raid5f: data_chunk_idx uninitialized variable fix

Change-Id: I11f00e8249f3f64879e077266eabf037e5235a0f
Signed-off-by: Slawomir Ptak <slawomir.ptak@intel.com>
Reviewed-on: https://review.spdk.io/gerr

raid5f: data_chunk_idx uninitialized variable fix

Change-Id: I11f00e8249f3f64879e077266eabf037e5235a0f
Signed-off-by: Slawomir Ptak <slawomir.ptak@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24864
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>

show more ...

ut/raid5f: fix buf_md undefined behavior

Only calculate buf_md offset if metadata is enabled.

Fixes: #3501

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Ie917d33d71a2c9

ut/raid5f: fix buf_md undefined behavior

Only calculate buf_md offset if metadata is enabled.

Fixes: #3501

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Ie917d33d71a2c91a46c81205d03ea0caf89187cf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24669
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Michal Berger <michal.berger@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>

show more ...

bdev/raid1: Support resize when increasing the size of base bdevs

Implement the resize function for RAID1. raid1_resize() calculate the
new raid_bdev's block count and if it is different from the ol

bdev/raid1: Support resize when increasing the size of base bdevs

Implement the resize function for RAID1. raid1_resize() calculate the
new raid_bdev's block count and if it is different from the old block
count, call spdk_bdev_notify_blockcnt_change() with the new block count.

Add a simple functional test for this feature. The test is to create
a raid1 bdev with two null bdevs, resize one null bdev, check if the
raid1 bdev is not resize, resize another null bdev, check if the raid1
bdev is resized.

The commit is an overall copy/adaptation of the work of Shuhei Matsumoto
with raid0.

Change-Id: I0737ba3fe4e1260d35d51e7b022c9cfd1eb6db58
Signed-off-by: Loïc Yavercovski <loic.yavercovski@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22619
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <ben@nvidia.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>

show more ...

bdev/raid: add qos for raid process

Change-Id: I5383d8658c59760ccaaec163e25d5e6d0cd8e1d0
Signed-off-by: xupeng-mingtu <jingmamour@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/

bdev/raid: add qos for raid process

Change-Id: I5383d8658c59760ccaaec163e25d5e6d0cd8e1d0
Signed-off-by: xupeng-mingtu <jingmamour@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21732
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Community-CI: Mellanox Build Bot

show more ...

raid1: handle read errors

If a read fails, try reading from other base bdevs and if that succeeds,
write to the bdev that returned the read error.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewic

raid1: handle read errors

If a read fails, try reading from other base bdevs and if that succeeds,
write to the bdev that returned the read error.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Iffca8921d0177e16f1ac3d661b8b6131f3dbd39f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22974
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>

show more ...

raid1: handle write errors

Fail base bdev on write error. If write to at least one base bdev
succeeds, complete the raid I/O as successful.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel

raid1: handle write errors

Fail base bdev on write error. If write to at least one base bdev
succeeds, complete the raid I/O as successful.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I0315f98937a548648f819bf7e8c5707d7adec991
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22846
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>

show more ...

raid: add a default completion status to raid_bdev_io

As base I/Os complete, the final raid I/O completion status will change
only if the base I/O status is different than the default. So if the
def

raid: add a default completion status to raid_bdev_io

As base I/Os complete, the final raid I/O completion status will change
only if the base I/O status is different than the default. So if the
default is "FAILED" and a base I/O completes with "SUCCESS", it will be
set to "SUCCESS" and won't change if subsequent I/Os complete with
"FAILED".

This will be used by raid1 writes, where the completion status should be
successful even if some base I/Os failed.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Idc800baacb9efc36207f77c31a01ec5a2867ccdd
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22845
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>

show more ...

raid: utility function to get a base bdev in io context

This will be used to get a pointer to struct raid_base_bdev_info from
I/O completion context when we only have the spdk_bdev.

