From a65dde2d1083a57824aecd1840dea417c98c553d Mon Sep 17 00:00:00 2001 From: Coiby Xu Date: Thu, 19 May 2022 11:39:25 +0800 Subject: [PATCH] Reduce kdump memory consumption by only installing needed NIC drivers Even after having asked NM to stop managing a unneeded NIC, a NIC driver may still waste memory. For example, mlx5_core uses a substantial amount of memory during driver initialization, ======== Report format module_summary: ======== Module mlx5_core using 350.2MB (89650 pages), peak allocation 367.4MB (94056 pages) Module squashfs using 13.1MB (3360 pages), peak allocation 13.1MB (3360 pages) Module overlay using 2.1MB (550 pages), peak allocation 2.2MB (555 pages) Module dns_resolver using 0.9MB (219 pages), peak allocation 5.2MB (1338 pages) Module mlxfw using 0.7MB (172 pages), peak allocation 5.3MB (1349 pages) ======== Report format module_summary END ======== ======== Report format module_top: ======== Top stack usage of module mlx5_core: (null) Pages: 89650 (peak: 94056) ret_from_fork (0xffffda088b4165f8) Pages: 60007 (peak: 60007) kthread (0xffffda088b4bd7e4) Pages: 60007 (peak: 60007) worker_thread (0xffffda088b4b48d0) Pages: 60007 (peak: 60007) process_one_work (0xffffda088b4b3f40) Pages: 60007 (peak: 60007) work_for_cpu_fn (0xffffda088b4aef00) Pages: 53906 (peak: 53906) local_pci_probe (0xffffda088b9e1e44) Pages: 53906 (peak: 53906) probe_one mlx5_core (0xffffda084f899cc8) Pages: 53518 (peak: 53518) mlx5_init_one mlx5_core (0xffffda084f8994ac) Pages: 49756 (peak: 49756) mlx5_function_setup.constprop.0 mlx5_core (0xffffda084f899100) Pages: 44434 (eak: 44434) mlx5_satisfy_startup_pages mlx5_core (0xffffda084f8a4f24) Pages: 44434 (peak: 44434) mlx5_function_setup.constprop.0 mlx5_core (0xffffda084f899078) Pages: 5285 (peak: 5285) mlx5_cmd_init mlx5_core (0xffffda084f89e414) Pages: 4818 (peak: 4818) mlx5_alloc_cmd_msg mlx5_core (0xffffda084f89aaa0) Pages: 4403 (peak: 4403) This memory consumption is completely unnecessary when kdump doesn't need this NIC. Only install needed NIC drivers to prevent this kind of waste. Note 1. this patch depends on [1] to ask dracut to not install NIC drivers. 2. "ethtool -i" somehow fails to get the vlan driver 3. team.ko doesn't depend on the team mode drivers so we need to install the team mode drivers manually. [1] https://github.com/dracutdevs/dracut/pull/1789 Signed-off-by: Coiby Xu Reviewed-by: Thomas Haller Reviewed-by: Philipp Rudo --- dracut-module-setup.sh | 31 +++++++++++++++++++++++++++++++ mkdumprd | 2 +- 2 files changed, 32 insertions(+), 1 deletion(-) diff --git a/dracut-module-setup.sh b/dracut-module-setup.sh index f4a026a..9ed8487 100755 --- a/dracut-module-setup.sh +++ b/dracut-module-setup.sh @@ -387,6 +387,36 @@ EOF inst "$_netif_allowlist_nm_conf" "/etc/NetworkManager/conf.d/10-kdump-netif_allowlist.conf" } +_get_nic_driver() { + ethtool -i "$1" | sed -n -E "s/driver: (.*)/\1/p" +} + +kdump_install_nic_driver() { + local _netif _driver _drivers + + _drivers=() + + for _netif in $1; do + _driver=$(_get_nic_driver "$_netif") + if [[ -z $_driver ]]; then + derror "Failed to get the driver of $_netif" + exit 1 + fi + + if [[ $_driver == "802.1Q VLAN Support" ]]; then + # ethtool somehow doesn't return the driver name for a VLAN NIC + _driver=8021q + elif [[ $_driver == "team" ]]; then + # install the team mode drivers like team_mode_roundrobin.ko as well + _driver='=drivers/net/team' + fi + + _drivers+=("$_driver") + done + + instmods "${_drivers[@]}" +} + kdump_setup_bridge() { local _netdev=$1 local _dev @@ -582,6 +612,7 @@ kdump_install_net() { kdump_install_nmconnections apply_nm_initrd_generator_timeouts kdump_install_nm_netif_allowlist "$_netifs" + kdump_install_nic_driver "$_netifs" fi } diff --git a/mkdumprd b/mkdumprd index 7b843a8..a069f92 100644 --- a/mkdumprd +++ b/mkdumprd @@ -27,7 +27,7 @@ SAVE_PATH=$(get_save_path) OVERRIDE_RESETTABLE=0 extra_modules="" -dracut_args=(--add kdumpbase --quiet --hostonly --hostonly-cmdline --hostonly-i18n --hostonly-mode strict -o "plymouth resume ifcfg earlykdump") +dracut_args=(--add kdumpbase --quiet --hostonly --hostonly-cmdline --hostonly-i18n --hostonly-mode strict --hostonly-nics '' -o "plymouth resume ifcfg earlykdump") MKDUMPRD_TMPDIR="$(mktemp -d -t mkdumprd.XXXXXX)" [ -d "$MKDUMPRD_TMPDIR" ] || perror_exit "dracut: mktemp -p -d -t dracut.XXXXXX failed."