http://wiki.lustre.org/api.php?action=feedcontributions&user=Jnunez&feedformat=atomLustre Wiki - User contributions [en]2024-03-29T05:00:20ZUser contributionsMediaWiki 1.39.3http://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=4051Test Groups for Patch Testing2021-11-15T21:41:54Z<p>Jnunez: Update all test sessions with correct test suites.</p>
<hr />
<div>When a patch is submitted to be considered for inclusion in Lustre, automated testing is run against a build of Lustre with the submitted patch. For a patch to land, some of these test groups must pass testing, enforced test groups, and other, optional, test groups may fail.<br />
== Enforced Test Groups ==<br />
There are ten test groups that every patch must pass in order for the patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and the test suites in each test group are run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs<br />
!review-ldiskfs-ubuntu<br />
|-<br />
|sanity-lnet<br />
|sanity-quota<br />
|lnet-selftest<br />
|-<br />
|sanity<br />
|sanity-flr<br />
|sanity<br />
|-<br />
|lnet-selftest<br />
|replay-single <br />
|sanity-lnet<br />
|-<br />
|<br />
|replay-ost-single<br />
|sanity-sec<br />
|-<br />
|<br />
|insanity<br />
|<br />
|-<br />
|<br />
|sanity-lsnapshot<br />
|<br />
|}<br />
<br />
All of the following test groups are run in a Lustre environment with DNE configured; all tests run with 2 MDSs with 2 MDTs each.<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-zfs-part-3<br />
!review-dne-part-4<br />
!review-dne-zfs-part-4<br />
!review-dne-part-5<br />
!review-dne-zfs-part-5<br />
!review-dne-part-6<br />
!review-dne-zfs-part-6<br />
!review-dne-part-7<br />
!review-dne-zfs-part-7<br />
|-<br />
|sanity <br />
|sanity <br />
|mds-survey<br />
|mds-survey<br />
|conf-sanity <br />
|conf-sanity <br />
|insanity<br />
|insanity<br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|replay-single<br />
|replay-single<br />
|large-scale<br />
|large-scale<br />
|-<br />
|sanity-pfl <br />
|sanity-pfl <br />
|replay-dual <br />
|replay-dual <br />
| <br />
|<br />
|mmp <br />
|mmp <br />
|recovery-small<br />
|recovery-small<br />
|ost-pools<br />
|ost-pools<br />
|sanity-pcc<br />
|sanity-pcc<br />
|-<br />
|<br />
| <br />
|runtests <br />
|runtests <br />
|<br />
| <br />
|replay-ost-single<br />
|replay-ost-single<br />
|sanity-scrub<br />
|sanity-scrub<br />
|<br />
|<br />
|<br />
|<br />
|-<br />
|<br />
|<br />
|sanity-lfsck<br />
|sanity-lfsck <br />
|<br />
|<br />
|sanity-dom<br />
|sanity-dom<br />
|sanityn<br />
|sanityn<br />
| <br />
|<br />
|<br />
|<br />
|-<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|<br />
|sanity-flr<br />
|sanity-flr<br />
|<br />
|<br />
|<br />
|<br />
|<br />
|<br />
|-<br />
|<br />
|<br />
| <br />
| <br />
|<br />
|<br />
|sanity-hsm<br />
|sanity-hsm<br />
|<br />
|<br />
|<br />
|<br />
|<br />
|<br />
|-<br />
|<br />
|<br />
|<br />
|<br />
|<br />
|<br />
|sanity-quota<br />
|sanity-quota<br />
|<br />
|<br />
|<br />
|<br />
|<br />
|<br />
|}<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-dne-selinux-ssk-part1<br />
!review-dne-selinux-ssk-part2<br />
|-<br />
|sanity<br />
|recovery-small<br />
|-<br />
|<br />
|sanity-sec<br />
|-<br />
|<br />
|sanity-selinux<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there are four optional test groups that do not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs (RHEL8.3 servers/8.4 clients)<br />
|-<br />
|lnet-selftest <br />
|-<br />
|sanity<br />
|-<br />
|sanity-lnet<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=4047Test Groups for Patch Testing2021-11-12T17:54:33Z<p>Jnunez: Updated review-ldiskfs and review-zfs</p>
<hr />
<div>When a patch is submitted to be considered for inclusion in Lustre, automated testing is run against a build of Lustre with the submitted patch. For a patch to land, some of these test groups must pass testing, enforced test groups, and other, optional, test groups may fail.<br />
== Enforced Test Groups ==<br />
There are ten test groups that every patch must pass in order for the patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and the test suites in each test group are run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs<br />
|-<br />
|sanity-lnet<br />
|sanity-quota<br />
|-<br />
|sanity<br />
|sanity-flr<br />
|-<br />
|lnet-selftest<br />
|replay-single <br />
|-<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|insanity<br />
|-<br />
|<br />
|sanity-lsnapshot<br />
|}<br />
<br />
All of the following test groups are run in a Lustre environment with DNE configured; all tests run with 2 MDSs with 2 MDTs each.<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-zfs-part-3<br />
!review-dne-part-4<br />
!review-dne-zfs-part-4<br />
|-<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|conf-sanity <br />
|mmp <br />
|mmp <br />
|-<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|<br />
|replay-single <br />
|replay-single <br />
|-<br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
|<br />
| <br />
|sanity-pfl<br />
|sanity-pfl<br />
|-<br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|<br />
|sanity-flr<br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|<br />
|sanity-dom<br />
|sanity-dom<br />
|-<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|<br />
|sanity-quota<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|<br />
|replay-ost-single<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|<br />
|insanity<br />
|insanity<br />
|-<br />
|<br />
|<br />
|sanity-pcc<br />
|sanity-pcc<br />
|<br />
|<br />
|<br />
|<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there are four optional test groups that do not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs-arm<br />
!review-dne-ssk<br />
!review-dne-selinux<br />
!review-dne-selinux-ssk<br />
|-<br />
|lnet-selftest <br />
|sanity<br />
|sanity<br />
|sanity<br />
|-<br />
|sanity<br />
|recovery-small<br />
|recovery-small<br />
|recovery-small<br />
|-<br />
|<br />
|sanity-selinux<br />
|sanity-sec<br />
|sanity-selinux<br />
|-<br />
|<br />
|<br />
|<br />
|sanity-sec<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Descriptions&diff=3787Test Descriptions2020-05-04T16:51:04Z<p>Jnunez: Replaced "Maloo" with "AutoTest".</p>
<hr />
<div>== Lustre Test Framework ==<br />
<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
! Description<br />
|-<br />
|data-sort-value="acceptance-small"| [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/acceptance-small.sh acceptance-small.sh (acc-sm)]<br />
|The acceptance-small.sh script is a wrapper around auster that runs the test group '[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/test-groups/regression regression]' unless tests are specified on the command line.<br />
|-<br />
|data-sort-value="auster"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/auster auster]<br />
|auster is used to run the Lustre tests. It can be used to run groups of tests, individual tests, or sub-tests. Provides setup and cleanup. <br />
|-<br />
|data-sort-value="functions"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/functions.sh functions.sh]<br />
|Provides functions for the run_*.sh tests, such as run_dd.sh or run_dbench.sh<br />
|-<br />
|data-sort-value="test-framework"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/test-framework.sh test-framework.sh]<br />
|Provides the fundamental functions needed by tests to create, setup, verify, start, stop, and reformat a Lustre filesystem. <br />
|}<br />
<br />
See the [[TestingLustreCode]] page for details on how to run these test scripts.<br />
<br />
== Lustre Unit, Feature, and Regression Tests ==<br />
<br />
{| class="wikitable"<br />
|+Status Key<br />
|-<br />
|<span style="color:green">Active</span><br />
|Test suite has been run in AutoTest or committed to in last year.<br />
|-<br />
|<span style="color:blue">Inactive</span><br />
|Test suite has not been run in AutoTest or committed to in over a year.<br />
|-<br />
|<span style="color:red">Deprecated</span><br />
|Test suite has been removed or replaced.<br />
|}<br />
<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Status<br />
!Test Description<br />
|-<br />
|data-sort-value="conf-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/conf-sanity.sh conf-sanity]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify the configuration tools, and runs Lustre with multiple different setups to ensure correct operation in unusual system configurations. <br />
|-<br />
|data-sort-value=dne-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/dne_sanity.sh dne_sanity]<br />
|<span style="color:blue">Inactive</span><br />
|Run sanity parallel on different directories at the same time.<br />
|-<br />
|data-sort-value="insanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/insanity.sh insanity]<br />
|<span style="color:green">Active</span><br />
|A set of tests that verify the multiple concurrent failure conditions. <br />
|-<br />
|data-sort-value="large-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/large-scale.sh large-scale]<br />
|<span style="color:green">Active</span><br />
|Large-scale tests that verify version-based recovery features. <br />
|-<br />
|data-sort-value="large-lun" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/large-lun.sh large-lun]<br />
|<span style="color:green">Active</span><br />
|Large LUN test<br />
|-<br />
|data-sort-value="lfsck" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lfsck.sh lfsck]<br />
|<span style="color:red">Deprecated</span><br />
|Replaced by sanity-lfsck. <br />
|-<br />
|data-sort-value="lfsck-performance" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lfsck-performance.sh lfsck-performance]<br />
|<span style="color:green">Active</span><br />
|lfsck performance test for the cases: lfsck with load, lfsck during create, backup/restore, simulate upgrade from 1.8.<br />
|-<br />
|data-sort-value="liblustre" | liblustre<br />
|<span style="color:red">Deprecated</span><br />
|Run tests linked to liblustre client library <br />
|-<br />
|data-sort-value="lustre-rsync-test" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lustre-rsync-test.sh lustre-rsync-test]<br />
|<span style="color:green">Active</span><br />
|Verifies the lustre_rsync (replication) feature. <br />
|-<br />
|data-sort-value="metadata-updates" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/metadata-updates.sh metadata-updates]<br />
