device-mapper-multipath/SOURCES/0100-libmultipath-Set-the-scsi-timeout-parameters-by-path.patch

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Benjamin Marzinski <bmarzins@redhat.com>
Date: Wed, 13 Apr 2022 23:27:38 -0500
Subject: [PATCH] libmultipath: Set the scsi timeout parameters by path

Instead of dev_loss, fast_io_fail, and eh_deadline belonging to the
multipath structure, have them belong to the path structure. This means
that they are selected per path, and that sysfs_set_scsi_tmo() doesn't
assume that all paths of a multipath device will have the same value.
Currently they will all be the same, but a future patch will make it
possible for paths to have different values based on their protocol.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Reviewed-by: Martin Wilck <mwilck@suse.com>
---
 libmultipath/configure.c |   5 +-
 libmultipath/discovery.c | 149 +++++++++++++++++++++++----------------
 libmultipath/discovery.h |   2 +-
 libmultipath/propsel.c   |  42 +++++------
 libmultipath/propsel.h   |   6 +-
 libmultipath/structs.c   |   1 -
 libmultipath/structs.h   |   6 +-
 7 files changed, 118 insertions(+), 93 deletions(-)

diff --git a/libmultipath/configure.c b/libmultipath/configure.c
index 9a9890f5..6cad0468 100644
--- a/libmultipath/configure.c
+++ b/libmultipath/configure.c
@@ -338,9 +338,6 @@ int setup_map(struct multipath *mpp, char *params, int params_size,
 	select_mode(conf, mpp);
 	select_uid(conf, mpp);
 	select_gid(conf, mpp);
-	select_fast_io_fail(conf, mpp);
-	select_dev_loss(conf, mpp);
-	select_eh_deadline(conf, mpp);
 	select_reservation_key(conf, mpp);
 	select_deferred_remove(conf, mpp);
 	select_marginal_path_err_sample_time(conf, mpp);
@@ -356,7 +353,7 @@ int setup_map(struct multipath *mpp, char *params, int params_size,
 	select_ghost_delay(conf, mpp);
 	select_flush_on_last_del(conf, mpp);
 
-	sysfs_set_scsi_tmo(mpp, conf->checkint);
+	sysfs_set_scsi_tmo(conf, mpp);
 	marginal_pathgroups = conf->marginal_pathgroups;
 	pthread_cleanup_pop(1);
 
diff --git a/libmultipath/discovery.c b/libmultipath/discovery.c
index 2404cb87..36cc389e 100644
--- a/libmultipath/discovery.c
+++ b/libmultipath/discovery.c
@@ -581,13 +581,13 @@ sysfs_get_asymmetric_access_state(struct path *pp, char *buff, int buflen)
 }
 
 static int
-sysfs_set_eh_deadline(struct multipath *mpp, struct path *pp)
+sysfs_set_eh_deadline(struct path *pp)
 {
 	struct udev_device *hostdev;
 	char host_name[HOST_NAME_LEN], value[16];
 	int ret;
 
-	if (mpp->eh_deadline == EH_DEADLINE_UNSET)
+	if (pp->eh_deadline == EH_DEADLINE_UNSET)
 		return 0;
 
 	sprintf(host_name, "host%d", pp->sg_id.host_no);
@@ -596,12 +596,12 @@ sysfs_set_eh_deadline(struct multipath *mpp, struct path *pp)
 	if (!hostdev)
 		return 1;
 
-	if (mpp->eh_deadline == EH_DEADLINE_OFF)
+	if (pp->eh_deadline == EH_DEADLINE_OFF)
 		sprintf(value, "off");
-	else if (mpp->eh_deadline == EH_DEADLINE_ZERO)
+	else if (pp->eh_deadline == EH_DEADLINE_ZERO)
 		sprintf(value, "0");
 	else
-		snprintf(value, 16, "%u", mpp->eh_deadline);
+		snprintf(value, 16, "%u", pp->eh_deadline);
 
 	ret = sysfs_attr_set_value(hostdev, "eh_deadline",
 				   value, strlen(value));
@@ -625,6 +625,9 @@ sysfs_set_rport_tmo(struct multipath *mpp, struct path *pp)
 	unsigned int tmo;
 	int ret;
 
