[dm-devel] [PATCH 17/18] multipath-tools: add HPE StoreVirtual P4000 family to hwtable

No official documentation. Based on field-tested configuration: https://www.citrix.com/blogs/2013/10/02/hp-p4000-multipath-config-file/ Cc: Christophe Varoqui Cc: device-mapper development Signed-off-by: Xose Vazquez Perez

[dm-devel] [PATCH 01/18] multipath-tools: add KOVE/XPD to hwtable

Info provided directly by the manufacturer - http://kove.net/xpd : .vendor= "KOVE", .product = "XPD", .features = DEFAULT_FEATURES, .hwhandler = DEFAULT_HWHANDLER, .selector = "round-robin 0", .pgpolicy = MULTIBUS, .pgfailback= -FAILBACK_IMMEDIATE, .rr_weight

[dm-devel] [PATCH 03/18] multipath-tools: reorganize NetApp devices

Cc: Martin George Cc: Sean Stewart Cc: Christophe Varoqui Cc: device-mapper development Signed-off-by: Xose Vazquez Perez --- libmultipath/hwtable.c | 21

[dm-devel] [PATCH 06/18] multipath-tools: add IBM/FlashSystem to hwtable

Based on documentation of the manufacturer: - FlashSystem 820 and FlashSystem 900: http://www.redbooks.ibm.com/redbooks/pdfs/sg248271.pdf vendor "IBM" product "FlashSystem-9840" path_selector "queue-length 0"# Linux 6.2, if available

[dm-devel] [PATCH 10/18] multipath-tools: add Nexsan E-Series and SATABeast/SATABoy to hwtable

Based on documentation provided by the manufacturer: https://drive.google.com/file/d/0B_B6YmEmO7cDeGRXeG85MXFVMEU Redhat 6: vendor "NEXSAN " product "NXS-B0.*|SATAB.*" getuid_callout "/lib/udev/scsi_id --whitelisted --device=/dev/%n" path_grouping_policy

[dm-devel] [PATCH 04/18] multipath-tools: add NetApp/SolidFir to hwtable

Based on info provided directly by the manufacturer: http://www.solidfire.com/ http://www.netapp.com/us/products/storage-systems/solidfire/ Redhat 7+: vendor "SolidFir" product "SSD SAN" path_grouping_policy multibus path_checker tur hardware_handler "0" failback immediate rr_weight uniform

[dm-devel] [PATCH 14/18] multipath-tools: change path grouping policy for EUROLOGC/FC2502

No prio defined and .pgpolicy=GROUP_BY_PRIO are an impossible combination. Cc: Christophe Varoqui Cc: device-mapper development Signed-off-by: Xose Vazquez Perez --- libmultipath/hwtable.c | 1 + 1 file changed, 1

[dm-devel] [PATCH 07/18] multipath-tools: add EMC/Celerra to hwtable

Based on documentation of the manufacturer: http://www.emc.com/collateral/TechnicalDocument/docu5128.pdf vendor "EMC" product "Celerra" path_grouping_policy "multibus" path_checker "tur" no_path_retry "30" Cc: Edward Goggin Cc: Christophe Varoqui

Re: [dm-devel] dm-flakey NOT to return -EIO on READ?

Mike, > This fix should resolve the problem, I'll be staging it to go upstream > during the 4.8-rc cycle (Akira, please test to verify your test fails as > expected now): I tested with the patch and it's now ok. Akira On 2016/07/30 2:30, Mike Snitzer wrote: > On Fri, Jul 29 2016 at 10:35am

[dm-devel] [PATCH 16/18] multipath-tools: Use ALUA for HP 3PAR

Original patch from Hannes Reinecke : .vendor= "3PARdata", .product = "VV", .features = DEFAULT_FEATURES, - .hwhandler = DEFAULT_HWHANDLER, - .pgpolicy = MULTIBUS, -

[dm-devel] [PATCH 09/18] multipath-tools: add VIOLIN/ "SAN ARRAY" and "SAN ARRAY ALUA" to hwtable

Based on documentation provided by the manufacturer: https://drive.google.com/open?id=0B_B6YmEmO7cDQlMzc1BsaUxZRVU * For "SAN ARRAY ALUA": - Red Hat Enterprise Linux 6.x: vendor "VIOLIN" product "SAN ARRAY ALUA" path_grouping_policy group_by_prio getuid_callout "/lib/udev/scsi_id --whitelisted

[dm-devel] [PATCH 13/18] multipath-tools: delete nearly all attribute of last member(NULL) in hwtable

They are "useless". Leave only mandatory attributes. Cc: Christophe Varoqui Cc: device-mapper development Signed-off-by: Xose Vazquez Perez --- libmultipath/hwtable.c | 23 --- 1 file changed, 23

[dm-devel] [PATCH 15/18] multipath-tools: add official name to Huawei devices

from http://www.t10.org/ftp/t10/vendorid.txt Its official name is: "HUASY" Just in case. Cc: Christophe Varoqui Cc: device-mapper development Signed-off-by: Xose Vazquez Perez --- libmultipath/hwtable.c | 2 +- 1