|<span style="color:green">Active</span><br />
| Tests that metadata updates are properly completed when multiple clients create/delete files and modify the attributes of files.<br />
|-<br />
|data-sort-value="mmp" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/mmp.sh mmp]<br />
|<span style="color:green">Active</span><br />
|Tests for multiple mount protection (MMP) feature.<br />
|-<br />
|data-sort-value="ost-pools" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/ost-pools.sh ost-pools]<br />
|<span style="color:green">Active</span><br />
|Tests that exercises the OST pools feature.<br />
|-<br />
|data-sort-value="performance-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/performance-sanity.sh performance-sanity]<br />
|<span style="color:green">Active</span><br />
|Performance mdsrate tests (small file create/open/delete, large file create/open/delete, lookup rate 10M file dir, lookup rate 10M file 10 dir, getattr small file, and getattr large files). <br />
|-<br />
|data-sort-value="parallel-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale.sh parallel-scale]<br />
|<span style="color:green">Active</span><br />
|Runs functional tests (connectathon, cascading_rw, write_disjoint, write_append_truncate, parallel_grouplock, statahead), performance tests (IOR, compilebench and metabench), and a stress test (simul). <br />
|-<br />
|data-sort-value="parallel-scale-cifs" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-cifs.sh parallel-scale-cifs]<br />
|<span style="color:green">Active</span><br />
|Tests Lustre exported via Samba and runs concurrent load compilebench, dbench, fsx, and iozone on Samba clients. The test assumes that Samba server and clients have necessary packages installed.<br />
|-<br />
|data-sort-value="parallel-scale-nfs" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfs.sh parallel-scale-nfs]<br />
|<span style="color:green">Active</span><br />
| Called by parallel-scale-nfsv3.sh and parallel-scale-nfsv4.sh with a version specified.<br />
|-<br />
|data-sort-value="parallel-scale-nfsv3" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfsv3.sh parallel-scale-nfsv3]<br />
|<span style="color:green">Active</span><br />
|Provide setup nfs within auster framework<br />
|-<br />
|data-sort-value="parallel-scale-nfsv4" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfsv4.sh parallel-scale-nfsv4]<br />
|<span style="color:green">Active</span><br />
|Provide setup nfs within auster framework<br />
|-<br />
|data-sort-value="posix" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/posix.sh posix]<br />
|<span style="color:green">Active</span><br />
|Automate POSIX compliance testing. Assuming that the POSIX source already installed, on the system, setup loop back ext4 filesystem, then install, build and run POSIX binaries on ext4. Run POSIX again Lustre and compare results from ext4 and Lustre.<br />
|-<br />
|data-sort-value="racer" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/racer.sh racer]<br />
|<span style="color:green">Active</span><br />
|Tests for filesystem race conditions by concurrently creating, moving, deleting, etc. a set of files. <br />
|-<br />
|data-sort-value="recovery-double-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-double-scale.sh recovery-double-scale]<br />
|<span style="color:green">Active</span><br />
|Failover test for all pair-wise combinations of node failures. <br />
|-<br />
|data-sort-value="recovery-mds-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-mds-scale.sh recovery-mds-scale]<br />
|<span style="color:green">Active</span><br />
|The server failover test: for a duration of 24 hours, repeatedly fail over a random facet (MDS or OST) at 10 minute intervals and verify that no application errors occur. <br />
|-<br />
|data-sort-value="recovery-random-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-random-scale.sh recovery-random-scale]<br />
|<span style="color:green">Active</span><br />
|Verifies client failure not affecting other clients. <br />
|-<br />
|data-sort-value="recovery-small" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-small.sh recovery-small]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify RPC replay after communications failure. <br />
|-<br />
|data-sort-value="replay-dual" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-dual.sh replay-dual]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify the recovery from two clients after server failure. <br />
|-<br />
|data-sort-value="replay-ost-single" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-ost-single.sh replay-ost-single]<br />
|<span style="color:green">Active</span><br />
| A set of unit tests that verify recovery after OST failure. <br />
|-<br />
|data-sort-value="replay-single" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-single.sh replay-single]<br />
|<span style="color:green">Active</span><br />
| A set of unit tests that verify recovery after MDS failure. <br />
|-<br />
|data-sort-value="replay-vbr" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-vbr.sh replay-vbr]<br />
|<span style="color:green">Active</span><br />
|Verifies version-based recovery feature. <br />
|-<br />
|data-sort-value="runtests" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/runtests runtests]<br />
|<span style="color:green">Active</span><br />
|Simple basic regression test that verifies data persistence across write, unmount, and remount. This is one of the few tests that verifies data integrity across a full filesystem shutdown and remount, unlike many tests which at most only verify the existence/size of files. <br />
|-<br />
|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity.sh sanity]<br />
|<span style="color:green">Active</span><br />
|A set of regression tests that verify operation under normal operating conditions. This tests a large number of unusual operations that have previously caused functional or data correctness issues with Lustre. Some of the tests are Lustre specific, and hook into the Lustre fault injection framework using the "lctl set_param fail_loc=X" command to activate triggers in the code to simulate unusual operating conditions that would otherwise be difficult or impossible to simulate. <br />
|-<br />
|data-sort-value="sanityn" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanityn.sh sanityn]<br />
|<span style="color:green">Active</span><br />
|Tests that verify operations from two clients under normal operating conditions. This is done by mounting the same filesystem twice on a single client, in order to allow a single script/program to execute and verify filesystem operations on multiple "clients" without having to be a distributed program itself.<br />
|-<br />
|data-sort-value="sanity-benchmark" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-benchmark.sh sanity-benchmark]<br />
|<span style="color:green">Active</span><br />
|Test basic functionality of the filesystem using simple benchmarks. Runs dbench, bonnie++, iozone, fsx, and pios.<br />
|-<br />
|data-sort-value="sanity-dom" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-dom.sh sanity-dom]<br />
|<span style="color:green">Active</span><br />
|Sanity test the Data on MDT feature.<br />
|-<br />
|data-sort-value="sanity-flr" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-flr.sh sanity-flr]<br />
|<span style="color:green">Active</span><br />
|Sanity test the File Level Redundancy feature.<br />
|-<br />
|data-sort-value="sanity-gss" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-gss.sh sanity-gss]<br />
|<span style="color:green">Active</span><br />
|Verifies GSSAPI features. A mechanism-agnostic test suite for just the GSSAPI code itself using the gssnull security flavor, which in turn uses the null GSSAPI mechanism.<br />
|-<br />
|data-sort-value="sanity-hsm" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-hsm.sh sanity-hsm]<br />
|<span style="color:green">Active</span><br />
|Sanity test for HSM feature.<br />
|-<br />
|data-sort-value="sanity-krb5" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-krb5.sh sanity-krb5]<br />
|<span style="color:green">Active</span><br />
|Verifies Kerberos features.<br />
|-<br />
|data-sort-value="sanity-lfsck" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-lfsck.sh sanity-lfsck]<br />
|<span style="color:green">Active</span><br />
|Sanity test for lfsck<br />
|-<br />
|data-sort-value="sanity-pcc" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-pcc.sh sanity-pcc]<br />
|<span style="color:green">Active</span><br />
|A set of tests verifying basic functionality of the Persistent Client Cache feature.<br />
|-<br />
|data-sort-value="sanity-pfl" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-pfl.sh sanity-pfl]<br />
|<span style="color:green">Active</span><br />
|Sanity tests for the Progressive File Layout feature.<br />
|-<br />
|data-sort-value="sanity-quota" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-quota.sh sanity-quota]<br />
|<span style="color:green">Active</span><br />
|A set of tests that verify filesystem quotas. <br />
|-<br />
|data-sort-value="sanity-scrub" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-scrub.sh sanity-scrub]<br />
|<span style="color:green">Active</span><br />
|Verifies OI scrub functionality.<br />
|-<br />
|data-sort-value="sanity-sec" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-sec.sh sanity-sec]<br />
|<span style="color:green">Active</span><br />
|Verifies Lustre identity features. , including UID/GID mapping<br />
|-<br />
|data-sort-value="scrub-performance" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/scrum-performance.sh scrub-performance]<br />
|<span style="color:green">Active</span><br />
|Test OI scrub performance<br />
|}<br />
<br />
== Benchmark Scripts ==<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Status<br />
!Script Description<br />
|-<br />
|data-sort-value="lnet-selftest" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lnet-selftest.sh lnet-selftest]<br />
|<span style="color:green">Active</span><br />
|LNET self-test is a kernel module that runs over LNET and the Lustre network drivers (LNDs). It is designed to test the connection ability of the Lustre network, run regression tests of the Lustre network, and test performance of the Lustre network.<br />
|-<br />
|data-sort-value="obdfilter-survey" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/obdfilter-survey.sh obdfilter-survey]<br />
