rust/neon
1
0
Fork 0
mirror of https://github.com/neondatabase/neon.git synced 2026-05-31 03:50:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

remov the "parallel" mode, as we won't ever enable this in practice and benchmarks have shown very limited upside over futures-unordered

Browse Source
This commit is contained in:
Christian Schwarz
2024-12-21 20:44:13 +01:00
parent d844ed098a
commit 4637389882
7 changed files with 12 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py
View File

@@ -67,7 +67,7 @@ def test_pageserver_characterize_throughput_with_n_tenants(
# which by default uses 64 connections
@pytest.mark.parametrize("n_clients", [1])
@pytest.mark.parametrize("n_tenants", [1])
@pytest.mark.parametrize("io_concurrency", ["serial", "parallel", "futures-unordered"])
@pytest.mark.parametrize("io_concurrency", ["serial", "futures-unordered"])
@pytest.mark.parametrize("ps_direct_io_mode", ["direct"])
@pytest.mark.timeout(2400)
@skip_on_ci(

2
test_runner/performance/pageserver/test_page_service_batching.py
View File

@@ -32,7 +32,7 @@ class PageServicePipeliningConfigPipelined(PageServicePipeliningConfig):
PS_DIRECT_IO = ["direct"]
PS_IO_CONCURRENCY = ["serial", "parallel", "futures-unordered"]
PS_IO_CONCURRENCY = ["serial", "futures-unordered"]
EXECUTION = ["concurrent-futures"]
NON_BATCHABLE: list[PageServicePipeliningConfig] = [PageServicePipeliningConfigSerial()]