Signed-off-by:

raid: utility function to get a base bdev in io context

This will be used to get a pointer to struct raid_base_bdev_info from
I/O completion context when we only have the spdk_bdev.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I4e1e87ed31c9812859f0a0e1444a3a678682db62
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22843
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>

show more ...

raid: write sb earlier when removing a base bdev

Update the superblock as soon as the raid bdev is quiesced, then
continue with removing the base bdev.

The condition in _raid_bdev_write_superblock(

raid: write sb earlier when removing a base bdev

Update the superblock as soon as the raid bdev is quiesced, then
continue with removing the base bdev.

The condition in _raid_bdev_write_superblock() has to be changed because
base_info->desc is not NULL now, only remove_scheduled is set at this
stage of removing the base bdev.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I6a55d0ed5d0c1e3fc38825ac23d1556d42d2e801
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22842
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot

show more ...

raid: move the raid I/O wrappers back to the header

Instead of having these in bdev_raid.c, just make
raid_bdev_remap_dix_reftag() public. This allows to have the unit tests
a little simpler and bet

raid: move the raid I/O wrappers back to the header

Instead of having these in bdev_raid.c, just make
raid_bdev_remap_dix_reftag() public. This allows to have the unit tests
a little simpler and better reflecting the real behavior.

This effectively reverts 2c9dfc37c ("module/raid: Move the RAID I/O
wrappers").

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I92de84d7cbc233f5d744aedf6e77d0728ecdaa72
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22828
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>

show more ...

ut/raid: move out raid0-specific tests to separate file

This was a leftover from the time when raid0 was the only supported
level and was implemented directly in bdev_raid.c.

Signed-off-by: Artur P

ut/raid: move out raid0-specific tests to separate file

This was a leftover from the time when raid0 was the only supported
level and was implemented directly in bdev_raid.c.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I416bd49843b04bf5c0c5fdc43e4aaf8566885630
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22820
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>

show more ...

ut/raid: make the common ut functions public

If a file including common.c doesn't use some of those functions it
would cause a "defined but not used" warning.

Signed-off-by: Artur Paszkiewicz <artu

ut/raid: make the common ut functions public

If a file including common.c doesn't use some of those functions it
would cause a "defined but not used" warning.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I1bdd1375babd1b400e7ba03de5a2b1a5f0e26f15
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22775
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <jim.harris@samsung.com>

show more ...

ut/raid: remove unused globals and functions

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Iafe94381a0b72c7b5c9c056d6c2798877bacdf19
Reviewed-on: https://review.spdk.io/g

ut/raid: remove unused globals and functions

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Iafe94381a0b72c7b5c9c056d6c2798877bacdf19
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22774
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Mateusz Kozlowski <mateusz.kozlowski@solidigm.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>

show more ...

raid: fix race between process starting and removing a base bdev

Abort starting the process if a base bdev was removed in the meantime.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com

raid: fix race between process starting and removing a base bdev

Abort starting the process if a base bdev was removed in the meantime.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I45345322c6e21837d257cbe0598c5eb19f3f41be
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22773
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Mateusz Kozlowski <mateusz.kozlowski@solidigm.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <jim.harris@samsung.com>

show more ...

raid: validate base bdev slot number when parsing superblock

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Ic2f9f6dd3367f7b0a15715e401937daa43c00796
Reviewed-on: https://

raid: validate base bdev slot number when parsing superblock

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Ic2f9f6dd3367f7b0a15715e401937daa43c00796
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22488
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>

show more ...

ut/raid: fix getting process thread

Use the new_thread_fn callback of spdk_thread_lib_init() to reliably get
the process thread.

The tests_single_run workaround can be removed now.

Signed-off-by:

ut/raid: fix getting process thread

Use the new_thread_fn callback of spdk_thread_lib_init() to reliably get
the process thread.

