Re: What is a typical precision of gettimeofday()? - Mailing list pgsql-hackers
| From | Tom Lane |
|---|---|
| Subject | Re: What is a typical precision of gettimeofday()? |
| Date | |
| Msg-id | 3112460.1719940814@sss.pgh.pa.us Whole thread Raw |
| In response to | Re: What is a typical precision of gettimeofday()? (Tom Lane <tgl@sss.pgh.pa.us>) |
| Responses |
Re: What is a typical precision of gettimeofday()?
Re: What is a typical precision of gettimeofday()? |
| List | pgsql-hackers |
BTW, getting back to the original point of the thread: I duplicated
Hannu's result showing that on Apple M1 the clock tick seems to be
about 40ns. But look at what I got with the v2 patch on my main
workstation (full output attached):
$ ./pg_test_timing
...
Per loop time including overhead: 16.60 ns
...
Timing durations less than 128 ns:
ns % of total running % count
15 3.2738 3.2738 5914914
16 49.0772 52.3510 88668783
17 36.4662 88.8172 65884173
18 9.5639 98.3810 17279249
19 1.5746 99.9556 2844873
20 0.0416 99.9972 75125
21 0.0004 99.9976 757
...
It sure looks like this is exact-to-the-nanosecond results,
since the modal values match the overall per-loop timing,
and there are no zero measurements.
This is a Dell tower from 2021, running RHEL8 on an Intel Xeon W-2245.
Not exactly top-of-the-line stuff.
regards, tom lane
Testing timing overhead for 3 seconds.
Per loop time including overhead: 16.60 ns
Histogram of timing durations:
<= ns % of total running % count
0 0.0000 0.0000 0
1 0.0000 0.0000 0
3 0.0000 0.0000 0
7 0.0000 0.0000 0
15 3.2738 3.2738 5914914
31 96.7241 99.9980 174753569
63 0.0001 99.9981 265
127 0.0001 99.9982 110
255 0.0000 99.9982 29
511 0.0000 99.9982 0
1023 0.0013 99.9995 2410
2047 0.0003 99.9999 586
4095 0.0000 99.9999 10
8191 0.0000 99.9999 3
16383 0.0001 100.0000 228
32767 0.0000 100.0000 1
Timing durations less than 128 ns:
ns % of total running % count
15 3.2738 3.2738 5914914
16 49.0772 52.3510 88668783
17 36.4662 88.8172 65884173
18 9.5639 98.3810 17279249
19 1.5746 99.9556 2844873
20 0.0416 99.9972 75125
21 0.0004 99.9976 757
22 0.0001 99.9978 252
23 0.0001 99.9978 101
24 0.0000 99.9979 50
25 0.0000 99.9979 32
26 0.0000 99.9979 28
27 0.0000 99.9979 27
28 0.0000 99.9979 19
29 0.0000 99.9979 21
30 0.0000 99.9980 34
31 0.0000 99.9980 45
32 0.0000 99.9980 42
33 0.0000 99.9980 30
34 0.0000 99.9980 17
35 0.0000 99.9980 14
36 0.0000 99.9980 13
37 0.0000 99.9981 13
38 0.0000 99.9981 13
39 0.0000 99.9981 12
40 0.0000 99.9981 8
41 0.0000 99.9981 13
42 0.0000 99.9981 12
43 0.0000 99.9981 9
44 0.0000 99.9981 9
45 0.0000 99.9981 5
46 0.0000 99.9981 3
47 0.0000 99.9981 3
48 0.0000 99.9981 5
49 0.0000 99.9981 5
50 0.0000 99.9981 4
51 0.0000 99.9981 4
52 0.0000 99.9981 2
53 0.0000 99.9981 2
54 0.0000 99.9981 2
55 0.0000 99.9981 4
56 0.0000 99.9981 1
57 0.0000 99.9981 2
58 0.0000 99.9981 2
59 0.0000 99.9981 4
60 0.0000 99.9981 2
61 0.0000 99.9981 6
62 0.0000 99.9981 2
63 0.0000 99.9981 2
64 0.0000 99.9981 2
65 0.0000 99.9981 2
66 0.0000 99.9981 2
67 0.0000 99.9981 2
72 0.0000 99.9981 1
73 0.0000 99.9981 1
74 0.0000 99.9981 1
77 0.0000 99.9981 1
78 0.0000 99.9981 2
87 0.0000 99.9981 1
91 0.0000 99.9981 1
94 0.0000 99.9981 4
95 0.0000 99.9981 3
96 0.0000 99.9982 16
97 0.0000 99.9982 5
98 0.0000 99.9982 7
99 0.0000 99.9982 14
100 0.0000 99.9982 10
101 0.0000 99.9982 10
102 0.0000 99.9982 4
103 0.0000 99.9982 2
104 0.0000 99.9982 2
105 0.0000 99.9982 1
106 0.0000 99.9982 3
107 0.0000 99.9982 1
108 0.0000 99.9982 4
109 0.0000 99.9982 4
112 0.0000 99.9982 1
115 0.0000 99.9982 2
127 0.0000 99.9982 1
pgsql-hackers by date: