feat(presto/bench): NUMA-aware Presto worker config generation

[misiugodfrey]

Summary

Rewrites generate_presto_config.sh to discover host NUMA topology at config-generation time and size each worker to its proportional share of the NUMA node(s) it will be bound to. Previously all workers on a host received identical configs sized to the full host, which over-allocated CPU and memory for multi-worker-per-host CPU runs.

Based on kjmph's bench33 POC patch.

• discover_cpu_numa_topology (new helper in common_functions.sh): uses lscpu, lsmem, and /proc/meminfo fallbacks to enumerate CPU NUMA nodes, their logical CPU counts, and their memory in GB; distinguishes CPU-hosting nodes from HBM-only memory nodes (relevant for Grace-Hopper hosts)
• cpu_numa_node_for_worker (new helper): maps a worker slot index to its NUMA node using balanced contiguous placement (yields 0; 0,1; 0,0,1,1 for 1/2/4 workers on a 2-socket host)
• count_linux_cpu_list (new helper): parses Linux Cpus_allowed_list-style range strings (e.g. 0-47,96-143) to a count
• generate_presto_config.sh: NUMA topology discovery runs when USE_NUMA=1; per-worker CPU thread and RAM limits derived from the smallest NUMA node share; CPU_NUMA_WORKER_LAYOUT exported as <node>:<count> map for downstream consumers; set_or_append_property helper for idempotent property file mutations; cuDF exchange guard restricted to GPU-only (was incorrectly gating CPU runs)

Dependencies

Depends on PR #390 (bench-fixes-tuning) for the common_functions.sh jq→python3 fix in wait_for_worker_node_registration. Rebase after PR #390 merges.

Verification

• On a 2-socket Grace host with CPU_WORKERS_PER_HOST=2 and USE_NUMA=1, verify generate_presto_config.sh produces two configs with CPU count = (total logical CPUs on one socket / 2) and RAM = (HBM on that socket / 2)
• On a host with USE_NUMA=0, verify the generated config is unchanged from the pre-patch behavior (full-host sizing, single worker)
• Verify CPU_NUMA_WORKER_LAYOUT is set correctly (e.g. 0:1,1:1 for 2 workers on a 2-socket host)
• Check that discover_cpu_numa_topology correctly ignores HBM-only NUMA nodes as CPU-hosting nodes on Grace-Hopper (nodes with CPU_NUMA_NODE_CPU_COUNTS[i] == 0 should not contribute CPU slots)
• Verify set_or_append_property is idempotent: running generate_presto_config.sh twice does not duplicate property entries
• Run ./ci/check_style.sh on changed files

[copy-pr-bot]

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.