)]}'
{
  "commit": "7cf059252bafe98c2088d20aac916347fb20b57b",
  "tree": "6426e8423c882a18f5b65462cfaa5518a773048f",
  "parents": [
    "2672fe23805a35a88d3a0a3aed281ede2d902fa9"
  ],
  "author": {
    "name": "reubent",
    "email": "reubent@google.com",
    "time": "Thu Feb 12 13:10:07 2026 -0800"
  },
  "committer": {
    "name": "Copybara-Service",
    "email": "copybara-worker@google.com",
    "time": "Thu Feb 12 13:11:08 2026 -0800"
  },
  "message": "Add new balsa_frame microbenchmark\n\nThis microbenchmark is very simple and tests the performance of parsing a chunked request with extensions with the strictest HttpValidationPolicy options available since they all add a bit of extra overhead. It also defines a nearly no-op visitor which should mimic the overhead required to invoke an integrators visitor implementation.\n\nA nearly identical test is added to balsa_frame_test.cc to test the correctness of the logic.\n\nAll `_benchmark.cc` are already excluded by copybara rules.\n\n```\nBenchmarking blaze-out/k8-opt/bin/third_party/quiche/balsa/balsa_frame_benchmark\nRun on reubent3.cam (128 X 2695 MHz CPUs); 2026-02-11T17:21:00.272874364-05:00\nCPU: AMD Rome (64 cores) dL1:32KB dL2:512KB dL3:256MB\n***WARNING*** CPU scaling is enabled, the benchmark timings may be noisy, see http://go/benchmark#cpu-scaling\nBenchmark                       Time(ns)        CPU(ns)     Iterations\n----------------------------------------------------------------------\nBM_ProcessInputChunked              1703           1762          36579 5.334kB/s\nBM_ProcessInputChunked              1741           1629          31899 6.615kB/s\nBM_ProcessInputChunked              1721           1719          39511 5.061kB/s\nBM_ProcessInputChunked              1731           1718          39599 5.053kB/s\nBM_ProcessInputChunked              1689           1712          39726 5.053kB/s\nBM_ProcessInputChunked              1699           1642          31726 6.599kB/s\nBM_ProcessInputChunked              1686           1719          39580 5.053kB/s\nBM_ProcessInputChunked              1685           1711          39837 5.044kB/s\nBM_ProcessInputChunked              1693           1716          39636 5.053kB/s\nBM_ProcessInputChunked              1693           1710          39783 5.053kB/s\nBM_ProcessInputChunked              1711           1702          39922 5.060kB/s\nBM_ProcessInputChunked_mean         1704           1706         417798 5.315kB/s\nBM_ProcessInputChunked_stddev         17.9           33.2       417798 566.449B/s\n```\n\nProtected by adding google3 only performance test.\n\nPiperOrigin-RevId: 869351347\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "1ff0488e39910ebe0c7e7c6e2709728f088a3700",
      "old_mode": 33188,
      "old_path": "quiche/balsa/balsa_frame_test.cc",
      "new_id": "3bf7873696b7b5982f89cd3dd4a6bd7583d6d591",
      "new_mode": 33188,
      "new_path": "quiche/balsa/balsa_frame_test.cc"
    },
    {
      "type": "modify",
      "old_id": "fc5cd7ef0d557d90d151df5a00e147c876b02c46",
      "old_mode": 33188,
      "old_path": "quiche/balsa/http_validation_policy.h",
      "new_id": "a1970719326a75cab4e7ff513ad9ed6c75250425",
      "new_mode": 33188,
      "new_path": "quiche/balsa/http_validation_policy.h"
    }
  ]
}