mirrors
/
tailscale
mirror of https://github.com/tailscale/tailscale.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
4,542 Commits 723 Branches 162 Tags 276 MiB
Commit Graph

16 Commits

Author SHA1 Message Date
Mihai Parparita 9214b293e3 tstime: add ParseDuration helper function 
More expressive than time.ParseDuration, also accepting d (days) and
w (weeks) literals.

Signed-off-by: Mihai Parparita <mihai@tailscale.com>
 2022-09-28 18:07:27 -07:00
Robert Fritzsche 0e62a7d1a2 tstime/mono: fix Before function comment 
Signed-off-by: Robert Fritzsche <r.fritzsche@gridx.de>
 2022-03-05 15:05:57 -08:00
Brad Fitzpatrick 6a2e94cbeb tstime/rate: deflake TestLongRunningQPS even more 
Previous de-flakings:
* 8cf1af8a07 for #3733
* 30458c71c8 for #2727

Fixes #4044

Change-Id: I506cf1ff37bb224f5a9929f1998901e60b24535d
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
 2022-02-28 20:22:16 -08:00
Josh Bleecher Snyder 8cf1af8a07 tstime/rate: deflake TestLongRunningQPS 
This test set the bar too high.
Just a couple of missed timers was enough to fail.
Change the test to more of a sanity check.
While we're here, run it for just 1s instead of 5s.

Prior to this change, on a 13" M1 MPB, with

stress -p 512 ./rate.test -test.run=QPS

I saw 90%+ failures.

After this change, I'm at 30k runs with no failures yet.

Fixes #3733

Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
 2022-01-13 16:48:29 -08:00
Emmanuel T Odeke 0daa32943e all: add (*testing.B).ReportAllocs() to every benchmark 
This ensures that we can properly track and catch allocation
slippages that could otherwise have been missed.

Fixes #2748
 2021-08-30 21:41:04 -07:00
Joe Tsai 30458c71c8
tstime/rate: deflake TestLongRunningQPS 
This test is highly dependent on the accuracy of OS timers.
Reduce the number of failures by decreasing the required
accuracy from 0.999 to 0.995.
Also, switch from repeated time.Sleep to using a time.Ticker
for improved accuracy.

Updates #2727

Signed-off-by: Joe Tsai <joetsai@digital-static.net>
 2021-08-30 10:46:41 -07:00
Josh Bleecher Snyder f013960d87 tstime/mono: make json.Unmarshal of a zero time.Time yield a zero Time 
This was the proximate cause of #2579.
#2582 is a deeper fix, but this will remain
as a footgun, so may as well fix it too.

Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
 2021-08-04 11:22:58 -07:00
Brad Fitzpatrick f3c96df162 ipn/ipnstate: move tailscale status "active" determination to tailscaled 
Fixes #2579

Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
 2021-08-04 09:10:49 -07:00
Josh Bleecher Snyder 9da4181606 tstime/rate: new package 
This is a simplified rate limiter geared for exactly our needs:
A fast, mono.Time-based rate limiter for use in tstun.
It was generated by stripping down the x/time/rate rate limiter
to just our needs and switching it to use mono.Time.

It removes one time.Now call per packet.

Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
 2021-07-29 12:56:58 -07:00
Josh Bleecher Snyder 142670b8c2 tstime/mono: new package 
Package mono provides a fast monotonic time.

Its primary advantage is that it is fast:
It is approximately twice as fast as time.Now.
This is because time.Now uses two clock calls,
one for wall time and one for monotonic time.

We ask for the current time 4-6 times per network packet.
At ~50ns per call to time.Now, that's enough to show
up in CPU profiles.

Package mono is a first step towards addressing that.
It is designed to be a near drop-in replacement for package time.

Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
 2021-07-29 12:56:58 -07:00
Brad Fitzpatrick 9f1b02699a tstime: add RandomDurationBetween helper 
Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
 2021-01-21 07:54:14 -08:00
Josh Bleecher Snyder aa9d7f4665 tstime: add Parse3339B, for byte slices 
Use go4.org/mem for memory safety.
A slight performance hit, but a huge performance win
for clients who start with a []byte.
The perf hit is due largely to the MapHash call, which adds ~25ns.
That is necessary to keep the fast path allocation-free.

