search for: intel_pstate

..., 120 threads) with some interesting results. In term of the performance benefit of this patch, I ran the high_systime workload (which does a lot of fork() and exit()) at various load levels (500, 1000, 1500 and 2000 users) on a 4-socket IvyBridge-EX bare-metal system (60 cores, 120 threads) with intel_pstate driver and performance scaling governor. The JPM (jobs/minutes) and execution time results were as follows: Kernel JPM Execution Time ------ --- -------------- At 500 users: 3.19 118857.14 26.25s 3.19-qspinlock 134889.75...

..., 120 threads) with some interesting results. In term of the performance benefit of this patch, I ran the high_systime workload (which does a lot of fork() and exit()) at various load levels (500, 1000, 1500 and 2000 users) on a 4-socket IvyBridge-EX bare-metal system (60 cores, 120 threads) with intel_pstate driver and performance scaling governor. The JPM (jobs/minutes) and execution time results were as follows: Kernel JPM Execution Time ------ --- -------------- At 500 users: 3.19 118857.14 26.25s 3.19-qspinlock 134889.75...

...vice common for all mice [ 0.523014] rtc_cmos 00:04: RTC can wake from S4 [ 0.523530] rtc_cmos 00:04: rtc core: registered rtc_cmos as rtc0 [ 0.523701] rtc_cmos 00:04: alarms up to one month, y3k, 242 bytes nvram, hpet irqs [ 0.523792] Intel P-state driver initializing. [ 0.523868] intel_pstate: HWP enabled [ 0.524475] intel_pstate: HWP enabled [ 0.525076] intel_pstate: HWP enabled [ 0.525647] intel_pstate: HWP enabled [ 0.526106] intel_pstate: HWP enabled [ 0.526503] intel_pstate: HWP enabled [ 0.526898] intel_pstate: HWP enabled [ 0.527293] intel_pstate: HWP enabled...

...chment 127486 --> https://bugs.freedesktop.org/attachment.cgi?id=127486&action=edit New dmesg output after manually turning on power management So Lekensteyn asked me to run a few commands to also shut off the bus the GPU is on. If I do so and then proceed by running powertop on battery, intel_pstate complains about turbo not being available, a usb device disconnects, a while later Nouveau resumes kernel object trees, Bluetooth reconnects and nouveau suspends again. The commands are: # echo auto > /sys/bus/pci/devices/0000\:00\:1c.4/power/control # grep . /sys/bus/pci/devices/0000:0{0:1c.4...

...0,0x64 irq 12 [ 0.700674] mousedev: PS/2 mouse device common for all mice [ 0.700688] rtc_cmos 00:02: RTC can wake from S4 [ 0.701095] rtc_cmos 00:02: rtc core: registered rtc_cmos as rtc0 [ 0.701182] rtc_cmos 00:02: alarms up to one month, y3k, 242 bytes nvram, hpet irqs [ 0.701189] intel_pstate: Intel P-state driver initializing [ 0.701242] intel_pstate: Disabling energy efficiency optimization [ 0.702151] intel_pstate: HWP enabled [ 0.702529] ledtrig-cpu: registered to indicate activity on CPUs [ 0.702875] NET: Registered protocol family 10 [ 0.703096] Segment Routing with...

Hi Waiman, As promised; here is the paravirt stuff I did during the trip to BOS last week. All the !paravirt patches are more or less the same as before (the only real change is the copyright lines in the first patch). The paravirt stuff is 'simple' and KVM only -- the Xen code was a little more convoluted and I've no real way to test that but it should be stright fwd to make work.

Hi Waiman, As promised; here is the paravirt stuff I did during the trip to BOS last week. All the !paravirt patches are more or less the same as before (the only real change is the copyright lines in the first patch). The paravirt stuff is 'simple' and KVM only -- the Xen code was a little more convoluted and I've no real way to test that but it should be stright fwd to make work.

...00] Linux version 4.10.0-rc2 (scanf at hafza) (gcc version 6.3.1 20161221 (Red Hat 6.3.1-1) (GCC) ) #1 SMP Wed Jan 4 20:16:20 CET 2017 [ 0.000000] Command line: BOOT_IMAGE=/vmlinuz-4.10.0-rc2 root=/dev/mapper/fedora_hafza-root ro rd.lvm.lv=fedora_hafza/root rd.lvm.lv=fedora_hafza/swap rhgb quiet intel_pstate=support_acpi_ppc [ 0.000000] x86/fpu: Supporting XSAVE feature 0x001: 'x87 floating point registers' [ 0.000000] x86/fpu: Supporting XSAVE feature 0x002: 'SSE registers' [ 0.000000] x86/fpu: Supporting XSAVE feature 0x004: 'AVX registers' [ 0.000000] x86/fpu: xst...

