New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

distsqlrun: fix tablereader microbenchmark #31337

Merged
merged 1 commit into from Oct 15, 2018

Conversation

Projects
None yet
3 participants
@jordanlewis
Member

jordanlewis commented Oct 14, 2018

It wasn't doing any work besides the initial fetch by accident. Oops!
Numbers look much more realistic now.

name                      old time/op    new time/op    delta
TableReader/rows=16-8       68.1µs ± 2%    77.7µs ± 1%    +14.20%
(p=0.000 n=10+10)
TableReader/rows=256-8       139µs ± 3%     243µs ±11%    +75.45%
(p=0.000 n=10+10)
TableReader/rows=4096-8      745µs ± 1%    2172µs ± 1%   +191.62%
(p=0.000 n=10+9)
TableReader/rows=65536-8    9.94ms ± 2%   33.45ms ± 1%   +236.60%
(p=0.000 n=10+10)

name                      old speed      new speed      delta
TableReader/rows=16-8     3.76MB/s ± 2%  3.29MB/s ± 1%    -12.44%
(p=0.000 n=10+10)
TableReader/rows=256-8    29.5MB/s ± 3%  16.9MB/s ±10%    -42.89%
(p=0.000 n=10+10)
TableReader/rows=4096-8   88.0MB/s ± 1%  30.2MB/s ± 1%    -65.71%
(p=0.000 n=10+9)
TableReader/rows=65536-8   106MB/s ± 2%    31MB/s ± 1%    -70.29%
(p=0.000 n=10+10)

name                      old alloc/op   new alloc/op   delta
TableReader/rows=16-8       9.60kB ± 2%   10.06kB ± 2%     +4.78%
(p=0.000 n=10+10)
TableReader/rows=256-8      9.50kB ± 1%   17.93kB ± 2%    +88.67%
(p=0.000 n=9+9)
TableReader/rows=4096-8     9.58kB ± 2%  142.82kB ± 3%  +1390.41%
(p=0.000 n=8+10)
TableReader/rows=65536-8    20.8kB ±93%  2090.0kB ± 1%  +9924.14%
(p=0.000 n=10+9)

name                      old allocs/op  new allocs/op  delta
TableReader/rows=16-8         78.6 ± 1%      79.7 ± 1%     +1.40%
(p=0.001 n=10+10)
TableReader/rows=256-8        79.0 ± 0%      80.0 ± 0%     +1.27%
(p=0.000 n=9+8)
TableReader/rows=4096-8       79.0 ± 0%      83.7 ±12%     +5.95%
(p=0.000 n=8+10)
TableReader/rows=65536-8       100 ±45%       453 ± 3%   +354.81%
(p=0.000 n=10+9)

Release note: None

distsqlrun: fix tablereader microbenchmark
It wasn't doing any work besides the initial fetch by accident. Oops!
Numbers look much more realistic now.

```
name                      old time/op    new time/op    delta
TableReader/rows=16-8       68.1µs ± 2%    77.7µs ± 1%    +14.20%
(p=0.000 n=10+10)
TableReader/rows=256-8       139µs ± 3%     243µs ±11%    +75.45%
(p=0.000 n=10+10)
TableReader/rows=4096-8      745µs ± 1%    2172µs ± 1%   +191.62%
(p=0.000 n=10+9)
TableReader/rows=65536-8    9.94ms ± 2%   33.45ms ± 1%   +236.60%
(p=0.000 n=10+10)

name                      old speed      new speed      delta
TableReader/rows=16-8     3.76MB/s ± 2%  3.29MB/s ± 1%    -12.44%
(p=0.000 n=10+10)
TableReader/rows=256-8    29.5MB/s ± 3%  16.9MB/s ±10%    -42.89%
(p=0.000 n=10+10)
TableReader/rows=4096-8   88.0MB/s ± 1%  30.2MB/s ± 1%    -65.71%
(p=0.000 n=10+9)
TableReader/rows=65536-8   106MB/s ± 2%    31MB/s ± 1%    -70.29%
(p=0.000 n=10+10)

name                      old alloc/op   new alloc/op   delta
TableReader/rows=16-8       9.60kB ± 2%   10.06kB ± 2%     +4.78%
(p=0.000 n=10+10)
TableReader/rows=256-8      9.50kB ± 1%   17.93kB ± 2%    +88.67%
(p=0.000 n=9+9)
TableReader/rows=4096-8     9.58kB ± 2%  142.82kB ± 3%  +1390.41%
(p=0.000 n=8+10)
TableReader/rows=65536-8    20.8kB ±93%  2090.0kB ± 1%  +9924.14%
(p=0.000 n=10+9)

name                      old allocs/op  new allocs/op  delta
TableReader/rows=16-8         78.6 ± 1%      79.7 ± 1%     +1.40%
(p=0.001 n=10+10)
TableReader/rows=256-8        79.0 ± 0%      80.0 ± 0%     +1.27%
(p=0.000 n=9+8)
TableReader/rows=4096-8       79.0 ± 0%      83.7 ±12%     +5.95%
(p=0.000 n=8+10)
TableReader/rows=65536-8       100 ±45%       453 ± 3%   +354.81%
(p=0.000 n=10+9)
```

Release note: None

@jordanlewis jordanlewis requested review from solongordon and asubiotto Oct 14, 2018

@jordanlewis jordanlewis requested review from cockroachdb/distsql-prs as code owners Oct 14, 2018

@cockroach-teamcity

This comment has been minimized.