[dm-devel] [PATCH 02/18] multipath-tools: Remove ONTAP IBM Nseries from hwtable

Originally from Martin George He wrote: "Even earlier, the NetApp IBM Nseries product line never used a VID/PID of "IBM" & "Nseries" respectively. Instead, it always used the same VID/PID of "NETAPP" & "LUN" itself, similar to the ONTAP product line. So this piece of code was

[dm-devel] [PATCH 08/18] multipath-tools: add FUJITSU/ETERNUS 2000/4000/8000 to hwtable

Based on documentation provided by the manufacturer: http://storage-system.fujitsu.com/global/manual/diskarray/pdf/p3am-3192-en.pdf For SUSE Linux Enterprise Server 11 vendor "FUJITSU" product "E[248]000" prioalua path_grouping_policy

Re: [dm-devel] dm-flakey NOT to return -EIO on READ?

I just looked at the patch. (not tested yet) I think the else part in the endio isn't necessary. > + else > + return -EIO; Akira On 2016/07/30 2:30, Mike Snitzer wrote: > On Fri, Jul 29 2016 at 10:35am -0400, > Mike Snitzer wrote: > >> On

Re: [dm-devel] dm-flakey NOT to return -EIO on READ?

Thanks Mike for fixing. This was my first attempt to fix something in kernel so I wasn't sure about the patch itself. - Lukas On Fri, Jul 29, 2016 at 7:30 PM, Mike Snitzer wrote: > On Fri, Jul 29 2016 at 10:35am -0400, > Mike Snitzer wrote: > > > On

Re: [dm-devel] dm-flakey NOT to return -EIO on READ?

On Fri, Jul 29 2016 at 10:35am -0400, Mike Snitzer wrote: > On Fri, Jul 29 2016 at 10:31am -0400, > Lukas Herbolt wrote: > > > - http://people.redhat.com/~lherbolt/dm-flakey/v4.7-dm_flakey.tar.gz > > > > Lukas > > Please post an incremental patch

Re: [dm-devel] [Patch] multipath-tools: Check if multipathd is running or not and print a warning

On Thu, Jul 28, 2016 at 04:35:21PM +0200, Hannes Reinecke wrote: > On 07/28/2016 01:48 PM, Milan P. Gandhi wrote: > > Hello, > > > > With this patch dm-multipath commands e.g. multipath -v2, > > multipath -ll etc. now checks if there are multipath > > device maps created, and multipathd service

Re: [dm-devel] dm-flakey NOT to return -EIO on READ?

On Fri, Jul 29 2016 at 10:31am -0400, Lukas Herbolt wrote: > - http://people.redhat.com/~lherbolt/dm-flakey/v4.7-dm_flakey.tar.gz > > Lukas Please post an incremental patch relative to 4.7 or latest Linus kernel. Don't make people suffer with tarballs of whatever you've

Re: [dm-devel] dm-flakey NOT to return -EIO on READ?

- http://people.redhat.com/~lherbolt/dm-flakey/v4.7-dm_flakey.tar.gz Lukas On Fri, Jul 29, 2016 at 8:32 AM, Akira Hayakawa wrote: > Hi Lukas, > > > I have patch ready, would you be able to test it before posting it. > > > > Let me know if I should build the kernel for you

Re: [dm-devel] bcache super block corruption with non 4k pages

On 28.07.2016 07:55, Kent Overstreet wrote: > On Wed, Jul 27, 2016 at 05:16:36PM +0200, Stefan Bader wrote: >> So here is another attempt which does half the proposed changes. And before >> you >> point out that it looks still ugly, let me explain some reasons. The goal >> for me >> would be to

Re: [dm-devel] To add, or not to add, a bio REQ_ROTATIONAL flag

On 29/07/16 01:50, Eric Wheeler wrote: > Hello all, > > With the many SSD caching layers being developed (bcache, dm-cache, > dm-writeboost, etc), how could we flag a bio from userspace to indicate > whether the bio is preferred to hit spinning disks instead of an SSD? > > Unnecessary

[dm-devel] To add, or not to add, a bio REQ_ROTATIONAL flag

Hello all, With the many SSD caching layers being developed (bcache, dm-cache, dm-writeboost, etc), how could we flag a bio from userspace to indicate whether the bio is preferred to hit spinning disks instead of an SSD? Unnecessary promotions, evections, and writeback increase the write

Re: [dm-devel] dm-flakey NOT to return -EIO on READ?

Hi Lukas, > I have patch ready, would you be able to test it before posting it. > > Let me know if I should build the kernel for you or just share the source > with you. OK. Please share the git tree and specify the branch to test. Akira On 2016/07/29 15:25, Lukas Herbolt wrote: > Hi Akira, >

Re: [dm-devel] dm-mq and end_clone_request()

On 07/28/2016 05:40 PM, Mike Snitzer wrote: > On Thu, Jul 28 2016 at 11:23am -0400, > Bart Van Assche wrote: > >> On 07/28/2016 06:33 AM, Mike Snitzer wrote: [ .. ] > > Reality is I just need a testbed to reproduce. This back and forth > isn't really helping us