Re: pNFS-related questions

[Boaz Harrosh <bharrosh@panasas.com>]

[-- Attachment #1: Type: text/plain, Size: 4031 bytes --]

On 05/13/2010 01:14 AM, Jiri Kortus wrote:
> Hi,
> 
> I'd like to ask two questions that are related to pNFS, I hope it's not 
> a problem that I put them in one post even though they aren't related 
> one to the other.
> 
> 1. How to configure a pNFS+exofs setup with multiple OSD targets? I was 
> able to use a setup with one OSD target, one OSD initiator+pNFS metadata 
> server and one client with the help of pNFS mailing list and the 
> instructions from here 
> http://mailman.open-osd.org/pipermail/osd-dev/2009-July/001033.html 
> which seems to be quite clear to me. But I've been thinking about how a 
> setup with more OSDs would look like? (I mean mainly the metadata 
> server). I suppose that I would configure more OSDs in the same way as I 
> did with one. Then how about the pNFS MDS setup? I've been wondering if 
> I could do it this way:
> - login to the targets, then mount /dev/osdX devices for example in 
> /exofs/osdX
> - set up the /etc/exports file in this way:
> /exofs    *(....,fsid=0,pnfs)
> /exofs/osd1    *(....)
> /exofs/osd2    *(....)
> ...
> /exofs/osdX    *(....)
> 

No not at all! ;-)

I'll be a paper about an experiment I did on Panasas labs with 8 osds and
8 clients 1 MDS. I'll be posting the complete scripts I used for setup and tests

So it is much more simple really.

- On X machines you just run ./up to load the osd-target.
  You now have X ip addresses/names
- On MDS/client you change your ./do-osd script to look like this (I'm attaching the complete script)
	login_iscsi_osd()
	{
		echo login into: $1 expect $2
		if $iscsiadm $ISCSI_DBG -m discovery -t sendtargets -p $1 --login; then 
			echo $iscsiadm $ISCSI_DBG -m discovery -t sendtargets -p $1 --login returned error ($?)!
			sleep 3; 
		fi
	
		sleep 1; 
		ls $2 
	}
	And then the do_start changes to:
	start_iscsi_intiator

	start_open_osd

	login_iscsi_osd $IP_OSD0 $DEV_OSD0
	login_iscsi_osd $IP_OSD1 $DEV_OSD1
	login_iscsi_osd $IP_OSD2 $DEV_OSD2
	login_iscsi_osd $IP_OSD3 $DEV_OSD3

	login_iscsi_osd $IP_OSD4 $DEV_OSD4
	login_iscsi_osd $IP_OSD5 $DEV_OSD5
	login_iscsi_osd $IP_OSD6 $DEV_OSD6
	login_iscsi_osd $IP_OSD7 $DEV_OSD7
  
   So basically before hand on client and MDS you login to all osds

- On MDS at one time you do a "format" (see attached script) which mkfs.exofs
  of a file systems with all the OSDs included (Yes exofs is multy device that's
  the all point. mirrors strips and groups are all supported)

  First do a format on MDS. Then do ./do-osd stop. Then do-osd start on MDS and all
  clients. Because format changes the osd-names and they must get updated in memory.

- Then you do the export just exactly as before just one /exp/exofs and exportfs -r.
  (Again this does not change from before)

- Finally you do the do-pnfs start on clients exactlly the same as before.
  There is a single file system. The pnfs/osd protocol takes care of all the
  multiple devices and file layouts.

So to sumerize the only thing different from before is that you need to iscsi login
to more then one OSD. And that the mkfs.exofs command has lots of devices.
(Or you can wait for my paper next week)

Boaz
> - then reload the exports by running "exportfs -r"
> - and finally I would login to the OSDs on the client, load 
> objlayoutdriver and mount the export from MDS with the "minorversion=1" 
> option.
> Could the content of /etc/exports file look like that? Or is it 
> fundamentally wrong? I'd be glad for any advice. I can't test it right 
> now but I have to know how to do it to describe it in my bachelor's thesis.
> 
> 
> 2. I'd like to know how well the IPv6 support in pNFS works - what 
> works, what doesn't, if there are any problems to solve etc., just 
> anything worth to know concerning the IPv6 support.
> 
> Thank you very much in advance.
> 
> Best regards,
> 
> Jiri Kortus
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 


[-- Attachment #2: do-ect2 --]
[-- Type: text/plain, Size: 6056 bytes --]

#!/bin/sh
#
# ect: Exofs Cluster Test

modprobe=/sbin/modprobe
service=/sbin/service
iscsiadm=/sbin/iscsiadm

# Name of iscsi service. .e.g at /etc/init.d/
ISCSI=iscsi

# 8 osds
DEV_OSD0=/dev/osd0
UUID0="8c0772c1-3b9b-44c0-bc28-dff56354ed39"

DEV_OSD1=/dev/osd1
UUID1="4680a768-e586-4d42-b4b6-43fdc5f02304"

