DanSandClaude Opus 5.5
7131b3673f
shim/ is an LD_PRELOAD guard around close/fclose/dup2/dup3: - before each close it resolves /proc/self/fd/N; - it reports, with a backtrace, a non-owner close of wallet.dat, database/log.* or blocks/*.dat, and every close that fails with EBADF (the second half of a double close); - FDGUARD_ABORT=1 aborts on the first hit; - run_tests.sh self-tests it (51 checks). repro/ runs a shimmed dragonxd on isolated regtest. Each run gets its own unprivileged network namespace (loopback only). The loads are: - rpc: a hammer with impatient/RST/half-open clients, work-queue bursts and long-polls; - p2p: TLS peers churned by disconnectnode, ban and kill, plus a raw TCP/TLS misbehaver; - tor: a fake control port; - mine: mining with blocknotify and autoshield. tools/tally.py groups the reports by closer. tools/scan_bdb.py finds BDB pages written into block files. With the wolfSSL CloseSocket macro in effect: - p2pmin (300 s) gives one EBADF double close per disconnect; - the full load (1200 s) gives 930 EBADF closes, 186 non-owner closes (37 of wallet/log/blk files) and a 632 KB db.log with BDB0060 PANIC; - RPC-only and Tor-only loads give none. After the fix, every count is 0 and db.log stays empty. The README has the commands and the numbers. Paths come from the environment (GOLDEN, BIN, RUNS, SHIM, ASMAP and the Sapling params). Run output goes to $RUNS, outside the tree. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
73 lines
3.1 KiB
Bash
73 lines
3.1 KiB
Bash
# shellcheck shell=bash
|
|
# Shared config + helpers for the fd-double-close REPRODUCTION harness.
|
|
# Regtest only. Meant to run INSIDE an unprivileged network namespace (see ns.sh),
|
|
# so every port is private to the namespace and nothing can reach a real network.
|
|
set +e
|
|
|
|
REPRO=${REPRO:-$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)}
|
|
SRCROOT=$(cd "$REPRO/../../.." && pwd)
|
|
BIN=${BIN:-$SRCROOT/src} # dir with dragonxd + dragonx-cli (build with -g -rdynamic for backtraces)
|
|
DRAGONXD=$BIN/dragonxd
|
|
CLI=$BIN/dragonx-cli
|
|
RUNS=${RUNS:-$HOME/fd-guard-runs} # run output (block files, logs): keep it out of the repo
|
|
GOLDEN=${GOLDEN:?set GOLDEN to a regtest datadir with a grown wallet (it is only ever copied)}
|
|
ASMAP=${ASMAP:-$SRCROOT/asmap.dat}
|
|
SP=${SP:-$HOME/.zcash-params/sapling-spend.params}
|
|
OP=${OP:-$HOME/.zcash-params/sapling-output.params}
|
|
SHIM=${SHIM:-$REPRO/../shim/libfdguard.so}
|
|
|
|
RPCUSER=ab
|
|
RPCPASS=abpass
|
|
RPC_T=18901 ; P2P_T=18911
|
|
RPC_H1=18902; P2P_H1=18912
|
|
RPC_H2=18903; P2P_H2=18913
|
|
TORPORT=18950
|
|
|
|
clin() { local dd=$1 rp=$2; shift 2; "$CLI" -regtest -datadir="$dd" -rpcuser=$RPCUSER -rpcpassword=$RPCPASS -rpcport=$rp "$@"; }
|
|
|
|
write_conf() { printf 'rpcuser=%s\nrpcpassword=%s\nrpcport=%s\n' "$RPCUSER" "$RPCPASS" "$2" > "$1/DRAGONX.conf"; }
|
|
|
|
# prep_golden <dd> : copy of the golden wallet datadir (2041 notes, txindex=1, height 286)
|
|
prep_golden() {
|
|
local dd=$1
|
|
rm -rf "$dd"; cp -a "$GOLDEN" "$dd"
|
|
cp -f "$ASMAP" "$dd/asmap.dat"; cp -f "$SP" "$dd/sapling-spend.params"; cp -f "$OP" "$dd/sapling-output.params"
|
|
write_conf "$dd" "$RPC_T"
|
|
: > "$dd/regtest/debug.log"; rm -f "$dd/regtest/db.log"
|
|
}
|
|
|
|
# prep_fresh <dd> <rpcport> : empty regtest datadir (helpers)
|
|
prep_fresh() {
|
|
local dd=$1 rp=$2
|
|
rm -rf "$dd"; mkdir -p "$dd"
|
|
cp -f "$ASMAP" "$dd/asmap.dat"; cp -f "$SP" "$dd/sapling-spend.params"; cp -f "$OP" "$dd/sapling-output.params"
|
|
write_conf "$dd" "$rp"
|
|
}
|
|
|
|
start_helper() { # <dd> <p2p> <rpc> <logfile>
|
|
local dd=$1 p2p=$2 rp=$3 lg=$4
|
|
( cd "$dd" && exec nice -n 10 "$DRAGONXD" -regtest -datadir="$dd" -testnode=1 -checkpoints=0 \
|
|
-listen=1 -bind=127.0.0.1 -port=$p2p -connect=127.0.0.1:1 -addnode=127.0.0.1:$P2P_T \
|
|
-dnsseed=0 -dns=0 -asmap="$dd/asmap.dat" -autoshield=0 \
|
|
-rpcuser=$RPCUSER -rpcpassword=$RPCPASS -rpcport=$rp -listenonion=0 -maxinboundfromip=100 \
|
|
-debug=net -debug=tls -daemon ) >> "$lg" 2>&1
|
|
}
|
|
|
|
waitrpc() { # <dd> <rpc> [secs]
|
|
local dd=$1 rp=$2 n=${3:-300} i
|
|
for i in $(seq 1 "$n"); do clin "$dd" "$rp" getblockcount >/dev/null 2>&1 && return 0; sleep 1; done
|
|
return 1
|
|
}
|
|
|
|
stop_daemon() { # <dd> <rpc> (helpers, started with -daemon)
|
|
local dd=$1 rp=$2 pid i
|
|
pid=$(cat "$dd/regtest/hushd.pid" 2>/dev/null)
|
|
clin "$dd" "$rp" stop >/dev/null 2>&1
|
|
for i in $(seq 1 90); do { [ -z "$pid" ] || ! kill -0 "$pid" 2>/dev/null; } && return 0; sleep 1; done
|
|
[ -n "$pid" ] && kill -9 "$pid" 2>/dev/null
|
|
}
|
|
|
|
MARKERS=('libevent: Epoll' 'Socket close failed' 'Bad file descriptor' 'Operation not permitted' 'Illegal seek'
|
|
'SSL_write' 'Unable to seek' 'socket select error' 'write failed for page' 'PANIC' 'error scanning DB'
|
|
'terminate' 'Assertion' 'EXCEPTION')
|