rust/neon
1
0
Fork 0
mirror of https://github.com/neondatabase/neon.git synced 2026-05-18 21:50:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

async-timer based approach (again, with data)

Browse Source 
Yep, it's clearly the best one with best batching factor at lowest CPU
usage.

https://www.notion.so/neondatabase/benchmarking-notes-143f189e004780c4a630cb5f426e39ba?pvs=4#144f189e004780d0a205e081458b46db
This commit is contained in:
Christian Schwarz
2024-11-20 14:36:46 +01:00
parent f9bf038d2c
commit 689788cbba
5 changed files with 31 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
test_runner/performance/pageserver/test_pageserver_getpage_merge.py
View File

@@ -9,7 +9,7 @@ from fixtures.log_helper import log
from fixtures.neon_fixtures import NeonEnvBuilder
from fixtures.utils import humantime_to_ms
TARGET_RUNTIME = 60
TARGET_RUNTIME = 5
@pytest.mark.parametrize(
@@ -18,10 +18,12 @@ TARGET_RUNTIME = 60
# the next 4 cases demonstrate how not-batchable workloads suffer from batching timeout
(50, None, TARGET_RUNTIME, 1, 128, "not batchable no batching"),
(50, "10us", TARGET_RUNTIME, 1, 128, "not batchable 10us timeout"),
(50, "20us", TARGET_RUNTIME, 1, 128, "not batchable 20us timeout"),
(50, "1ms", TARGET_RUNTIME, 1, 128, "not batchable 1ms timeout"),
# the next 4 cases demonstrate how batchable workloads benefit from batching
(50, None, TARGET_RUNTIME, 100, 128, "batchable no batching"),
(50, "10us", TARGET_RUNTIME, 100, 128, "batchable 10us timeout"),
(50, "20us", TARGET_RUNTIME, 100, 128, "batchable 20us timeout"),
(50, "100us", TARGET_RUNTIME, 100, 128, "batchable 100us timeout"),
(50, "1ms", TARGET_RUNTIME, 100, 128, "batchable 1ms timeout"),
],