|<span style="color:green">Active</span><br />
|This survey script does sequential I/O with varying numbers of threads and objects (files) by using lctl to drive the echo_client connected to local or remote obdfilter instances, or remote obdecho instances. It can be used to characterize the performance of the following Lustre components.<br />
|-<br />
|data-sort-value="sgpdd-survey" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sgpdd-survey.sh sgpdd-survey]<br />
|<span style="color:green">Active</span><br />
|This survey may be used to characterize the performance of a SCSI device. It simulates an OST serving multiple stripe files. The data gathered by it can help set expectations for the performance of a Lustre OST exporting the device.<br />
|}<br />
<br />
== Auxiliary Tests and Benchmarks Tools == <br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Script Description<br />
|-<br />
|data-sort-value="bonnie" | [http://www.coker.com.au/bonnie++/ bonnie++]<br />
|Bonnie++ benchmark for creation, reading, and deleting many small files.<br />
|-<br />
|data-sort-value="dbench" | [https://dbench.samba.org/ dbench]<br />
|Dbench benchmark for simulating N clients to produce the filesystem load.<br />
|-<br />
|data-sort-value="fsx" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/fsx.c fsx]<br />
|The file system exerciser was developed outside of Lustre and is intended to stress test unusual IO and file operations. It does buffered and mmap reads and writes with random size and offset, truncate, open, close on a file. It verifies data integrity after each step. A lustre-developed extension allows fsx to run against multiple mountpoints to verify distributed IO operation correctness. (Source [https://wiki.whamcloud.com/display/PUB/Auster Auster])<br />
|-<br />
|data-sort-value="iozone" | [http://www.iozone.org/ iozone]<br />
|Iozone benchmark for generating and measuring a variety of file operations.<br />
|-<br />
|data-sort-value="oos.sh" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/oos.sh oos.sh]<br />
|Script used to check out-of-space detection in sanity.sh test 64b.<br />
|-<br />
|data-sort-value="oos2.sh" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/oos2.sh oos2.sh]<br />
|Script used to check out-of-space detection with multiple writers in sanityn.sh test 15.<br />
|-<br />
|data-sort-value="pios" | pios<br />
|pios is a parallel IO simulator. It can simulate shared file per process and file per process IO. Used in sanity-benchmark. pios-1.2-wc1 is available from the build of the toolkit repo for various distributions, e.g. RHEL6 x86_64 https://build.whamcloud.com/job/toolkit/arch=x86_64,distro=el6/lastSuccessfulBuild/artifact/_topdir/RPMS/x86_64/<br />
|}<br />
<br />
[[Category:Testing]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Release_2.14.0&diff=3739Release 2.14.02019-12-17T16:13:36Z<p>Jnunez: Changed "the 2.13 release cycle" to "the 2.14 release cycle"</p>
<hr />
<div>(Draft version - work in progress)<br />
<br />
== Current Schedule ==<br />
<br />
* February 29 2020 - Feature Cut-off (Only features will patches already in review at this point still considered)<br />
* Mar 30 2020 - Feature Freeze (Final date for features to land for 2.14)<br />
* May 31 2020 - Code Freeze<br />
* June 30 2020 - Release 2.14.0<br />
<br />
(Note: these are very rough guidelines. For more accurate details on the schedule please refer to LWG call minutes)<br />
<br />
== Scope ==<br />
<br />
=== Test Matrix ===<br />
* Servers: RHEL 8.1<br />
* Clients RHEL 8.1, SLES 15 SP1, Ubuntu 20.04<br />
* OFED: inkernel<br />
* E2FSProgs: v1.45.2.wc1<br />
* Interoperability: Latest 2.12.X and 2.13 Servers/Clients,<br />
<br />
=== Features ===<br />
<br />
The following features are under active development and could be possible for landing during the 2.14 release cycle<br />
<br />
{| class="wikitable sortable"<br />
|-<br />
! Feature !! Developers !! Reviewers !! Testers !! Docs !! Confirmed in 2.14<br />
|-<br />
<br />
| [https://jira.whamcloud.com/browse/LU-10911 FLR Erasure Coding] || Bobijam Xu || TBD || TBD || TBD || Not yet<br />
|-<br />
| [https://jira.whamcloud.com/browse/LU-11023 Pool Quota] || Sergey Cheremencev || Alexey Layshkov, Shaun Tancheff || Elena Gryaznova || Sergey Cheremencev || Not yet<br />
|-<br />
| [https://jira.whamcloud.com/browse/LU-11025 DNE Auto-Restriping] || Lai Siyao || TBD || TBD || TBD || Not yet<br />
|-<br />
|}<br />
<br />
=== General Work and Maintenance ===<br />
<br />
From the [https://jira.whamcloud.com/browse/LU Lustre project page] in the [https://jira.whamcloud.com Lustre issue tracker], we can see a dashboard for the project. On that page under the "Versions: Unreleased" section, there are links to future releases and all of the issues that are either targeted to be addressed in that release, or are already addressed for the release. Here is a shortcut to Lustre 2.13.0's issue summary page:<br />
<br />
* [https://jira.whamcloud.com/projects/LU/versions/14490 Lustre 2.14.0 Issues]<br />
<br />
Any issue that contains "Lustre 2.14.0" in the "Fix Version/s" field of a ticket is intended to be fixed for version 2.14.0. The Lustre 2.14.0 Issues list is fluid, and will be updated on a continual basis as resources and priorities change.<br />
<br />
If you would like to own one or more tasks for the release but are not currently listed in the drop-down list of developers in JIRA then please email [mailto:peter.a.jones@intel.com Peter Jones] to get that setup<br />
<br />
A convenience search filter is supplied for anyone looking for work that needs to be done for 2.14.0:<br />
<br />
* [https://jira.whamcloud.com/issues/?filter=15815 Lustre 2.14.0 Unassigned Issues]<br />
<br />
In addition, a search filter is available for anyone looking to start Lustre development with some simple development tasks, or anyone with a few minutes/hours available to improve Lustre:<br />
<br />
* [https://jira.whamcloud.com/issues/?jql=resolution=Unresolved%20AND%20labels=easy Lustre easy-to-fix issues]<br />
<br />
[[Category: Releases]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Lustre_2.12.3_Changelog&diff=3698Lustre 2.12.3 Changelog2019-10-24T16:31:57Z<p>Jnunez: Updated recommended e2fsprogs version</p>
<hr />
<div>'''Server support for kernels: '''<br /><br />
*RHEL 7.7 (3.10.0-1062.1.1.el7)<br />
<br />
'''Client support for unpatched kernels: '''<br /><br />
*RHEL 7.7 (3.10.0-1062.1.1.el7)<br />
*SLES12 SP4 (4.12.14-95.29.1)<br />
*Ubuntu 18.04 (4.15.0-64)<br />
<br />
'''Recommended e2fsprogs version: '''<br /><br />
*v1.45.2.wc1-0<br />
<br />
'''Interoperability Support: '''<br /><br />
*Clients & Servers: Latest 2.10.X and Latest 2.11.X<br />
<br />
== Issues fixed between 2.12.2 and 2.12.3 ==<br />
''' Bug '''<br />
*[https://jira.whamcloud.com/browse/LU-8047 LU-8047]: optimize ll_md_blocking_ast() for a failed lock<br />
*[https://jira.whamcloud.com/browse/LU-10094 LU-10094]: sanity test_17f: 'ls' fails with &quot;ls: reading directory *: Input/output error&quot;<br />
*[https://jira.whamcloud.com/browse/LU-10100 LU-10100]: sanity test_27a: setstripe failed with &quot;error on ioctl 0x8008669a for '*' (3): Invalid argument&quot;<br />
*[https://jira.whamcloud.com/browse/LU-10717 LU-10717]: several conf-sanity tests failed: FAIL: start mgs failed<br />
*[https://jira.whamcloud.com/browse/LU-11359 LU-11359]: racer test 1 times out with client hung in dir_create.sh, ls, … and MDS in ldlm_completion_ast()<br />
*[https://jira.whamcloud.com/browse/LU-11403 LU-11403]: lov_io_init_empty() Page fault on a file without stripes<br />
*[https://jira.whamcloud.com/browse/LU-11426 LU-11426]: 2/2 Olafs agree: changelog entries are emitted out of order<br />
*[https://jira.whamcloud.com/browse/LU-11453 LU-11453]: sanity test 184a: Basic layout swap panics on Power8<br />
*[https://jira.whamcloud.com/browse/LU-11485 LU-11485]: MDS allows &quot;lfs setstripe&quot; to mark last mirror as stale<br />
*[https://jira.whamcloud.com/browse/LU-11537 LU-11537]: Fix assertion: osd_trans_exec_op()) ASSERTION( !ldiskfs_track_declares_assert )<br />
*[https://jira.whamcloud.com/browse/LU-11542 LU-11542]: Race between imp_state and imp_invalid<br />
*[https://jira.whamcloud.com/browse/LU-11566 LU-11566]: sanity test_60aa: llog_print_cb()) not enough space for print log records<br />
*[https://jira.whamcloud.com/browse/LU-11617 LU-11617]: lockdep exposed a possible deadlock in chlg_open()<br />
*[https://jira.whamcloud.com/browse/LU-11634 LU-11634]: sanityn/test_77 improvements<br />
*[https://jira.whamcloud.com/browse/LU-11672 LU-11672]: improving lru_max_age policy when lru resize is disabled<br />
*[https://jira.whamcloud.com/browse/LU-11675 LU-11675]: Don't allow new HSM requests during CDT_INIT<br />
*[https://jira.whamcloud.com/browse/LU-11678 LU-11678]: sanity-quota test 1 fails with 'user write success, but expect EDQUOT'<br />
*[https://jira.whamcloud.com/browse/LU-11690 LU-11690]: LBUG with very wide striping: lod_ea_store_resize()) ASSERTION( round &lt;= lov_mds_md_size(2000, (0x0BD30000 | 0x0BD0))<br />
*[https://jira.whamcloud.com/browse/LU-11721 LU-11721]: &quot;lfs df -i&quot; prints used blocks percentage instead of inodes<br />
*[https://jira.whamcloud.com/browse/LU-11729 LU-11729]: ARM: sanity test_810: BAD WRITE CHECKSUM with adler<br />
*[https://jira.whamcloud.com/browse/LU-11742 LU-11742]: ERROR: RPATH is not allowed<br />
*[https://jira.whamcloud.com/browse/LU-11743 LU-11743]: lctl pool operations cannot be run on separate MGS system<br />
*[https://jira.whamcloud.com/browse/LU-11755 LU-11755]: Remove redundant LASSERT() in ns_is_{client,server}()<br />
*[https://jira.whamcloud.com/browse/LU-11756 LU-11756]: kib_conn leak<br />
*[https://jira.whamcloud.com/browse/LU-11760 LU-11760]: formatted OST recognition change<br />
*[https://jira.whamcloud.com/browse/LU-11761 LU-11761]: blocked MDT mount and high cpu usage from lodXXXX_recYYYY threads<br />
*[https://jira.whamcloud.com/browse/LU-11771 LU-11771]: bad output in target_handle_reconnect: Recovery already passed deadline 71578:57<br />
*[https://jira.whamcloud.com/browse/LU-11796 LU-11796]: Remove LASSERT(r0-&gt;lo_nr &lt;= lov_targets_nr(dev)) in maintenance branches<br />
*[https://jira.whamcloud.com/browse/LU-11816 LU-11816]: LNet Health: Correct timeout defaults<br />
*[https://jira.whamcloud.com/browse/LU-11851 LU-11851]: kernel BUG at ...ldiskfs/htree_lock.c:665<br />
