Merge branch 'main' into omdb-sensors

.envrc

@@ -5,3 +5,8 @@ PATH_add out/cockroachdb/bin
 PATH_add out/clickhouse
 PATH_add out/dendrite-stub/bin
 PATH_add out/mgd/root/opt/oxide/mgd/bin
+
+if nix flake show &> /dev/null
+then
+    use flake;
+fi

.github/buildomat/build-and-test.sh

@@ -20,9 +20,13 @@ curl -sSfL --retry 10 https://get.nexte.st/"$NEXTEST_VERSION"/"$1" | gunzip | ta
 # we can check later whether we left detritus around.
 #
 TEST_TMPDIR='/var/tmp/omicron_tmp'
-echo "tests will store output in $TEST_TMPDIR" >&2
+echo "tests will store ephemeral output in $TEST_TMPDIR" >&2
 mkdir "$TEST_TMPDIR"
 
+OUTPUT_DIR='/work'
+echo "tests will store non-ephemeral output in $OUTPUT_DIR" >&2
+mkdir -p "$OUTPUT_DIR"
+
 #
 # Set up our PATH for the test suite.
 #
@@ -50,18 +54,27 @@ ptime -m bash ./tools/install_builder_prerequisites.sh -y
 #
 banner build
 export RUSTFLAGS="-D warnings"
+export RUSTDOCFLAGS="-D warnings"
 # When running on illumos we need to pass an additional runpath that is
 # usually configured via ".cargo/config" but the `RUSTFLAGS` env variable
 # takes precedence. This path contains oxide specific libraries such as
 # libipcc.
 if [[ $target_os == "illumos" ]]; then
-	RUSTFLAGS="-D warnings -C link-arg=-R/usr/platform/oxide/lib/amd64"
+    RUSTFLAGS="$RUSTFLAGS -C link-arg=-R/usr/platform/oxide/lib/amd64"
 fi
-export RUSTDOCFLAGS="-D warnings"
-export TMPDIR=$TEST_TMPDIR
+export TMPDIR="$TEST_TMPDIR"
 export RUST_BACKTRACE=1
+# We're building once, so there's no need to incur the overhead of an incremental build.
 export CARGO_INCREMENTAL=0
-ptime -m cargo test --locked --verbose --no-run
+# This allows us to build with unstable options, which gives us access to some
+# timing information.
+#
+# If we remove "--timings=json" below, this would no longer be needed.
+export RUSTC_BOOTSTRAP=1
+
+# Build all the packages and tests, and keep track of how long each took to build.
+# We report build progress to stderr, and the "--timings=json" output goes to stdout.
+ptime -m cargo build -Z unstable-options --timings=json --workspace --tests --locked --verbose 1> "$OUTPUT_DIR/crate-build-timings.json"
 
 #
 # We apply our own timeout to ensure that we get a normal failure on timeout

.github/buildomat/jobs/build-and-test-helios.sh

@@ -5,6 +5,7 @@
 #: target = "helios-2.0"
 #: rust_toolchain = "1.72.1"
 #: output_rules = [
+#:	"%/work/*",
 #:	"%/var/tmp/omicron_tmp/*",
 #:	"!/var/tmp/omicron_tmp/crdb-base*",
 #:	"!/var/tmp/omicron_tmp/rustc*",

.github/buildomat/jobs/build-and-test-linux.sh

@@ -5,6 +5,7 @@
 #: target = "ubuntu-22.04"
 #: rust_toolchain = "1.72.1"
 #: output_rules = [
+#:	"%/work/*",
 #:	"%/var/tmp/omicron_tmp/*",
 #:	"!/var/tmp/omicron_tmp/crdb-base*",
 #:	"!/var/tmp/omicron_tmp/rustc*",

.github/buildomat/jobs/deploy.sh

@@ -2,9 +2,10 @@
 #:
 #: name = "helios / deploy"
 #: variety = "basic"
-#: target = "lab-2.0-opte-0.27"
+#: target = "lab-2.0-opte-0.28"
 #: output_rules = [
 #:  "%/var/svc/log/oxide-sled-agent:default.log*",
+#:  "%/zone/oxz_*/root/var/svc/log/oxide-*.log*",
 #:  "%/pool/ext/*/crypt/zone/oxz_*/root/var/svc/log/oxide-*.log*",
 #:  "%/pool/ext/*/crypt/zone/oxz_*/root/var/svc/log/system-illumos-*.log*",
 #:  "%/pool/ext/*/crypt/zone/oxz_ntp_*/root/var/log/chrony/*.log*",
@@ -33,6 +34,9 @@ _exit_trap() {
 	local status=$?
 	[[ $status -eq 0 ]] && exit 0
 
+    # XXX paranoia
+    pfexec cp /tmp/opteadm /opt/oxide/opte/bin/opteadm
+
 	set +o errexit
 	set -o xtrace
 	banner evidence
@@ -50,6 +54,7 @@ _exit_trap() {
 		standalone \
 		dump-state
 	pfexec /opt/oxide/opte/bin/opteadm list-ports
+	pfexec /opt/oxide/opte/bin/opteadm dump-v2b
 	z_swadm link ls
 	z_swadm addr list
 	z_swadm route list
@@ -97,6 +102,19 @@ z_swadm () {
 	pfexec zlogin oxz_switch /opt/oxide/dendrite/bin/swadm $@
 }
 
