Merge remote-tracking branch 'origin/master' into tanabarr/control-au…

…to-faulty-config Features: control Required-githooks: true Signed-off-by: Tom Nabarro <[email protected]>
daos-stack · Jan 8, 2024 · f4102e6 · f4102e6
2 parents 044a837 + bf6c881
commit f4102e6
Show file tree

Hide file tree

Showing 62 changed files with 2,610 additions and 3,296 deletions.
diff --git a/.github/workflows/pylint.yml b/.github/workflows/pylint.yml
@@ -14,11 +14,16 @@ jobs:
         uses: actions/checkout@v3
         with:
           ref: ${{ github.event.pull_request.head.sha }}
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
       - name: Install core python packages
         run: python3 -m pip install --requirement requirements.txt
       - name: Install extra python packages
         run: python3 -m pip install --requirement utils/cq/requirements.txt
       - name: Install enchant
         run: sudo apt-get update && sudo apt-get -y install python3-enchant
+      - name: Show versions
+        run: ./utils/cq/daos_pylint.py --version
       - name: Run pylint check.
         run: ./utils/cq/daos_pylint.py --git --output-format github
diff --git a/Jenkinsfile b/Jenkinsfile
@@ -1202,7 +1202,7 @@ pipeline {
                             stage_tags: 'hw,medium,provider',
                             default_tags: startedByTimer() ? 'pr daily_regression' : 'pr',
                             default_nvme: 'auto',
-                            provider: 'ucx+dc_x',
+                            provider: cachedCommitPragma('Test-provider-ucx', 'ucx+ud_x'),
                             run_if_pr: false,
                             run_if_landing: false,
                             job_status: job_status_internal

diff --git a/ci/provisioning/post_provision_config.sh b/ci/provisioning/post_provision_config.sh
@@ -19,6 +19,9 @@ source ci/provisioning/post_provision_config_common_functions.sh
 # shellcheck disable=SC1091
 source ci/junit.sh
 
+
+: "${MLNX_VER_NUM:=latest-5.8}"
+
 : "${DISTRO:=EL_7}"
 DSL_REPO_var="DAOS_STACK_${DISTRO}_LOCAL_REPO"
 DSG_REPO_var="DAOS_STACK_${DISTRO}_GROUP_REPO"
@@ -44,6 +47,7 @@ if ! retry_cmd 2400 clush -B -S -l root -w "$NODESTRING" \
            DISTRO=\"$DISTRO\"
            DAOS_STACK_RETRY_DELAY_SECONDS=\"$DAOS_STACK_RETRY_DELAY_SECONDS\"
            DAOS_STACK_RETRY_COUNT=\"$DAOS_STACK_RETRY_COUNT\"
+           MLNX_VER_NUM=\"$MLNX_VER_NUM\"
            BUILD_URL=\"$BUILD_URL\"
            STAGE_NAME=\"$STAGE_NAME\"
            OPERATIONS_EMAIL=\"$OPERATIONS_EMAIL\"

diff --git a/ci/provisioning/post_provision_config_common.sh b/ci/provisioning/post_provision_config_common.sh
@@ -53,6 +53,3 @@ case "$ID_LIKE" in
         EXCLUDE_UPGRADE+=,fuse,fuse-libs,fuse-devel
         ;;
 esac
-
-# shellcheck disable=SC2034
-MLNX_VER_NUM=5.8-3.0.7.0
diff --git a/ci/provisioning/post_provision_config_nodes_EL_8.sh b/ci/provisioning/post_provision_config_nodes_EL_8.sh
@@ -55,19 +55,21 @@ install_mofed() {
     stream=false
     gversion="$VERSION_ID"
     if [ "$gversion" == "8" ]; then
-        gversion="8.6"
+        # Mellanox does not have a release for 8.9 yet.
+        gversion="8.8"
         stream=true
      elif [[ $gversion = *.*.* ]]; then
         gversion="${gversion%.*}"
     fi
 
     # Add a repo to install MOFED RPMS
-    repo_url=https://artifactory.dc.hpdd.intel.com/artifactory/mlnx_ofed/"$MLNX_VER_NUM-rhel$gversion"-x86_64/
+    artifactory_base_url="https://artifactory.dc.hpdd.intel.com/artifactory/"
+    mellanox_proxy="${artifactory_base_url}mellanox-proxy/mlnx_ofed/"
+    mellanox_key_url="${artifactory_base_url}mlnx_ofed/RPM-GPG-KEY-Mellanox"
+    rpm --import "$mellanox_key_url"
+    repo_url="$mellanox_proxy$MLNX_VER_NUM/rhel$gversion/x86_64/"
     dnf -y config-manager --add-repo="$repo_url"
-    curl -L -O "$repo_url"RPM-GPG-KEY-Mellanox
     dnf -y config-manager --save --setopt="$(url_to_repo "$repo_url")".gpgcheck=1
-    rpm --import RPM-GPG-KEY-Mellanox
-    rm -f RPM-GPG-KEY-Mellanox
     dnf repolist || true
 
     time dnf -y install mlnx-ofed-basic ucx-cma ucx-ib ucx-knem ucx-rdmacm ucx-xpmem

diff --git a/src/cart/README.env b/src/cart/README.env
@@ -139,6 +139,12 @@ This file lists the environment variables used in CaRT.
    It its value exceed 256, then will use 256 for flow control.
    Set it to zero means disable the flow control in cart.
 
+ . D_QUOTA_RPCS
+   Set it as the max number of per-context inflight RPCs that a sender will send
+   onto a wire. Quota on each context is independent of each other.
+   If it is not set the default value of 64 is used.
+   Setting it to 0 disables quota
+
  . CRT_CTX_SHARE_ADDR
    Set it to non-zero to make all the contexts share one network address, in
    this case CaRT will create one SEP and each context maps to one tx/rx