bench: Add benchmark for rollback

[MyonKeminta]

Signed-off-by: MyonKeminta MyonKeminta@users.noreply.github.com

What have you changed? (mandatory)

This PR adds benchmarks for MvccTxn::rollback.

It's divided two three different cases:

• rollback_prewrote: Prewrite happens before the rollback
• rollback_conflict: Another transaction's Prewrite happens before the rollback
• rollback_non_prewrote: The rollback happens before prewrite

What are the type of the changes? (mandatory)

• Improvement (change which is an improvement to an existing feature)

How has this PR been tested? (mandatory)

By CI

Does this PR affect documentation (docs) update? (mandatory)

No

Does this PR affect tidb-ansible update? (mandatory)

No

[breezewish]

/run-integration-tests

[MyonKeminta]

@breeswish Do you have any idea about the failing test? Although it's not related to this PR.

[kennytm]

The test itself was broken and has been fixed in pingcap/tidb-test#773.

/run-integration-common-test

[MyonKeminta]

@breeswish PTAL, thanks!

[breezewish]

Looks fine. How is the benchmark result?

[MyonKeminta]

mvcc_rollback_prewrote/BTree_KL64_VL64                                                                                                                                                                                                       [71/1830]
                        time:   [10.225 us 10.708 us 11.218 us]
Found 12 outliers among 100 measurements (12.00%)
  3 (3.00%) high mild
  9 (9.00%) high severe
mvcc_rollback_prewrote/BTree_KL64_VL65
                        time:   [11.002 us 11.091 us 11.181 us]
Found 9 outliers among 100 measurements (9.00%)
  4 (4.00%) low mild
  4 (4.00%) high mild
  1 (1.00%) high severe

mvcc_rollback_conflict/BTree_KL64_VL64
                        time:   [13.135 us 13.226 us 13.319 us]
Found 6 outliers among 100 measurements (6.00%)
  1 (1.00%) low mild
  5 (5.00%) high mild
mvcc_rollback_conflict/BTree_KL64_VL65
                        time:   [13.257 us 13.861 us 14.551 us]
Found 17 outliers among 100 measurements (17.00%)
  3 (3.00%) low mild
  1 (1.00%) high mild
  13 (13.00%) high severe

mvcc_rollback_non_prewrote/BTree_KL64_VL64
                        time:   [11.307 us 11.798 us 12.334 us]
Found 16 outliers among 100 measurements (16.00%)
  5 (5.00%) high mild
  11 (11.00%) high severe
mvcc_rollback_non_prewrote/BTree_KL64_VL65
                        time:   [11.051 us 11.475 us 11.980 us]
Found 14 outliers among 100 measurements (14.00%)
  1 (1.00%) high mild
  13 (13.00%) high severe

mvcc_rollback_prewrote/Rocks_KL64_VL64
                        time:   [35.643 us 37.843 us 40.116 us]
mvcc_rollback_prewrote/Rocks_KL64_VL65
                        time:   [35.081 us 37.399 us 39.843 us]
Found 2 outliers among 100 measurements (2.00%)
  2 (2.00%) high mild

mvcc_rollback_conflict/Rocks_KL64_VL64
                        time:   [52.123 us 54.932 us 57.835 us]
mvcc_rollback_conflict/Rocks_KL64_VL65
                        time:   [48.584 us 50.529 us 52.538 us]
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild

mvcc_rollback_non_prewrote/Rocks_KL64_VL64
                        time:   [46.432 us 48.767 us 51.157 us]
mvcc_rollback_non_prewrote/Rocks_KL64_VL65
                        time:   [44.486 us 47.163 us 50.265 us]

txn_rollback_prewrote/BTree_KL64_VL64
                        time:   [24.663 us 25.006 us 25.323 us]
txn_rollback_prewrote/BTree_KL64_VL65
                        time:   [27.438 us 27.688 us 27.931 us]
Found 4 outliers among 100 measurements (4.00%)
  2 (2.00%) low mild
  2 (2.00%) high mild

txn_rollback_conflict/BTree_KL64_VL64
                        time:   [30.000 us 32.053 us 34.725 us]
Found 9 outliers among 100 measurements (9.00%)
  1 (1.00%) low mild
  8 (8.00%) high severe
txn_rollback_conflict/BTree_KL64_VL65
                        time:   [30.093 us 30.332 us 30.562 us]
Found 3 outliers among 100 measurements (3.00%)
  3 (3.00%) low mild

txn_rollback_non_prewrote/BTree_KL64_VL64
                        time:   [29.220 us 30.477 us 32.041 us]
Found 17 outliers among 100 measurements (17.00%)
  8 (8.00%) high mild
  9 (9.00%) high severe
txn_rollback_non_prewrote/BTree_KL64_VL65
                        time:   [27.890 us 28.497 us 29.210 us]
Found 3 outliers among 100 measurements (3.00%)
  1 (1.00%) high mild
  2 (2.00%) high severe

txn_rollback_prewrote/Rocks_KL64_VL64
                        time:   [381.48 us 394.98 us 407.82 us]
Found 3 outliers among 100 measurements (3.00%)
  2 (2.00%) high mild
  1 (1.00%) high severe
txn_rollback_prewrote/Rocks_KL64_VL65
                        time:   [374.66 us 391.05 us 408.22 us]
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild

txn_rollback_conflict/Rocks_KL64_VL64
                        time:   [382.33 us 397.98 us 414.41 us]
Found 4 outliers among 100 measurements (4.00%)
  4 (4.00%) high mild
txn_rollback_conflict/Rocks_KL64_VL65
                        time:   [371.65 us 383.53 us 395.70 us]
Found 6 outliers among 100 measurements (6.00%)
  2 (2.00%) low mild
  3 (3.00%) high mild
  1 (1.00%) high severe

txn_rollback_non_prewrote/Rocks_KL64_VL64
                        time:   [465.25 us 483.34 us 502.85 us]
Found 12 outliers among 100 measurements (12.00%)
  4 (4.00%) high mild
  8 (8.00%) high severe
txn_rollback_non_prewrote/Rocks_KL64_VL65
                        time:   [416.96 us 437.67 us 460.22 us]
Found 9 outliers among 100 measurements (9.00%)
  2 (2.00%) high mild
  7 (7.00%) high severe

[AndreMouche]

LGTM

[AndreMouche]

Please fix the conflicts.

[MyonKeminta]

@AndreMouche @breeswish PTAL again thanks!
Git diff works terrible in this PR, which makes it hard to resolve conflicts... Hope this will not cause confusions to you.

[AndreMouche]

LGTM

[MyonKeminta]

/run-integration-tests