[ofa-general] [PATCH] infiniband-diags/scripts: Add ibcheckroutes to scripts

[Doron Shoham]

ibcheckroutes validates route between all hosts in the fabric.
This script finds all leaf switches (switches that are connected to HCAs)
and runs ibtracert between them.
When using various routing algorithms (e.g. up-down),
if fabric topology is not suitable there will be no
routes between some nodes.
It reports when the route exists between source and destination LIDs.

Signed-off-by: Doron Shoham <dorons at voltaire.com>
---
 infiniband-diags/Makefile.am              |    4 +-
 infiniband-diags/configure.in             |    1 +
 infiniband-diags/man/ibcheckroutes.8      |   39 +++++++++++
 infiniband-diags/scripts/ibcheckroutes.in |  101 +++++++++++++++++++++++++++++
 4 files changed, 143 insertions(+), 2 deletions(-)
 create mode 100644 infiniband-diags/man/ibcheckroutes.8
 create mode 100755 infiniband-diags/scripts/ibcheckroutes.in

diff --git a/infiniband-diags/Makefile.am b/infiniband-diags/Makefile.am
index 1cdb60e..57363c4 100644
--- a/infiniband-diags/Makefile.am
+++ b/infiniband-diags/Makefile.am
@@ -33,7 +33,7 @@ sbin_SCRIPTS = scripts/ibcheckerrs scripts/ibchecknet scripts/ibchecknode \
 	       scripts/iblinkinfo.pl scripts/ibprintswitch.pl \
 	       scripts/ibprintca.pl scripts/ibprintrt.pl \
 	       scripts/ibfindnodesusing.pl scripts/ibidsverify.pl \
-	       scripts/check_lft_balance.pl
+	       scripts/check_lft_balance.pl scripts/ibcheckroutes
 
 noinst_LIBRARIES = libcommon.a
 
@@ -76,7 +76,7 @@ man_MANS = man/ibaddr.8 man/ibcheckerrors.8 man/ibcheckerrs.8 \
 	man/ibprintswitch.8 man/ibprintca.8 man/ibfindnodesusing.8 \
 	man/ibdatacounts.8 man/ibdatacounters.8 \
 	man/ibrouters.8 man/ibprintrt.8 man/ibidsverify.8 \
-	man/check_lft_balance.8
+	man/check_lft_balance.8 man/ibcheckroutes.8
 
