Use zstd to compress large allure artifacts (#5458)

## Problem - Because we compress artifacts file by file, we don't need to put them into `tar` containers (ie instead of `tar.gz` we can use just `gz`). - Pythons gz single-threaded and pretty slow. A benchmark has shown ~20 times speedup (19.876176291 vs 0.8748335830000009) on my laptop (for a pageserver.log size is 1.3M) ## Summary of changes - Replace tarfile with zstandart - Update allure to 2.24.0
2025-12-22 21:59:59 +00:00 · 2023-10-04 16:20:16 +01:00
parent 25a37215f3
commit 7a2cafb34d
4 changed files with 79 additions and 13 deletions
--- a/.github/actions/allure-report-generate/action.yml
+++ b/.github/actions/allure-report-generate/action.yml
@@ -76,8 +76,8 @@ runs:
          rm -f ${ALLURE_ZIP}
        fi
      env:
-        ALLURE_VERSION: 2.23.1
-        ALLURE_ZIP_SHA256: 11141bfe727504b3fd80c0f9801eb317407fd0ac983ebb57e671f14bac4bcd86
+        ALLURE_VERSION: 2.24.0
+        ALLURE_ZIP_SHA256: 60b1d6ce65d9ef24b23cf9c2c19fd736a123487c38e54759f1ed1a7a77353c90

    # Potentially we could have several running build for the same key (for example, for the main branch), so we use improvised lock for this
    - name: Acquire lock
--- a/poetry.lock
+++ b/poetry.lock
@@ -2648,7 +2648,65 @@ files = [
 docs = ["jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx"]
 testing = ["func-timeout", "jaraco.itertools", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"]

