multipathd failback

multipathd failback

[Yonathan Cohen]

Hello.
My "multipathd" daemon does not FailBack
It does not check the availability of a failed path and of course does 
not reinstate it
My configuration is as follows:
cat /etc/multipath.conf

defaults {

        failback        immediate
}
I am using the following packages:
multipath-tools-0.4.5-0.11
device-mapper-1.01.01-1.6
I have them installed on a SUSE LINUX Enterprise Server 9 (x86_64) sp-3
With kernel version: 2.6.5-7.244-smp
Please help.
Thanks.

____________________________________________________________

Cohen Yonatan   |  +972-9-9718607 (o)  

Software. Eng,  Storage group

Voltaire - _The Grid Backbone_

AW: multipathd failback

[Herr, Manuel]

On which Hardware? (HBAs, SAN)?

> -----Ursprüngliche Nachricht-----
> Von: dm-devel-bounces@redhat.com 
> [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> Gesendet: Mittwoch, 25. Oktober 2006 08:50
> An: dm-devel@redhat.com
> Betreff: [dm-devel] multipathd failback
> 
> Hello.
> My "multipathd" daemon does not FailBack It does not check 
> the availability of a failed path and of course does not 
> reinstate it My configuration is as follows:
> cat /etc/multipath.conf
> 
> defaults {
> 
>         failback        immediate
> }
> I am using the following packages:
> multipath-tools-0.4.5-0.11
> device-mapper-1.01.01-1.6
> I have them installed on a SUSE LINUX Enterprise Server 9 
> (x86_64) sp-3 With kernel version: 2.6.5-7.244-smp Please help.
> Thanks.
> 
> ____________________________________________________________
> 
> Cohen Yonatan   |  +972-9-9718607 (o)  
> 
> Software. Eng,  Storage group
> 
> Voltaire - _The Grid Backbone_
> 
> --
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
> 

Re: AW: multipathd failback

[Yonathan Cohen]

sorry but I am not sure what you mean.
I am using an iscsi initiator (linux-iscsi rev 4.2)
and this is what the multipathd daemon sees
pepper:~ # multipath -l
dm names   N
dm table 3600c0ff00000000007c1d167985b4b06  N
dm table 3600c0ff00000000007c1d167985b4b06  N
dm status 3600c0ff00000000007c1d167985b4b06  N
dm info 3600c0ff00000000007c1d167985b4b06  O
3600c0ff00000000007c1d167985b4b06
[size=20 GB][features="0"][hwhandler="0"]
\_ round-robin 0 [enabled]
 \_ 14:0:0:0 sda 8:0  [failed]
 \_ round-robin 0 [active]
  \_ 14:1:0:0 sdb 8:16 [active]

sda and sdb are actually the same device discovered by iscsi via 2 
different paths.
when sda failed multipathd identified the problem and diverted traffic 
to sdb
but after correcting the sda problem, multipathd did not become aware of 
this and of course when
i failed sdb it did not failback to sda.
i know that multipathd is suppose to poll for failed paths and reinstate 
them when they become valid.
but for some reason it does not.


Herr, Manuel wrote:
>
> On which Hardware? (HBAs, SAN)?
>
> > -----Ursprüngliche Nachricht-----
> > Von: dm-devel-bounces@redhat.com
> > [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> > Gesendet: Mittwoch, 25. Oktober 2006 08:50
> > An: dm-devel@redhat.com
> > Betreff: [dm-devel] multipathd failback
> >
> > Hello.
> > My "multipathd" daemon does not FailBack It does not check
> > the availability of a failed path and of course does not
> > reinstate it My configuration is as follows:
> > cat /etc/multipath.conf
> >
> > defaults {
> >
> >         failback        immediate
> > }
> > I am using the following packages:
> > multipath-tools-0.4.5-0.11
> > device-mapper-1.01.01-1.6
> > I have them installed on a SUSE LINUX Enterprise Server 9
> > (x86_64) sp-3 With kernel version: 2.6.5-7.244-smp Please help.
> > Thanks.
> >
> > ____________________________________________________________
> >
> > Cohen Yonatan   |  +972-9-9718607 (o) 
> >
> > Software. Eng,  Storage group
> >
> > Voltaire - _The Grid Backbone_
> >
> > --
> > dm-devel mailing list
> > dm-devel@redhat.com
> > https://www.redhat.com/mailman/listinfo/dm-devel
> >
>
> -- 
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
>

AW: AW: multipathd failback

[Herr, Manuel]

I have no Problem with the failover also with SLES 9 2.6.5-7.244-smp.
But i'm not working with the isci initiator.