DEV_OSD2=/dev/osd2
UUID2="f71a5dbd-49c8-4558-bba8-a1bb12c8bff6"

DEV_OSD3=/dev/osd3
UUID3="e432ae72-81d6-49ab-8b61-93b5bb0268e3"


DEV_OSD4=/dev/osd4
UUID4="7f518365-1c3b-4ce1-a511-40eabad1ce58"

DEV_OSD5=/dev/osd5
UUID5="93edbb0a-cf91-492a-a4af-931be496fd55"

DEV_OSD6=/dev/osd6
UUID6="fbd8966e-0ff0-4965-baa5-4ceff832d5f8"

DEV_OSD7=/dev/osd7
UUID7="c1462bab-999f-4a25-a95d-ebd158818bf1"

IP_OSD0=10.70.4.120:3260
IP_OSD1=10.70.4.121:3260
IP_OSD2=10.70.4.122:3260
IP_OSD3=10.70.4.123:3260

IP_OSD4=10.70.4.124:3260
IP_OSD5=10.70.4.125:3260
IP_OSD6=10.70.4.126:3260
IP_OSD7=10.70.4.127:3260

# mkexofs layout
OO_ROOT=`dirname $0`
EXOFS_DIR=$OO_ROOT/fs/exofs
USR_DIR=$OO_ROOT/usr
MOUNTDIR=/mnt/exofs

PID=0x10000
PID4=0x20004
PID2=0x20002
PID1=0x20001

FORMAT_SIZE=0
RAID=0
MIRRORS=0
STRIPE_PAGES=16
GROUP_WIDTH=0
GROUP_DEPTH=0

do_cmd()
{
	$* 2>&1 | logger &
}

start_iscsi_intiator()
{
	echo start iscsi service

	if ! $service $ISCSI status; then

		echo iscsi not started running [$service $ISCSI start]

		do_cmd $service $ISCSI start ;

		until cat /sys/class/iscsi_transport/tcp/handle 2>/dev/null ; do
			echo wait for iscsi-transport
			sleep 1;
		done
	fi

	sleep 7
	echo start iscsi done
}
stop_iscsi_intiator()
{
	echo stop iscsi

	do_cmd $service $ISCSI stop

	until [ -n `$modprobe -l scsi_transport_iscsi` ]; do
		sleep 1;
	done

	echo stop iscsi done
}

ISCSIDB=/var/lib/iscsi
# ISCSIDB=/etc/iscsi
do_iscsi_clean()
{
	rm -rfv $ISCSIDB/ifaces/*
	rm -rfv $ISCSIDB/nodes/*
	rm -rfv $ISCSIDB/send_targets/*
}

# ISCSI_DBG=--debug=8
# usage login_iscsi_osd $IP_OSDX $DEV_OSDX
login_iscsi_osd()
{
	echo login into: $1 expect $2
	if $iscsiadm $ISCSI_DBG -m discovery -t sendtargets -p $1 --login; then 
		echo $iscsiadm $ISCSI_DBG -m discovery -t sendtargets -p $1 --login returned error ($?)!
		sleep 3; 
	fi

	sleep 1; 
	ls $2 
}
# usage logout_iscsi_osd $IP_OSDX $DEV_OSDX
logout_iscsi_osd()
{
	echo login out of $1 expected on $2
	do_cmd $iscsiadm -m node -p $1 --logout

#	while ls $3 2>/dev/null; do sleep 1; done
	sleep 1;
}

start_open_osd()
{
# In-tree
	echo start osd

	$modprobe osd;
}
stop_open_osd()
{
# In-tree
	echo stop osd

	$modprobe --remove osd;
}

do_start()
{
	start_iscsi_intiator

	start_open_osd

	login_iscsi_osd $IP_OSD0 $DEV_OSD0
	login_iscsi_osd $IP_OSD1 $DEV_OSD1
	login_iscsi_osd $IP_OSD2 $DEV_OSD2
	login_iscsi_osd $IP_OSD3 $DEV_OSD3

	login_iscsi_osd $IP_OSD4 $DEV_OSD4
	login_iscsi_osd $IP_OSD5 $DEV_OSD5
	login_iscsi_osd $IP_OSD6 $DEV_OSD6
	login_iscsi_osd $IP_OSD7 $DEV_OSD7
}
do_stop()
{
	logout_iscsi_osd $IP_OSD7 $DEV_OSD7
	logout_iscsi_osd $IP_OSD6 $DEV_OSD6
	logout_iscsi_osd $IP_OSD5 $DEV_OSD5
	logout_iscsi_osd $IP_OSD4 $DEV_OSD4

	logout_iscsi_osd $IP_OSD3 $DEV_OSD3
	logout_iscsi_osd $IP_OSD2 $DEV_OSD2
	logout_iscsi_osd $IP_OSD1 $DEV_OSD1
	logout_iscsi_osd $IP_OSD0 $DEV_OSD0