Show comment
Hide comment
@cockroach-teamcity

cockroach-teamcity Oct 14, 2018

Member

This change is Reviewable

Member

cockroach-teamcity commented Oct 14, 2018

This change is Reviewable

@solongordon

D'oh, looks like I broke this when I added the different input sizes. Thanks for the fix. Did you already audit the other microbenchmarks to make sure the same issue doesn't exist elsewhere? I'm happy to take a look if not.

@jordanlewis

This comment has been minimized.

Show comment
Hide comment
@jordanlewis

jordanlewis Oct 15, 2018

Member

I didn't audit.

bors r+

Member

jordanlewis commented Oct 15, 2018

I didn't audit.

bors r+

craig bot pushed a commit that referenced this pull request Oct 15, 2018

Merge #31325 #31337 #31362
31325: sql: assert no dependencies on storage or CGo r=jordanlewis a=jordanlewis

No longer necessary for sql to depend on either storage or CGo - let's keep it that way!

All commits but last one from dependent PRs.

Closes #30001.

31337: distsqlrun: fix tablereader microbenchmark r=jordanlewis a=jordanlewis

It wasn't doing any work besides the initial fetch by accident. Oops!
Numbers look much more realistic now.

```
name                      old time/op    new time/op    delta
TableReader/rows=16-8       68.1µs ± 2%    77.7µs ± 1%    +14.20%
(p=0.000 n=10+10)
TableReader/rows=256-8       139µs ± 3%     243µs ±11%    +75.45%
(p=0.000 n=10+10)
TableReader/rows=4096-8      745µs ± 1%    2172µs ± 1%   +191.62%
(p=0.000 n=10+9)
TableReader/rows=65536-8    9.94ms ± 2%   33.45ms ± 1%   +236.60%
(p=0.000 n=10+10)

name                      old speed      new speed      delta
TableReader/rows=16-8     3.76MB/s ± 2%  3.29MB/s ± 1%    -12.44%
(p=0.000 n=10+10)
TableReader/rows=256-8    29.5MB/s ± 3%  16.9MB/s ±10%    -42.89%
(p=0.000 n=10+10)
TableReader/rows=4096-8   88.0MB/s ± 1%  30.2MB/s ± 1%    -65.71%
(p=0.000 n=10+9)
TableReader/rows=65536-8   106MB/s ± 2%    31MB/s ± 1%    -70.29%
(p=0.000 n=10+10)

name                      old alloc/op   new alloc/op   delta
TableReader/rows=16-8       9.60kB ± 2%   10.06kB ± 2%     +4.78%
(p=0.000 n=10+10)
TableReader/rows=256-8      9.50kB ± 1%   17.93kB ± 2%    +88.67%
(p=0.000 n=9+9)
TableReader/rows=4096-8     9.58kB ± 2%  142.82kB ± 3%  +1390.41%
(p=0.000 n=8+10)
TableReader/rows=65536-8    20.8kB ±93%  2090.0kB ± 1%  +9924.14%
(p=0.000 n=10+9)

name                      old allocs/op  new allocs/op  delta
TableReader/rows=16-8         78.6 ± 1%      79.7 ± 1%     +1.40%
(p=0.001 n=10+10)
TableReader/rows=256-8        79.0 ± 0%      80.0 ± 0%     +1.27%
(p=0.000 n=9+8)
TableReader/rows=4096-8       79.0 ± 0%      83.7 ±12%     +5.95%
(p=0.000 n=8+10)
TableReader/rows=65536-8       100 ±45%       453 ± 3%   +354.81%
(p=0.000 n=10+9)
```

Release note: None

31362: ui: Have the range debug page correctly handle missing lease times r=BramGruneir a=BramGruneir

Before this change, the value was always assumed to be not-null and it was null
would crash. It will now correctly handled the missing value and display a
`no timestamp` warning.

Fixes #31260.

Release note (bug fix): The range debug page will now correctly handle cases in
which there is no lease start or expiration time.

![screen shot 2018-10-15 at 10 35 07](https://user-images.githubusercontent.com/1614265/46958094-08a46300-d067-11e8-92cb-182882f8dd19.png)


Co-authored-by: Jordan Lewis <jordanthelewis@gmail.com>
Co-authored-by: Bram Gruneir <bram@cockroachlabs.com>
@craig

This comment has been minimized.

Show comment
Hide comment
@craig

craig bot commented Oct 15, 2018

Build succeeded

@craig craig bot merged commit 74f5d02 into cockroachdb:master Oct 15, 2018

3 checks passed

GitHub CI (Cockroach) TeamCity build finished
Details
bors Build succeeded
Details
license/cla Contributor License Agreement is signed.
Details

@jordanlewis jordanlewis deleted the jordanlewis:fix-tr-bench branch Oct 16, 2018

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment