| 1 |
On Thursday, 3 May 2018 16:41:55 BST Grant Edwards wrote: |
| 2 |
> On 2018-05-03, Mick <michaelkintzios@×××××.com> wrote: |
| 3 |
> > OK, I know my laptop is quite old, or at least Intel thinks so, but |
| 4 |
> > emerging |
| 5 |
> > chromium is now taking *much* longer than it ever did: |
| 6 |
> A while back I accidentally broke the CPU throttling on my laptop, and |
| 7 |
> it was always running at 1/4 speed. [That effected all emerges.] I'd |
| 8 |
> start by doing a "grep MHz /proc/cpuinfo" during the build to verify |
| 9 |
> that all the CPUs have open throttles. |
| 10 |
> |
| 11 |
> That said, I've noticed that Chromium in particular is taking a lot |
| 12 |
> longer than it used to... |
| 13 |
|
| 14 |
Thank you Peter and Grant for your replies. I have once or twice used a |
| 15 |
faster machine to build a Chromium binary and then copied over to the slow |
| 16 |
laptop, but it is a bit of a faff. I may have to do this in the future, |
| 17 |
although with the landscape changing (GPZ patches, gcc upgrade, etc.) the |
| 18 |
build times are changing all the time. They may never reduce again, in which |
| 19 |
case it will be an option to consider. |
| 20 |
|
| 21 |
I don't think I have an issue with CPU throttling. i7z shows the CPU with |
| 22 |
turbo regularly goes up to 2.6GHz: |
| 23 |
|
| 24 |
================================= |
| 25 |
Cpu speed from cpuinfo 1595.00Mhz |
| 26 |
cpuinfo might be wrong if cpufreq is enabled. To guess correctly try |
| 27 |
estimating via tsc |
| 28 |
Linux's inbuilt cpu_khz code emulated now |
| 29 |
True Frequency (without accounting Turbo) 1595 MHz |
| 30 |
CPU Multiplier 12x || Bus clock frequency (BCLK) 132.92 MHz |
| 31 |
|
| 32 |
Socket [0] - [physical cores=4, logical cores=8, max online cores ever=4] |
| 33 |
TURBO ENABLED on 4 Cores, Hyper Threading ON |
| 34 |
Max Frequency without considering Turbo 1727.92 MHz (132.92 x [13]) |
| 35 |
Max TURBO Multiplier (if Enabled) with 1/2/3/4 Cores is 21x/18x/13x/13x |
| 36 |
Real Current Frequency 2244.06 MHz [132.92 x 16.88] (Max of below) |
| 37 |
Core [core-id] :Actual Freq (Mult.) C0% Halt(C1)% C3 % C6 % |
| 38 |
C7 % Temp VCore |
| 39 |
Core 1 [0]: 1454.95 (10.95x) 4.76 11.2 54.6 29.9 0 |
| 40 |
69 0.0000 |
| 41 |
Core 2 [1]: 1634.49 (12.30x) 3.09 4.5 52.6 39.7 0 |
| 42 |
69 0.0000 |
| 43 |
Core 3 [2]: 2244.06 (16.88x) 99.5 0 0 0 0 72 |
| 44 |
0.0000 |
| 45 |
Core 4 [3]: 2235.68 (16.82x) 99.4 0 0 0 0 |
| 46 |
69 0.0000 |
| 47 |
|
| 48 |
|
| 49 |
|
| 50 |
C0 = Processor running without halting |
| 51 |
C1 = Processor running with halts (States >C0 are power saver modes with cores |
| 52 |
idling) |
| 53 |
C3 = Cores running with PLL turned off and core cache turned off |
| 54 |
C6, C7 = Everything in C3 + core state saved to last level cache, C7 is deeper |
| 55 |
than C6 |
| 56 |
Above values in table are in percentage over the last 1 sec |
| 57 |
[core-id] refers to core-id number in /proc/cpuinfo |
| 58 |
'Garbage Values' message printed when garbage values are read |
| 59 |
============================================================= |
| 60 |
|
| 61 |
/proc/cpuinfo shows a number of cores regularly @1600MHz while syslog does not |
| 62 |
report any problems. |
| 63 |
|
| 64 |
-- |
| 65 |
Regards, |
| 66 |
Mick |
Archives