1 |
On 03/28 05:59, Mark Knecht wrote: |
2 |
> On Fri, Mar 27, 2020 at 10:58 PM <tuxic@××××××.de> wrote: |
3 |
> > |
4 |
> > On 03/27 11:51, Mark Knecht wrote: |
5 |
> > > On Fri, Mar 27, 2020 at 11:11 AM <tuxic@××××××.de> wrote: |
6 |
> > > > |
7 |
> > > > On 03/27 06:04, Andrea Conti wrote: |
8 |
> > > > > Hello, |
9 |
> > > > > |
10 |
> > > > > > Thread(s) per core: 1 <<<<< |
11 |
> > > > > > Does my CPU hyperthread? |
12 |
> > > > > |
13 |
> > > > > Definitely not. |
14 |
> > > > > |
15 |
> > > > > Your kernel config is fine, chances are hyperthreading (aka "SMT |
16 |
> mode") |
17 |
> > > is |
18 |
> > > > > disabled in your BIOS settings. |
19 |
> > > > > |
20 |
> > > > > andrea |
21 |
> > > > > |
22 |
> > > > |
23 |
> > > > Hi Andrea, |
24 |
> > > > |
25 |
> > > > I checked that: The BIOS setting was set to use hyperthreading. |
26 |
> > > > |
27 |
> > > > But "Number of cores" was set to six. I changed that to 12 and |
28 |
> > > > Voila! I got two threads per core. |
29 |
> > > > |
30 |
> > > > I think "Number of cores" is a little misleading, since there |
31 |
> > > > are six physical cores (not threads) with a RYZEN 5. |
32 |
> > > > |
33 |
> > > > I feeling not that comfortable with this solution. |
34 |
> > > > |
35 |
> > > > Is there any way to check for the validity of this setting |
36 |
> > > > beside a tool, which prints a "2" after the word "threads" ;) ? |
37 |
> > > > |
38 |
> > > > Cheers! |
39 |
> > > > Meino |
40 |
> > > > |
41 |
> > > > |
42 |
> > > |
43 |
> > > cat /proc/cpu should give info for each thread. I've been running an i7 |
44 |
> 980 |
45 |
> > > Extreme processor @3.33GHz here at home for about 12 years or so. It's 6 |
46 |
> > > cores but shows 12 processors on both Gentoo and now Kubuntu. |
47 |
> > > |
48 |
> > > I generally run top and then hit '1' and 'z'. You can watch what |
49 |
> percentage |
50 |
> > > each core/thread is using. |
51 |
> > > |
52 |
> > > Time a BIG compile job twice, once with each kernel. If it's working |
53 |
> you'll |
54 |
> > > measure a significant difference in time. Note that it won't be 2x as |
55 |
> > > you'll also be limited by disk read/write throughput, but you'll know |
56 |
> it's |
57 |
> > > basically working. |
58 |
> > > |
59 |
> > > On Gentoo make sure you're compile settings in (I think make.conf - I no |
60 |
> > > longer run Gentoo much) are set to take advantage of all your cores and |
61 |
> not |
62 |
> > > limited to something smaller. Also watch overheating when using more |
63 |
> > > cores/threads. On older PCs like mine when you possibly have dust in CPU |
64 |
> > > coolers might not be as efficient as when they are new. |
65 |
> > > |
66 |
> > > HTH, |
67 |
> > > Mark |
68 |
> > |
69 |
> > Hi Mark, |
70 |
> > |
71 |
> > thank you for your explanations! :) |
72 |
> > |
73 |
> > /proc/cpu doesn't exist on my system....may be you are referring to |
74 |
> > /proc/cpuinfo? |
75 |
> > |
76 |
> > The problem was caused by a kernel misconfiguration by me. |
77 |
> > |
78 |
> > In the kernel setup there is a setting "Number of cores" which |
79 |
> > I had set to six ... since my CPU has 6 physical core. |
80 |
> > |
81 |
> > Setting this to twelve (and blurring the syntactically border between |
82 |
> > threads and cores thereby...) gives me twelves cores in top, htop |
83 |
> > and such and (as an example) compiling the kernel is faster - |
84 |
> > so it is not a display gimmick only. |
85 |
> > |
86 |
> > I think "Number of cores" is a misnomer...or am I wrong? |
87 |
> > |
88 |
> > Cheers! |
89 |
> > Meino |
90 |
> > |
91 |
> |
92 |
> Meino, |
93 |
> Yes, /proc/cpuinfo. Sorry. |
94 |
> |
95 |
> Well yes, I guess the 'Number of cores' is a misnomer if you're trying |
96 |
> to equate the language in the kernel against Intel/AMD marketing data for |
97 |
> physical cores. 6 physical cores with or without hyperthreading is still 6 |
98 |
> physical cores. However 6 physical cores (my processor) _WITH_ |
99 |
> hyperthreading enabled is 12 _LOGICAL_ cores which is more what I think the |
100 |
> kernel verbiage is about. Semantics I suppose. |
101 |
> |
102 |
> I'm glad you found it wasn't a gimmicky number. It really does work, |
103 |
> within the limits of the hardware being able to figure out what one thread |
104 |
> should be fetching or writing while the other thread is computing. It's not |
105 |
> a perfect 2:1 like 12 physical cores might be, but it's a lot less silicon |
106 |
> and therefore a lot less expensive. |
107 |
> |
108 |
> Cheers, |
109 |
> Mark |
110 |
|
111 |
Hi Mark, |
112 |
|
113 |
In the meanwhile I found "glance" and installed it, which is the |
114 |
bazooka-out-of-the-box-no-configuration terminal-brethren of "conky" |
115 |
:) |
116 |
|
117 |
Enough plugins enabled (which come with it preinstalled), you can |
118 |
watch in realtime, what each core/thread is doing right now...nearly. Big |
119 |
Brother for the sustem with no bad intention in mind. I am only |
120 |
curious :) |
121 |
|
122 |
And you get your sensors diplayed, the workload of your GPU (nvidia in |
123 |
my case), all processes and lot lot more. |
124 |
|
125 |
The faster the CPU gets (my previous PC was 12 years old...), the |
126 |
more the peripheral devices are becoming show stoppers ("stoppers" |
127 |
in the barest truth of its meaning). |
128 |
|
129 |
Unfortunatelu the SSD I ordered is in status "ready for delivery" |
130 |
since 23.03.2020....corona....you know... |
131 |
|
132 |
And with 12 cores enabled on a recent CPU and running for example a |
133 |
bigger update via emerge (enabled for 12 threads of course) |
134 |
....all the cores are simply waiting a lot |
135 |
faster......for the harddisc :) |
136 |
|
137 |
Thanks for your help -- stay healthy! |
138 |
|
139 |
Cheers! |
140 |
Meino |