28 lines
2.5 KiB
Bash
Executable file
28 lines
2.5 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
# The prover-floor agent's known-failed case (6 October 2026, 13:05Z): rebuild sp1-gpu-server from patch v5 (the panic
|
|
# hook that turns a failed device allocation into "FLOOR abort ..." and exit 70) and re-run the 2^27 compressed point
|
|
# alone on a card it cannot fit; report the host's failing line, the server's FLOOR abort line and the seconds.
|
|
set -uo pipefail
|
|
F=/root/fleet; OUT=$F/out; FLOOR=/opt/igneum-floor; SRC=$FLOOR/sp1; HOST=$FLOOR/bin/igneum-prove-host
|
|
export PATH="$HOME/.cargo/bin:$FLOOR/go/bin:$PATH" RUSTUP_TOOLCHAIN=stable GOPATH=$FLOOR/gopath GOCACHE=$FLOOR/gocache GOFLAGS=-mod=mod CUDA_ARCHS="${ARCHS:-86}" CARGO_TARGET_DIR=$FLOOR/target
|
|
exec >> $OUT/floor-v5.log 2>&1
|
|
stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; }
|
|
echo "RESULT v5_start $(stamp) patch_sha256=$(sha256sum $F/in/floor-v5.patch | cut -c1-16)"
|
|
bash $F/in/box-kill.sh >/dev/null 2>&1
|
|
cd "$SRC" && git checkout -q -- . && git clean -qfd sp1-gpu/crates >/dev/null 2>&1
|
|
git apply $F/in/floor-v5.patch || { echo "RESULT v5_failed patch does not apply"; exit 2; }
|
|
touch sp1-gpu/crates/prover_components/src/builder.rs sp1-gpu/crates/jagged_tracegen/src/lib.rs sp1-gpu/crates/server/src/server.rs sp1-gpu/crates/cuda/src/task.rs sp1-gpu/crates/server/src/main.rs
|
|
echo "RESULT v5_patched $(git diff --stat | tail -1)"
|
|
t0=$(date +%s)
|
|
cargo build --release --bin sp1-gpu-server -j $(( $(nproc) > 16 ? 16 : $(nproc) )) > $FLOOR/logs/build-server-v5.log 2>&1; rc=$?
|
|
echo "RESULT v5_build_exit $rc time_s=$(( $(date +%s) - t0 ))"
|
|
[ $rc -eq 0 ] || { grep -n -A6 '^error' $FLOOR/logs/build-server-v5.log | head -30; echo "RESULT v5_failed build"; exit 2; }
|
|
mkdir -p $FLOOR/home-v5/.sp1/bin && cp $FLOOR/target/release/sp1-gpu-server $FLOOR/home-v5/.sp1/bin/ && chmod +x $FLOOR/home-v5/.sp1/bin/sp1-gpu-server
|
|
echo "RESULT v5_server sha256=$(sha256sum $FLOOR/home-v5/.sp1/bin/sp1-gpu-server | cut -c1-16) bytes=$(stat -c %s $FLOOR/home-v5/.sp1/bin/sp1-gpu-server)"
|
|
pkill -9 -x sp1-gpu-server; rm -f /tmp/sp1-cuda-*.sock; sleep 2
|
|
t1=$(date +%s)
|
|
env HOME=$FLOOR/home-v5 SP1_PROVER=cuda RUST_LOG=off SP1_GPU_FLOOR_LOG=1 SP1_GPU_ELEMENT_THRESHOLD=134217728 timeout 900 $HOST $FLOOR/prove/proving/fixtures/fees-v1-shards2.json --mode compressed --shard 0 --out $OUT/v5-point.json > $OUT/v5-point.log 2>&1; rc=$?
|
|
echo "RESULT v5_point rc=$rc wall_s=$(( $(date +%s) - t1 ))"
|
|
grep -n -E 'FLOOR abort|panicked|Error|error|RESULT' $OUT/v5-point.log | head -12 | cut -c1-300
|
|
pkill -9 -x sp1-gpu-server; rm -f /tmp/sp1-cuda-*.sock
|
|
echo "RESULT v5_done $(stamp)"
|