mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-03 10:37:35 +01:00
pingqiuandClaude Opus 4.6
ebe95b6e2e
Bug: flusher.go:336 allocated make([]byte, entryLen) per dirty block instead of per unique WAL entry. A 4MB WriteLBA creates 1024 dirty map entries (one per 4KB block), all sharing the same WAL offset. The flusher read the full 4MB WAL entry 1024 times into separate buffers: 1024 × 4MB = 4GB per 4MB write → OOM on mkfs.ext4. Root cause: flusher assumed 1:1 dirty-block-to-WAL-entry mapping. WriteLBA supports multi-block writes but the flusher never deduplicated shared WAL offsets. Fix: deduplicate WAL reads by WalOffset in flushOnceLocked(). Multiple dirty blocks from the same WAL entry share one read buffer and one DecodeWALEntry call. Memory: O(WAL_entries × size) not O(blocks × size). For a 4MB write: 4GB → 4MB. Verified on hardware (m01/M02 25Gbps RoCE): - Before: mkfs.ext4 → VS RSS 100MB→25GB → OOM killed - After: mkfs.ext4 → VS RSS 129MB stable, mkfs succeeds - pgbench TPC-B c=4: 1,248 TPS (RF=1, previously blocked by OOM) Tests added: - flusher_test.go: flush_multiblock_shared_wal_read (16 blocks share one WAL offset, flush dedup verified) - flusher_test.go: flush_multiblock_data_correct (3 mixed multi-block writes, all data correct after flush) - test/component/large_write_test.go: 7 component tests (single 4MB, sequential mkfs sim, concurrent, mixed sizes, production volume, flusher throughput 30s sustained) - iscsi/large_write_mem_test.go: 2 iSCSI session memory tests (4MB R2T flow, slow device) Testrunner enhancements (same commit — all tested on hardware): - discover_primary action: maps primary IP → topology node name, supports alt_ips for multi-NIC (RoCE + management) - NodeSpec.AltIPs field for multi-NIC node identification - 5 new YAML scenarios: ec3, ec5, degraded sync_all/best_effort, pgbench - All 13 hardware-verified scenarios PASS Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
210 lines
5.1 KiB
YAML
210 lines
5.1 KiB
YAML
name: benchmark-pgbench
|
|
timeout: 15m
|
|
|
|
# Database benchmark: PostgreSQL pgbench on sw-block.
|
|
#
|
|
# Measures TPS for TPC-B (mixed read/write) and SELECT-only at various
|
|
# client counts. This is the most product-relevant benchmark — operators
|
|
# care about database performance on block storage.
|
|
#
|
|
# Competitive reference (March 2024, RF=2 sync, 25Gbps):
|
|
# Ceph RBD: 431 TPS
|
|
# Longhorn V1: 2,754 TPS
|
|
# sw-block: 3,226 TPS (old code, commit e92263b)
|
|
# Mayastor: 5,801 TPS
|
|
#
|
|
# Current sw-block number after syncWithWALProgress fix: unknown.
|
|
|
|
env:
|
|
master_url: "http://10.0.0.3:9433"
|
|
volume_name: bench-pgbench
|
|
# 2GB is enough for pgbench scale=10 (~150MB data).
|
|
# 4GB caused OOM on VS (20GB RSS → OOM killed).
|
|
vol_size: "2147483648"
|
|
|
|
topology:
|
|
nodes:
|
|
m01:
|
|
host: 192.168.1.181
|
|
alt_ips: ["10.0.0.1"]
|
|
user: testdev
|
|
key: "/opt/work/testdev_key"
|
|
m02:
|
|
host: 192.168.1.184
|
|
alt_ips: ["10.0.0.3"]
|
|
user: testdev
|
|
key: "/opt/work/testdev_key"
|
|
|
|
phases:
|
|
- name: cluster-start
|
|
actions:
|
|
- action: exec
|
|
node: m02
|
|
cmd: "fuser -k 9433/tcp 18480/tcp 2>/dev/null; sleep 1; rm -rf /tmp/sw-pgb-master /tmp/sw-pgb-vs1; mkdir -p /tmp/sw-pgb-master /tmp/sw-pgb-vs1/blocks"
|
|
root: "true"
|
|
ignore_error: true
|
|
- action: exec
|
|
node: m01
|
|
cmd: "fuser -k 18480/tcp 2>/dev/null; sleep 1; rm -rf /tmp/sw-pgb-vs2; mkdir -p /tmp/sw-pgb-vs2/blocks"
