How trespassing works using ALUA (Failover mode 4) on a CLARiiON storage system
Environment:
Product: CLARiiON CX4 Series
Environment:
Product: CLARiiON CX3 Series
Environment:
Active/Active (ALUA) Failover Mode
Environment:
Asymmetric Logical Unit Access (ALUA)
Environment:
EMC Firmware: FLARE Release 26 (0x.26)
Fix:
Since FLARE 26, Asymmetric Active/Active has provided a new way for CLARiiON arrays to present LUNs to hosts, eliminating the need for hosts to deal with the LUN ownership model. Prior to FLARE 26, all CLARiiON arrays used the standard active/passive presentation feature which one SP "owns" the LUN and all I/O to that LUN is sent only to that SP. If all paths to that SP fail, the ownership of the LUN was 'trespassed' to the other SP and the host-based path management software adjusted the I/O path accordingly.
Asymmetric Active/Active introduces a new initiator Failover Mode (Failover mode 4) where initiators are permitted to send I/O to a LUN regardless of which SP actually owns the LUN.
Manual trespass
When a manual trespass is issued (using Navisphere Manager or CLI) to a LUN on a SP that is accessed by a host with Failover Mode 1, subsequent I/O for that LUN is rejected over the SP on which the manual trespass was issued. The failover software redirects I/O to the SP that owns the LUN.
A manual trespass operation causes the ownership of a given LUN owned by a given SP to change. If this LUN is accessed by an ALUA host (Failover Mode is set to 4), and I/O is sent to the SP that does not currently own the LUN, this would cause I/O redirection. In such a situation, the array based on how many I/Os (threshold of 64000 +/- I/Os) a LUN processes on each SP will change the ownership of the LUN.
Path, HBA, switch failure
If a host is configured with Failover Mode 1 and all the paths to the SP that owns a LUN fail, the LUN is trespassed to the other SP by the host’s failover software.
With Failover Mode 4, in the case of a path, HBA, or switch failure, when I/O routes to the non-owning SP, the LUN may not trespass immediately (depending on the failover software on the host). If the LUN is not trespassed to the owning SP, FLARE will trespass the LUN to the SP that receives the most I/O requests to that LUN. This is accomplished by the array keeping track of how many I/Os a LUN processes on each SP. If the non-optimized SP processes 64,000 or more I/Os than the optimal SP, the array will change the ownership to the non-optimal SP, making it optimal.
SP failure
In case of an SP failure for a host configured as Failover Mode 1, the failover software trespasses the LUN to the surviving SP.
With Failover Mode 4, if an I/O arrives from an ALUA initiator on the surviving SP (non-optimal), FLARE initiates an internal trespass operation. This operation changes ownership of the target LUN to the surviving SP since its peer SP is dead. Hence, the host (failover software) must have access to the secondary SP so that it can issue an I/O under these circumstances.
Single backend failure
Before FLARE Release 26, if the failover software was misconfigured (for example, a single attach configuration), a single back-end failure (for example, an LCC or BCC failure) would generate an I/O error since the failover software would not be able to try the alternate path to the other SP with a stable backend.
With release 26 of FLARE, regardless of the Failover Mode for a given host, when the SP that owns the LUN cannot access that LUN due to a back-end failure, I/O is redirected through the other SP by the lower redirector. In this situation, the LUN is trespassed by FLARE to the SP that can access the LUN. After the failure is corrected, the LUN is trespassed back to the SP that previously owned the LUN. See the “Enabler for masking back-end failures” section for more information.
I've been reading the PDF document (and trying to fully understand it).
In broad strokes, we could say that in Failover Mode = 1, if a front-end path fails, Power Path makes a trespass and change not-optimal path to optimal path, and in Failover Mode = 4, there is no trespass, and the SP does not own the LUN accept I/O and redirects through CMI Upper-redirector to SP owner LUN ?
Is that the main difference between these Failover Modes ?