*[https://jira.whamcloud.com/browse/LU-11873 LU-11873]: sanity test_801a: FAIL: (2) unexpected barrier status 'expired'<br />
*[https://jira.whamcloud.com/browse/LU-11925 LU-11925]: Attributes not updated after open+append and write to archived,released file<br />
*[https://jira.whamcloud.com/browse/LU-11946 LU-11946]: configure --enable-dist fails if libyaml-devel or zlib-devel are not installed<br />
*[https://jira.whamcloud.com/browse/LU-12017 LU-12017]: Truncate vs setxattr deadlock with DoM<br />
*[https://jira.whamcloud.com/browse/LU-12034 LU-12034]: env allocation in ptlrpc_set_wait() causes slowdown on the client<br />
*[https://jira.whamcloud.com/browse/LU-12080 LU-12080]: LNet Health: references left on eq<br />
*[https://jira.whamcloud.com/browse/LU-12095 LU-12095]: ocd_connect_flags are wrong during reconnect<br />
*[https://jira.whamcloud.com/browse/LU-12098 LU-12098]: changelog_deregister appears not to reliably clear all changelog entries<br />
*[https://jira.whamcloud.com/browse/LU-12120 LU-12120]: LustreError: 15069:0:(tgt_grant.c:561:tgt_grant_incoming()) LBUG<br />
*[https://jira.whamcloud.com/browse/LU-12131 LU-12131]: Improve GSS/SSK handling in Lustre test suite<br />
*[https://jira.whamcloud.com/browse/LU-12152 LU-12152]: lnetctl export corrupts memory on routers<br />
*[https://jira.whamcloud.com/browse/LU-12165 LU-12165]: Enable quota enforcement crashed kernel<br />
*[https://jira.whamcloud.com/browse/LU-12166 LU-12166]: Tests if ZFS backend project supported is broken<br />
*[https://jira.whamcloud.com/browse/LU-12169 LU-12169]: Assertion on mdc_pack_name<br />
*[https://jira.whamcloud.com/browse/LU-12178 LU-12178]: MDS deadlock with 2.12.0 (quotas?)<br />
*[https://jira.whamcloud.com/browse/LU-12195 LU-12195]: sanity/43 and sanityn/14 fail on local setups<br />
*[https://jira.whamcloud.com/browse/LU-12199 LU-12199]: md's are not detached from uncommitted messages that have health check performed on them<br />
*[https://jira.whamcloud.com/browse/LU-12225 LU-12225]: jobid_get_from_cache stalled on spin_lock(&amp;pidmap-&gt;jp_lock)<br />
*[https://jira.whamcloud.com/browse/LU-12229 LU-12229]: ost-pools test 1j fails with 'test_1j returned 1'<br />
*[https://jira.whamcloud.com/browse/LU-12232 LU-12232]: replay-ost-single test 6 fails with ''space grew after dd: before:13442048 after_dd:13442048''<br />
*[https://jira.whamcloud.com/browse/LU-12248 LU-12248]: sanity test_418: df and lfs df inodes output mismatch<br />
*[https://jira.whamcloud.com/browse/LU-12264 LU-12264]: The lnet peer discovery queue (lnet_peer.lp_dc_pendq) is susceptible to concurrent manipulation<br />
*[https://jira.whamcloud.com/browse/LU-12267 LU-12267]: sanity test_103a: some ACL tests fail with SELinux enforced<br />
*[https://jira.whamcloud.com/browse/LU-12282 LU-12282]: Pass IB_OPTIONS to debian rules doesn't work<br />
*[https://jira.whamcloud.com/browse/LU-12309 LU-12309]: write fails with -EOPNOTSUPP with zfs 0.8.0-rc5 using 0.7.x pool<br />
*[https://jira.whamcloud.com/browse/LU-12314 LU-12314]: Add Missing Description to sanity test 258a<br />
*[https://jira.whamcloud.com/browse/LU-12323 LU-12323]: save_stack_trace_tsk is not exported on arm architectures<br />
*[https://jira.whamcloud.com/browse/LU-12324 LU-12324]: zero transno on transaction commit<br />
*[https://jira.whamcloud.com/browse/LU-12342 LU-12342]: lsvcgss config file overwritten on update<br />
*[https://jira.whamcloud.com/browse/LU-12343 LU-12343]: osc_lock.c:687:osc_ldlm_weigh_ast()) LBUG<br />
*[https://jira.whamcloud.com/browse/LU-12350 LU-12350]: sanity-flr test_33: file content error: expected: ost1, actual: ost2<br />
*[https://jira.whamcloud.com/browse/LU-12361 LU-12361]: cp --sparse doesn't work correctly in<br />
*[https://jira.whamcloud.com/browse/LU-12374 LU-12374]: client went down w/ panic during lustre_rmmod<br />
*[https://jira.whamcloud.com/browse/LU-12375 LU-12375]: lnet should start after opa service<br />
*[https://jira.whamcloud.com/browse/LU-12381 LU-12381]: o2iblnd uses wrong IB interface<br />
*[https://jira.whamcloud.com/browse/LU-12382 LU-12382]: Deadloop on tiny write<br />
*[https://jira.whamcloud.com/browse/LU-12383 LU-12383]: lfs project inhert difference between ldiskfs and zfs<br />
*[https://jira.whamcloud.com/browse/LU-12385 LU-12385]: 2.12.2: IOR read testing reliably inducing LNetError: Timed out RDMA with ...@o2ib1 (6): c: 0, oc: 0, rc: 63<br />
*[https://jira.whamcloud.com/browse/LU-12387 LU-12387]: l_tunedisk does not properly handle multipath devices<br />
*[https://jira.whamcloud.com/browse/LU-12394 LU-12394]: lctl get_param llite.lfs*.extents_stats only displays first two buckets<br />
*[https://jira.whamcloud.com/browse/LU-12395 LU-12395]: Failed dependencies while installing lustre-client-tests and lustre-iokit rpms on RHEL 8.0 client<br />
*[https://jira.whamcloud.com/browse/LU-12399 LU-12399]: sanity test_420: FAIL: incorrect perms on /mnt/lustre/d420.sanity/testdir/testfile<br />
*[https://jira.whamcloud.com/browse/LU-12401 LU-12401]: Various issues with checksum calculation for Kerberos and SSK<br />
*[https://jira.whamcloud.com/browse/LU-12447 LU-12447]: Fedora28 Lustre client build failure<br />
*[https://jira.whamcloud.com/browse/LU-12456 LU-12456]: kernel update [RHEL8.0 4.18.0-80.4.2.el8_0]<br />
*[https://jira.whamcloud.com/browse/LU-12457 LU-12457]: support for RHEL 7.7<br />
*[https://jira.whamcloud.com/browse/LU-12458 LU-12458]: kernel update [RHEL7.6 3.10.0-957.21.3.el7]<br />
*[https://jira.whamcloud.com/browse/LU-12478 LU-12478]: RHEL8 packaging<br />
*[https://jira.whamcloud.com/browse/LU-12479 LU-12479]: gcc8 warnings<br />
*[https://jira.whamcloud.com/browse/LU-12485 LU-12485]: (osd_handler.c:2146:osd_object_release()) ASSERTION( !(o-&gt;oo_destroyed == 0 &amp;&amp; o-&gt;oo_inode &amp;&amp; o-&gt;oo_inode-&gt;i_nlink == 0) ) faile<br />
*[https://jira.whamcloud.com/browse/LU-12491 LU-12491]: large-scale: crash in lu_env_remove() RIP: memcmp+0x9/0x50<br />
*[https://jira.whamcloud.com/browse/LU-12494 LU-12494]: kernel update [SLES12 SP4 4.12.14-95.19.1]<br />
*[https://jira.whamcloud.com/browse/LU-12498 LU-12498]: kernel update [SLES12 SP3 4.4.180-94.97.1]<br />
*[https://jira.whamcloud.com/browse/LU-12501 LU-12501]: lfs df can never return<br />
*[https://jira.whamcloud.com/browse/LU-12510 LU-12510]: mds server hangs cv_wait_common<br />
*[https://jira.whamcloud.com/browse/LU-12539 LU-12539]: Pass --with-o2ib option along when building deb packages<br />
*[https://jira.whamcloud.com/browse/LU-12559 LU-12559]: Reconnecting from idle exposes import in IMP_NEW state, resulting in EIO<br />
*[https://jira.whamcloud.com/browse/LU-12566 LU-12566]: GPF when umounting client<br />
*[https://jira.whamcloud.com/browse/LU-12569 LU-12569]: IBLND_CREDITS_HIGHWATER does not check connection queue depth<br />
*[https://jira.whamcloud.com/browse/LU-12570 LU-12570]: sanity test 134a crash with SSK in use<br />
*[https://jira.whamcloud.com/browse/LU-12575 LU-12575]: lbuild: build MOFED on el8<br />
*[https://jira.whamcloud.com/browse/LU-12581 LU-12581]: Slab object &quot;Freechain corrupt&quot; on client<br />
*[https://jira.whamcloud.com/browse/LU-12586 LU-12586]: truncate to start of uninstantiated PFL component silently fails<br />
*[https://jira.whamcloud.com/browse/LU-12589 LU-12589]: sanity test_102a: setfattr: /mnt/lustre/f102a.sanity: Numerical result out of range<br />
*[https://jira.whamcloud.com/browse/LU-12590 LU-12590]: Lustre lustre_msg_hdr_size_v2() bug<br />
*[https://jira.whamcloud.com/browse/LU-12600 LU-12600]: Lustre tgt_brw_write() bug<br />
*[https://jira.whamcloud.com/browse/LU-12602 LU-12602]: Lustre mdt_getxattr_pack_reply() bug<br />
*[https://jira.whamcloud.com/browse/LU-12603 LU-12603]: Lustre ldlm_request_cancel() bug<br />
*[https://jira.whamcloud.com/browse/LU-12604 LU-12604]: Lustre mdt_file_secctx_unpack() bug<br />
*[https://jira.whamcloud.com/browse/LU-12605 LU-12605]: Lustre target_handle_connect() bug<br />
*[https://jira.whamcloud.com/browse/LU-12608 LU-12608]: kernel update [RHEL7.6 3.10.0-957.27.2.el7]<br />
*[https://jira.whamcloud.com/browse/LU-12612 LU-12612]: Lustre osd_bufs_get() bug<br />
*[https://jira.whamcloud.com/browse/LU-12613 LU-12613]: Lustre lustre_msg_string() bug<br />
*[https://jira.whamcloud.com/browse/LU-12614 LU-12614]: Lustre ldlm_cancel_hpreq_check() bug<br />
*[https://jira.whamcloud.com/browse/LU-12615 LU-12615]: Lustre mdt_object_remote() bug<br />
*[https://jira.whamcloud.com/browse/LU-12620 LU-12620]: kernel update [RHEL8.0 4.18.0-80.7.1.el8_0]<br />
*[https://jira.whamcloud.com/browse/LU-12626 LU-12626]: Attempt to create existing net returns EINVAL<br />
*[https://jira.whamcloud.com/browse/LU-12650 LU-12650]: get_root_path() filesystem name compare error that leads to fid2path fail<br />
*[https://jira.whamcloud.com/browse/LU-12657 LU-12657]: sanity/103 and sanityn/25 fail with 4.18 kernel<br />
*[https://jira.whamcloud.com/browse/LU-12660 LU-12660]: kernel update [SLES12 SP4 4.12.14-95.29.1]<br />
*[https://jira.whamcloud.com/browse/LU-12690 LU-12690]: error handling of ll_och_fill()<br />
*[https://jira.whamcloud.com/browse/LU-12705 LU-12705]: build fails on power9 client<br />
*[https://jira.whamcloud.com/browse/LU-12724 LU-12724]: kernel update [RHEL7.7 3.10.0-1062.1.1.el7]<br />
*[https://jira.whamcloud.com/browse/LU-12755 LU-12755]: CPU soft lockup on mkfs.lustre<br />
*[https://jira.whamcloud.com/browse/LU-12777 LU-12777]: conf-sanity test 103 fails with ‘set mdt quota type failed’<br />
*[https://jira.whamcloud.com/browse/LU-12790 LU-12790]: LustreError: 96800:0:(jobid.c:103:jobid_get_from_environ()) jobid: get 'PBS_JOBID' failed: rc = -75<br />
<br />
''' New Feature '''<br />
*[https://jira.whamcloud.com/browse/LU-11297 LU-11297]: Need to align LNet routing with Multi-Rail and LNet health<br />
<br />
''' Task '''<br />
*[https://jira.whamcloud.com/browse/LU-10171 LU-10171]: define pct(a,b) once<br />
<br />
''' Improvement '''<br />
*[https://jira.whamcloud.com/browse/LU-9625 LU-9625]: remove &quot;lfs ls&quot; and &quot;lfs cp&quot; and references<br />
*[https://jira.whamcloud.com/browse/LU-10258 LU-10258]: lfs mirror command to open fd on component<br />
*[https://jira.whamcloud.com/browse/LU-10885 LU-10885]: enable flock by default<br />
*[https://jira.whamcloud.com/browse/LU-11233 LU-11233]: gcc8 support<br />
*[https://jira.whamcloud.com/browse/LU-11285 LU-11285]: don't stop on the first blocked lock in ldlm_reprocess_queue()<br />
