000: 0 4 24 /sys/devices/system/cpu/cpu0/cpufreq/stats/trans_table: 1280000: 0 0 4 /sys/devices/system/cpu/cpu0/cpufreq/stats/trans_table: 800000: 28 0 0
does powertop show anything obvious ?
(In reply to comment #5) > does powertop show anything obvious ? $su -c "powertop" From Idle stats Package | CPU 0 POLL 0.0% | POLL 0.0% 0.0 ms C1 9.0% | C1 9.5% 0.5 ms C2 59.3% | C2 57.1% 2.1 ms | CPU 1 | POLL 0.0% 0.0 ms | C1 8.6% 0.5 ms | C2 61.5% 2.8 ms From Device stats tab Usage Device name 20.4% CPU use 100.0% Audio codec hwC0D0: Conexant 100.0% Display backlight 56046 pkts/s Network interface: wlan0 (rtl8192ce) 100.0% USB device: USB-PS/2 Optical Mouse (Logitech) 100.0% USB device: OHCI Host Controller 100.0% PCI Device: ATI Technologies Inc SB700/SB800 USB OHCI0 100.0% PCI Device: ATI Technologies Inc SB700/SB800 USB OHCI0 100.0% PCI Device: ATI Technologies Inc SB700/SB800 USB EHCI 100.0% PCI Device: ATI Technologies Inc SB700/SB800 SATA Cont 100.0% PCI Device: ATI Technologies Inc Device 9802 100.0% Radio device: rtl8192ce 100.0% PCI Device: ATI Technologies Inc SB700/SB800 USB EHCI 100.0% PCI Device: ATI Technologies Inc Device 43a1 100.0% PCI Device: Advanced Micro Devices [AMD] Device 1703 100.0% PCI Device: ATI Technologies Inc SB700/SB800 USB EHCI 100.0% PCI Device: ATI Technologies Inc SB700/SB800 USB OHCI0 100.0% PCI Device: ATI Technologies Inc SBx00 SMBus From tunable tab >> Bad Wireless Power Saving for interface wlan0 Bad Enable SATA link power management for /dev/sda Bad NMI watchdog should be turned off Bad Power Aware CPU scheduler Bad VM writeback timeout Bad Enable Audio codec power management Bad Autosuspend for USB device USB-PS/2 Optical Mouse [Logitech] Bad Runtime PM for PCI Device Atheros Communications AR8152 v2.0 Fast Et Bad Runtime PM for PCI Device ATI Technologies Inc Device 43a1 Bad Runtime PM for PCI Device ATI Technologies Inc SB700/SB800 USB OHCI0 Bad Runtime PM for PCI Device ATI Technologies Inc SB700/SB800 USB EHCI Bad Runtime PM for PCI Device ATI Technologies Inc SB700/SB800 USB EHCI Bad Runtime PM for PCI Device ATI Technologies Inc SBx00 SMBus Controlle Bad Runtime PM for PCI Device ATI Technologies Inc SBx00 Azalia (Intel H Bad Runtime PM for PCI Device ATI Technologies Inc Device 43a0 Bad Runtime PM for PCI Device Realtek Semiconductor Co., Ltd. Device 817 Bad Runtime PM for PCI Device ATI Technologies Inc SB700/SB800 USB OHCI0 Bad Runtime PM for PCI Device ATI Technologies Inc SB700/SB800 USB OHCI0 Bad Runtime PM for PCI Device
what about the overview tab ? (after leaving it for 10 seconds without touching touchpad/keyboard etc). Also, were you downloading something at the time you took those ? 56046 pkts/s Network interface: wlan0 (rtl8192ce) seems absurdly high.
(In reply to comment #7) > what about the overview tab ? (after leaving it for 10 seconds without touching > touchpad/keyboard etc). I was unable to get overview tab because the entire Fedora 15 froze. I reset my AMD E-350 Toshiba laptop which froze during the booting process. I will provide result when the laptop cooled off. Strangely, the behaviour does not happen on Windows 7. > Also, were you downloading something at the time you > took those ? > 56046 pkts/s Network interface: wlan0 (rtl8192ce) > > seems absurdly high. I only checked email via Thunderbird and Firefox 5 session was open without download.
