diff --git a/0137-multipathd-Make-sure-to-disable-queueing-if-recovery.patch b/0137-multipathd-Make-sure-to-disable-queueing-if-recovery.patch new file mode 100644 index 0000000..1f87568 --- /dev/null +++ b/0137-multipathd-Make-sure-to-disable-queueing-if-recovery.patch @@ -0,0 +1,76 @@ +From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 +From: Benjamin Marzinski +Date: Wed, 22 Nov 2023 16:41:22 -0500 +Subject: [PATCH] multipathd: Make sure to disable queueing if recovery has + failed. + +If a multipath device has no_path_retry set to a number and has lost all +paths, gone into recovery mode, and timed out, it will disable +queue_if_no_paths. After that, if the device is reloaded by multipath +outside of multipathd, it will re-enable queuieng on the device. When +multipathd later calls set_no_path_retry() to update the queueing state, +it will not disable queue_if_no_paths, since the device is still in the +recovery state, so it believes no work needs to be done. The device will +remain in the recovery state, with retry_ticks at 0, and queueing +enabled, even though there are no usable paths. + +To fix this, in set_no_path_retry(), if no_path_retry is set to a number +and the device is queueing but it is in recovery mode and out of +retries with no usable paths, manually disable queue_if_no_path. + +Signed-off-by: Benjamin Marzinski +--- + libmultipath/structs_vec.c | 26 ++++++++++++++++++++++++-- + 1 file changed, 24 insertions(+), 2 deletions(-) + +diff --git a/libmultipath/structs_vec.c b/libmultipath/structs_vec.c +index 9613252f..0304777b 100644 +--- a/libmultipath/structs_vec.c ++++ b/libmultipath/structs_vec.c +@@ -377,8 +377,19 @@ void __set_no_path_retry(struct multipath *mpp, bool check_features) + !mpp->in_recovery) + dm_queue_if_no_path(mpp->alias, 1); + leave_recovery_mode(mpp); +- } else +- enter_recovery_mode(mpp); ++ } else { ++ /* ++ * If in_recovery is set, enter_recovery_mode does ++ * nothing. If the device is already in recovery ++ * mode and has already timed out, manually call ++ * dm_queue_if_no_path to stop it from queueing. ++ */ ++ if ((!mpp->features || is_queueing) && ++ mpp->in_recovery && mpp->retry_tick == 0) ++ dm_queue_if_no_path(mpp->alias, 0); ++ if (pathcount(mpp, PATH_PENDING) == 0) ++ enter_recovery_mode(mpp); ++ } + break; + } + } +@@ -521,6 +532,11 @@ int verify_paths(struct multipath *mpp, struct vectors *vecs) + * -1 (FAIL) : fail_if_no_path + * 0 (UNDEF) : nothing + * >0 : queue_if_no_path enabled, turned off after polling n times ++ * ++ * Since this will only be called when fail_path(), update_multipath(), or ++ * io_err_stat_handle_pathfail() are failing a previously active path, the ++ * device cannot already be in recovery mode, so there will never be a need ++ * to disable queueing here. + */ + void update_queue_mode_del_path(struct multipath *mpp) + { +@@ -534,6 +550,12 @@ void update_queue_mode_del_path(struct multipath *mpp) + condlog(2, "%s: remaining active paths: %d", mpp->alias, active); + } + ++/* ++ * Since this will only be called from check_path() -> reinstate_path() after ++ * the queueing state has been updated in set_no_path_retry, this does not ++ * need to worry about modifying the queueing state except when actually ++ * leaving recovery mode. ++ */ + void update_queue_mode_add_path(struct multipath *mpp) + { + int active = count_active_paths(mpp); diff --git a/device-mapper-multipath.spec b/device-mapper-multipath.spec index 999e2a4..70e4bff 100644 --- a/device-mapper-multipath.spec +++ b/device-mapper-multipath.spec @@ -1,7 +1,7 @@ Summary: Tools to manage multipath devices using device-mapper Name: device-mapper-multipath Version: 0.8.4 -Release: 40%{?dist} +Release: 41%{?dist} License: GPLv2 Group: System Environment/Base URL: http://christophe.varoqui.free.fr/ @@ -147,6 +147,7 @@ Patch00133: 0133-libmultipath-make-prflag-an-enum.patch Patch00134: 0134-multipathd-handle-no-active-paths-in-update_map_pr.patch Patch00135: 0135-libmpathpersist-fix-resource-leak-in-update_map_pr.patch Patch00136: 0136-multipathd-Added-support-to-handle-FPIN-Li-events-fo.patch +Patch00137: 0137-multipathd-Make-sure-to-disable-queueing-if-recovery.patch # runtime Requires: %{name}-libs = %{version}-%{release} @@ -351,6 +352,10 @@ fi %{_pkgconfdir}/libdmmp.pc %changelog +* Fri Jan 5 2024 Benjamin Marzinski 0.8.4-41 +- Add 0137-multipathd-Make-sure-to-disable-queueing-if-recovery.patch +- Resolves: RHEL-16563 + * Thu Nov 2 2023 Benjamin Marzinski 0.8.4-40 - Add 0136-multipathd-Added-support-to-handle-FPIN-Li-events-fo.patch * Add support in multipathd for NVMe to listen for FPIN-Li events and