*[https://jira.whamcloud.com/browse/LU-11296 LU-11296]: page cache cleanup improvement on lock flush<br />
*[https://jira.whamcloud.com/browse/LU-11355 LU-11355]: Add Lustre trim support<br />
*[https://jira.whamcloud.com/browse/LU-11830 LU-11830]: Quiet compiler warnings on ARM<br />
*[https://jira.whamcloud.com/browse/LU-11838 LU-11838]: Support linux kernel version 4.18<br />
*[https://jira.whamcloud.com/browse/LU-11845 LU-11845]: Support encrypted ZFS volumes<br />
*[https://jira.whamcloud.com/browse/LU-11963 LU-11963]: Add nonrotational flag to obd_statfs<br />
*[https://jira.whamcloud.com/browse/LU-12045 LU-12045]: Ability to split test script execution into parts<br />
*[https://jira.whamcloud.com/browse/LU-12090 LU-12090]: Create an lfs command to remove files by FID<br />
*[https://jira.whamcloud.com/browse/LU-12093 LU-12093]: CAP_SYS_RESOURCE capability check overhead<br />
*[https://jira.whamcloud.com/browse/LU-12270 LU-12270]: Support linux kernel version 4.19<br />
*[https://jira.whamcloud.com/browse/LU-12331 LU-12331]: hardened usercopy whitelisting<br />
*[https://jira.whamcloud.com/browse/LU-12516 LU-12516]: volatile file creation in .lustre/fid/<br />
*[https://jira.whamcloud.com/browse/LU-12553 LU-12553]: polling mode for changelog driver<br />
*[https://jira.whamcloud.com/browse/LU-12621 LU-12621]: o2iblnd QP sizing -EINVAL retries<br />
*[https://jira.whamcloud.com/browse/LU-12789 LU-12789]: Mellanox MOFED 4.7 support.<br />
*[https://jira.whamcloud.com/browse/LU-12802 LU-12802]: racer test stucks after test finishes<br />
*[https://jira.whamcloud.com/browse/LU-12825 LU-12825]: Build MOFED 4.7<br />
<br />
''' Technical task '''<br />
*[https://jira.whamcloud.com/browse/LU-10777 LU-10777]: DoM performance is bad with FIO write<br />
*[https://jira.whamcloud.com/browse/LU-11478 LU-11478]: LNet: discovery sequence numbers could be misleading<br />
*[https://jira.whamcloud.com/browse/LU-12163 LU-12163]: Fix cpt confusion<br />
*[https://jira.whamcloud.com/browse/LU-12201 LU-12201]: LNet: detach response tracker<br />
*[https://jira.whamcloud.com/browse/LU-12249 LU-12249]: LNet Health: list corruption<br />
*[https://jira.whamcloud.com/browse/LU-12254 LU-12254]: lnet: correct discovery event queue release<br />
*[https://jira.whamcloud.com/browse/LU-12339 LU-12339]: LNet Health: selecting loopback interface for sending<br />
*[https://jira.whamcloud.com/browse/LU-12344 LU-12344]: LNet Health: tweak health errors</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3697Test Groups for Patch Testing2019-10-22T22:28:29Z<p>Jnunez: Added optional test groups.</p>
<hr />
<div>When a patch is submitted to be considered for inclusion in Lustre, automated testing is run against a build of Lustre with the submitted patch. Some of these test groups must pass testing, enforced test groups, and other, optional, test groups may fail.<br />
== Enforced Test Groups ==<br />
There are ten test groups that every patch must pass in order for the patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and the test suites in each test group are run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs<br />
|-<br />
|sanity <br />
|sanity-quota<br />
|-<br />
|lnet-selftest <br />
|sanity-flr<br />
|-<br />
|<br />
|replay-single <br />
|-<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|insanity<br />
|}<br />
<br />
All of the following test groups are run in a Lustre environment with DNE configured; all tests run with 2 MDSs with 2 MDTs each.<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-zfs-part-3<br />
!review-dne-part-4<br />
!review-dne-zfs-part-4<br />
|-<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|conf-sanity <br />
|mmp <br />
|mmp <br />
|-<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|<br />
|replay-single <br />
|replay-single <br />
|-<br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
|<br />
| <br />
|sanity-pfl<br />
|sanity-pfl<br />
|-<br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|<br />
|sanity-flr<br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|<br />
|sanity-dom<br />
|sanity-dom<br />
|-<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|<br />
|sanity-quota<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|<br />
|replay-ost-single<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|<br />
|insanity<br />
|insanity<br />
|-<br />
|<br />
|<br />
|sanity-pcc<br />
|sanity-pcc<br />
|<br />
|<br />
|<br />
|<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there are four optional test groups that do not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs-arm<br />
!review-dne-ssk<br />
!review-dne-selinux<br />
!review-dne-selinux-ssk<br />
|-<br />
|lnet-selftest <br />
|sanity<br />
|sanity<br />
|sanity<br />
|-<br />
|sanity<br />
|recovery-small<br />
|recovery-small<br />
|recovery-small<br />
|-<br />
|<br />
|sanity-selinux<br />
|sanity-sec<br />
|sanity-selinux<br />
|-<br />
|<br />
|<br />
|<br />
|sanity-sec<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Testing&diff=3685Testing2019-10-01T13:48:34Z<p>Jnunez: Updated link to Auster test framework information</p>
<hr />
<div>* [[Testing HOWTO | Run Lustre Tests HOWTO]]<br />
* [[Test Descriptions | Test Framework and Descriptions of Unit, Regression, and Feature Tests]]<br />
* [[Testing Setup To Induce Race Conditions | Testing setup to induce otherwise hard to hit race conditions]]<br />
* [[Test Groups for Patch Testing | Test Groups for Patch Testing]]<br />
* [[Test Configuration Variables | Test Configuration and Environment Variables]]<br />
----<br />
Whamcloud's testing results database for patches: [https://testing.whamcloud.com/ Maloo]<br />
<br />
Whamcloud Wiki pages related to testing:<br />
* [https://wiki.whamcloud.com/display/PUB/Testing+a+Lustre+filesystem Testing a Lustre filesystem]<br />
* [https://wiki.whamcloud.com/display/PUB/Lustre+Test+Tools+Environment+Variables Lustre Test Tools Environment Variables]<br />
* [https://wiki.whamcloud.com/display/PUB/Testing+a+Lustre+filesystem#TestingaLustrefilesystem-auster Auster]<br />
----<br />
wiki.old.lustre.org pages related to testing:<br />
* [http://wiki.old.lustre.org/index.php/Acceptance_Small_%28acc-sm%29_Testing_on_Lustre Acceptance Small (acc-sm) Testing on Lustre]<br />
* [http://wiki.old.lustre.org/index.php/Testing_Lustre_Code Testing Lustre Code]<br />
<br />
[[Category:Testing]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Descriptions&diff=3630Test Descriptions2019-08-23T22:29:58Z<p>Jnunez: Added sanity-pcc entry</p>
<hr />
<div>== Lustre Test Framework ==<br />
<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
! Description<br />
|-<br />
|data-sort-value="acceptance-small"| [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/acceptance-small.sh acceptance-small.sh (acc-sm)]<br />
|The acceptance-small.sh script is a wrapper around auster that runs the test group '[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/test-groups/regression regression]' unless tests are specified on the command line.<br />
|-<br />
|data-sort-value="auster"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/auster auster]<br />
|auster is used to run the Lustre tests. It can be used to run groups of tests, individual tests, or sub-tests. Provides setup and cleanup. <br />
|-<br />
|data-sort-value="functions"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/functions.sh functions.sh]<br />
|Provides functions for the run_*.sh tests, such as run_dd.sh or run_dbench.sh<br />
|-<br />
|data-sort-value="test-framework"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/test-framework.sh test-framework.sh]<br />
|Provides the fundamental functions needed by tests to create, setup, verify, start, stop, and reformat a Lustre filesystem. <br />
|}<br />
<br />
See the [[TestingLustreCode]] page for details on how to run these test scripts.<br />
<br />
== Lustre Unit, Feature, and Regression Tests ==<br />
<br />
{| class="wikitable"<br />
|+Status Key<br />
|-<br />
|<span style="color:green">Active</span><br />
|Test suite has been run on Maloo or committed to in last year.<br />
|-<br />
|<span style="color:blue">Inactive</span><br />
|Test suite has not been run on Maloo or committed to in over a year.<br />
|-<br />
|<span style="color:red">Deprecated</span><br />
|Test suite has been removed or replaced.<br />
|}<br />
<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Status<br />
!Test Description<br />
|-<br />
|data-sort-value="conf-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/conf-sanity.sh conf-sanity]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify the configuration tools, and runs Lustre with multiple different setups to ensure correct operation in unusual system configurations. <br />
|-<br />
|data-sort-value=dne-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/dne_sanity.sh dne_sanity]<br />
|<span style="color:blue">Inactive</span><br />
|Run sanity parallel on different directories at the same time.<br />
|-<br />
|data-sort-value="insanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/insanity.sh insanity]<br />
|<span style="color:green">Active</span><br />
|A set of tests that verify the multiple concurrent failure conditions. <br />
|-<br />
|data-sort-value="large-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/large-scale.sh large-scale]<br />
|<span style="color:green">Active</span><br />
|Large-scale tests that verify version-based recovery features. <br />
|-<br />
|data-sort-value="large-lun" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/large-lun.sh large-lun]<br />
|<span style="color:green">Active</span><br />
|Large LUN test<br />
|-<br />
|data-sort-value="lfsck" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lfsck.sh lfsck]<br />
|<span style="color:red">Deprecated</span><br />
|Replaced by sanity-lfsck. <br />
|-<br />
|data-sort-value="lfsck-performance" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lfsck-performance.sh lfsck-performance]<br />
|<span style="color:green">Active</span><br />
|lfsck performance test for the cases: lfsck with load, lfsck during create, backup/restore, simulate upgrade from 1.8.<br />
|-<br />
|data-sort-value="liblustre" | liblustre<br />
|<span style="color:red">Deprecated</span><br />
|Run tests linked to liblustre client library <br />
|-<br />
|data-sort-value="lustre-rsync-test" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lustre-rsync-test.sh lustre-rsync-test]<br />