We do approximately no power management on the GPU at present, and so increased temperature compared in Windows is expected.
(In reply to comment #7) > what about the overview tab ? (after leaving it for 10 seconds without touching > touchpad/keyboard etc). Also, were you downloading something at the time you > took those ? > 56046 pkts/s Network interface: wlan0 (rtl8192ce) > > seems absurdly high. Overview tab result from Powertop Summary: 271.5 wakeups/second, 0.0 GPU ops/second and 0.0 VFS ops/sec Usage Events/s Category Description 100.0% Device Audio codec hwC0D0: Conexant 5.5 ms/s 63.6 Interrupt [6] tasklet(softirq) 96.5 ms/s 15.2 kWork ieee80211_scan_work 20.9 ms/s 36.2 Process nm-applet 19.1 ms/s 34.9 Process /usr/bin/Xorg :0 -background none -verbose -auth 7.3 ms/s 37.9 Timer tick_sched_timer 197.3 us/s 18.8 kWork ieee80211_iface_work 6.9 ms/s 11.9 Interrupt [40] radeon 23.9 ms/s 4.5 Process /usr/bin/gnome-shell 457.3 us/s 12.3 Timer hrtimer_wakeup 11.1 ms/s 5.5 Process /bin/dbus-daemon --system --address=systemd: --no 10.8 ms/s 3.6 Process /usr/sbin/wpa_supplicant -c /etc/wpa_supplicant/w 10.3 ms/s 2.6 Process /usr/sbin/NetworkManager --no-daemon 1.5 ms/s 4.5 Process /sbin/rsyslogd -n -c 5 219.0 us/s 2.6 Process [ksoftirqd/0] 6.2 ms/s 0.00 Process [kworker/u:2] 84.9 us/s 2.0 Process [ksoftirqd/1] 167.4 us/s 1.7 kWork ieee80211_work_work 191.3 us/s 1.5 Interrupt [7] sched(softirq) 0.8 ms/s 0.9 Process gnome-terminal 3.1 ms/s 0.00 Process [kworker/u:3] 0.8 ms/s 0.9 Process gnome-power-manager 154.3 us/s 0.9 Process abrt-dump-oops -d /var/spool/abrt -rwx /var/log/m 2.4 ms/s 0.00 Process [khugepaged] 2.3 ms/s 0.00 Interrupt [16] hda_intel 196.3 us/s 0.8 kWork disk_events_workfn 169.4 us/s 0.8 Process udisks-daemon: polling /dev/sr0 67.5 us/s 0.7 kWork __cfg80211_scan_done 1.2 ms/s 0.25 Process powertop 6.5 us/s 0.6 kWork sync_cmos_clock (In reply to comment #9) > We do approximately no power management on the GPU at present, and so increased > temperature compared in Windows is expected. In this case, the temperature is abnormally high than it should be. On Gnome Shell, it displayed 55C on Toshiba C650D laptop.
Your system has the GPU built into the CPU, and we don't do any power management on the GPU. The outcome is that your CPU will run abnormally high, if your definition of normal is either "A CPU without a built-in Radeon" or "This CPU running under Windows".
(In reply to comment #11) > Your system has the GPU built into the CPU, and we don't do any power > management on the GPU. The outcome is that your CPU will run abnormally high, > if your definition of normal is either "A CPU without a built-in Radeon" or > "This CPU running under Windows". Oh well. Then it is up to videocard manufacturers to provide the basic specification for GPU power management. Until then, I think the bug will stay open for several release. =/
Might as well move this to rawhide. There's not point in leaving it in a specific release until some power management for this kind of chip is available.
This bug appears to have been reported against 'rawhide' during the Fedora 19 development cycle. Changing version to '19'. (As we did not run this process for some time, it could affect also pre-Fedora 19 development cycle bugs. We are very sorry. It will help us with cleanup during Fedora 19 End Of Life. Thank you.) More information and reason for this action is here: https://fedoraproject.org/wiki/BugZappers/HouseKeeping/Fedora19
Is this still a problem with 3.9 based F19 kernels?
The problem appears to be less severe than several release ago. I will publish the report when I access my laptop.