My Config:
defaults 
{
        multipath_tool  "/sbin/multipath -v0"
        udev_dir        /dev
        polling_interval 5
        default_selector        "round-robin 0"
        default_getuid_callout  "/sbin/scsi_id -g -u -s /block/%n"
        default_prio_callout    "/bin/true"
        failback        immediate
}
There are newer Multipath tools available:
Im working with: multipath-tools-0.4.5-0.20
(Device Mapper is same)
I recommend to update them first. :)

This one is talking about the same Problem you have.
http://www.querzone.de/wiki/Wiki.jsp?page=EMCClariion
I don't know if this error is clariion specific. 

Regards,
Manuel

> -----Ursprüngliche Nachricht-----
> Von: dm-devel-bounces@redhat.com 
> [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> Gesendet: Mittwoch, 25. Oktober 2006 09:22
> An: device-mapper development
> Betreff: Re: AW: [dm-devel] multipathd failback
> 
> sorry but I am not sure what you mean.
> I am using an iscsi initiator (linux-iscsi rev 4.2) and this 
> is what the multipathd daemon sees pepper:~ # multipath -l
> dm names   N
> dm table 3600c0ff00000000007c1d167985b4b06  N dm table 
> 3600c0ff00000000007c1d167985b4b06  N dm status 
> 3600c0ff00000000007c1d167985b4b06  N dm info 
> 3600c0ff00000000007c1d167985b4b06  O
> 3600c0ff00000000007c1d167985b4b06
> [size=20 GB][features="0"][hwhandler="0"] \_ round-robin 0 
> [enabled]  \_ 14:0:0:0 sda 8:0  [failed]  \_ round-robin 0 [active]
>   \_ 14:1:0:0 sdb 8:16 [active]
> 
> sda and sdb are actually the same device discovered by iscsi 
> via 2 different paths.
> when sda failed multipathd identified the problem and 
> diverted traffic to sdb but after correcting the sda problem, 
> multipathd did not become aware of this and of course when i 
> failed sdb it did not failback to sda.
> i know that multipathd is suppose to poll for failed paths 
> and reinstate them when they become valid.
> but for some reason it does not.
> 
> 
> Herr, Manuel wrote:
> >
> > On which Hardware? (HBAs, SAN)?
> >
> > > -----Ursprüngliche Nachricht-----
> > > Von: dm-devel-bounces@redhat.com
> > > [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> > > Gesendet: Mittwoch, 25. Oktober 2006 08:50
> > > An: dm-devel@redhat.com
> > > Betreff: [dm-devel] multipathd failback
> > >
> > > Hello.
> > > My "multipathd" daemon does not FailBack It does not check the 
> > > availability of a failed path and of course does not 
> reinstate it My 
> > > configuration is as follows:
> > > cat /etc/multipath.conf
> > >
> > > defaults {
> > >
> > >         failback        immediate
> > > }
> > > I am using the following packages:
> > > multipath-tools-0.4.5-0.11
> > > device-mapper-1.01.01-1.6
> > > I have them installed on a SUSE LINUX Enterprise Server 9
> > > (x86_64) sp-3 With kernel version: 2.6.5-7.244-smp Please help.
> > > Thanks.
> > >
> > > ____________________________________________________________
> > >
> > > Cohen Yonatan   |  +972-9-9718607 (o) 
> > >
> > > Software. Eng,  Storage group
> > >
> > > Voltaire - _The Grid Backbone_
> > >
> > > --
> > > dm-devel mailing list
> > > dm-devel@redhat.com
> > > https://www.redhat.com/mailman/listinfo/dm-devel
> > >
> >
> > --
> > dm-devel mailing list
> > dm-devel@redhat.com
> > https://www.redhat.com/mailman/listinfo/dm-devel
> >
> 
> --
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
> 

Re: AW: AW: multipathd failback

[Yonathan Cohen]