|<span style="color:green">Active</span><br />
|Verifies the lustre_rsync (replication) feature. <br />
|-<br />
|data-sort-value="metadata-updates" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/metadata-updates.sh metadata-updates]<br />
|<span style="color:green">Active</span><br />
| Tests that metadata updates are properly completed when multiple clients create/delete files and modify the attributes of files.<br />
|-<br />
|data-sort-value="mmp" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/mmp.sh mmp]<br />
|<span style="color:green">Active</span><br />
|Tests for multiple mount protection (MMP) feature.<br />
|-<br />
|data-sort-value="ost-pools" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/ost-pools.sh ost-pools]<br />
|<span style="color:green">Active</span><br />
|Tests that exercises the OST pools feature.<br />
|-<br />
|data-sort-value="performance-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/performance-sanity.sh performance-sanity]<br />
|<span style="color:green">Active</span><br />
|Performance mdsrate tests (small file create/open/delete, large file create/open/delete, lookup rate 10M file dir, lookup rate 10M file 10 dir, getattr small file, and getattr large files). <br />
|-<br />
|data-sort-value="parallel-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale.sh parallel-scale]<br />
|<span style="color:green">Active</span><br />
|Runs functional tests (connectathon, cascading_rw, write_disjoint, write_append_truncate, parallel_grouplock, statahead), performance tests (IOR, compilebench and metabench), and a stress test (simul). <br />
|-<br />
|data-sort-value="parallel-scale-cifs" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-cifs.sh parallel-scale-cifs]<br />
|<span style="color:green">Active</span><br />
|Tests Lustre exported via Samba and runs concurrent load compilebench, dbench, fsx, and iozone on Samba clients. The test assumes that Samba server and clients have necessary packages installed.<br />
|-<br />
|data-sort-value="parallel-scale-nfs" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfs.sh parallel-scale-nfs]<br />
|<span style="color:green">Active</span><br />
| Called by parallel-scale-nfsv3.sh and parallel-scale-nfsv4.sh with a version specified.<br />
|-<br />
|data-sort-value="parallel-scale-nfsv3" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfsv3.sh parallel-scale-nfsv3]<br />
|<span style="color:green">Active</span><br />
|Provide setup nfs within auster framework<br />
|-<br />
|data-sort-value="parallel-scale-nfsv4" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfsv4.sh parallel-scale-nfsv4]<br />
|<span style="color:green">Active</span><br />
|Provide setup nfs within auster framework<br />
|-<br />
|data-sort-value="posix" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/posix.sh posix]<br />
|<span style="color:green">Active</span><br />
|Automate POSIX compliance testing. Assuming that the POSIX source already installed, on the system, setup loop back ext4 filesystem, then install, build and run POSIX binaries on ext4. Run POSIX again Lustre and compare results from ext4 and Lustre.<br />
|-<br />
|data-sort-value="racer" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/racer.sh racer]<br />
|<span style="color:green">Active</span><br />
|Tests for filesystem race conditions by concurrently creating, moving, deleting, etc. a set of files. <br />
|-<br />
|data-sort-value="recovery-double-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-double-scale.sh recovery-double-scale]<br />
|<span style="color:green">Active</span><br />
|Failover test for all pair-wise combinations of node failures. <br />
|-<br />
|data-sort-value="recovery-mds-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-mds-scale.sh recovery-mds-scale]<br />
|<span style="color:green">Active</span><br />
|The server failover test: for a duration of 24 hours, repeatedly fail over a random facet (MDS or OST) at 10 minute intervals and verify that no application errors occur. <br />
|-<br />
|data-sort-value="recovery-random-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-random-scale.sh recovery-random-scale]<br />
|<span style="color:green">Active</span><br />
|Verifies client failure not affecting other clients. <br />
|-<br />
|data-sort-value="recovery-small" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-small.sh recovery-small]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify RPC replay after communications failure. <br />
|-<br />
|data-sort-value="replay-dual" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-dual.sh replay-dual]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify the recovery from two clients after server failure. <br />
|-<br />
|data-sort-value="replay-ost-single" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-ost-single.sh replay-ost-single]<br />
|<span style="color:green">Active</span><br />
| A set of unit tests that verify recovery after OST failure. <br />
|-<br />
|data-sort-value="replay-single" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-single.sh replay-single]<br />
|<span style="color:green">Active</span><br />
| A set of unit tests that verify recovery after MDS failure. <br />
|-<br />
|data-sort-value="replay-vbr" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-vbr.sh replay-vbr]<br />
|<span style="color:green">Active</span><br />
|Verifies version-based recovery feature. <br />
|-<br />
|data-sort-value="runtests" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/runtests runtests]<br />
|<span style="color:green">Active</span><br />
|Simple basic regression test that verifies data persistence across write, unmount, and remount. This is one of the few tests that verifies data integrity across a full filesystem shutdown and remount, unlike many tests which at most only verify the existence/size of files. <br />
|-<br />
|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity.sh sanity]<br />
|<span style="color:green">Active</span><br />
|A set of regression tests that verify operation under normal operating conditions. This tests a large number of unusual operations that have previously caused functional or data correctness issues with Lustre. Some of the tests are Lustre specific, and hook into the Lustre fault injection framework using the "lctl set_param fail_loc=X" command to activate triggers in the code to simulate unusual operating conditions that would otherwise be difficult or impossible to simulate. <br />
|-<br />
|data-sort-value="sanityn" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanityn.sh sanityn]<br />
|<span style="color:green">Active</span><br />
|Tests that verify operations from two clients under normal operating conditions. This is done by mounting the same filesystem twice on a single client, in order to allow a single script/program to execute and verify filesystem operations on multiple "clients" without having to be a distributed program itself.<br />
|-<br />
|data-sort-value="sanity-benchmark" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-benchmark.sh sanity-benchmark]<br />
|<span style="color:green">Active</span><br />
|Test basic functionality of the filesystem using simple benchmarks. Runs dbench, bonnie++, iozone, fsx, and pios.<br />
|-<br />
|data-sort-value="sanity-dom" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-dom.sh sanity-dom]<br />
|<span style="color:green">Active</span><br />
|Sanity test the Data on MDT feature.<br />
|-<br />
|data-sort-value="sanity-flr" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-flr.sh sanity-flr]<br />
|<span style="color:green">Active</span><br />
|Sanity test the File Level Redundancy feature.<br />
|-<br />
|data-sort-value="sanity-gss" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-gss.sh sanity-gss]<br />
|<span style="color:green">Active</span><br />
|Verifies GSSAPI features. A mechanism-agnostic test suite for just the GSSAPI code itself using the gssnull security flavor, which in turn uses the null GSSAPI mechanism.<br />
|-<br />
|data-sort-value="sanity-hsm" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-hsm.sh sanity-hsm]<br />
|<span style="color:green">Active</span><br />
|Sanity test for HSM feature.<br />
|-<br />
|data-sort-value="sanity-krb5" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-krb5.sh sanity-krb5]<br />
|<span style="color:green">Active</span><br />
|Verifies Kerberos features.<br />
|-<br />
|data-sort-value="sanity-lfsck" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-lfsck.sh sanity-lfsck]<br />
|<span style="color:green">Active</span><br />
|Sanity test for lfsck<br />
|-<br />
|data-sort-value="sanity-pcc" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-pcc.sh sanity-pcc]<br />
|<span style="color:green">Active</span><br />
|A set of tests verifying basic functionality of the Persistent Client Cache feature.<br />
|-<br />
|data-sort-value="sanity-pfl" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-pfl.sh sanity-pfl]<br />
|<span style="color:green">Active</span><br />
|Sanity tests for the Progressive File Layout feature.<br />
|-<br />
|data-sort-value="sanity-quota" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-quota.sh sanity-quota]<br />
|<span style="color:green">Active</span><br />
|A set of tests that verify filesystem quotas. <br />
|-<br />
|data-sort-value="sanity-scrub" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-scrub.sh sanity-scrub]<br />
|<span style="color:green">Active</span><br />
|Verifies OI scrub functionality.<br />
|-<br />
|data-sort-value="sanity-sec" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-sec.sh sanity-sec]<br />
|<span style="color:green">Active</span><br />
|Verifies Lustre identity features. , including UID/GID mapping<br />
|-<br />
|data-sort-value="scrub-performance" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/scrum-performance.sh scrub-performance]<br />
|<span style="color:green">Active</span><br />
|Test OI scrub performance<br />
|}<br />
<br />
== Benchmark Scripts ==<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Status<br />
!Script Description<br />
|-<br />
|data-sort-value="lnet-selftest" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lnet-selftest.sh lnet-selftest]<br />
|<span style="color:green">Active</span><br />
|LNET self-test is a kernel module that runs over LNET and the Lustre network drivers (LNDs). It is designed to test the connection ability of the Lustre network, run regression tests of the Lustre network, and test performance of the Lustre network.<br />