+# XXX remove. This is just to test against a development branch of OPTE in CI.
+set +x
+OPTE_COMMIT="73d4669ea213d0b7aca35c4babb6fd09ed51d29e"
+curl  -sSfOL https://buildomat.eng.oxide.computer/public/file/oxidecomputer/opte/module/$OPTE_COMMIT/xde
+pfexec rem_drv xde || true
+pfexec mv xde /kernel/drv/amd64/xde
+pfexec add_drv xde || true
+curl -sSfOL https://buildomat.eng.oxide.computer/wg/0/artefact/01HM09S4M15WNXB2B2MX8R1GBT/yLalJU5vT4S4IEpwSeY4hPuspxw3JcINokZmlfNU14npHkzG/01HM09SJ2RQSFGW7MVKC9JKZ8D/01HM0A58D888AJ7YP6N1Q6T6ZD/opteadm
+chmod +x opteadm
+cp opteadm /tmp/opteadm
+pfexec mv opteadm /opt/oxide/opte/bin/opteadm
+set -x
+
 #
 # XXX work around 14537 (UFS should not allow directories to be unlinked) which
 # is probably not yet fixed in xde branch?  Once the xde branch merges from
@@ -236,7 +254,7 @@ infra_ip_last = \"$UPLINK_IP\"
 		/^routes/c\\
 routes = \\[{nexthop = \"$GATEWAY_IP\", destination = \"0.0.0.0/0\"}\\]
 		/^addresses/c\\
-addresses = \\[\"$UPLINK_IP/32\"\\]
+addresses = \\[\"$UPLINK_IP/24\"\\]
 	}
 " pkg/config-rss.toml
 diff -u pkg/config-rss.toml{~,} || true

.github/buildomat/jobs/package.sh

@@ -37,7 +37,7 @@ rustc --version
 # trampoline global zone images.
 #
 COMMIT=$(git rev-parse HEAD)
-VERSION="5.0.0-0.ci+git${COMMIT:0:11}"
+VERSION="6.0.0-0.ci+git${COMMIT:0:11}"
 echo "$VERSION" >/work/version.txt
 
 ptime -m ./tools/install_builder_prerequisites.sh -yp
@@ -91,7 +91,7 @@ ptime -m cargo run --locked --release --bin omicron-package -- \
   -t host target create -i standard -m gimlet -s asic -r multi-sled
 ptime -m cargo run --locked --release --bin omicron-package -- \
   -t host package
-stamp_packages omicron-sled-agent mg-ddm-gz propolis-server overlay
+stamp_packages omicron-sled-agent mg-ddm-gz propolis-server overlay oxlog
 
 # Create global zone package @ /work/global-zone-packages.tar.gz
 ptime -m ./tools/build-global-zone-packages.sh "$tarball_src_dir" /work
@@ -117,7 +117,7 @@ zones=(
   out/internal-dns.tar.gz
   out/omicron-nexus.tar.gz
   out/omicron-nexus-single-sled.tar.gz
-  out/oximeter-collector.tar.gz
+  out/oximeter.tar.gz
   out/propolis-server.tar.gz
   out/switch-*.tar.gz
   out/ntp.tar.gz

.github/buildomat/jobs/tuf-repo.sh

@@ -71,7 +71,7 @@ set -o errexit
 set -o pipefail
 set -o xtrace
 
-ALL_BOARDS=(gimlet-{c..e} psc-{b..c} sidecar-{b..c})
+ALL_BOARDS=(gimlet-{c..f} psc-{b..c} sidecar-{b..c})
 
 TOP=$PWD
 VERSION=$(< /input/package/work/version.txt)
@@ -278,8 +278,8 @@ EOF
     done
 }
 # usage:              SERIES           ROT_DIR      ROT_VERSION              BOARDS...
-add_hubris_artifacts  rot-staging-dev  staging/dev  cert-staging-dev-v1.0.4  "${ALL_BOARDS[@]}"
-add_hubris_artifacts  rot-prod-rel     prod/rel     cert-prod-rel-v1.0.4     "${ALL_BOARDS[@]}"
+add_hubris_artifacts  rot-staging-dev  staging/dev  cert-staging-dev-v1.0.5  "${ALL_BOARDS[@]}"
+add_hubris_artifacts  rot-prod-rel     prod/rel     cert-prod-rel-v1.0.5     "${ALL_BOARDS[@]}"
 
 for series in "${SERIES_LIST[@]}"; do
     /work/tufaceous assemble --no-generate-key /work/manifest-"$series".toml /work/repo-"$series".zip

.github/workflows/hakari.yml

@@ -24,7 +24,7 @@ jobs:
         with:
           toolchain: stable
       - name: Install cargo-hakari
-        uses: taiki-e/install-action@4f8e32492b3baed061f7836e6a4d40eb19e49b71 # v2
+        uses: taiki-e/install-action@f0940d272d95b8f48df48b1fc7ead81b95bca8b6 # v2
         with:
           tool: cargo-hakari
       - name: Check workspace-hack Cargo.toml is up-to-date

.gitignore

@@ -15,3 +15,4 @@ debug.out
 rusty-tags.vi
 *.sw*
 tags
+.direnv