I also have no probelm with failover only with failback
but ill try upgrading to multipath-tools-0.4.5-0.20
thanks.
Herr, Manuel wrote:
>
> I have no Problem with the failover also with SLES 9 2.6.5-7.244-smp.
> But i'm not working with the isci initiator.
>
> My Config:
> defaults
> {
>         multipath_tool  "/sbin/multipath -v0"
>         udev_dir        /dev
>         polling_interval 5
>         default_selector        "round-robin 0"
>         default_getuid_callout  "/sbin/scsi_id -g -u -s /block/%n"
>         default_prio_callout    "/bin/true"
>         failback        immediate
> }
> There are newer Multipath tools available:
> Im working with: multipath-tools-0.4.5-0.20
> (Device Mapper is same)
> I recommend to update them first. :)
>
> This one is talking about the same Problem you have.
> http://www.querzone.de/wiki/Wiki.jsp?page=EMCClariion
> I don't know if this error is clariion specific.
>
> Regards,
> Manuel
>
> > -----Ursprüngliche Nachricht-----
> > Von: dm-devel-bounces@redhat.com
> > [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> > Gesendet: Mittwoch, 25. Oktober 2006 09:22
> > An: device-mapper development
> > Betreff: Re: AW: [dm-devel] multipathd failback
> >
> > sorry but I am not sure what you mean.
> > I am using an iscsi initiator (linux-iscsi rev 4.2) and this
> > is what the multipathd daemon sees pepper:~ # multipath -l
> > dm names   N
> > dm table 3600c0ff00000000007c1d167985b4b06  N dm table
> > 3600c0ff00000000007c1d167985b4b06  N dm status
> > 3600c0ff00000000007c1d167985b4b06  N dm info
> > 3600c0ff00000000007c1d167985b4b06  O
> > 3600c0ff00000000007c1d167985b4b06
> > [size=20 GB][features="0"][hwhandler="0"] \_ round-robin 0
> > [enabled]  \_ 14:0:0:0 sda 8:0  [failed]  \_ round-robin 0 [active]
> >   \_ 14:1:0:0 sdb 8:16 [active]
> >
> > sda and sdb are actually the same device discovered by iscsi
> > via 2 different paths.
> > when sda failed multipathd identified the problem and
> > diverted traffic to sdb but after correcting the sda problem,
> > multipathd did not become aware of this and of course when i
> > failed sdb it did not failback to sda.
> > i know that multipathd is suppose to poll for failed paths
> > and reinstate them when they become valid.
> > but for some reason it does not.
> >
> >
> > Herr, Manuel wrote:
> > >
> > > On which Hardware? (HBAs, SAN)?
> > >
> > > > -----Ursprüngliche Nachricht-----
> > > > Von: dm-devel-bounces@redhat.com
> > > > [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> > > > Gesendet: Mittwoch, 25. Oktober 2006 08:50
> > > > An: dm-devel@redhat.com
> > > > Betreff: [dm-devel] multipathd failback
> > > >
> > > > Hello.
> > > > My "multipathd" daemon does not FailBack It does not check the
> > > > availability of a failed path and of course does not
> > reinstate it My
> > > > configuration is as follows:
> > > > cat /etc/multipath.conf
> > > >
> > > > defaults {
> > > >
> > > >         failback        immediate
> > > > }
> > > > I am using the following packages:
> > > > multipath-tools-0.4.5-0.11
> > > > device-mapper-1.01.01-1.6
> > > > I have them installed on a SUSE LINUX Enterprise Server 9
> > > > (x86_64) sp-3 With kernel version: 2.6.5-7.244-smp Please help.
> > > > Thanks.
> > > >
> > > > ____________________________________________________________
> > > >
> > > > Cohen Yonatan   |  +972-9-9718607 (o)
> > > >
> > > > Software. Eng,  Storage group
> > > >
> > > > Voltaire - _The Grid Backbone_
> > > >
> > > > --
> > > > dm-devel mailing list
> > > > dm-devel@redhat.com
> > > > https://www.redhat.com/mailman/listinfo/dm-devel
> > > >
> > >
> > > --
> > > dm-devel mailing list
> > > dm-devel@redhat.com
> > > https://www.redhat.com/mailman/listinfo/dm-devel
> > >
> >
> > --
> > dm-devel mailing list
> > dm-devel@redhat.com
> > https://www.redhat.com/mailman/listinfo/dm-devel
> >
>
> -- 
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
>

Re: AW: AW: multipathd failback

[Yonathan Cohen]

Hello again.
can you please tell me how to upgrade to multipath-tools-0.4.5-0.20
i found multipath-0.4.5.tar.bz2 on the site 
(http://christophe.varoqui.free.fr/multipath-tools/ )
but i guess that multipath-tools-0.4.5-0.20 is after applying some patches
if so can you tell me which ones ?
thanks.