|-<br />
|data-sort-value="obdfilter-survey" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/obdfilter-survey.sh obdfilter-survey]<br />
|<span style="color:green">Active</span><br />
|This survey script does sequential I/O with varying numbers of threads and objects (files) by using lctl to drive the echo_client connected to local or remote obdfilter instances, or remote obdecho instances. It can be used to characterize the performance of the following Lustre components.<br />
|-<br />
|data-sort-value="sgpdd-survey" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sgpdd-survey.sh sgpdd-survey]<br />
|<span style="color:green">Active</span><br />
|This survey may be used to characterize the performance of a SCSI device. It simulates an OST serving multiple stripe files. The data gathered by it can help set expectations for the performance of a Lustre OST exporting the device.<br />
|}<br />
<br />
== Auxiliary Tests and Benchmarks Tools == <br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Script Description<br />
|-<br />
|data-sort-value="bonnie" | [http://www.coker.com.au/bonnie++/ bonnie++]<br />
|Bonnie++ benchmark for creation, reading, and deleting many small files.<br />
|-<br />
|data-sort-value="dbench" | [https://dbench.samba.org/ dbench]<br />
|Dbench benchmark for simulating N clients to produce the filesystem load.<br />
|-<br />
|data-sort-value="fsx" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/fsx.c fsx]<br />
|The file system exerciser was developed outside of Lustre and is intended to stress test unusual IO and file operations. It does buffered and mmap reads and writes with random size and offset, truncate, open, close on a file. It verifies data integrity after each step. A lustre-developed extension allows fsx to run against multiple mountpoints to verify distributed IO operation correctness. (Source [https://wiki.whamcloud.com/display/PUB/Auster Auster])<br />
|-<br />
|data-sort-value="iozone" | [http://www.iozone.org/ iozone]<br />
|Iozone benchmark for generating and measuring a variety of file operations.<br />
|-<br />
|data-sort-value="oos.sh" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/oos.sh oos.sh]<br />
|Script used to check out-of-space detection in sanity.sh test 64b.<br />
|-<br />
|data-sort-value="oos2.sh" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/oos2.sh oos2.sh]<br />
|Script used to check out-of-space detection with multiple writers in sanityn.sh test 15.<br />
|-<br />
|data-sort-value="pios" | pios<br />
|pios is a parallel IO simulator. It can simulate shared file per process and file per process IO. Used in sanity-benchmark. pios-1.2-wc1 is available from the build of the toolkit repo for various distributions, e.g. RHEL6 x86_64 https://build.whamcloud.com/job/toolkit/arch=x86_64,distro=el6/lastSuccessfulBuild/artifact/_topdir/RPMS/x86_64/<br />
|}<br />
<br />
[[Category:Testing]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3629Test Groups for Patch Testing2019-08-23T22:25:00Z<p>Jnunez: /* Enforced Test Groups */</p>
<hr />
<div>When a patch is submitted to Lustre, automated testing is run against a build of Lustre with the submitted patch. Some of these test groups must pass testing, enforced test groups, and other, optional, test groups may fail.<br />
== Enforced Test Groups ==<br />
There are ten test groups that every patch must pass in order for the patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and the test suites in each test group are run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-ldiskfs-arm<br />
!review-zfs<br />
|-<br />
|sanity <br />
|sanity <br />
|sanity-quota<br />
|-<br />
|lnet-selftest <br />
|lnet-selftest <br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|replay-single <br />
|-<br />
|<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|insanity<br />
|}<br />
<br />
Test groups confgured with DNE; all tests run with 2 MDSs with 2 MDTs each.<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-zfs-part-3<br />
!review-dne-part-4<br />
!review-dne-zfs-part-4<br />
|-<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|conf-sanity <br />
|mmp <br />
|mmp <br />
|-<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|<br />
|replay-single <br />
|replay-single <br />
|-<br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
|<br />
| <br />
|sanity-pfl<br />
|sanity-pfl<br />
|-<br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|<br />
|sanity-flr<br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|<br />
|sanity-dom<br />
|sanity-dom<br />
|-<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|<br />
|sanity-quota<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|<br />
|replay-ost-single<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|<br />
|insanity<br />
|insanity<br />
|-<br />
|<br />
|<br />
|sanity-pcc<br />
|sanity-pcc<br />
|<br />
|<br />
|<br />
|<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there is one optional test group that does not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
There are no optional test groups at this time.</div>Jnunezhttp://wiki.lustre.org/index.php?title=User:Jnunez&diff=3528User:Jnunez2019-05-28T17:44:42Z<p>Jnunez: Updated current position/company</p>
<hr />
<div>James Nunez is a member of the Quality Engineering and Test Team at Whamcloud. His primary concern is the coverage, correctness and efficiency of the Lustre test suites and testing of new Lustre features. Previously, James supported Lustre users with bug fixes, patch management, and supported large sites including Oak Ridge National Lab and Los Alamos National Lab. Prior to joining Whamcloud, James was a Quality Engineer with the High Performance Data Division at Intel Corporation, a scientist at Los Alamos National Lab where he explored I/O, file systems and storage for exascale systems, involved with the ASC File System Path Forward effort to create a high scalable global parallel file system based on secure object storage technology, organized the High End Computing File Systems and I/O (HECFSIO) Workshop for several years, and concerned with evaluating and benchmarking HPC file systems, I/O middleware solutions, and understanding the I/O interface and application of new storage innovations to material science applications.</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3527Test Groups for Patch Testing2019-05-28T17:39:56Z<p>Jnunez: Moved optional test group to mandatory</p>
<hr />
<div>When a patch is submitted to Lustre, automated testing is run against a build of Lustre with the submitted patch. Some of these test groups must pass testing, enforced test groups, and other, optional, test groups may fail.<br />
== Enforced Test Groups ==<br />
There are ten test groups that every patch must pass in order for the patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and the test suites in each test group are run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-ldiskfs-arm<br />
!review-zfs<br />
|-<br />
|sanity <br />
|sanity <br />
|sanity-quota<br />
|-<br />
|lnet-selftest <br />
|lnet-selftest <br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|replay-single <br />
|-<br />
|<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|insanity<br />
|}<br />
<br />
Test groups confgured with DNE; all tests run with 2 MDSs with 2 MDTs each.<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-zfs-part-3<br />
!review-dne-part-4<br />
!review-dne-zfs-part-4<br />
|-<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|conf-sanity <br />
|mmp <br />
|mmp <br />
|-<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|<br />
|replay-single <br />
|replay-single <br />
|-<br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
|<br />
| <br />
|sanity-pfl<br />
|sanity-pfl<br />
|-<br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|<br />
|sanity-flr<br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|<br />
|sanity-dom<br />
|sanity-dom<br />
|-<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|<br />
|sanity-quota<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|<br />
|replay-ost-single<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|<br />
|insanity<br />
|insanity<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there is one optional test group that does not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
There are no optional test groups at this time.</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3498Test Groups for Patch Testing2019-03-07T17:44:11Z<p>Jnunez: Moved optional test group to mandatory</p>
<hr />
<div>When a patch is submitted to Lustre, automated testing is run against a build of Lustre with the submitted patch. Some of these test groups must pass testing, enforced test groups, and other, optional, test groups may fail.<br />
== Enforced Test Groups ==<br />
There are ten test groups that every patch must pass in order for the patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and the test suites in each test group are run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs<br />
|-<br />
|sanity <br />
|sanity-quota<br />
|-<br />
|lnet-selftest <br />
|sanity-flr<br />
|-<br />
|<br />
|replay-single <br />
|-<br />
|<br />
|replay-ost-single<br />
<br />
|-<br />
|<br />
|insanity<br />
|}<br />
<br />
Test groups confgured with DNE; all tests run with 2 MDSs with 2 MDTs each.<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-zfs-part-3<br />
!review-dne-part-4<br />
!review-dne-zfs-part-4<br />
|-<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|conf-sanity <br />
|mmp <br />
|mmp <br />
|-<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|<br />
|replay-single <br />
|replay-single <br />
|-<br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
|<br />
| <br />
|sanity-pfl<br />
|sanity-pfl<br />
|-<br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|<br />
|sanity-flr<br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|<br />
|sanity-dom<br />
|sanity-dom<br />
|-<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|<br />
|sanity-quota<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|<br />
|replay-ost-single<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|<br />
|insanity<br />
|insanity<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there is one optional test group that does not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
