Re: Need help with multipath and iscsi in CentOS 5.4
Using a single path (without MPIO) as a baseline: With bonding I saw, on average 99-100% of the speed (worst case 78%) of a single path. With MPIO (2 nics) I saw, on average 82% of the speed (worst case 66%) of the single path. With MPIO with one nic (ifconfig downed the second), I saw, on average 86% of the speed (worst case 66%) of the single path. There were situations where bonding and MPIO both scored slightly higher than the single path, but that is most likely due to differences on the array, since the tests weren't run back to back. --Kyle On 1/6/10, Mike Christie wrote: > On 12/30/2009 11:48 AM, Kyle Schmitt wrote: >> On Wed, Dec 9, 2009 at 8:52 PM, Mike Christie >> wrote: So far single connections work: If I setup the box to use one NIC, I get one connection and can use it just fine. >>> Could you send the /var/log/messages for when you run the login command >>> so I can see the disk info? >> >> Sorry for the delay. In the meanwhile I tore down the server and >> re-configured it using ethernet bonding. It worked, according to >> iozone, provided moderately better throughput than the single >> connection I got before. Moderately. Measurably. Not significantly. >> >> I tore it down after that and reconfigured again using MPIO, and funny >> enough, this time it worked. I can access the lun now using two >> devices (sdb and sdd), and both ethernet devices that connect to iscsi >> show traffic. >> >> The weird thing is that aside from writing bonding was measurably >> faster than MPIO. Does that seem right? >> > > With MPIO are you seeing the same throughput you would see if you only > used one path at a time? > -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to open-is...@googlegroups.com. To unsubscribe from this group, send email to open-iscsi+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
Re: Need help with multipath and iscsi in CentOS 5.4
On 12/30/2009 11:48 AM, Kyle Schmitt wrote: On Wed, Dec 9, 2009 at 8:52 PM, Mike Christie wrote: So far single connections work: If I setup the box to use one NIC, I get one connection and can use it just fine. Could you send the /var/log/messages for when you run the login command so I can see the disk info? Sorry for the delay. In the meanwhile I tore down the server and re-configured it using ethernet bonding. It worked, according to iozone, provided moderately better throughput than the single connection I got before. Moderately. Measurably. Not significantly. I tore it down after that and reconfigured again using MPIO, and funny enough, this time it worked. I can access the lun now using two devices (sdb and sdd), and both ethernet devices that connect to iscsi show traffic. The weird thing is that aside from writing bonding was measurably faster than MPIO. Does that seem right? With MPIO are you seeing the same throughput you would see if you only used one path at a time? -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to open-is...@googlegroups.com. To unsubscribe from this group, send email to open-iscsi+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
Re: Need help with multipath and iscsi in CentOS 5.4
Note, the EMC specific bits of that multipath.conf were just copied from boxes that use FC to the SAN, and use MPIO successfully. -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to open-is...@googlegroups.com. To unsubscribe from this group, send email to open-iscsi+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
Re: Need help with multipath and iscsi in CentOS 5.4
On Thu, Dec 31, 2009 at 8:23 AM, Pasi Kärkkäinen wrote: > If you have just a single iscsi connection/login from the initiator to the > target, then you'll have only one tcp connection, and that means bonding > won't help you at all - you'll be only able to utilize one link of the > bond. > > bonding needs multiple tcp/ip connections for being able to give more > bandwidth. That's what I thought, but I figured it was one of the following three possibilities: MPIO was (mis)configured and using more overhead than bonding OR the initiator was firing multiple concurrent requests (which you say it doesn't, I'll believe you) OR the san was under massively different load between the test runs (not too likely, but possible. Only one other lun is in use). > That seems a bit weird. That's what I thought, otherwise I would have just gone with it. > How did