Herr, Manuel wrote:
>
> I have no Problem with the failover also with SLES 9 2.6.5-7.244-smp.
> But i'm not working with the isci initiator.
>
> My Config:
> defaults
> {
>         multipath_tool  "/sbin/multipath -v0"
>         udev_dir        /dev
>         polling_interval 5
>         default_selector        "round-robin 0"
>         default_getuid_callout  "/sbin/scsi_id -g -u -s /block/%n"
>         default_prio_callout    "/bin/true"
>         failback        immediate
> }
> There are newer Multipath tools available:
> Im working with: multipath-tools-0.4.5-0.20
> (Device Mapper is same)
> I recommend to update them first. :)
>
> This one is talking about the same Problem you have.
> http://www.querzone.de/wiki/Wiki.jsp?page=EMCClariion
> I don't know if this error is clariion specific.
>
> Regards,
> Manuel
>
> > -----Ursprüngliche Nachricht-----
> > Von: dm-devel-bounces@redhat.com
> > [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> > Gesendet: Mittwoch, 25. Oktober 2006 09:22
> > An: device-mapper development
> > Betreff: Re: AW: [dm-devel] multipathd failback
> >
> > sorry but I am not sure what you mean.
> > I am using an iscsi initiator (linux-iscsi rev 4.2) and this
> > is what the multipathd daemon sees pepper:~ # multipath -l
> > dm names   N
> > dm table 3600c0ff00000000007c1d167985b4b06  N dm table
> > 3600c0ff00000000007c1d167985b4b06  N dm status
> > 3600c0ff00000000007c1d167985b4b06  N dm info
> > 3600c0ff00000000007c1d167985b4b06  O
> > 3600c0ff00000000007c1d167985b4b06
> > [size=20 GB][features="0"][hwhandler="0"] \_ round-robin 0
> > [enabled]  \_ 14:0:0:0 sda 8:0  [failed]  \_ round-robin 0 [active]
> >   \_ 14:1:0:0 sdb 8:16 [active]
> >
> > sda and sdb are actually the same device discovered by iscsi
> > via 2 different paths.
> > when sda failed multipathd identified the problem and
> > diverted traffic to sdb but after correcting the sda problem,
> > multipathd did not become aware of this and of course when i
> > failed sdb it did not failback to sda.
> > i know that multipathd is suppose to poll for failed paths
> > and reinstate them when they become valid.
> > but for some reason it does not.
> >
> >
> > Herr, Manuel wrote:
> > >
> > > On which Hardware? (HBAs, SAN)?
> > >
> > > > -----Ursprüngliche Nachricht-----
> > > > Von: dm-devel-bounces@redhat.com
> > > > [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> > > > Gesendet: Mittwoch, 25. Oktober 2006 08:50
> > > > An: dm-devel@redhat.com
> > > > Betreff: [dm-devel] multipathd failback
> > > >
> > > > Hello.
> > > > My "multipathd" daemon does not FailBack It does not check the
> > > > availability of a failed path and of course does not
> > reinstate it My
> > > > configuration is as follows:
> > > > cat /etc/multipath.conf
> > > >
> > > > defaults {
> > > >
> > > >         failback        immediate
> > > > }
> > > > I am using the following packages:
> > > > multipath-tools-0.4.5-0.11
> > > > device-mapper-1.01.01-1.6
> > > > I have them installed on a SUSE LINUX Enterprise Server 9
> > > > (x86_64) sp-3 With kernel version: 2.6.5-7.244-smp Please help.
> > > > Thanks.
> > > >
> > > > ____________________________________________________________
> > > >
> > > > Cohen Yonatan   |  +972-9-9718607 (o)
> > > >
> > > > Software. Eng,  Storage group
> > > >
> > > > Voltaire - _The Grid Backbone_
> > > >
> > > > --
> > > > dm-devel mailing list
> > > > dm-devel@redhat.com
> > > > https://www.redhat.com/mailman/listinfo/dm-devel
> > > >
> > >
> > > --
> > > dm-devel mailing list
> > > dm-devel@redhat.com
> > > https://www.redhat.com/mailman/listinfo/dm-devel
> > >
> >
> > --
> > dm-devel mailing list
> > dm-devel@redhat.com
> > https://www.redhat.com/mailman/listinfo/dm-devel
> >
>
> -- 
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
>

AW: AW: AW: multipathd failback

[Herr, Manuel]

Multipath-tools are supported by Novell. So try to update
them with YOU (Yast online update).