|
|
root: "true"
|
|
ignore_error: true
|
|
|
|
- action: start_weed_master
|
|
node: m02
|
|
port: "9433"
|
|
dir: /tmp/sw-pgb-master
|
|
extra_args: "-ip=10.0.0.3"
|
|
save_as: master_pid
|
|
|
|
- action: sleep
|
|
duration: 3s
|
|
|
|
- action: start_weed_volume
|
|
node: m02
|
|
port: "18480"
|
|
master: "10.0.0.3:9433"
|
|
dir: /tmp/sw-pgb-vs1
|
|
extra_args: "-block.dir=/tmp/sw-pgb-vs1/blocks -block.listen=:3295 -ip=10.0.0.3"
|
|
save_as: vs1_pid
|
|
|
|
- action: start_weed_volume
|
|
node: m01
|
|
port: "18480"
|
|
master: "10.0.0.3:9433"
|
|
dir: /tmp/sw-pgb-vs2
|
|
extra_args: "-block.dir=/tmp/sw-pgb-vs2/blocks -block.listen=:3295 -ip=10.0.0.1"
|
|
save_as: vs2_pid
|
|
|
|
- action: sleep
|
|
duration: 3s
|
|
|
|
- action: wait_cluster_ready
|
|
node: m02
|
|
master_url: "{{ master_url }}"
|
|
|
|
- action: wait_block_servers
|
|
count: "2"
|
|
|
|
- name: create-volume
|
|
actions:
|
|
- action: create_block_volume
|
|
name: "{{ volume_name }}"
|
|
size_bytes: "{{ vol_size }}"
|
|
replica_factor: "2"
|
|
durability_mode: "sync_all"
|
|
|
|
- action: wait_volume_healthy
|
|
name: "{{ volume_name }}"
|
|
timeout: 60s
|
|
|
|
- name: connect
|
|
actions:
|
|
- action: lookup_block_volume
|
|
name: "{{ volume_name }}"
|
|
save_as: vol
|
|
|
|
- action: iscsi_login_direct
|
|
node: m01
|
|
host: "{{ vol_iscsi_host }}"
|
|
port: "{{ vol_iscsi_port }}"
|
|
iqn: "{{ vol_iqn }}"
|
|
save_as: device
|
|
|
|
# Short sleep for device to settle.
|
|
- action: sleep
|
|
duration: 3s
|
|
|
|
- name: pgbench-setup
|
|
actions:
|
|
- action: pgbench_init
|
|
node: m01
|
|
device: "{{ device }}"
|
|
mount: "/mnt/pgbench"
|
|
port: "5434"
|
|
scale: "10"
|
|
fstype: "ext4"
|
|
|
|
- name: tpcb-c1
|
|
actions:
|
|
- action: pgbench_run
|
|
node: m01
|
|
clients: "1"
|
|
duration: "30"
|
|
save_as: tps_c1
|
|
|
|
- action: print
|
|
msg: "TPC-B c=1: {{ tps_c1 }} TPS"
|
|
|
|
- name: tpcb-c4
|
|
actions:
|
|
- action: pgbench_run
|
|
node: m01
|
|
clients: "4"
|
|
duration: "30"
|
|
save_as: tps_c4
|
|
|
|
- action: print
|
|
msg: "TPC-B c=4: {{ tps_c4 }} TPS"
|
|
|
|
- name: tpcb-c8
|
|
actions:
|
|
- action: pgbench_run
|
|
node: m01
|
|
clients: "8"
|
|
duration: "30"
|
|
save_as: tps_c8
|
|
|
|
- action: print
|
|
msg: "TPC-B c=8: {{ tps_c8 }} TPS"
|
|
|
|
- name: select-c4
|
|
actions:
|
|
- action: pgbench_run
|
|
node: m01
|
|
clients: "4"
|
|
duration: "30"
|
|
select_only: "true"
|
|
save_as: tps_sel
|
|
|
|
- action: print
|
|
msg: "SELECT-only c=4: {{ tps_sel }} TPS"
|
|
|
|
- name: results
|
|
actions:
|
|
- action: print
|
|
msg: "=== pgbench: RF=2 sync_all iSCSI/RoCE ==="
|
|
- action: print
|
|
msg: "TPC-B c=1: {{ tps_c1 }} TPS"
|
|
- action: print
|
|
msg: "TPC-B c=4: {{ tps_c4 }} TPS"
|
|
- action: print
|
|
msg: "TPC-B c=8: {{ tps_c8 }} TPS"
|
|
- action: print
|
|
msg: "SELECT-only c=4: {{ tps_sel }} TPS"
|
|
|
|
- action: collect_results
|
|
title: "pgbench: RF=2 sync_all iSCSI/RoCE"
|
|
volume_name: "{{ volume_name }}"
|
|
|
|
- name: cleanup
|
|
always: true
|
|
actions:
|
|
- action: pgbench_cleanup
|
|
node: m01
|
|
ignore_error: true
|
|
- action: iscsi_cleanup
|
|
node: m01
|
|
ignore_error: true
|
|
- action: stop_weed
|
|
node: m01
|
|
pid: "{{ vs2_pid }}"
|
|
ignore_error: true
|
|
- action: stop_weed
|
|
node: m02
|
|
pid: "{{ vs1_pid }}"
|
|
ignore_error: true
|
|
- action: stop_weed
|
|
node: m02
|
|
pid: "{{ master_pid }}"
|
|
ignore_error: true
|