you configure multipath? Please paste your multipath settings. > > -- Pasi Here's the /etc/multipath.conf. Where there other config options that you'd need to see? devnode_blacklist { devnode "^sda[0-9]*" devnode "^(ram|raw|loop|fd|md|dm-|sr|scd|st)[0-9]*" devnode "^hd[a-z][[0-9]*]" devnode "^cciss!c[0-9]d[0-9]*[p[0-9]*]" } devices { device { vendor "EMC " product "SYMMETRIX" path_grouping_policy multibus getuid_callout "/sbin/scsi_id -g -u -s /block/%n" path_selector "round-robin 0" features "0" hardware_handler "0" failback immediate } device { vendor "DGC" product "*" path_grouping_policy group_by_prio getuid_callout "/sbin/scsi_id -g -u -s /block/%n" prio_callout "/sbin/mpath_prio_emc /dev/%n" hardware_handler "1 emc" features "1 queue_if_no_path" no_path_retry 300 path_checker emc_clariion failback immediate } } -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to open-is...@googlegroups.com. To unsubscribe from this group, send email to open-iscsi+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
Re: Need help with multipath and iscsi in CentOS 5.4
On Wed, Dec 30, 2009 at 11:48:31AM -0600, Kyle Schmitt wrote: > On Wed, Dec 9, 2009 at 8:52 PM, Mike Christie wrote: > >> So far single connections work: If I setup the box to use one NIC, I > >> get one connection and can use it just fine. > > Could you send the /var/log/messages for when you run the login command > > so I can see the disk info? > > Sorry for the delay. In the meanwhile I tore down the server and > re-configured it using ethernet bonding. It worked, according to > iozone, provided moderately better throughput than the single > connection I got before. Moderately. Measurably. Not significantly. > If you have just a single iscsi connection/login from the initiator to the target, then you'll have only one tcp connection, and that means bonding won't help you at all - you'll be only able to utilize one link of the bond. bonding needs multiple tcp/ip connections for being able to give more bandwidth. > I tore it down after that and reconfigured again using MPIO, and funny > enough, this time it worked. I can access the lun now using two > devices (sdb and sdd), and both ethernet devices that connect to iscsi > show traffic. > > The weird thing is that aside from writing bonding was measurably > faster than MPIO. Does that seem right? > That seems a bit weird. How did you configure multipath? Please paste your multipath settings. -- Pasi > > Here's the dmesg, if that lends any clues. Thanks for any input! > > --Kyle > > 156 lines of dmesg follows > > cxgb3i: tag itt 0x1fff, 13 bits, age 0xf, 4 bits. > iscsi: registered transport (cxgb3i) > device-mapper: table: 253:6: multipath: error getting device > device-mapper: ioctl: error adding target to table > device-mapper: table: 253:6: multipath: error getting device > device-mapper: ioctl: error adding target to table > Broadcom NetXtreme II CNIC Driver cnic v2.0.0 (March 21, 2009) > cnic: Added CNIC device: eth0 > cnic: Added CNIC device: eth1 > cnic: Added CNIC device: eth2 > cnic: Added CNIC device: eth3 > Broadcom NetXtreme II iSCSI Driver bnx2i v2.0.1e (June 22, 2009) > iscsi: registered transport (bnx2i) > scsi3 : Broadcom Offload iSCSI Initiator > scsi4 : Broadcom Offload iSCSI Initiator > scsi5 : Broadcom Offload iSCSI Initiator > scsi6 : Broadcom Offload iSCSI Initiator > iscsi: registered transport (tcp) > iscsi: registered transport (iser) > bnx2: eth0: using MSIX > ADDRCONF(NETDEV_UP): eth0: link is not ready > bnx2i: iSCSI not supported, dev=eth0 > bnx2i: iSCSI not supported, dev=eth0 > bnx2: eth0 NIC Copper Link is Up, 1000 Mbps full duplex, receive & > transmit flow control ON > ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready > bnx2: eth2: using MSIX > ADDRCONF(NETDEV_UP): eth2: link is not ready > bnx2i: iSCSI not supported, dev=eth2 > bnx2i: iSCSI not supported, dev=eth2 > bnx2: eth2 NIC Copper Link is Up, 1000 Mbps full duplex > ADDRCONF(NETDEV_CHANGE): eth2: link becomes ready > bnx2: eth3: using MSIX > ADDRCONF(NETDEV_UP): eth3: link is not ready > bnx2i: iSCSI not supported, dev=eth3 > bnx2i: iSCSI not supported, dev=eth3 > bnx2: eth3 NIC Copper Link is Up, 1000 Mbps full duplex > ADDRCONF(NETDEV_CHANGE): eth3: link becomes ready > eth0: no IPv6 routers present > eth2: no IPv6 routers present > scsi7 : iSCSI Initiator over TCP/IP > scsi8 : iSCSI Initiator over TCP/IP > scsi9 : iSCSI Initiator