According to sensors command: $ sensors acpitz-virtual-0 Adapter: Virtual device temp1: +58.0°C (crit = +105.0°C) radeon-pci-0008 Adapter: PCI adapter temp1: +58.0°C k10temp-pci-00c3 Adapter: PCI adapter temp1: +58.5°C (high = +70.0°C) (crit = +115.0°C, hyst = +115.0°C) Apparently, temperature is still the same since the opening of this bug meaning there are still no power management on the APU i.e. GPU part. I don't know if the newest kernel can handle it. Test done on Fedora 19 with kernel 3.9.0-0.rc7.git3.1.fc19.x86_64. Should I assign the report to rawhide?
*********** MASS BUG UPDATE ************** We apologize for the inconvenience. There is a large number of bugs to go through and several of them have gone stale. Due to this, we are doing a mass bug update across all of the Fedora 19 kernel bugs. Fedora 19 has now been rebased to 3.11.1-200.fc19. Please test this kernel update and let us know if you issue has been resolved or if it is still present with the newer kernel. If you experience different issues, please open a new bug report for those.
not much different than in comment#17 since idle is still near 50 degC instead of 30 degC. similar hardware: Toshiba Satellite L75D-A7283 with AMD A4-5000 apu with embedded [AMD/ATI] Kabini [Radeon HD 8330] (for more hardware info see https://bugzilla.redhat.com/show_bug.cgi?id=1006527) kernel-3.11.1-200.fc19 linux-firmware-20130724-29.git31f6b30.fc19.noarch (amd code here now) microcode_ctl-2:2.0-5.fc19.x86_64 (no amd code here anymore) according to comment#0 there should be idle temperature near 30 degC. the sensors command gives: $ sensors acpitz-virtual-0 Adapter: Virtual device temp1: +54.0°C (crit = +105.0°C) k10temp-pci-00c3 Adapter: PCI adapter temp1: +53.2°C (high = +70.0°C) (crit = +100.0°C, hyst = +99.0°C) fam15h_power-pci-00c4 Adapter: PCI adapter power1: 0.00 W (crit = 15.00 W)
Update with kernel 3.11.9-300.fc20.x86_64 $ sensors acpitz-virtual-0 Adapter: Virtual device temp1: +54.0°C (crit = +105.0°C) radeon-pci-0008 Adapter: PCI adapter temp1: +57.0°C k10temp-pci-00c3 Adapter: PCI adapter temp1: +54.6°C (high = +70.0°C) (crit = +115.0°C, hyst = +115.0°C) Slight drop compared to #17 Perhaps it is normal for this kind of chipset.
*********** MASS BUG UPDATE ************** We apologize for the inconvenience. There is a large number of bugs to go through and several of them have gone stale. Due to this, we are doing a mass bug update across all of the Fedora 19 kernel bugs. Fedora 19 has now been rebased to 3.12.6-200.fc19. Please test this kernel update (or newer) and let us know if you issue has been resolved or if it is still present with the newer kernel. If you have moved on to Fedora 20, and are still experiencing this issue, please change the version to Fedora 20. If you experience different issues, please open a new bug report for those.
updating comment#19 not sure of target temp and machine is slow and havent had much luck with 3.12.x kernels booting but with kernel-3.13.0-0.rc5.git0.1.fc20.x86_64 i am getting some improvement in idle temperature: $ sensors acpitz-virtual-0 Adapter: Virtual device temp1: +46.0°C (crit = +105.0°C) radeon-pci-0008 Adapter: PCI adapter temp1: +46.0°C k10temp-pci-00c3 Adapter: PCI adapter temp1: +46.0°C (high = +70.0°C) (crit = +100.0°C, hyst = +99.0°C) fam15h_power-pci-00c4 Adapter: PCI adapter power1: 0.00 W (crit = 15.00 W)
correction for cocmment#22: kernel was 3.13.x should read fc21 not fc20
*********** MASS BUG UPDATE ************** This bug has been in a needinfo state for more than 1 month and is being closed with insufficient data due to inactivity. If this is still an issue with Fedora 19, please feel free to reopen the bug and provide the additional information requested.