Commit Graph

9 Commits

Author SHA1 Message Date
Kamil Godzwon
14c0f94c88 test/fio: supress fio output files
verify.state files are not very useful because
we fail the tests at any first failure.
If there was something wrong with IO verification
then autotest.sh would fail.

Fio files with metrics output (IOPS, BW, latency, etc)
are also not very useful as per-patch tests are not
focused on benchmarking.

Fixes #2546

Signed-off-by: Kamil Godzwon <kamilx.godzwon@intel.com>
Change-Id: I33fbe2fb0749d840f08ffe0d606d206268140991
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13019
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2022-06-23 07:43:36 +00:00
Pawel Kaminski
766b1f62d9 test/vhost: test multiple connections to a single vhost device
Two fio instancess will try to do simultaneous I/O
to a single vhost block device.

The test uses default_initiator.job as a fio config,
which apparently wasn't used anywhere and had to be
slightly adjusted to work. Specificaly, we had to
specify an empty job in the config file, as specifying
it from the command line wouldn't make it inherit
any options from the [global] section in the file.

Change-Id: I2c2a96a709c567f5c910715a5b3d85a4e28bcb97
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/419066
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2019-01-28 17:00:03 +00:00
Chen Wang
b1a8455ac8 autotest: vhost_fio_test (porting from nightly to autotest)
Add vhost-scsi and vhost-blk fio test cases which used more cores
and controllers in nightly

Change-Id: I51b47f6272c1b29dff890384087014627238dc68
Signed-off-by: Chen Wang <chenx.wang@intel.com>
Reviewed-on: https://review.gerrithub.io/389072
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-01-25 14:42:42 -05:00
Seth Howell
52bd445367 fio_jobs: add fsync_on_close to fio args
This is to help facilitate the update of the fio_ubuntu binary to fio-3.3

Change-Id: I4c896dc60255f821a5cf66af818396f210304f07
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/395394
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-01-19 15:37:08 -05:00
Karol Latecki
8175e30229 test/vhost: Remove norandommap from vhost initiator tests
Removing norandommap as it is not correct to use with
verify-enabled tests

From fio man:
Normally fio will cover every block of the file when doing
random I/O. If this parameter is given, a new offset will be
chosen without looking at past I/O history.
This parameter is mutually exclusive with verify.

Change-Id: I739642461b3dbe9ab8698836aa120bfb14c2b79e
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/385431
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2017-11-16 18:26:35 -05:00
Pawel Kaminski
96bd19093b test/vhost: Fio tests for vhost initiator.
Change-Id: Iad11eef12c0f7f80c26264f65a38df798eae1a27
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/378071
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-11 11:10:13 -04:00
Daniel Verkamp
e960eb4733 Revert "test/vhost: lower fio job iodepth"
Now that the bdev layer handles ENOMEM errors internally, we can restore
the original fio queue depths that were reduced to avoid test pool
failures.

This reverts commit 26a40ff914.

Change-Id: Ib7f1bd1e0251f4b2a6370cfd84e2f60e8ee15428
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/380855
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
2017-10-02 14:07:34 -04:00
Karol Latecki
26a40ff914 test/vhost: lower fio job iodepth
Temporarily lower iodepth to avoid random test pool
failures while running vhost blk fio tests.

Reenable old iodepth value once 'too high' vhost blk performance
is solved.

Change-Id: I385ff3151b4433b331807be6ce0f3103980bae7c
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/377697
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-09-08 17:16:54 -04:00
Lukasz Galka
3d738d4569 test/vhost: move fiotest functions to common directory
Move files from test/vhost/fiotest to test/vhost/common.
Scripts and functions from fio tests will be re-used in
any new test scripts.

Change-Id: I2423d636d41dcb2b2af12987769961607e969392
Signed-off-by: Lukasz Galka <lukaszx.galka@intel.com>
Reviewed-on: https://review.gerrithub.io/372545
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-09-05 13:54:47 -04:00