aboutsummaryrefslogtreecommitdiffstats
path: root/docs/gettingstarted/developers/infrastructure.md
diff options
context:
space:
mode:
authorDave Barach <dave@barachs.net>2020-04-01 18:04:32 -0400
committerFlorin Coras <florin.coras@gmail.com>2020-04-02 01:24:28 +0000
commit883bf3d1a378dcf99837ce2491cf4e448dc498f6 (patch)
treeed5168f94dbb6722acf6d183c06db4d0286580ec /docs/gettingstarted/developers/infrastructure.md
parentd7b828f0cf0e21eebc4ae836668db68971225dd1 (diff)
docs: add a timebase precision section
Type: docs Signed-off-by: Dave Barach <dave@barachs.net> Change-Id: I47434cb305f291a6221780ff4ee9a2c1bb041286
Diffstat (limited to 'docs/gettingstarted/developers/infrastructure.md')
-rw-r--r--docs/gettingstarted/developers/infrastructure.md20
1 files changed, 20 insertions, 0 deletions
diff --git a/docs/gettingstarted/developers/infrastructure.md b/docs/gettingstarted/developers/infrastructure.md
index 55b01e1c2ef..952be26cacf 100644
--- a/docs/gettingstarted/developers/infrastructure.md
+++ b/docs/gettingstarted/developers/infrastructure.md
@@ -239,6 +239,26 @@ reference time, at the current clock tick rate:
* c->clocks_per_second;
```
+### Timebase precision
+
+Cognoscenti may notice that vlib/clib\_time\_now(...) return a 64-bit
+floating-point value; the number of seconds since vpp started.
+
+Please see [this Wikipedia
+article](https://en.wikipedia.org/wiki/Double-precision_floating-point_format)
+for more information. C double-precision floating point numbers
+(called f64 in the vpp code base) have a 53-bit effective mantissa,
+and can accurately represent 15 decimal digits' worth of precision.
+
+There are 315,360,000.000001 seconds in ten years plus one
+microsecond. That string has exactly 15 decimal digits. The vpp time
+base retains 1us precision for roughly 30 years.
+
+vlib/clib\_time\_now do *not* provide precision in excess of 1e-6
+seconds. If necessary, please use clib_cpu_time_now(...) for direct
+access to the CPU clock-cycle counter. Note that the number of CPU
+clock cycles per second varies significantly across CPU architectures.
+
Format
------