Re: [dm-devel] BFQ + dm-mpath

> Il giorno 07 set 2017, alle ore 17:52, Mike Snitzer ha > scritto: > > On Tue, Sep 05 2017 at 10:15am -0400, > Bart Van Assche wrote: > >> On Tue, 2017-09-05 at 09:56 +0200, Paolo Valente wrote: >>> Ok, my suspects seem confirmed: the path

Re: [dm-devel] [PATCH 1/4] multipathd: don't flood system with sd_notify calls

On Tue, Aug 29, 2017 at 12:05:33AM +0200, Martin Wilck wrote: > DAEMON_RUNNING is only used by checkerloop to indicate that > path checkers are running. checkerloop switches back and forth > between DAEMON_IDLE and DAEMON_RUNNING in every iteration, i.e. > it performs two status changes per second

Re: [dm-devel] [PATCH 4/4] multipath: delegate dangerous commands to multipathd

On Thu, 2017-09-07 at 16:57 -0500, Benjamin Marzinski wrote: > On Tue, Aug 29, 2017 at 12:05:36AM +0200, Martin Wilck wrote: > > Some multipath commands are dangerous to run while multipathd is > > running. > > For example, "multipath -r" may apply a modified configuration to > > the kernel, > >

Re: [dm-devel] [PATCH] dm mpath: switch IO scheduler of underlying paths to "none" [was: Re: BFQ + dm-mpath]

On 09/08/2017 10:41 AM, Mike Snitzer wrote: > On Fri, Sep 08 2017 at 5:13P -0400, > Paolo Valente wrote: > >> >>> Il giorno 07 set 2017, alle ore 17:52, Mike Snitzer ha >>> scritto: >>> >>> On Tue, Sep 05 2017 at 10:15am -0400, >>> Bart Van Assche

[dm-devel] [PATCH 5/5] mpathpersist: add support for prkeys file

When the reservation_key is set to "file", the reservation key needs to be added to the prkeys file for multipathd to be able to register new paths as they are added to the device. This patch adds support to the mpathpersist command to message multipathd when a key is registered or unregistered

[dm-devel] [PATCH 2/5] libmultipath: change reservation_key to a uint64_t

The reservation key is currently being stored as any array of 8 unsigned chars. This is exactly the same in-memory representation as a big endian 64 bit integer. However, the code for dealing with a big endian 64 bit integer is much simpler, so switch to use that instead. Signed-off-by: Benjamin

[dm-devel] [PATCH 1/5] libmultipath: pull functions into util.c

This patch just pulls safe_write out of rbd. and the persistent reservation key parsing code out of dict.c and puts them in util.c, so that other functions can make use of them. Signed-off-by: Benjamin Marzinski --- libmultipath/checkers/rbd.c | 16 +---

Re: [dm-devel] dm mpath: switch IO scheduler of underlying paths to "none" [was: Re: BFQ + dm-mpath]

On Fri, Sep 08 2017 at 12:48pm -0400, Jens Axboe wrote: > On 09/08/2017 10:41 AM, Mike Snitzer wrote: > > On Fri, Sep 08 2017 at 5:13P -0400, > > Paolo Valente wrote: > > > >> > >>> Il giorno 07 set 2017, alle ore 17:52, Mike Snitzer

[dm-devel] [PATCH 0/5] multipath: alternative reservation_key method

The scsi persistent reservation API doesn't force devices to implement any method to display the mapping from a reservation key to an I_T Nexus (the READ_FULL_STATUS action is an optional later addition, and a number of devices don't support it). To allow multipathd to determine the correct

[dm-devel] [PATCH 4/5] multipath: add alternate reservation_key method

The scsi persistent reservation API doesn't force devices to implement any method to display the mapping from a reservation key to an I_T Nexus (the READ_FULL_STATUS action is an optional later addition, and a number of devices don't support it). To allow multipathd to determine the correct

[dm-devel] [PATCH 3/5] libmpathpersist: fix update_prflag code

There are multiple problems with the prflag code. First, it doesn't do anything useful at all currently. update_prflags is called with "set" and "unset" instead of "setprstatus" and "unsetprstatus", so it doesn't actually enable persistent reservation tracking in multipathd when a key is

[dm-devel] [PATCH] dm mpath: switch IO scheduler of underlying paths to "none" [was: Re: BFQ + dm-mpath]

On Fri, Sep 08 2017 at 5:13P -0400, Paolo Valente wrote: > > > Il giorno 07 set 2017, alle ore 17:52, Mike Snitzer ha > > scritto: > > > > On Tue, Sep 05 2017 at 10:15am -0400, > > Bart Van Assche wrote: > > > >> On

Re: [dm-devel] [PATCH 1/5] libmultipath: pull functions into util.c

On Fri, 2017-09-08 at 13:45 -0500, Benjamin Marzinski wrote: > This patch just pulls safe_write out of rbd. and the persistent > reservation key parsing code out of dict.c and puts them in util.c, > so that other functions can make use of them. > > Signed-off-by: Benjamin Marzinski