+	if (!pp->dev_loss && pp->fast_io_fail == MP_FAST_IO_FAIL_UNSET)
+		return;
+
 	sprintf(rport_id, "rport-%d:%d-%d",
 		pp->sg_id.host_no, pp->sg_id.channel, pp->sg_id.transport_id);
 	rport_dev = udev_device_new_from_subsystem_sysname(udev,
@@ -664,14 +667,14 @@ sysfs_set_rport_tmo(struct multipath *mpp, struct path *pp)
 	 * then set fast_io_fail, and _then_ set dev_loss_tmo
 	 * to the correct value.
 	 */
-	if (mpp->fast_io_fail != MP_FAST_IO_FAIL_UNSET &&
-	    mpp->fast_io_fail != MP_FAST_IO_FAIL_ZERO &&
-	    mpp->fast_io_fail != MP_FAST_IO_FAIL_OFF) {
+	if (pp->fast_io_fail != MP_FAST_IO_FAIL_UNSET &&
+	    pp->fast_io_fail != MP_FAST_IO_FAIL_ZERO &&
+	    pp->fast_io_fail != MP_FAST_IO_FAIL_OFF) {
 		/* Check if we need to temporarily increase dev_loss_tmo */
-		if ((unsigned int)mpp->fast_io_fail >= tmo) {
+		if ((unsigned int)pp->fast_io_fail >= tmo) {
 			/* Increase dev_loss_tmo temporarily */
 			snprintf(value, sizeof(value), "%u",
-				 (unsigned int)mpp->fast_io_fail + 1);
+				 (unsigned int)pp->fast_io_fail + 1);
 			ret = sysfs_attr_set_value(rport_dev, "dev_loss_tmo",
 						   value, strlen(value));
 			if (ret <= 0) {
@@ -685,20 +688,20 @@ sysfs_set_rport_tmo(struct multipath *mpp, struct path *pp)
 				goto out;
 			}
 		}
-	} else if (mpp->dev_loss > DEFAULT_DEV_LOSS_TMO &&
-		mpp->no_path_retry != NO_PATH_RETRY_QUEUE) {
+	} else if (pp->dev_loss > DEFAULT_DEV_LOSS_TMO &&
+		   mpp->no_path_retry != NO_PATH_RETRY_QUEUE) {
 		condlog(3, "%s: limiting dev_loss_tmo to %d, since "
 			"fast_io_fail is not set",
 			rport_id, DEFAULT_DEV_LOSS_TMO);
-		mpp->dev_loss = DEFAULT_DEV_LOSS_TMO;
+		pp->dev_loss = DEFAULT_DEV_LOSS_TMO;
 	}
-	if (mpp->fast_io_fail != MP_FAST_IO_FAIL_UNSET) {
-		if (mpp->fast_io_fail == MP_FAST_IO_FAIL_OFF)
+	if (pp->fast_io_fail != MP_FAST_IO_FAIL_UNSET) {
+		if (pp->fast_io_fail == MP_FAST_IO_FAIL_OFF)
 			sprintf(value, "off");
-		else if (mpp->fast_io_fail == MP_FAST_IO_FAIL_ZERO)
+		else if (pp->fast_io_fail == MP_FAST_IO_FAIL_ZERO)
 			sprintf(value, "0");
 		else
-			snprintf(value, 16, "%u", mpp->fast_io_fail);
+			snprintf(value, 16, "%u", pp->fast_io_fail);
 		ret = sysfs_attr_set_value(rport_dev, "fast_io_fail_tmo",
 					   value, strlen(value));
 		if (ret <= 0) {
@@ -709,8 +712,8 @@ sysfs_set_rport_tmo(struct multipath *mpp, struct path *pp)
 					rport_id, value, -ret);
 		}
 	}
-	if (mpp->dev_loss > 0) {
-		snprintf(value, 16, "%u", mpp->dev_loss);
+	if (pp->dev_loss > 0) {
+		snprintf(value, 16, "%u", pp->dev_loss);
 		ret = sysfs_attr_set_value(rport_dev, "dev_loss_tmo",
 					   value, strlen(value));
 		if (ret <= 0) {
@@ -726,7 +729,7 @@ out:
 }
 
