kata-containers/cloud-hypervisor
1
0
Fork 0
mirror of https://github.com/cloud-hypervisor/cloud-hypervisor.git synced 2026-08-05 02:19:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

performance-metrics: Add QCOW2 multi-cluster read micro benchmark

Browse Source 
Add micro_bench_qcow_multi_cluster_read which issues large reads
spanning 8 contiguous clusters (512 KiB) per read_vectored call.
This exercises the mapping coalesce path where multiple L2 entries
are merged into fewer host I/O operations.

Workloads: 128 and 256 total clusters (16 and 32 reads).
Signed-off-by: Anatol Belski <anbelski@linux.microsoft.com>
This commit is contained in:
Anatol Belski
2026-03-26 22:53:32 +01:00
committed by Rob Bradford
parent 7dd1978fce
commit 94f78edcf0
2 changed files with 55 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
performance-metrics/src/main.rs
View File

@@ -378,7 +378,7 @@ mod adjuster {
}
}
const TEST_LIST: [PerformanceTest; 78] = [
const TEST_LIST: [PerformanceTest; 80] = [
PerformanceTest {
name: "boot_time_ms",
func_ptr: performance_boot_time,
@@ -1445,6 +1445,30 @@ const TEST_LIST: [PerformanceTest; 78] = [
},
unit_adjuster: adjuster::s_to_us,
},
PerformanceTest {
name: "micro_block_qcow_multi_cluster_read_128_us",
func_ptr: micro_bench_block::micro_bench_qcow_multi_cluster_read,
control: PerformanceTestControl {
test_timeout: 10,
test_iterations: 20,
warmup_iterations: 5,
num_ops: Some(128),
..PerformanceTestControl::default()
},
unit_adjuster: adjuster::s_to_us,
},
PerformanceTest {
name: "micro_block_qcow_multi_cluster_read_256_us",
func_ptr: micro_bench_block::micro_bench_qcow_multi_cluster_read,
control: PerformanceTestControl {
test_timeout: 10,
test_iterations: 20,
warmup_iterations: 5,
num_ops: Some(256),
..PerformanceTestControl::default()
},
unit_adjuster: adjuster::s_to_us,
},
];
fn run_test_with_timeout(