# Stand evidence collected 2026-10-07T01:45Z ## sel-db CPU(s): 16 Model name: Intel(R) Xeon(R) Gold 6354 CPU @ 3.00GHz Thread(s) per core: 2 Core(s) per socket: 4 Socket(s): 2 NUMA node(s): 1 total used free shared buff/cache available Mem: 62 1 42 0 19 60 6.12.111+deb13-amd64 Debian GNU/Linux 13 (trixie) ## sel-load CPU(s): 16 Model name: Intel(R) Xeon(R) Gold 6354 CPU @ 3.00GHz Thread(s) per core: 2 Core(s) per socket: 4 Socket(s): 2 NUMA node(s): 1 total used free shared buff/cache available Mem: 62 0 60 0 2 61 6.12.111+deb13-amd64 Debian GNU/Linux 13 (trixie) ## sel-db PostgreSQL and data PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on x86_64-pc-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit max_connections=1000 pg_local_cache.allow_plaintext_network=on pg_local_cache.allow_superuser=off pg_local_cache.binary_build_id=final-c431bcc pg_local_cache.binary_version=3.1.0 pg_local_cache.bind_address=192.168.0.2 pg_local_cache.cache_entries=1048576 pg_local_cache.database=pglc_demo pg_local_cache.dirty_marker_entries=-1 pg_local_cache.dirty_marker_memory_mb=-1 pg_local_cache.enabled=on pg_local_cache.idle_timeout_ms=300000 pg_local_cache.lock_partitions=64 pg_local_cache.lock_timeout_ms=250 pg_local_cache.max_clients=2048 pg_local_cache.max_clients_per_worker=256 pg_local_cache.max_deferred_misses=8 pg_local_cache.max_dirty_keys=4096 pg_local_cache.max_pipeline_commands=256 pg_local_cache.memory_budget_mb=1024 pg_local_cache.port=6380 pg_local_cache.relation_states=1024 pg_local_cache.role=local_cache_worker pg_local_cache.singleflight_wait_ms=25 pg_local_cache.statement_timeout_ms=2000 pg_local_cache.tls=off pg_local_cache.tls_ca_file= pg_local_cache.tls_cert_file= pg_local_cache.tls_key_file= pg_local_cache.tls_min_protocol_version=TLSv1.2 pg_local_cache.workers=8 shared_buffers=1048576 synchronous_commit=on items rows=100000 avg_json_bytes=166 io-threads 8 appendonly no save "" Valkey server v=8.1.1 sha=00000000:0 malloc=jemalloc-5.3.0 bits=64 build=ad0f3ed608b40934 ## network (sel-load -> sel-db private address) [SUM] 0.00-5.00 sec 6.04 GBytes 10.4 Gbits/sec receiver rtt min/avg/max/mdev = 0.090/0.143/0.871/0.167 ms ## Notes Valkey io-threads during write-overhead, mixed and stale runs: 8 (set by final4.sh before phase C); io-threads 1/2/4/8 per-core runs as labelled in the JSONL file names.