+[[package]]
+name = "zstandard"
+version = "0.21.0"
+description = "Zstandard bindings for Python"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "zstandard-0.21.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:649a67643257e3b2cff1c0a73130609679a5673bf389564bc6d4b164d822a7ce"},
+    {file = "zstandard-0.21.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:144a4fe4be2e747bf9c646deab212666e39048faa4372abb6a250dab0f347a29"},
+    {file = "zstandard-0.21.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b72060402524ab91e075881f6b6b3f37ab715663313030d0ce983da44960a86f"},
+    {file = "zstandard-0.21.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8257752b97134477fb4e413529edaa04fc0457361d304c1319573de00ba796b1"},
+    {file = "zstandard-0.21.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:c053b7c4cbf71cc26808ed67ae955836232f7638444d709bfc302d3e499364fa"},
+    {file = "zstandard-0.21.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2769730c13638e08b7a983b32cb67775650024632cd0476bf1ba0e6360f5ac7d"},
+    {file = "zstandard-0.21.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7d3bc4de588b987f3934ca79140e226785d7b5e47e31756761e48644a45a6766"},
+    {file = "zstandard-0.21.0-cp310-cp310-win32.whl", hash = "sha256:67829fdb82e7393ca68e543894cd0581a79243cc4ec74a836c305c70a5943f07"},
+    {file = "zstandard-0.21.0-cp310-cp310-win_amd64.whl", hash = "sha256:e6048a287f8d2d6e8bc67f6b42a766c61923641dd4022b7fd3f7439e17ba5a4d"},
+    {file = "zstandard-0.21.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:7f2afab2c727b6a3d466faee6974a7dad0d9991241c498e7317e5ccf53dbc766"},
+    {file = "zstandard-0.21.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ff0852da2abe86326b20abae912d0367878dd0854b8931897d44cfeb18985472"},
+    {file = "zstandard-0.21.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d12fa383e315b62630bd407477d750ec96a0f438447d0e6e496ab67b8b451d39"},
+    {file = "zstandard-0.21.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f1b9703fe2e6b6811886c44052647df7c37478af1b4a1a9078585806f42e5b15"},
+    {file = "zstandard-0.21.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:df28aa5c241f59a7ab524f8ad8bb75d9a23f7ed9d501b0fed6d40ec3064784e8"},
+    {file = "zstandard-0.21.0-cp311-cp311-win32.whl", hash = "sha256:0aad6090ac164a9d237d096c8af241b8dcd015524ac6dbec1330092dba151657"},
+    {file = "zstandard-0.21.0-cp311-cp311-win_amd64.whl", hash = "sha256:48b6233b5c4cacb7afb0ee6b4f91820afbb6c0e3ae0fa10abbc20000acdf4f11"},
+    {file = "zstandard-0.21.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e7d560ce14fd209db6adacce8908244503a009c6c39eee0c10f138996cd66d3e"},
+    {file = "zstandard-0.21.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e6e131a4df2eb6f64961cea6f979cdff22d6e0d5516feb0d09492c8fd36f3bc"},
+    {file = "zstandard-0.21.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e1e0c62a67ff425927898cf43da2cf6b852289ebcc2054514ea9bf121bec10a5"},
+    {file = "zstandard-0.21.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:1545fb9cb93e043351d0cb2ee73fa0ab32e61298968667bb924aac166278c3fc"},
+    {file = "zstandard-0.21.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fe6c821eb6870f81d73bf10e5deed80edcac1e63fbc40610e61f340723fd5f7c"},
+    {file = "zstandard-0.21.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:ddb086ea3b915e50f6604be93f4f64f168d3fc3cef3585bb9a375d5834392d4f"},
+    {file = "zstandard-0.21.0-cp37-cp37m-win32.whl", hash = "sha256:57ac078ad7333c9db7a74804684099c4c77f98971c151cee18d17a12649bc25c"},
+    {file = "zstandard-0.21.0-cp37-cp37m-win_amd64.whl", hash = "sha256:1243b01fb7926a5a0417120c57d4c28b25a0200284af0525fddba812d575f605"},
+    {file = "zstandard-0.21.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ea68b1ba4f9678ac3d3e370d96442a6332d431e5050223626bdce748692226ea"},
+    {file = "zstandard-0.21.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:8070c1cdb4587a8aa038638acda3bd97c43c59e1e31705f2766d5576b329e97c"},
+    {file = "zstandard-0.21.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4af612c96599b17e4930fe58bffd6514e6c25509d120f4eae6031b7595912f85"},
+    {file = "zstandard-0.21.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cff891e37b167bc477f35562cda1248acc115dbafbea4f3af54ec70821090965"},
+    {file = "zstandard-0.21.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a9fec02ce2b38e8b2e86079ff0b912445495e8ab0b137f9c0505f88ad0d61296"},
+    {file = "zstandard-0.21.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0bdbe350691dec3078b187b8304e6a9c4d9db3eb2d50ab5b1d748533e746d099"},
+    {file = "zstandard-0.21.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:b69cccd06a4a0a1d9fb3ec9a97600055cf03030ed7048d4bcb88c574f7895773"},
+    {file = "zstandard-0.21.0-cp38-cp38-win32.whl", hash = "sha256:9980489f066a391c5572bc7dc471e903fb134e0b0001ea9b1d3eff85af0a6f1b"},
+    {file = "zstandard-0.21.0-cp38-cp38-win_amd64.whl", hash = "sha256:0e1e94a9d9e35dc04bf90055e914077c80b1e0c15454cc5419e82529d3e70728"},
+    {file = "zstandard-0.21.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d2d61675b2a73edcef5e327e38eb62bdfc89009960f0e3991eae5cc3d54718de"},
+    {file = "zstandard-0.21.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:25fbfef672ad798afab12e8fd204d122fca3bc8e2dcb0a2ba73bf0a0ac0f5f07"},
+    {file = "zstandard-0.21.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:62957069a7c2626ae80023998757e27bd28d933b165c487ab6f83ad3337f773d"},
+    {file = "zstandard-0.21.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:14e10ed461e4807471075d4b7a2af51f5234c8f1e2a0c1d37d5ca49aaaad49e8"},
+    {file = "zstandard-0.21.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:9cff89a036c639a6a9299bf19e16bfb9ac7def9a7634c52c257166db09d950e7"},
+    {file = "zstandard-0.21.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:52b2b5e3e7670bd25835e0e0730a236f2b0df87672d99d3bf4bf87248aa659fb"},
+    {file = "zstandard-0.21.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:b1367da0dde8ae5040ef0413fb57b5baeac39d8931c70536d5f013b11d3fc3a5"},
+    {file = "zstandard-0.21.0-cp39-cp39-win32.whl", hash = "sha256:db62cbe7a965e68ad2217a056107cc43d41764c66c895be05cf9c8b19578ce9c"},
+    {file = "zstandard-0.21.0-cp39-cp39-win_amd64.whl", hash = "sha256:a8d200617d5c876221304b0e3fe43307adde291b4a897e7b0617a61611dfff6a"},
+    {file = "zstandard-0.21.0.tar.gz", hash = "sha256:f08e3a10d01a247877e4cb61a82a319ea746c356a3786558bed2481e6c405546"},
+]
+
+[package.dependencies]
+cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\""}
+
+[package.extras]
+cffi = ["cffi (>=1.11)"]
+
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "c40f62277e788011920f4edb6f7392046ee440f792a104c903097415def9a916"
+content-hash = "c5981d8d7c2deadd47c823bc35f86f830c8e320b653d2d3718bade1f4d2dabca"
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -37,6 +37,7 @@ aiohttp = "3.8.5"
 pytest-rerunfailures = "^11.1.2"
 types-pytest-lazy-fixture = "^0.6.3.3"
 pytest-split = "^0.8.1"
+zstandard = "^0.21.0"