> -----Ursprüngliche Nachricht-----
> Von: dm-devel-bounces@redhat.com 
> [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> Gesendet: Sonntag, 29. Oktober 2006 17:26
> An: device-mapper development
> Betreff: Re: AW: AW: [dm-devel] multipathd failback
> 
> Hello again.
> can you please tell me how to upgrade to 
> multipath-tools-0.4.5-0.20 i found multipath-0.4.5.tar.bz2 on 
> the site (http://christophe.varoqui.free.fr/multipath-tools/ 
> ) but i guess that multipath-tools-0.4.5-0.20 is after 
> applying some patches if so can you tell me which ones ?
> thanks.
> 
> Herr, Manuel wrote:
> >
> > I have no Problem with the failover also with SLES 9 
> 2.6.5-7.244-smp.
> > But i'm not working with the isci initiator.
> >
> > My Config:
> > defaults
> > {
> >         multipath_tool  "/sbin/multipath -v0"
> >         udev_dir        /dev
> >         polling_interval 5
> >         default_selector        "round-robin 0"
> >         default_getuid_callout  "/sbin/scsi_id -g -u -s /block/%n"
> >         default_prio_callout    "/bin/true"
> >         failback        immediate
> > }
> > There are newer Multipath tools available:
> > Im working with: multipath-tools-0.4.5-0.20 (Device Mapper 
> is same) I 
> > recommend to update them first. :)
> >
> > This one is talking about the same Problem you have.
> > http://www.querzone.de/wiki/Wiki.jsp?page=EMCClariion
> > I don't know if this error is clariion specific.
> >
> > Regards,
> > Manuel
> >
> > > -----Ursprüngliche Nachricht-----
> > > Von: dm-devel-bounces@redhat.com
> > > [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan Cohen
> > > Gesendet: Mittwoch, 25. Oktober 2006 09:22
> > > An: device-mapper development
> > > Betreff: Re: AW: [dm-devel] multipathd failback
> > >
> > > sorry but I am not sure what you mean.
> > > I am using an iscsi initiator (linux-iscsi rev 4.2) and 
> this is what 
> > > the multipathd daemon sees pepper:~ # multipath -l
> > > dm names   N
> > > dm table 3600c0ff00000000007c1d167985b4b06  N dm table
> > > 3600c0ff00000000007c1d167985b4b06  N dm status
> > > 3600c0ff00000000007c1d167985b4b06  N dm info
> > > 3600c0ff00000000007c1d167985b4b06  O
> > > 3600c0ff00000000007c1d167985b4b06
> > > [size=20 GB][features="0"][hwhandler="0"] \_ round-robin 
> 0 [enabled]  
> > > \_ 14:0:0:0 sda 8:0  [failed]  \_ round-robin 0 [active]
> > >   \_ 14:1:0:0 sdb 8:16 [active]
> > >
> > > sda and sdb are actually the same device discovered by 
> iscsi via 2 
> > > different paths.
> > > when sda failed multipathd identified the problem and diverted 
> > > traffic to sdb but after correcting the sda problem, 
> multipathd did 
> > > not become aware of this and of course when i failed sdb 
> it did not 
> > > failback to sda.
> > > i know that multipathd is suppose to poll for failed paths and 
> > > reinstate them when they become valid.
> > > but for some reason it does not.
> > >
> > >
> > > Herr, Manuel wrote:
> > > >
> > > > On which Hardware? (HBAs, SAN)?
> > > >
> > > > > -----Ursprüngliche Nachricht-----
> > > > > Von: dm-devel-bounces@redhat.com 
> > > > > [mailto:dm-devel-bounces@redhat.com] Im Auftrag von Yonathan 
> > > > > Cohen
> > > > > Gesendet: Mittwoch, 25. Oktober 2006 08:50
> > > > > An: dm-devel@redhat.com
> > > > > Betreff: [dm-devel] multipathd failback
> > > > >
> > > > > Hello.
> > > > > My "multipathd" daemon does not FailBack It does not 
> check the 
> > > > > availability of a failed path and of course does not
> > > reinstate it My
> > > > > configuration is as follows:
> > > > > cat /etc/multipath.conf
> > > > >
> > > > > defaults {
> > > > >
> > > > >         failback        immediate
> > > > > }
> > > > > I am using the following packages:
> > > > > multipath-tools-0.4.5-0.11
> > > > > device-mapper-1.01.01-1.6
> > > > > I have them installed on a SUSE LINUX Enterprise Server 9
> > > > > (x86_64) sp-3 With kernel version: 2.6.5-7.244-smp 
> Please help.
> > > > > Thanks.
> > > > >
> > > > > ____________________________________________________________
> > > > >
> > > > > Cohen Yonatan   |  +972-9-9718607 (o)
> > > > >
> > > > > Software. Eng,  Storage group
> > > > >
> > > > > Voltaire - _The Grid Backbone_
> > > > >
> > > > > --
> > > > > dm-devel mailing list
> > > > > dm-devel@redhat.com
> > > > > https://www.redhat.com/mailman/listinfo/dm-devel
> > > > >
> > > >
> > > > --
> > > > dm-devel mailing list
> > > > dm-devel@redhat.com
> > > > https://www.redhat.com/mailman/listinfo/dm-devel
> > > >
> > >
> > > --
> > > dm-devel mailing list
> > > dm-devel@redhat.com
> > > https://www.redhat.com/mailman/listinfo/dm-devel
> > >
> >
> > --
> > dm-devel mailing list
> > dm-devel@redhat.com
> > https://www.redhat.com/mailman/listinfo/dm-devel
> >
> 
> --
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
> 