over TCP/IP > scsi10 : iSCSI Initiator over TCP/IP > Vendor: DGC Model: RAID 5Rev: 0429 > Type: Direct-Access ANSI SCSI revision: 04 > sdb : very big device. try to use READ CAPACITY(16). > SCSI device sdb: 7693604864 512-byte hdwr sectors (3939126 MB) > sdb: Write Protect is off > sdb: Mode Sense: 7d 00 00 08 > SCSI device sdb: drive cache: write through > sdb : very big device. try to use READ CAPACITY(16). > SCSI device sdb: 7693604864 512-byte hdwr sectors (3939126 MB) > sdb: Write Protect is off > sdb: Mode Sense: 7d 00 00 08 > SCSI device sdb: drive cache: write through > sdb:<5> Vendor: DGC Model: RAID 5Rev: 0429 > Type: Direct-Access ANSI SCSI revision: 04 > Vendor: DGC Model: RAID 5Rev: 0429 > Type: Direct-Access ANSI SCSI revision: 04 > sdc : very big device. try to use READ CAPACITY(16). > SCSI device sdc: 7693604864 512-byte hdwr sectors (3939126 MB) > sdc: test WP failed, assume Write Enabled > sdc: asking for cache data failed > sdc: assuming drive cache: write through > Vendor: DGC Model: RAID 5Rev: 0429 > Type: Direct-Access ANSI SCSI revision: 04 > sdc : very big device. try to use READ CAPACITY(16). > SCSI device sdc: 7693604864 512-byte hdwr sectors (3939126 MB) > sdc: test WP failed, assume Write Enabled > sde : very big device. try to use READ CAPACITY(16). > sdc: asking for cache data failed > sdc: assuming drive cache: write through > sdc:<5>SCSI device sde: 7693604864 512-byte hdwr sectors (3939126 MB)
Re: Need help with multipath and iscsi in CentOS 5.4
On Wed, Dec 9, 2009 at 8:52 PM, Mike Christie wrote: >> So far single connections work: If I setup the box to use one NIC, I >> get one connection and can use it just fine. > Could you send the /var/log/messages for when you run the login command > so I can see the disk info? Sorry for the delay. In the meanwhile I tore down the server and re-configured it using ethernet bonding. It worked, according to iozone, provided moderately better throughput than the single connection I got before. Moderately. Measurably. Not significantly. I tore it down after that and reconfigured again using MPIO, and funny enough, this time it worked. I can access the lun now using two devices (sdb and sdd), and both ethernet devices that connect to iscsi show traffic. The weird thing is that aside from writing bonding was measurably faster than MPIO. Does that seem right? Here's the dmesg, if that lends any clues. Thanks for any input! --Kyle 156 lines of dmesg follows cxgb3i: tag itt 0x1fff, 13 bits, age 0xf, 4 bits. iscsi: registered transport (cxgb3i) device-mapper: table: 253:6: multipath: error getting device device-mapper: ioctl: error adding target to table device-mapper: table: 253:6: multipath: error getting device device-mapper: ioctl: error adding target to table Broadcom NetXtreme II CNIC Driver cnic v2.0.0 (March 21, 2009) cnic: Added CNIC device: eth0 cnic: Added CNIC device: eth1 cnic: Added CNIC device: eth2 cnic: Added CNIC device: eth3 Broadcom NetXtreme II iSCSI Driver bnx2i v2.0.1e (June 22, 2009) iscsi: registered transport (bnx2i) scsi3 : Broadcom Offload iSCSI Initiator scsi4 : Broadcom Offload iSCSI Initiator scsi5 : Broadcom Offload iSCSI Initiator scsi6 : Broadcom Offload iSCSI Initiator iscsi: registered transport (tcp) iscsi: registered transport (iser) bnx2: eth0: using MSIX ADDRCONF(NETDEV_UP): eth0: link is not ready bnx2i: iSCSI not supported, dev=eth0 bnx2i: iSCSI not supported, dev=eth0 bnx2: eth0 NIC Copper Link is Up, 1000 Mbps full duplex, receive & transmit flow control ON ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready bnx2: eth2: using MSIX ADDRCONF(NETDEV_UP): eth2: link is not ready bnx2i: iSCSI not supported, dev=eth2 bnx2i: iSCSI not supported, dev=eth2 bnx2: eth2 NIC Copper Link is Up, 1000 Mbps full duplex ADDRCONF(NETDEV_CHANGE): eth2: link becomes ready bnx2: eth3: using MSIX ADDRCONF(NETDEV_UP): eth3: link is not ready bnx2i: iSCSI not supported, dev=eth3 bnx2i: iSCSI not supported, dev=eth3 bnx2: eth3 NIC Copper Link is Up, 1000 Mbps full duplex ADDRCONF(NETDEV_CHANGE): eth3: link becomes ready eth0: no IPv6 routers present eth2: no IPv6 routers present scsi7 : iSCSI Initiator over TCP/IP scsi8 : iSCSI Initiator over TCP/IP scsi9 : iSCSI Initiator over TCP/IP scsi10 : iSCSI Initiator over TCP/IP Vendor: DGC Model: RAID 5Rev: 0429 Type: Direct-Access ANSI SCSI revision: 04 sdb : very big device. try to use READ CAPACITY(16). SCSI device