name                     old time/op    new time/op    delta
GoParse3339/Z-8             281ns ± 1%     283ns ± 2%     ~     (p=0.366 n=9+9)
GoParse3339/TZ-8            509ns ± 0%     510ns ± 1%     ~     (p=0.059 n=9+9)
GoParse3339InLocation-8     330ns ± 1%     330ns ± 0%     ~     (p=0.802 n=10+6)
Parse3339/Z-8              69.3ns ± 1%    74.4ns ± 1%   +7.45%  (p=0.000 n=9+10)
Parse3339/TZ-8              110ns ± 1%     140ns ± 3%  +27.42%  (p=0.000 n=9+10)
ParseInt-8                 8.20ns ± 1%    8.17ns ± 1%     ~     (p=0.452 n=9+9)

name                     old alloc/op   new alloc/op   delta
GoParse3339/Z-8             0.00B          0.00B          ~     (all equal)
GoParse3339/TZ-8             160B ± 0%      160B ± 0%     ~     (all equal)
GoParse3339InLocation-8     0.00B          0.00B          ~     (all equal)
Parse3339/Z-8               0.00B          0.00B          ~     (all equal)
Parse3339/TZ-8              0.00B          0.00B          ~     (all equal)

name                     old allocs/op  new allocs/op  delta
GoParse3339/Z-8              0.00           0.00          ~     (all equal)
GoParse3339/TZ-8             3.00 ± 0%      3.00 ± 0%     ~     (all equal)
GoParse3339InLocation-8      0.00           0.00          ~     (all equal)
Parse3339/Z-8                0.00           0.00          ~     (all equal)
Parse3339/TZ-8               0.00           0.00          ~     (all equal)


Signed-off-by: Josh Bleecher Snyder <josh@tailscale.com>
 2020-11-19 14:47:11 -08:00
David Anderson b925e18f70 tstime: hand-implement parseInt for specific needs of rfc3339 parsing. 
Makes parsing 4.6x faster.

name         old time/op  new time/op  delta
ParseInt-12  32.1ns ± 1%   6.9ns ± 2%  -78.55%  (p=0.000 n=10+9)

Signed-off-by: David Anderson <danderson@tailscale.com>
 2020-04-14 12:36:55 -07:00
Brad Fitzpatrick 71d6738333 tstime: change an Errorf+return to Fatalf in subtest 
Forgot to git add this during review. Fail.
 2020-04-06 08:20:15 -07:00
Brad Fitzpatrick febdac0499 tstime: write Parse3339 parse that doesn't use time.Parse 
It doesn't allocate and it's half the time of time.Parse (which
allocates), and 2/3rds the time of time.ParseInLocation (which
doesn't).

Go with a UTC time:

BenchmarkGoParse3339/Z-8                 2200995               534 ns/op               0 B/op          0 allocs/op
BenchmarkGoParse3339/Z-8                 2254816               554 ns/op               0 B/op          0 allocs/op
BenchmarkGoParse3339/Z-8                 2159504               522 ns/op               0 B/op          0 allocs/op

Go allocates with a "-08:00" suffix instead of ending in "Z":

BenchmarkGoParse3339/TZ-8                1276491               884 ns/op             144 B/op          3 allocs/op
BenchmarkGoParse3339/TZ-8                1355858               942 ns/op             144 B/op          3 allocs/op
BenchmarkGoParse3339/TZ-8                1385484               911 ns/op             144 B/op          3 allocs/op

Go doesn't allocate if you use time.ParseInLocation, but then you need
to parse the string to find the location anyway, so might as well go
all the way (below).

BenchmarkGoParse3339InLocation-8         1912254               597 ns/op               0 B/op          0 allocs/op
BenchmarkGoParse3339InLocation-8         1980043               612 ns/op               0 B/op          0 allocs/op
BenchmarkGoParse3339InLocation-8         1891366               612 ns/op               0 B/op          0 allocs/op

Parsing RFC3339 ourselves, UTC:

BenchmarkParse3339/Z-8                   3889220               307 ns/op               0 B/op          0 allocs/op
BenchmarkParse3339/Z-8                   3718500               309 ns/op               0 B/op          0 allocs/op
BenchmarkParse3339/Z-8                   3621231               303 ns/op               0 B/op          0 allocs/op

Parsing RFC3339 ourselves, with timezone (w/ *time.Location fetched
from sync.Map)

BenchmarkParse3339/TZ-8                  3019612               418 ns/op               0 B/op          0 allocs/op
BenchmarkParse3339/TZ-8                  2921618               401 ns/op               0 B/op          0 allocs/op
BenchmarkParse3339/TZ-8                  3031671               408 ns/op               0 B/op          0 allocs/op

Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
 2020-04-06 08:19:17 -07:00
Brad Fitzpatrick d503dee6f1 tstime: add new package for time utilities, starting with Parse3339 
Go's time.Parse always allocates a FixedZone for time strings not in
UTC (ending in "Z"). This avoids that allocation, at the cost of
adding a cache.

Signed-off-by: Brad Fitzpatrick <bradfitz@tailscale.com>
 2020-04-05 20:05:49 -07:00