Re: [dm-devel] [PATCH] block: directly insert blk-mq request from blk_insert_cloned_request()

On 09/08/2017 03:42 PM, Mike Snitzer wrote: > diff --git a/block/blk-core.c b/block/blk-core.c > index d709c0e..7a06b2b 100644 > --- a/block/blk-core.c > +++ b/block/blk-core.c > @@ -2342,7 +2342,7 @@ blk_status_t blk_insert_cloned_request(struct > request_queue *q, struct request * > if

Re: [dm-devel] dm mpath: switch IO scheduler of underlying paths to "none" [was: Re: BFQ + dm-mpath]

On 09/08/2017 01:58 PM, Mike Snitzer wrote: > On Fri, Sep 08 2017 at 1:07pm -0400, > Mike Snitzer wrote: > >> On Fri, Sep 08 2017 at 12:48pm -0400, >> Jens Axboe wrote: >> Please see the following untested patch. All testing/review/comments/acks

Re: [dm-devel] [PATCH 2/5] libmultipath: change reservation_key to a uint64_t

On Fri, 2017-09-08 at 13:45 -0500, Benjamin Marzinski wrote: > The reservation key is currently being stored as any array of 8 > unsigned > chars. This is exactly the same in-memory representation as a big > endian 64 bit integer. However, the code for dealing with a big > endian > 64 bit integer

Re: [dm-devel] [PATCH 3/5] libmpathpersist: fix update_prflag code

On Fri, 2017-09-08 at 13:45 -0500, Benjamin Marzinski wrote: > There are multiple problems with the prflag code. First, it doesn't > do > anything useful at all currently. update_prflags is called with "set" > and "unset" instead of "setprstatus" and "unsetprstatus", so it > doesn't > actually

Re: [dm-devel] [PATCH 5/5] mpathpersist: add support for prkeys file

On Fri, 2017-09-08 at 13:45 -0500, Benjamin Marzinski wrote: > When the reservation_key is set to "file", the reservation key needs > to > be added to the prkeys file for multipathd to be able to register new > paths as they are added to the device. This patch adds support to > the > mpathpersist

Re: [dm-devel] [PATCH 4/5] multipath: add alternate reservation_key method

On Fri, 2017-09-08 at 13:45 -0500, Benjamin Marzinski wrote: > The scsi persistent reservation API doesn't force devices to > implement > any method to display the mapping from a reservation key to an I_T > Nexus > (the READ_FULL_STATUS action is an optional later addition, and a > number > of

[dm-devel] [PATCH] block: directly insert blk-mq request from blk_insert_cloned_request()

On Fri, Sep 08 2017 at 4:28P -0400, Jens Axboe wrote: > On 09/08/2017 01:58 PM, Mike Snitzer wrote: > > On Fri, Sep 08 2017 at 1:07pm -0400, > > Mike Snitzer wrote: > > > >> On Fri, Sep 08 2017 at 12:48pm -0400, > >> Jens Axboe wrote: >

Re: [dm-devel] dm mpath: switch IO scheduler of underlying paths to "none" [was: Re: BFQ + dm-mpath]

On Fri, Sep 08 2017 at 1:07pm -0400, Mike Snitzer wrote: > On Fri, Sep 08 2017 at 12:48pm -0400, > Jens Axboe wrote: > > > > Please see the following untested patch. All > > > testing/review/comments/acks appreciated. > > > > > > I elected to use

Re: [dm-devel] block: directly insert blk-mq request from blk_insert_cloned_request()

On Fri, Sep 08 2017 at 5:50pm -0400, Jens Axboe wrote: > On 09/08/2017 03:42 PM, Mike Snitzer wrote: > > diff --git a/block/blk-core.c b/block/blk-core.c > > index d709c0e..7a06b2b 100644 > > --- a/block/blk-core.c > > +++ b/block/blk-core.c > > @@ -2342,7 +2342,7 @@

Re: [dm-devel] [PATCH 2/5] libmultipath: change reservation_key to a uint64_t

On Fri, Sep 08, 2017 at 11:09:17PM +0200, Martin Wilck wrote: > On Fri, 2017-09-08 at 13:45 -0500, Benjamin Marzinski wrote: > > The reservation key is currently being stored as any array of 8 > > unsigned > > chars. This is exactly the same in-memory representation as a big > > endian 64 bit

Re: [dm-devel] [PATCH 4/5] multipath: add alternate reservation_key method

On Fri, Sep 08, 2017 at 11:34:48PM +0200, Martin Wilck wrote: > On Fri, 2017-09-08 at 13:45 -0500, Benjamin Marzinski wrote: > > The scsi persistent reservation API doesn't force devices to > > implement > > any method to display the mapping from a reservation key to an I_T > > Nexus > > (the