sdb: 7693604864 512-byte hdwr sectors (3939126 MB) sdb: Write Protect is off sdb: Mode Sense: 7d 00 00 08 SCSI device sdb: drive cache: write through sdb : very big device. try to use READ CAPACITY(16). SCSI device sdb: 7693604864 512-byte hdwr sectors (3939126 MB) sdb: Write Protect is off sdb: Mode Sense: 7d 00 00 08 SCSI device sdb: drive cache: write through sdb:<5> Vendor: DGC Model: RAID 5Rev: 0429 Type: Direct-Access ANSI SCSI revision: 04 Vendor: DGC Model: RAID 5Rev: 0429 Type: Direct-Access ANSI SCSI revision: 04 sdc : very big device. try to use READ CAPACITY(16). SCSI device sdc: 7693604864 512-byte hdwr sectors (3939126 MB) sdc: test WP failed, assume Write Enabled sdc: asking for cache data failed sdc: assuming drive cache: write through Vendor: DGC Model: RAID 5Rev: 0429 Type: Direct-Access ANSI SCSI revision: 04 sdc : very big device. try to use READ CAPACITY(16). SCSI device sdc: 7693604864 512-byte hdwr sectors (3939126 MB) sdc: test WP failed, assume Write Enabled sde : very big device. try to use READ CAPACITY(16). sdc: asking for cache data failed sdc: assuming drive cache: write through sdc:<5>SCSI device sde: 7693604864 512-byte hdwr sectors (3939126 MB) sd 8:0:0:0: Device not ready: <6>: Current: sense key: Not Ready Add. Sense: Logical unit not ready, manual intervention required end_request: I/O error, dev sdc, sector 0 Buffer I/O error on device sdc, logical block 0 sd 8:0:0:0: Device not ready: <6>: Current: sense key: Not Ready Add. Sense: Logical unit not ready, manual intervention required end_request: I/O error, dev sdc, sector 0 ... that repeats a bunch of times Buffer I/O error on device sdc, logical block 0 unable to read partition table sdd : very big device. try to use READ CAPACITY(16). sd 8:0:0:0: Attached scsi disk sdc SCSI device sdd: 7693604864 512-byte hdwr sectors (3939126 MB) sd
Re: Need help with multipath and iscsi in CentOS 5.4
On Wed, Dec 9, 2009 at 8:52 PM, Mike Christie wrote: > Kyle Schmitt wrote: > What do you mean by works? Can you dd it, or fdisk it? it works by most any measure sdc: I can dd it, fdisk it, mkfs.ext3 it, run iozone, etc. In contrast sdb sdd and sde cant be fdisked, dded, or even less -fed. > Have you created a lun that is accessible to the initiator defined in > /etc/iscsi/initiatorname.iscsi? Yup, I've got a lun, and can read/write to it. > Could you send the /var/log/messages for when you run the login command > so I can see the disk info? Sure, let me dig it out... it'll be a few minutes. -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to open-is...@googlegroups.com. To unsubscribe from this group, send email to open-iscsi+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
RE: Need help with multipath and iscsi in CentOS 5.4
Hi Kyle. For your configuration do you have a LUN in the storage group assigned to your server? If so, the LUN is presented to both SPs (service processors) but only owned by one. If your storage group for the server has been configured for the default mode the LUN is presented in PNR mode; therefore, only one SP owns it and can be used for the IO. In order to use the LUN thru the other SP the LUN needs to be trespassed to that SP. If the storage group for the server is configured for ALUA mode then you can read and write thru both SPs without a trespass command. If there are no LUNs assigned in a storage group for your server, then the LUN that is presented to the server is a LUNZ and you will not be able to access it. You indicate below that you are able to fdisk one of the SCSI devices but not all four. If you are configured in the manner you described you should be able to access it thru the two NICs that attached to the SP that owns the LUN. Regards, Wayne. EMC Corp -Original Message- From: open-iscsi@googlegroups.com [mailto:open-is...