 static void
-sysfs_set_session_tmo(struct multipath *mpp, struct path *pp)
+sysfs_set_session_tmo(struct path *pp)
 {
 	struct udev_device *session_dev = NULL;
 	char session_id[64];
@@ -743,18 +746,18 @@ sysfs_set_session_tmo(struct multipath *mpp, struct path *pp)
 	condlog(4, "target%d:%d:%d -> %s", pp->sg_id.host_no,
 		pp->sg_id.channel, pp->sg_id.scsi_id, session_id);
 
-	if (mpp->dev_loss) {
+	if (pp->dev_loss) {
 		condlog(3, "%s: ignoring dev_loss_tmo on iSCSI", pp->dev);
 	}
-	if (mpp->fast_io_fail != MP_FAST_IO_FAIL_UNSET) {
-		if (mpp->fast_io_fail == MP_FAST_IO_FAIL_OFF) {
+	if (pp->fast_io_fail != MP_FAST_IO_FAIL_UNSET) {
+		if (pp->fast_io_fail == MP_FAST_IO_FAIL_OFF) {
 			condlog(3, "%s: can't switch off fast_io_fail_tmo "
 				"on iSCSI", pp->dev);
-		} else if (mpp->fast_io_fail == MP_FAST_IO_FAIL_ZERO) {
+		} else if (pp->fast_io_fail == MP_FAST_IO_FAIL_ZERO) {
 			condlog(3, "%s: can't set fast_io_fail_tmo to '0'"
 				"on iSCSI", pp->dev);
 		} else {
-			snprintf(value, 11, "%u", mpp->fast_io_fail);
+			snprintf(value, 11, "%u", pp->fast_io_fail);
 			if (sysfs_attr_set_value(session_dev, "recovery_tmo",
 						 value, strlen(value)) <= 0) {
 				condlog(3, "%s: Failed to set recovery_tmo, "
@@ -767,12 +770,15 @@ sysfs_set_session_tmo(struct multipath *mpp, struct path *pp)
 }
 
 static void
-sysfs_set_nexus_loss_tmo(struct multipath *mpp, struct path *pp)
+sysfs_set_nexus_loss_tmo(struct path *pp)
 {
 	struct udev_device *sas_dev = NULL;
 	char end_dev_id[64];
 	char value[11];
 
+	if (!pp->udev || !pp->dev_loss)
+		return;
+
 	sprintf(end_dev_id, "end_device-%d:%d",
 		pp->sg_id.host_no, pp->sg_id.transport_id);
 	sas_dev = udev_device_new_from_subsystem_sysname(udev,
@@ -785,8 +791,8 @@ sysfs_set_nexus_loss_tmo(struct multipath *mpp, struct path *pp)
 	condlog(4, "target%d:%d:%d -> %s", pp->sg_id.host_no,
 		pp->sg_id.channel, pp->sg_id.scsi_id, end_dev_id);
 
-	if (mpp->dev_loss) {
-		snprintf(value, 11, "%u", mpp->dev_loss);
+	if (pp->dev_loss) {
+		snprintf(value, 11, "%u", pp->dev_loss);
 		if (sysfs_attr_set_value(sas_dev, "I_T_nexus_loss_timeout",
 					 value, strlen(value)) <= 0)
 			condlog(3, "%s: failed to update "
@@ -798,53 +804,76 @@ sysfs_set_nexus_loss_tmo(struct multipath *mpp, struct path *pp)
 }
 
 int
-sysfs_set_scsi_tmo (struct multipath *mpp, unsigned int checkint)
+sysfs_set_scsi_tmo (struct config *conf, struct multipath *mpp)
 {
 	struct path *pp;
 	int i;
-	unsigned int dev_loss_tmo = mpp->dev_loss;
+	unsigned int min_dev_loss = 0;
+	bool warn_dev_loss = false;
+	bool warn_fast_io_fail = false;
 