The tests_single_run workaround can be removed now.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Id03671d411d89db746411bbffecb836a195f6b5d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21729
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Mateusz Kozlowski <mateusz.kozlowski@solidigm.com>

show more ...

ut/raid: don't use ut_multithread.c

test_raid_process() abuses this framework because it needs to test a
thread created during the test. Initialize the thread lib and set up the
app thread manually

ut/raid: don't use ut_multithread.c

test_raid_process() abuses this framework because it needs to test a
thread created during the test. Initialize the thread lib and set up the
app thread manually instead.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I5631fcbbc84a8dfc8a033f4ea8bb780f004d0957
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21728
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>

show more ...

raid: move blocklen_shift to r5f_info

This is not generally useful now but there is one case in raid5f where
it is used to avoid a division, so move it there.

Signed-off-by: Artur Paszkiewicz <artu

raid: move blocklen_shift to r5f_info

This is not generally useful now but there is one case in raid5f where
it is used to avoid a division, so move it there.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I2662160e72a71b2bae499655fe4fb7d236fb766f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21684
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Mateusz Kozlowski <mateusz.kozlowski@solidigm.com>
Community-CI: Mellanox Build Bot

show more ...

raid5f: interleaved md support

Also enable it in the unit tests.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I2ee7aad32f79af7e8434771ada69308998ad152d
Reviewed-on: htt

raid5f: interleaved md support

Also enable it in the unit tests.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I2ee7aad32f79af7e8434771ada69308998ad152d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21683
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Mateusz Kozlowski <mateusz.kozlowski@solidigm.com>
Community-CI: Mellanox Build Bot

show more ...

raid: refactor to use write_named_uuid function

Use spdk_json_write_named_uuid() in
raid_bdev_write_*_json() functions

Change-Id: I589815c4328a39d7d3da99051671a8e0a497397a
Signed-off-by: Eugene Kob

raid: refactor to use write_named_uuid function

Use spdk_json_write_named_uuid() in
raid_bdev_write_*_json() functions

Change-Id: I589815c4328a39d7d3da99051671a8e0a497397a
Signed-off-by: Eugene Kobyak <eugene.kobyak@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22880
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>

show more ...

ut/raid: allow testing interleaved md

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: If0dea0014723017d55181ec673903d097a01b427
Reviewed-on: https://review.spdk.io/gerrit/c

ut/raid: allow testing interleaved md

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: If0dea0014723017d55181ec673903d097a01b427
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21682
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>

show more ...

ut/raid: refactor setting test params

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Ib06297159ebcb354da5198b9b0c4eeef087cde1c
Reviewed-on: https://review.spdk.io/gerrit/c

ut/raid: refactor setting test params

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Ib06297159ebcb354da5198b9b0c4eeef087cde1c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21681
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Community-CI: Mellanox Build Bot

show more ...

raid: superblock interleaved md support

Correctly write and read superblock from bdevs with interleaved
metadata. For writes, use a second buffer and copy the sb contents there
before writing, leavi

raid: superblock interleaved md support

Correctly write and read superblock from bdevs with interleaved
metadata. For writes, use a second buffer and copy the sb contents there
before writing, leaving "gaps" for md. For reads, rewrite the buffer,
removing the md, before parsing the superblock.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Id133bb34abecdc82d89604abfa3e3ba7b777961f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21680
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot

show more ...

raid: add fields for superblock io buf

For now this just points to the superblock buffer but will be different
for interleaved md.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Cha

raid: add fields for superblock io buf

For now this just points to the superblock buffer but will be different
for interleaved md.

Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I81805b94d79579d7ad466c3358fe334ebe987497
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/22818
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Jim Harris <jim.harris@samsung.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot

show more ...

module/raid: DIX support for RAID 0

Added an ability for the application to use DIX protection
(separate metadata) with the RAID bdev, with RAID level 0.

In order to handle the protection informati

module/raid: DIX support for RAID 0

Added an ability for the application to use DIX protection
(separate metadata) with the RAID bdev, with RAID level 0.

In order to handle the protection information correctly for
RAID bdevs, the patch introduces Reference Tag remapping between
the RAID bdev and base bdevs on read and write paths.

Change-Id: I4056a3e4410a4df3282b993b655f6e6e2715e5a9
Signed-off-by: Slawomir Ptak <slawomir.ptak@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/21618
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <jim.harris@samsung.com>

show more ...