Buckets:

glennmatlin's picture
download
raw
1.53 kB
#!/usr/bin/env bash
#SBATCH --job-name=soc91_eda_array
#SBATCH -A gts-schava6-qcf
#SBATCH -q embers
#SBATCH --partition=cpu-small
#SBATCH --cpus-per-task=8
#SBATCH --mem=32G
#SBATCH --time=08:00:00
#SBATCH --array=0-0
#SBATCH --output=logs/soc91_sidecar_eda/%x_%A_%a.out
#SBATCH --error=logs/soc91_sidecar_eda/%x_%A_%a.err
set -euo pipefail
REPO_DIR="${SLURM_SUBMIT_DIR:-$(cd "$(dirname "$0")/../../.." && pwd)}"
cd "$REPO_DIR"
mkdir -p logs/soc91_sidecar_eda
export PYTHONPATH="${REPO_DIR}/src${PYTHONPATH:+:$PYTHONPATH}"
PYTHONEXEC="${PYTHONEXEC:-$REPO_DIR/.venv/bin/python}"
if [ ! -x "$PYTHONEXEC" ]; then
echo "ERROR: Python executable not found: $PYTHONEXEC"
exit 1
fi
R2_ENV_FILE="${R2_ENV_FILE:-$HOME/.r2_credentials}"
if [ -f "$R2_ENV_FILE" ]; then
source "$R2_ENV_FILE"
fi
if [ -z "${R2_ACCESS_KEY_ID:-}" ] || [ -z "${R2_SECRET_ACCESS_KEY:-}" ]; then
echo "ERROR: R2 credentials not set"
exit 1
fi
OUTDIR="${OUTDIR:-$HOME/scratch/soc91/sidecar_eda_runs/current}"
MANIFEST_PATH="${MANIFEST_PATH:?MANIFEST_PATH is required}"
CHUNK_COUNT="${CHUNK_COUNT:-32}"
WORKERS_DIR="${WORKERS_DIR:-$OUTDIR/workers}"
WORKER_OUTPUT_DIR="$WORKERS_DIR/${SLURM_ARRAY_TASK_ID}"
mkdir -p "$WORKER_OUTPUT_DIR"
srun "$PYTHONEXEC" scripts/validation/analyze_sidecar_labels.py \
--mode worker \
--output-dir "$OUTDIR" \
--worker-output-dir "$WORKER_OUTPUT_DIR" \
--manifest-path "$MANIFEST_PATH" \
--chunk-count "$CHUNK_COUNT" \
--chunk-index "$SLURM_ARRAY_TASK_ID" \
--no-write-final-outputs

Xet Storage Details

Size:
1.53 kB
·
Xet hash:
be83620d2d0ba5072d593dd51deaaf35c73d4cc2a3fa011f22a20b4e26c78c1c

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.