multipath features

[Peter Koutoupis]

I cannot seem to find an answer for this no matter where I look, but if
I wanted to queue all IO if there was no path for a LIMITED time before
it eventually times out, does a feature exist?  Currently I am using "1
queue_if_no_path" but the last thing I want is for a path to be
unavailable and have it consume all host resources until the host cannot
handle it anymore.  Thanks in advance.

Regards,

Peter Koutoupis
Systems Engineer
Xyratex International, Inc.
1804 Centre Point Circle
Suite 112
Naperville, IL 60563 USA
(630)364-7656

Re: multipath features

[Eli Stair]

Check multipath.conf.annotated in the source.  This will retry n times 
before failing.

    no_path_retry           {n}

I have repeatable issues with setting this higher than about 3-5 
however, where IO queues (more like blocks) forever, even after failing 
the path back... requiring a reboot, and resulting in data corruption. YMMV.


/eli




Peter Koutoupis wrote:
> I cannot seem to find an answer for this no matter where I look, but if
> I wanted to queue all IO if there was no path for a LIMITED time before
> it eventually times out, does a feature exist?  Currently I am using "1
> queue_if_no_path" but the last thing I want is for a path to be
> unavailable and have it consume all host resources until the host cannot
> handle it anymore.  Thanks in advance.
> 
> Regards,
> 
> Peter Koutoupis
> Systems Engineer
> Xyratex International, Inc.
> 1804 Centre Point Circle
> Suite 112
> Naperville, IL 60563 USA
> (630)364-7656
> 
> --
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
> 

RE: multipath features

[Peter Koutoupis]

Thank you very much for your quick response.  I can give this a try and
tweak it as I go along.

Peter 

-----Original Message-----
From: dm-devel-bounces@redhat.com [mailto:dm-devel-bounces@redhat.com]
On Behalf Of Eli Stair
Sent: Wednesday, October 25, 2006 3:53 PM
To: device-mapper development
Subject: Re: [dm-devel] multipath features


Check multipath.conf.annotated in the source.  This will retry n times
before failing.

    no_path_retry           {n}

I have repeatable issues with setting this higher than about 3-5
however, where IO queues (more like blocks) forever, even after failing
the path back... requiring a reboot, and resulting in data corruption.
YMMV.


/eli




Peter Koutoupis wrote:
> I cannot seem to find an answer for this no matter where I look, but 
> if I wanted to queue all IO if there was no path for a LIMITED time 
> before it eventually times out, does a feature exist?  Currently I am 
> using "1 queue_if_no_path" but the last thing I want is for a path to 
> be unavailable and have it consume all host resources until the host 
> cannot handle it anymore.  Thanks in advance.
> 
> Regards,
> 
> Peter Koutoupis
> Systems Engineer
> Xyratex International, Inc.
> 1804 Centre Point Circle
> Suite 112
> Naperville, IL 60563 USA
> (630)364-7656
> 
> --
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
> 

--
dm-devel mailing list
dm-devel@redhat.com
https://www.redhat.com/mailman/listinfo/dm-devel