[PATCH] scsi: fix race between simultaneous decrements of ->host_failed

async_sas_ata_eh(), which will call scsi_eh_finish_cmd() in some case, would be performed simultaneously in sas_ata_strategy_handler(). In this case, ->host_failed may be decreased simultaneously in scsi_eh_finish_cmd() on different CPUs, and become abnormal. It will lead to permanently inequal

Re: [PATCH v3] ibmvscsis: Initial commit of IBM VSCSI Tgt Driver

Hi Bryant, On Fri, 2016-05-27 at 09:32 -0500, Bryant G. Ly wrote > diff --git a/drivers/scsi/ibmvscsi/ibmvscsi_tgt.c > b/drivers/scsi/ibmvscsi/ibmvscsi_tgt.c > new file mode 100644 > index 000..292d129 > --- /dev/null > +++ b/drivers/scsi/ibmvscsi/ibmvscsi_tgt.c > + > +static struct

[GIT PULL] target updates for v4.7-rc1

Hi Linus, Here are the outstanding target pending updates for v4.7-rc1. Please go ahead and pull from: git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git for-next The highlights this round include: - Allow external PR/ALUA metadata path be defined at runtime via top

Re: [PATCH 2/2] mpt3sas - avoid mpt3sas_transport_port_add NULL parent_dev

Hi, This patch looks good. Please consider this patch as Ack-by: Sreekanth Reddy Thanks, Sreekanth On Thu, May 26, 2016 at 12:44 AM, Joe Lawrence wrote: > If _scsih_sas_host_add's call to mpt3sas_config_get_sas_iounit_pg0 > fails,

Re: [PATCH 1/2] mpt3sas - set num_phys after allocating phy[] space

Hi, This patch looks good. Please consider this patch as Ack-by: Sreekanth Reddy Thanks, Sreekanth On Thu, May 26, 2016 at 12:44 AM, Joe Lawrence wrote: > In _scsih_sas_host_add, the number of HBA phys are determined and then > later

Re: [PATCH 3/5] target: call queue reset if supported

On Wed, May 25, 2016 at 02:55:01AM -0500, mchri...@redhat.com wrote: > From: Mike Christie > > Instead of waiting for commands, map the lun reset operation > to a queue reset. > > We do not check the result of blk_reset_queue because if > it works then we need to wait for

Re: [PATCH 4/5] scsi: add new async device reset support

Adding Hannes to the Cc list as he's been looking into EH improvements in this area. On Wed, May 25, 2016 at 02:55:02AM -0500, mchri...@redhat.com wrote: > From: Mike Christie > > Currently, if the SCSI eh runs then before we do a LUN_RESET > we stop the host. This patch

Re: bio-based DM multipath is back from the dead [was: Re: Notes from the four separate IO track sessions at LSF/MM]

On 05/26/2016 04:38 AM, Mike Snitzer wrote: On Thu, Apr 28 2016 at 11:40am -0400, James Bottomley wrote: On Thu, 2016-04-28 at 08:11 -0400, Mike Snitzer wrote: Full disclosure: I'll be looking at reinstating bio-based DM multipath to regain efficiencies

Re: bio-based DM multipath is back from the dead [was: Re: Notes from the four separate IO track sessions at LSF/MM]

On Fri, May 27 2016 at 4:39am -0400, Hannes Reinecke wrote: > On 05/26/2016 04:38 AM, Mike Snitzer wrote: > >On Thu, Apr 28 2016 at 11:40am -0400, > >James Bottomley wrote: > > > >>On Thu, 2016-04-28 at 08:11 -0400, Mike Snitzer wrote: >

[PATCH v3] ibmvscsis: Initial commit of IBM VSCSI Tgt Driver

Version 1: This initial commit contains WIP of the IBM VSCSI Target Fabric Module. It currently supports read/writes, and I have tested the ability to create a file backstore with the driver, install RHEL, and then boot up the partition via filio backstore through the driver. This driver is a

Re: [PATCH 4/5] scsi: add new async device reset support

On 05/27/2016 10:23 AM, Christoph Hellwig wrote: Adding Hannes to the Cc list as he's been looking into EH improvements in this area. On Wed, May 25, 2016 at 02:55:02AM -0500, mchri...@redhat.com wrote: From: Mike Christie Currently, if the SCSI eh runs then before we do

Re: iscsi fails to attach to targets with kernel 4.4.0

I'm facing the same problem, attaching additional log (maybe it helps) May 27 07:47:05 oldcompute02 kernel: [ 1168.239065] [ cut here ] May 27 07:47:05 oldcompute02 kernel: [ 1168.239077] WARNING: CPU: 24 PID: 12116 at /build/linux-lts-xenial-7RlTta/linux-lts-

Re: BLKZEROOUT not zeroing md dev on VMDK

There seems to be some sort of race condition between blkdev_issue_zeroout() and the scsi disk driver (disabling write same after an illegal request). On my UAS drive, sometimes `blkdiscard -z /dev/sdX` will return right away, even though if I then check `write_same_max_bytes` it has turned 0.

Re: bio-based DM multipath is back from the dead [was: Re: Notes from the four separate IO track sessions at LSF/MM]

On 05/27/2016 04:44 PM, Mike Snitzer wrote: On Fri, May 27 2016 at 4:39am -0400, Hannes Reinecke wrote: [ .. ] No, the real issue is load-balancing. If you have several paths you have to schedule I/O across all paths, _and_ you should be feeding these paths efficiently.

Re: bio-based DM multipath is back from the dead [was: Re: Notes from the four separate IO track sessions at LSF/MM]

On Fri, May 27 2016 at 11:42am -0400, Hannes Reinecke wrote: > On 05/27/2016 04:44 PM, Mike Snitzer wrote: > >On Fri, May 27 2016 at 4:39am -0400, > >Hannes Reinecke wrote: > > > [ .. ] > >>No, the real issue is load-balancing. > >>If you have several paths you have