 BUILT_SOURCES = ibdiag_version
 ibdiag_version:
diff --git a/infiniband-diags/configure.in b/infiniband-diags/configure.in
index 3ef35cc..aa178c5 100644
--- a/infiniband-diags/configure.in
+++ b/infiniband-diags/configure.in
@@ -158,6 +158,7 @@ AC_CONFIG_FILES([\
 	scripts/ibcheckportwidth \
 	scripts/ibcheckstate \
 	scripts/ibcheckwidth \
+	scripts/ibcheckroutes \
 	scripts/ibclearcounters \
 	scripts/ibclearerrors \
 	scripts/ibdatacounts \
diff --git a/infiniband-diags/man/ibcheckroutes.8 b/infiniband-diags/man/ibcheckroutes.8
new file mode 100644
index 0000000..a6a073f
--- /dev/null
+++ b/infiniband-diags/man/ibcheckroutes.8
@@ -0,0 +1,39 @@
+.TH IBCHECKPORT 8 "September 10, 2009" "OpenIB" "OpenIB Diagnostics"
+
+.SH NAME
+ibcheckroutes \- validates routes between all hosts in fabric
+
+.SH SYNOPSIS
+.B ibcheckroutes
+[\-h] [\-N] [\-b] [\-e] [\-C ca_name] [\-P ca_port] [\-t(imeout) timeout_ms]
+
+.SH DESCRIPTION
+.PP
+ibcheckroutes is a script which uses a full topology file that was created by ibnetdiscover,
+scans the network to validate routes between all hosts in the fabric.
+
+.SH OPTIONS
+.PP
+\-h  Show help.
+.PP
+\-N  Use mono rather than color mode.
+.PP
+\-b  Suppress output.
+.PP
+\-e  Show errors only.
+.PP
+\-C <ca_name>    Use the specified ca_name.
+.PP
+\-P <ca_port>    Use the specified ca_port.
+.PP
+\-t <timeout_ms> Override the default timeout for the solicited mads.
+
+.SH SEE ALSO
+.BR ibnetdiscover(8),
+.BR ibtracert(8),
+.BR ibroute(8)
+
+.SH AUTHOR
+.TP
+Doron Shoham
+.RI < dorons at voltaire.com >
diff --git a/infiniband-diags/scripts/ibcheckroutes.in b/infiniband-diags/scripts/ibcheckroutes.in
new file mode 100755
index 0000000..eb3ad30
--- /dev/null
+++ b/infiniband-diags/scripts/ibcheckroutes.in
@@ -0,0 +1,101 @@
+#!/bin/sh
+
+IBPATH=${IBPATH:- at IBSCRIPTPATH@}
+
+function usage() {
+	echo Usage: `basename $0` "[-h] [-N] [-b] [-e] [-C ca_name] [-P ca_port] [-t(imeout) timeout_ms]"
+    	echo -e "   validate routes between all hosts in fabric"
+	echo -e " -h   - Show help"
+	echo -e " -N   - Use mono rather than color mode"
+	echo -e " -b   - Suppress output"
+	echo -e " -e   - Show errors only"
+	echo -e " -C   - Use the specified ca_name"
+	echo -e " -P   - Use the specified ca_port"
+	echo -e " -t   - Override the default timeout for the solicited" 
+	exit -1
+}
+
+function user_abort() {
+	echo "Aborted"
+	exit 1
+}
+
+function green() {
+	if [ "$bw" = "yes" ]; then
+		printf "${res_col}[OK]\n" $1
+		return
+	fi
+	printf "\033[1;032m${res_col}[OK]\033[0;39m\n" $1
+}
+
+function red() {
+	if [ "$bw" = "yes" ]; then
+		printf "${res_col}[FAILED]\n" "$1"
+		return
+	fi
+	printf "\033[31m${res_col}[FAILED]\033[0m\n" "$1"
+}
+
+trap user_abort SIGINT SIGTERM
+
+bw=""
+brief=0
+error=0
+ca_info=""
+st=0
+topofile=/tmp/net
+res_col="%-20.20s"
+
+function get_opts() {
+	while getopts P:C:t:beNh o; do
+		case "$o" in
+		h)
+			usage
+			;;
+		N)
+			bw="yes"
+			;;
+		b)
+			brief=1
+			;;
+		e)
+			error=1
+			;;
+		P | C | t | timeout)
+			ca_info="$ca_info -$o $OPTARG"
+			;;
+		*)
+			usage
+			;;
+		esac
+	done
+}
+
+get_opts $*
+
+$IBPATH/ibnetdiscover $ca_info > $topofile
+
+# find all leaf switches LIDs
+LIDS=($(awk  '/# lid /{a[$(NF-1)]=$(NF-1)} END{for(v in a) print v}' $topofile))
+N=${#LIDS[@]}
+
+if [ $N -lt 2 ]; then
+	echo "Fabric contains only one switch"
+	exit 0
+fi
+
+# check routes between all switches in fabric
+[ $brief -eq 0 ] && echo -e "Checking route between:\nSource lid --> Destination lid"
+for((s=0; s<N-1; s++)); do
+	for ((d=s+1; d<N; d++)); do
+		$IBPATH/ibtracert $ca_info ${LIDS[$s]} ${LIDS[$d]} > /dev/null
+		if [ $? -eq 0 ]; then
+			[ $brief -eq 0 ] && [ $error -eq 0 ] && green "${LIDS[$s]}-->${LIDS[$d]}"
+		else
+			[ $brief -eq 0 ] && red "${LIDS[$s]}-->${LIDS[$d]}"
+			st=1
+		fi
+	done
+done
+
+exit $st
-- 
1.5.4