 	if (mpp->no_path_retry > 0) {
 		uint64_t no_path_retry_tmo =
-			(uint64_t)mpp->no_path_retry * checkint;
+			(uint64_t)mpp->no_path_retry * conf->checkint;
 
 		if (no_path_retry_tmo > MAX_DEV_LOSS_TMO)
-			no_path_retry_tmo = MAX_DEV_LOSS_TMO;
-		if (no_path_retry_tmo > dev_loss_tmo)
-			dev_loss_tmo = no_path_retry_tmo;
-		condlog(3, "%s: update dev_loss_tmo to %u",
-			mpp->alias, dev_loss_tmo);
-	} else if (mpp->no_path_retry == NO_PATH_RETRY_QUEUE) {
-		dev_loss_tmo = MAX_DEV_LOSS_TMO;
-		condlog(3, "%s: update dev_loss_tmo to %u",
-			mpp->alias, dev_loss_tmo);
-	}
-	mpp->dev_loss = dev_loss_tmo;
-	if (mpp->dev_loss && mpp->fast_io_fail > 0 &&
-	    (unsigned int)mpp->fast_io_fail >= mpp->dev_loss) {
-		condlog(3, "%s: turning off fast_io_fail (%d is not smaller than dev_loss_tmo)",
-			mpp->alias, mpp->fast_io_fail);
-		mpp->fast_io_fail = MP_FAST_IO_FAIL_OFF;
-	}
-	if (!mpp->dev_loss && mpp->fast_io_fail == MP_FAST_IO_FAIL_UNSET &&
-	    mpp->eh_deadline == EH_DEADLINE_UNSET)
-		return 0;
+			min_dev_loss = MAX_DEV_LOSS_TMO;
+		else
+			min_dev_loss = no_path_retry_tmo;
+	} else if (mpp->no_path_retry == NO_PATH_RETRY_QUEUE)
+		min_dev_loss = MAX_DEV_LOSS_TMO;
 
 	vector_foreach_slot(mpp->paths, pp, i) {
+		select_fast_io_fail(conf, pp);
+		select_dev_loss(conf, pp);
+		select_eh_deadline(conf, pp);
+
+		if (!pp->dev_loss && pp->eh_deadline == EH_DEADLINE_UNSET &&
+		    pp->fast_io_fail == MP_FAST_IO_FAIL_UNSET)
+			continue;
+
 		if (pp->bus != SYSFS_BUS_SCSI)
 			continue;
+		sysfs_set_eh_deadline(pp);
+
+		if (!pp->dev_loss && pp->fast_io_fail == MP_FAST_IO_FAIL_UNSET)
+			continue;
+
+		if (pp->sg_id.proto_id != SCSI_PROTOCOL_FCP &&
+		    pp->sg_id.proto_id != SCSI_PROTOCOL_ISCSI &&
+		    pp->sg_id.proto_id != SCSI_PROTOCOL_SAS)
+			continue;
+
+		if (pp->dev_loss > 0 && pp->dev_loss < min_dev_loss) {
+			warn_dev_loss = true;
+			pp->dev_loss = min_dev_loss;
+		}
+		if (pp->dev_loss > 0 && pp->fast_io_fail > 0 &&
+		    (unsigned int)pp->fast_io_fail >= pp->dev_loss) {
+			warn_fast_io_fail = true;
+			pp->fast_io_fail = MP_FAST_IO_FAIL_OFF;
+		}
 