@googlegroups.com] On Behalf Of Mike Christie Sent: Wednesday, December 09, 2009 9:52 PM To: open-iscsi@googlegroups.com Subject: Re: Need help with multipath and iscsi in CentOS 5.4 Kyle Schmitt wrote: > I'm cross-posting here from linux-iscsi-users since I've seen no linux-scsi-users would be for centos 4. Centos 5 uses a different initiator, but you are the right place finally :) > traffic in the weeks since I posted this. > > Hi, I needed a little help or advice with my setup. I'm trying to > configure multipathed iscsi on a CentOS 5.4 (RHEL 5.4 clone) box. > > Very short version: One server with two NICs for iSCSI sees storage on > EMC. Storage shows up as four discs, but only one works. > > So far single connections work: If I setup the box to use one NIC, I > get one connection and can use it just fine. > > When I setup multiple connections I have problems... > I created two interfaces, and assigned each one to a NIC > iscsiadm -m iface -I iface0 --op=new > iscsiadm -m iface -I iface0 --op=update -n iface.net_ifacename -v eth2 > iscsiadm -m iface -I iface1 --op=new > iscsiadm -m iface -I iface1 --op=update -n iface.net_ifacename -v eth3 > > Each interface saw two paths to their storage, four total, so far so > good. > I logged all four of them them in with: > iscsiadm -m node -T -l > > I could see I was connected to all four via > iscsiadm-m session > > At this point, I thought I was set, I had four new devices > /dev/sdb /dev/sdc /dev/sdd /dev/sde > > Ignoring multipath at this point for now, here's where the problem > started. I have all four devices, but I can only communicate through > one of them: /dev/sdc. > > As a quick test I tried to fdisk all four partitions, to see if I saw > the same thing in each place, and only /dev/sdc works. What do you mean by works? Can you dd it, or fdisk it? > > Turning on multipath, I got a multipathed device consisting of sdb sdc > sdd and sde, but sdb sdd and sde are failed with a message of > checker msg is "emc_clariion_checker: Logical Unit is unbound or LUNZ" > Have you created a lun that is accessible to the initiator defined in /etc/iscsi/initiatorname.iscsi? Could you send the /var/log/messages for when you run the login command so I can see the disk info? -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to open-is...@googlegroups.com. To unsubscribe from this group, send email to open-iscsi+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en. -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to open-is...@googlegroups.com. To unsubscribe from this group, send email to open-iscsi+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
Re: Need help with multipath and iscsi in CentOS 5.4
Kyle Schmitt wrote: > I'm cross-posting here from linux-iscsi-users since I've seen no linux-scsi-users would be for centos 4. Centos 5 uses a different initiator, but you are the right place finally :) > traffic in the weeks since I posted this. > > Hi, I needed a little help or advice with my setup. I'm trying to > configure multipathed iscsi on a CentOS 5.4 (RHEL 5.4 clone) box. > > Very short version: One server with two NICs for iSCSI sees storage on > EMC. Storage shows up as four discs, but only one works. > > So far single connections work: If I setup the box to use one NIC, I > get one connection and can use it just fine. > > When I setup multiple connections I have problems... > I created two interfaces, and assigned each one to a NIC > iscsiadm -m iface -I iface0 --op=new > iscsiadm -m iface -I iface0 --op=update -n iface.net_ifacename -v eth2 > iscsiadm -m iface -I iface1 --op=new > iscsiadm -m iface -I iface1 --op=update -n iface.net_ifacename -v eth3 > > Each interface saw two paths to their storage, four total, so far so > good. > I logged all four of them them in with: > iscsiadm -m node -T -l > > I could see I was connected to all four via > iscsiadm-m session > > At this point, I thought I was set, I had four new devices > /dev/sdb /dev/sdc /dev/sdd /dev/sde > > Ignoring multipath at this point for now, here's where the problem > started. I have all four devices, but I can only communicate through > one of them: /dev/sdc. > > As a quick test I tried to fdisk all four partitions, to see if I saw > the same thing in each place, and only /dev/sdc works. What do you mean by works? Can you dd it, or fdisk it? > > Turning on multipath, I got a multipathed device consisting of sdb sdc > sdd and sde, but sdb sdd and sde are failed with a message of > checker msg is "emc_clariion_checker: Logical Unit is unbound or LUNZ" > Have you created a lun that is accessible to the initiator defined in /etc/iscsi/initiatorname.iscsi? Could you send the /var/log/messages for when you run the login command so I can see the disk info? -- You received this message because you are subscribed to the Google Groups "open-iscsi" group. To post to this group, send email to open-is...@googlegroups.com. To unsubscribe from this group, send email to open-iscsi+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.