I have VMware ESXi 4.0 with CX4 with flare 30 and Failover Mode configured with 1. Should I use 4 ?
dynamox
9 Legend
•
20.4K Posts
0
March 23rd, 2010 20:00
Asymmetric Active/Active introduces a new initiator Failover Mode (Failover mode 4) where initiators are permitted to send I/O to a LUN regardless of which SP actually owns the LUN.
Manual trespass
When a manual trespass is issued (using Navisphere Manager or CLI) to a LUN on a SP that is accessed by a host with Failover Mode 1, subsequent I/O for that LUN is rejected over the SP on which the manual trespass was issued. The failover software redirects I/O to the SP that owns the LUN.
A manual trespass operation causes the ownership of a given LUN owned by a given SP to change. If this LUN is accessed by an ALUA host (Failover Mode is set to 4), and I/O is sent to the SP that does not currently own the LUN, this would cause I/O redirection. In such a situation, the array based on how many I/Os (threshold of 64000 +/- I/Os) a LUN processes on each SP will change the ownership of the LUN.
Path, HBA, switch failure
If a host is configured with Failover Mode 1 and all the paths to the SP that owns a LUN fail, the LUN is trespassed to the other SP by the host’s failover software.
With Failover Mode 4, in the case of a path, HBA, or switch failure, when I/O routes to the non-owning SP, the LUN may not trespass immediately (depending on the failover software on the host). If the LUN is not trespassed to the owning SP, FLARE will trespass the LUN to the SP that receives the most I/O requests to that LUN. This is accomplished by the array keeping track of how many I/Os a LUN processes on each SP. If the non-optimized SP processes 64,000 or more I/Os than the optimal SP, the array will change the ownership to the non-optimal SP, making it optimal.
SP failure
In case of an SP failure for a host configured as Failover Mode 1, the failover software trespasses the LUN to the surviving SP.
With Failover Mode 4, if an I/O arrives from an ALUA initiator on the surviving SP (non-optimal), FLARE initiates an internal trespass operation. This operation changes ownership of the target LUN to the surviving SP since its peer SP is dead. Hence, the host (failover software) must have access to the secondary SP so that it can issue an I/O under these circumstances.
Single backend failure
Before FLARE Release 26, if the failover software was misconfigured (for example, a single attach configuration), a single back-end failure (for example, an LCC or BCC failure) would generate an I/O error since the failover software would not be able to try the alternate path to the other SP with a stable backend.
With release 26 of FLARE, regardless of the Failover Mode for a given host, when the SP that owns the LUN cannot access that LUN due to a back-end failure, I/O is redirected through the other SP by the lower redirector. In this situation, the LUN is trespassed by FLARE to the SP that can access the LUN. After the failure is corrected, the LUN is trespassed back to the SP that previously owned the LUN. See the “Enabler for masking back-end failures” section for more information.
dynamox
9 Legend
•
20.4K Posts
0
March 23rd, 2010 18:00
do you have access to PowerLink, if yes download this paper
https://powerlink.emc.com/nsepn/webapps/btg548664833igtcuup4826/km/live1/en_US/Offering_Technical/White_Paper/H2890-clariion-asym-active.pdf
kums1
1 Rookie
•
10 Posts
0
March 23rd, 2010 20:00
THanks for the detailed explanation.
kums1
1 Rookie
•
10 Posts
0
March 23rd, 2010 20:00
Im waiting for the powerlink access. Could you jus explain me that in simple terms what exactly it is? will go thru the powerlink once i have access.
MaC15
1 Rookie
•
36 Posts
0
March 17th, 2011 08:00
I've been reading the PDF document (and trying to fully understand it).
In broad strokes, we could say that in Failover Mode = 1, if a front-end path fails, Power Path makes a trespass and change not-optimal path to optimal path, and in Failover Mode = 4, there is no trespass, and the SP does not own the LUN accept I/O and redirects through CMI Upper-redirector to SP owner LUN ?
Is that the main difference between these Failover Modes ?
I have VMware ESXi 4.0 with CX4 with flare 30 and Failover Mode configured with 1. Should I use 4 ?
Thanks a lot,
Mariano.