 [tool.poetry.group.dev.dependencies]
 black = "^23.3.0"
--- a/test_runner/fixtures/utils.py
+++ b/test_runner/fixtures/utils.py
@@ -3,7 +3,6 @@ import json
 import os
 import re
 import subprocess
-import tarfile
 import threading
 import time
 from pathlib import Path
@@ -11,6 +10,7 @@ from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Tuple, Ty
 from urllib.parse import urlencode

 import allure
+import zstandard
 from psycopg2.extensions import cursor

 from fixtures.log_helper import log
@@ -231,19 +231,26 @@ def allure_attach_from_dir(dir: Path):

    for attachment in Path(dir).glob("**/*"):
        if ATTACHMENT_NAME_REGEX.fullmatch(attachment.name) and attachment.stat().st_size > 0:
-            source = str(attachment)
            name = str(attachment.relative_to(dir))

-            # compress files larger than 1Mb, they're hardly readable in a browser
-            if attachment.stat().st_size > 1024 * 1024:
-                source = f"{attachment}.tar.gz"
-                with tarfile.open(source, "w:gz") as tar:
-                    tar.add(attachment, arcname=attachment.name)
-                name = f"{name}.tar.gz"
+            # compress files that are larger than 1Mb, they're hardly readable in a browser
+            if attachment.stat().st_size > 1024**2:
+                compressed = attachment.with_suffix(".zst")

-            if source.endswith(".tar.gz"):
+                cctx = zstandard.ZstdCompressor()
+                with attachment.open("rb") as fin, compressed.open("wb") as fout:
+                    cctx.copy_stream(fin, fout)
+
+                name = f"{name}.zst"
+                attachment = compressed
+
+            source = str(attachment)
+            if source.endswith(".gz"):
                attachment_type = "application/gzip"
-                extension = "tar.gz"
+                extension = "gz"
+            elif source.endswith(".zst"):
+                attachment_type = "application/zstd"
+                extension = "zst"
            elif source.endswith(".svg"):
                attachment_type = "image/svg+xml"
                extension = "svg"