-		if (mpp->dev_loss ||
-		    mpp->fast_io_fail != MP_FAST_IO_FAIL_UNSET) {
-			if (pp->sg_id.proto_id == SCSI_PROTOCOL_FCP)
-				sysfs_set_rport_tmo(mpp, pp);
-			else if (pp->sg_id.proto_id == SCSI_PROTOCOL_ISCSI)
-				sysfs_set_session_tmo(mpp, pp);
-			else if (pp->sg_id.proto_id == SCSI_PROTOCOL_SAS)
-				sysfs_set_nexus_loss_tmo(mpp, pp);
+		switch (pp->sg_id.proto_id) {
+		case SCSI_PROTOCOL_FCP:
+			sysfs_set_rport_tmo(mpp, pp);
+			break;
+		case SCSI_PROTOCOL_ISCSI:
+			sysfs_set_session_tmo(pp);
+			break;
+		case SCSI_PROTOCOL_SAS:
+			sysfs_set_nexus_loss_tmo(pp);
+			break;
+		default:
+			break;
 		}
-		sysfs_set_eh_deadline(mpp, pp);
 	}
+	if (warn_dev_loss)
+		condlog(2, "%s: Raising dev_loss_tmo to %u because of no_path_retry setting",
+			mpp->alias, min_dev_loss);
+	if (warn_fast_io_fail)
+		condlog(3, "%s: turning off fast_io_fail (not smaller than dev_loss_tmo)",
+			mpp->alias);
 	return 0;
 }
 
diff --git a/libmultipath/discovery.h b/libmultipath/discovery.h
index a5446b4d..b6eea258 100644
--- a/libmultipath/discovery.h
+++ b/libmultipath/discovery.h
@@ -42,7 +42,7 @@ int alloc_path_with_pathinfo (struct config *conf, struct udev_device *udevice,
 int store_pathinfo (vector pathvec, struct config *conf,
 		    struct udev_device *udevice, int flag,
 		    struct path **pp_ptr);
-int sysfs_set_scsi_tmo (struct multipath *mpp, unsigned int checkint);
+int sysfs_set_scsi_tmo (struct config *conf, struct multipath *mpp);
 int sysfs_get_timeout(const struct path *pp, unsigned int *timeout);
 int sysfs_get_host_pci_name(const struct path *pp, char *pci_name);
 int sysfs_get_iscsi_ip_address(const struct path *pp, char *ip_address);
diff --git a/libmultipath/propsel.c b/libmultipath/propsel.c
index 127b3370..25326eb6 100644
--- a/libmultipath/propsel.c
+++ b/libmultipath/propsel.c
@@ -766,51 +766,51 @@ int select_minio(struct config *conf, struct multipath *mp)
 		return select_minio_bio(conf, mp);
 }
 
-int select_fast_io_fail(struct config *conf, struct multipath *mp)
+int select_fast_io_fail(struct config *conf, struct path *pp)
 {
 	const char *origin;
 	char buff[12];
 
-	mp_set_ovr(fast_io_fail);
-	mp_set_hwe(fast_io_fail);
-	mp_set_conf(fast_io_fail);
-	mp_set_default(fast_io_fail, DEFAULT_FAST_IO_FAIL);
+	pp_set_ovr(fast_io_fail);
+	pp_set_hwe(fast_io_fail);
+	pp_set_conf(fast_io_fail);
+	pp_set_default(fast_io_fail, DEFAULT_FAST_IO_FAIL);
 out:
-	print_undef_off_zero(buff, 12, mp->fast_io_fail);
-	condlog(3, "%s: fast_io_fail_tmo = %s %s", mp->alias, buff, origin);
+	print_undef_off_zero(buff, 12, pp->fast_io_fail);
+	condlog(3, "%s: fast_io_fail_tmo = %s %s", pp->dev, buff, origin);
 	return 0;
 }
 
-int select_dev_loss(struct config *conf, struct multipath *mp)
+int select_dev_loss(struct config *conf, struct path *pp)
 {
 	const char *origin;
 	char buff[12];
 
-	mp_set_ovr(dev_loss);
-	mp_set_hwe(dev_loss);
-	mp_set_conf(dev_loss);
-	mp->dev_loss = 0;
+	pp_set_ovr(dev_loss);
+	pp_set_hwe(dev_loss);
+	pp_set_conf(dev_loss);
+	pp->dev_loss = 0;
 	return 0;
 out:
-	print_dev_loss(buff, 12, mp->dev_loss);
-	condlog(3, "%s: dev_loss_tmo = %s %s", mp->alias, buff, origin);
+	print_dev_loss(buff, 12, pp->dev_loss);
+	condlog(3, "%s: dev_loss_tmo = %s %s", pp->dev, buff, origin);
 	return 0;
 }
 