...ch ------------------------------------------ In term of the performance benefit of this patch, I ran the high_systime workload (which does a lot of fork() and exit()) at various load levels (500, 1000, 1500 and 2000 users) on a 4-socket IvyBridge-EX bare-metal system (60 cores, 120 threads) with intel_pstate driver and performance scaling governor. The JPM (jobs/minutes) and execution time results were as follows: Kernel JPM Execution Time ------ --- -------------- At 500 users: 3.19 118857.14 26.25s 3.19-qspinlock 134889.75 23.13s % change +13.5% -11.9% At 1000 users:...

...ch ------------------------------------------ In term of the performance benefit of this patch, I ran the high_systime workload (which does a lot of fork() and exit()) at various load levels (500, 1000, 1500 and 2000 users) on a 4-socket IvyBridge-EX bare-metal system (60 cores, 120 threads) with intel_pstate driver and performance scaling governor. The JPM (jobs/minutes) and execution time results were as follows: Kernel JPM Execution Time ------ --- -------------- At 500 users: 3.19 118857.14 26.25s 3.19-qspinlock 134889.75 23.13s % change +13.5% -11.9% At 1000 users:...

...erformance ---------------------------------- In term of the performance benefit of this patch, I ran the high_systime workload (which does a lot of fork() and exit()) at various load levels (500, 1000, 1500 and 2000 users) on a 4-socket IvyBridge-EX bare-metal system (60 cores, 120 threads) with intel_pstate driver and performance scaling governor. The JPM (jobs/minutes) and execution time results were as follows: Kernel JPM Execution Time ------ --- -------------- At 500 users: 3.19 118857.14 26.25s 3.19-qspinlock 134889.75 23.13s % change +13.5% -11.9% At 1000 users:...

...erformance ---------------------------------- In term of the performance benefit of this patch, I ran the high_systime workload (which does a lot of fork() and exit()) at various load levels (500, 1000, 1500 and 2000 users) on a 4-socket IvyBridge-EX bare-metal system (60 cores, 120 threads) with intel_pstate driver and performance scaling governor. The JPM (jobs/minutes) and execution time results were as follows: Kernel JPM Execution Time ------ --- -------------- At 500 users: 3.19 118857.14 26.25s 3.19-qspinlock 134889.75 23.13s % change +13.5% -11.9% At 1000 users:...

...ISA slot 5 [ 0.726716] platform eisa.0: Cannot allocate resource for EISA slot 6 [ 0.726719] platform eisa.0: Cannot allocate resource for EISA slot 7 [ 0.726721] platform eisa.0: Cannot allocate resource for EISA slot 8 [ 0.726723] platform eisa.0: EISA: Detected 0 cards [ 0.726728] intel_pstate: CPU model not supported [ 0.726831] ledtrig-cpu: registered to indicate activity on CPUs [ 0.727337] NET: Registered protocol family 10 [ 0.745679] battery: ACPI: Battery Slot [BAT0] (battery present) [ 0.747362] Segment Routing with IPv6 [ 0.747395] NET: Registered protocol family...

...terface driver usbserial_generic [ 0.788513] usbserial: USB Serial support registered for generic [ 0.788542] rtc_cmos 00:01: RTC can wake from S4 [ 0.788691] rtc_cmos 00:01: registered as rtc0 [ 0.788721] rtc_cmos 00:01: alarms up to one month, 242 bytes nvram, hpet irqs [ 0.788778] intel_pstate: CPU model not supported [ 0.788835] ledtrig-cpu: registered to indicate activity on CPUs [ 0.789248] NET: Registered protocol family 10 [ 0.797623] Segment Routing with IPv6 [ 0.797658] NET: Registered protocol family 17 [ 0.797951] mce: Using 6 MCE banks [ 0.797971] RAS: Correct...

...CI interrupt [ 31.616131] i801_smbus 0000:00:1f.3: SMBus using PCI interrupt [ 31.619918] iTCO_wdt: Intel TCO WatchDog Timer Driver v1.11 [ 31.619965] iTCO_wdt: unable to reset NO_REBOOT flag, device disabled by hardware/BIOS [ 31.619979] iTCO_vendor_support: vendor-support=0 [ 31.619994] intel_pstate: Intel P-state driver initializing [ 31.640414] hidraw: raw HID events driver (C) Jiri Kosina [ 31.640494] usbcore: registered new interface driver usbhid [ 31.640495] usbhid: USB HID core driver [ 31.640778] drop_monitor: Initializing network drop monitor service [ 31.640958] Initializin...

...CI interrupt [ 31.616131] i801_smbus 0000:00:1f.3: SMBus using PCI interrupt [ 31.619918] iTCO_wdt: Intel TCO WatchDog Timer Driver v1.11 [ 31.619965] iTCO_wdt: unable to reset NO_REBOOT flag, device disabled by hardware/BIOS [ 31.619979] iTCO_vendor_support: vendor-support=0 [ 31.619994] intel_pstate: Intel P-state driver initializing [ 31.640414] hidraw: raw HID events driver (C) Jiri Kosina [ 31.640494] usbcore: registered new interface driver usbhid [ 31.640495] usbhid: USB HID core driver [ 31.640778] drop_monitor: Initializing network drop monitor service [ 31.640958] Initializin...