	stop_iscsi_intiator

	stop_open_osd
}

mkexofs_format()
{
	$USR_DIR/mkfs.exofs \
		--pid=$PID --raid=$RAID --mirrors=$MIRRORS \
		--stripe_pages=$STRIPE_PAGES \
		--group_width=$GROUP_WIDTH --group_depth=$GROUP_DEPTH \
		--dev=$DEV_OSD0 --format=$FORMAT_SIZE  --osdname=$UUID0 \
		--dev=$DEV_OSD1 --format=$FORMAT_SIZE  --osdname=$UUID1 \
		--dev=$DEV_OSD2 --format=$FORMAT_SIZE  --osdname=$UUID2 \
		--dev=$DEV_OSD3 --format=$FORMAT_SIZE  --osdname=$UUID3 \
		--dev=$DEV_OSD4 --format=$FORMAT_SIZE  --osdname=$UUID4 \
		--dev=$DEV_OSD5 --format=$FORMAT_SIZE  --osdname=$UUID5 \
		--dev=$DEV_OSD6 --format=$FORMAT_SIZE  --osdname=$UUID6 \
		--dev=$DEV_OSD7 --format=$FORMAT_SIZE  --osdname=$UUID7
}

mkexofs_mkfs4()
{
	$USR_DIR/mkfs.exofs \
		--pid=$PID4 --raid=$RAID --mirrors=$MIRRORS \
		--stripe_pages=$STRIPE_PAGES \
		--group_width=$GROUP_WIDTH --group_depth=$GROUP_DEPTH \
		--dev=$DEV_OSD0 \
		--dev=$DEV_OSD1 \
		--dev=$DEV_OSD2 \
		--dev=$DEV_OSD3
}

mkexofs_mkfs2()
{
	$USR_DIR/mkfs.exofs \
		--pid=$PID2 --raid=$RAID --mirrors=$MIRRORS \
		--stripe_pages=$STRIPE_PAGES \
		--group_width=$GROUP_WIDTH --group_depth=$GROUP_DEPTH \
		--dev=$DEV_OSD0 \
		--dev=$DEV_OSD1
}

mkexofs_mkfs1()
{
	$USR_DIR/mkfs.exofs \
		--pid=$PID1 --raid=$RAID --mirrors=$MIRRORS \
		--stripe_pages=$STRIPE_PAGES \
		--group_width=$GROUP_WIDTH --group_depth=$GROUP_DEPTH \
		--dev=$DEV_OSD0
}

do_mount()
{
	OPT="pid=$PID,_netdev"

	mount -t exofs -o $OPT $DEV_OSD0 $MOUNTDIR
}
do_umount()
{
	umount $MOUNTDIR
}

PNFS_SRV=compute-4-18
PNFS_MNT=/mnt/pnfs

do_pnfs_start()
{
# 	service nfs start

	mkdir -p $PNFS_MNT
	modprobe objlayoutdriver
	mount -t nfs4 -o minorversion=1 $PNFS_SRV:/ $PNFS_MNT
}
do_pnfs_stop()
{
	umount $PNFS_MNT
	modprobe --remove objlayoutdriver

# 	service nfs stop
}

do_pnfs_dd_test()
{
	# let in an IO for the grace period
	dd if=/dev/zero of=$PNFS_MNT/dd_$(hostname) bs=64k count=131072
}

prompt()
{
	read -p "$* >>> "
}

case $1 in
iscsi_clean)
	do_iscsi_clean
	;;

start)
	echo $0 Starting | logger
	do_start
	echo $0 Initialized | logger
	;;

stop)
	echo $0 Stopping | logger
	do_stop
	echo $0 Stopped | logger
	;;

format)
	prompt mkexofs_format
	mkexofs_format
	echo $0 format | logger
	;;

mkfs4)
	prompt mkexofs_mkfs4
	mkexofs_mkfs4
	echo $0 mkexofs_mkfs4 | logger
	;;
mkfs2)
	prompt mkexofs_mkfs2
	mkexofs_mkfs2
	echo $0 mkexofs_mkfs2 | logger
	;;
mkfs1)
	prompt mkexofs_mkfs1
	mkexofs_mkfs1
	echo $0 mkexofs_mkfs1 | logger
	;;

mount)
	echo $0 mounting | logger
	do_mount
	echo $0 mounted | logger
	;;

umount)
	echo $0 umounting | logger
	do_umount
	echo $0 umounted | logger
	;;

pnfs_start)
	echo $0 mounting | logger
	do_pnfs_start
	echo $0 mounted | logger
	;;

pnfs_stop)
	echo $0 umounting | logger
	do_pnfs_stop
	echo $0 umounted | logger
	;;

pnfs_dd_test)
	do_pnfs_dd_test
	;;

*)
	echo "!! iscsi_clean|start|stop|format|mount|umount|pnfs_start|pnfs_stop|pnfs_dd_test"
	;;
esac