-int select_eh_deadline(struct config *conf, struct multipath *mp)
+int select_eh_deadline(struct config *conf, struct path *pp)
 {
 	const char *origin;
 	char buff[12];
 
-	mp_set_ovr(eh_deadline);
-	mp_set_hwe(eh_deadline);
-	mp_set_conf(eh_deadline);
-	mp->eh_deadline = EH_DEADLINE_UNSET;
+	pp_set_ovr(eh_deadline);
+	pp_set_hwe(eh_deadline);
+	pp_set_conf(eh_deadline);
+	pp->eh_deadline = EH_DEADLINE_UNSET;
 	/* not changing sysfs in default cause, so don't print anything */
 	return 0;
 out:
-	print_undef_off_zero(buff, 12, mp->eh_deadline);
-	condlog(3, "%s: eh_deadline = %s %s", mp->alias, buff, origin);
+	print_undef_off_zero(buff, 12, pp->eh_deadline);
+	condlog(3, "%s: eh_deadline = %s %s", pp->dev, buff, origin);
 	return 0;
 }
 
diff --git a/libmultipath/propsel.h b/libmultipath/propsel.h
index 72a7e33c..152ca44c 100644
--- a/libmultipath/propsel.h
+++ b/libmultipath/propsel.h
@@ -16,9 +16,9 @@ int select_minio(struct config *conf, struct multipath *mp);
 int select_mode(struct config *conf, struct multipath *mp);
 int select_uid(struct config *conf, struct multipath *mp);
 int select_gid(struct config *conf, struct multipath *mp);
-int select_fast_io_fail(struct config *conf, struct multipath *mp);
-int select_dev_loss(struct config *conf, struct multipath *mp);
-int select_eh_deadline(struct config *conf, struct multipath *mp);
+int select_fast_io_fail(struct config *conf, struct path *pp);
+int select_dev_loss(struct config *conf, struct path *pp);
+int select_eh_deadline(struct config *conf, struct path *pp);
 int select_reservation_key(struct config *conf, struct multipath *mp);
 int select_retain_hwhandler (struct config *conf, struct multipath * mp);
 int select_detect_prio(struct config *conf, struct path * pp);
diff --git a/libmultipath/structs.c b/libmultipath/structs.c
index 19099bed..9f86eb69 100644
--- a/libmultipath/structs.c
+++ b/libmultipath/structs.c
@@ -230,7 +230,6 @@ alloc_multipath (void)
 		mpp->bestpg = 1;
 		mpp->mpcontext = NULL;
 		mpp->no_path_retry = NO_PATH_RETRY_UNDEF;
-		mpp->fast_io_fail = MP_FAST_IO_FAIL_UNSET;
 		dm_multipath_to_gen(mpp)->ops = &dm_gen_multipath_ops;
 	}
 	return mpp;
diff --git a/libmultipath/structs.h b/libmultipath/structs.h
index ab99852f..875e726e 100644
--- a/libmultipath/structs.h
+++ b/libmultipath/structs.h
@@ -344,6 +344,9 @@ struct path {
 	int marginal;
 	int vpd_vendor_id;
 	int recheck_wwid;
+	int fast_io_fail;
+	unsigned int dev_loss;
+	int eh_deadline;
 	/* configlet pointers */
 	vector hwe;
 	struct gen_path generic_path;
@@ -371,7 +374,6 @@ struct multipath {
 	int minio;
 	int flush_on_last_del;
 	int attribute_flags;
-	int fast_io_fail;
 	int retain_hwhandler;
 	int deferred_remove;
 	bool in_recovery;
@@ -389,8 +391,6 @@ struct multipath {
 	int needs_paths_uevent;
 	int ghost_delay;
 	int ghost_delay_tick;
-	unsigned int dev_loss;
-	int eh_deadline;
 	uid_t uid;
 	gid_t gid;
 	mode_t mode;