The Lustre test suites that compose each optional test group are:<br />
{| class="wikitable"<br />
! style="text-align:left;" |review-ldiskfs-arm<br />
|-<br />
|sanity<br />
|-<br />
|lnet-selftest<br />
|-<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Development&diff=3486Development2019-02-07T19:19:40Z<p>Jnunez: Changed "next release under development" to 2.13.0</p>
<hr />
<div>== Lustre Development Activities ==<br />
The next release under development (accepting new features)<br />
* [[Release 2.13.0]]<br />
<br />
If you are looking for small development projects to add minor improvements to Lustre and/or become more familiar with the code and development process, there is a keyword '''easy''' that is added to tickets that are suitable:<br />
[https://jira.hpdd.intel.com/issues/?jql=labels%3Deasy%20AND%20resolution%3Dunresolved easier development items]<br />
<br />
== Submitting Changes ==<br />
<br />
The [[Submitting Changes]] page covers steps you'll need to follow to contribute code changes.<br />
<br />
== Code Reviews ==<br />
<br />
The [[Code Reviewers]] page lists people willing to perform code reviews on particular sections of the Lustre code.<br />
<br />
== Upstream contributing ==<br />
<br />
The [[Upstream contributing]] page covers how to contribute to the Linux kernel Lustre client.<br />
<br />
== Updating Documentation ==<br />
<br />
Updating the [http://lustre.org/documentation Lustre User Manual] is a very useful way for non-coders to contribute to Lustre.<br />
See [https://wiki.hpdd.intel.com/display/PUB/Making+changes+to+the+Lustre+Manual Making Changes to the Lustre Manual] for more information on how to contribute changes, and the list of [https://jira.hpdd.intel.com/issues/?jql=project%3DLUDOC%20AND%20resolution%3Dunresolved open documentation tickets].<br />
<br />
== Developer Meetings ==<br />
<br />
* [http://wiki.opensfs.org/Lustre_Developer_Meeting_2015-01-22 Developer Meeting 2015-01-22]<br />
<br />
== Feature Development ==<br />
<br />
All known development efforts are tracked on the [[Projects]] page. The [[:Category:Architecture|Architecture]] and [[:Category:Design|Design]] documents of various projects are available for review and future reference.<br />
<br />
Please see [[Lustre Coding Style Guidelines]] and [[Lustre Style Guide Includes]] for information about writing Lustre code, and [[Submitting Changes]] for details on how to submit patches. There is also [[Lustre Script Coding Style]] for writing test scripts.<br />
<br />
Patches and landing status can be tracked via some Gerrit searches courtesy of John Hammond:<br />
<br />
* [https://wiki.whamcloud.com/display/PUB/Patch+Status]<br />
<br />
* [https://wiki.whamcloud.com/display/PUB/Patch+Status+2?src=contextnavpagetreemode]<br />
<br />
== Protocol Documentation ==<br />
<br />
There is some work-in-progress [https://build.hpdd.intel.com/job/lustre-protocol-reviews/lastSuccessfulBuild/artifact/protocol.html Lustre Protocol Documentation] available ([https://build.hpdd.intel.com/job/lustre-protocol-reviews/lastSuccessfulBuild/artifact/protocol.pdf PDF format]). While the documentation is not complete, it may still prove to be a valuable resource for developers, and contributions and improvements to the [https://review.whamcloud.com/#/q/project:doc/protocol protocol documentation project] are welcome.<br />
<br />
[[Category: Development]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3454Test Groups for Patch Testing2019-01-24T19:20:03Z<p>Jnunez: Updated optional and enforced test groups.</p>
<hr />
<div>When a patch is submitted to Lustre, automated testing is run against a build of Lustre with the submitted patch. Some of these test groups must pass testing, enforced test groups, and others may fail, optional test groups.<br />
== Enforced Test Groups ==<br />
There are nine test groups that every patch submitted to Lustre must pass in order for a patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs<br />
|-<br />
|sanity <br />
|sanity-quota<br />
|-<br />
|lnet-selftest <br />
|sanity-flr<br />
|-<br />
|<br />
|replay-single <br />
|-<br />
|<br />
|replay-ost-single<br />
<br />
|-<br />
|<br />
|insanity<br />
|}<br />
<br />
Test groups confgured with DNE; all tests run with 2 MDSs with 2 MDTs each.<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-zfs-part-3<br />
!review-dne-part-4<br />
|-<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|conf-sanity <br />
|mmp <br />
|-<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|<br />
|replay-single <br />
|-<br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
|<br />
| <br />
|sanity-pfl<br />
|-<br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|<br />
|insanity<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there are two optional test groups that do not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
The Lustre test suites that compose each optional test group are:<br />
{| class="wikitable"<br />
! style="text-align:left;" |review-ldiskfs-arm<br />
!review-dne-zfs-part-4<br />
|-<br />
|sanity<br />
|mmp<br />
|-<br />
|lnet-selftest<br />
|replay-single<br />
|-<br />
|<br />
|sanity-pfl<br />
|-<br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|insanity<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Release_2.13.0&diff=3451Release 2.13.02019-01-10T19:19:36Z<p>Jnunez: Updated e2fsprogs version</p>
<hr />
<div>(Draft version - work in progress)<br />
<br />
== Current Schedule ==<br />
<br />
* March 31 2019 - Feature Cut-off (Only features will patches already in review at this point still considered)<br />
* Apr 30 2019 - Feature Freeze (Final date for features to land for 2.13)<br />
* June 30 2019 - Code Freeze<br />
* July 31 2019 - Release 2.13.0<br />
<br />
(Note: these are very rough guidelines. For more accurate details on the schedule please refer to LWG call minutes)<br />
<br />
== Scope ==<br />
<br />
=== Test Matrix ===<br />
* Servers: RHEL 7.6<br />
* Clients RHEL 7.6, SLES 12 SP4, Ubuntu 18.04<br />
* OFED: inkernel<br />
* E2FSProgs: v1.44.3.wc1<br />
* Interoperability: Latest 2.12.X Servers/Clients<br />
<br />
=== Features ===<br />
<br />
The following features are under active development and could be possible for landing during the 2.13 release cycle<br />
<br />
{| class="wikitable sortable"<br />
|-<br />
! Feature !! Developers !! Reviewers !! Testers !! Docs !! Confirmed in 2.13<br />
|-<br />
<br />
| [https://jira.whamcloud.com/browse/LU-10092 Persistent Client Cache] || Li Xi || TBD || TBD || TBD || Not Yet<br />
|-<br />
| [https://jira.whamcloud.com/browse/LU-9121 NW Selection Policy] || Amir Shehata || TBD || TBD || TBD || Not Yet<br />
|-<br />
| [https://jira.whamcloud.com/browse/LU-10070 Self Extending Layouts] || Patrick Farrell || TBD || TBD || TBD || Not Yet<br />
|-<br />
|}<br />
<br />
=== General Work and Maintenance ===<br />
<br />
From the [https://jira.whamcloud.com/browse/LU Lustre project page] in the [https://jira.whamcloud.com Lustre issue tracker], we can see a dashboard for the project. On that page under the "Versions: Unreleased" section, there are links to future releases and all of the issues that are either targeted to be addressed in that release, or are already addressed for the release. Here is a shortcut to Lustre 2.13.0's issue summary page:<br />
<br />
* [https://jira.whamcloud.com/projects/LU/versions/14290 Lustre 2.13.0 Issues]<br />
<br />
Any issue that contains "Lustre 2.13.0" in the "Fix Version/s" field of a ticket is intended to be fixed for version 2.13.0. The Lustre 2.13.0 Issues list is fluid, and will be updated on a continual basis as resources and priorities change.<br />
<br />
If you would like to own one or more tasks for the release but are not currently listed in the drop-down list of developers in JIRA then please email [mailto:peter.a.jones@intel.com Peter Jones] to get that setup<br />
<br />
A convenience search filter is supplied for anyone looking for work that needs to be done for 2.13.0:<br />
<br />
* [https://jira.whamcloud.com/issues/?filter=15514 Lustre 2.13.0 Unassigned Issues]<br />
<br />
In addition, a search filter is available for anyone looking to start Lustre development with some simple development tasks, or anyone with a few minutes/hours available to improve Lustre:<br />
<br />
* [https://jira.whamcloud.com/issues/?jql=resolution=Unresolved%20AND%20labels=easy Lustre easy-to-fix issues]<br />
<br />
[[Category: Releases]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3443Test Groups for Patch Testing2018-12-06T16:31:58Z<p>Jnunez: Added review-ldiskfs-arm</p>
<hr />
<div>When a patch is submitted to Lustre, automated testing is run against a build of Lustre with the submitted patch. Some of these test groups must pass testing, enforced test groups, and others may fail, optional test groups.<br />
== Enforced Test Groups ==<br />
There are eight test groups that every patch submitted to Lustre must pass in order for a patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs<br />
!review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-part-4<br />
|-<br />
|sanity <br />
|sanity-quota<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|mmp <br />
<br />
|-<br />
|lnet-selftest <br />
|sanity-flr<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|replay-single <br />
|-<br />
|<br />
|replay-single <br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
| <br />
|sanity-pfl<br />
|-<br />
|<br />
|conf-sanity <br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|replay-ost-single <br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|insanity<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|insanity<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there are three optional test groups that do not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
The Lustre test suites that compose each optional test group are:<br />
{| class="wikitable"<br />
! style="text-align:left;" |review-ldiskfs-arm<br />
!review-dne-zfs-part-3<br />
!review-dne-zfs-part-4<br />
|-<br />
|sanity<br />
|conf-sanity <br />
|mmp<br />
|-<br />
|lnet-selftest<br />
|<br />
|replay-single<br />
|-<br />
|<br />
| <br />
|sanity-pfl<br />
|-<br />
|<br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|insanity<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3421Test Groups for Patch Testing2018-09-27T14:34:52Z<p>Jnunez: remove racer from review-ldiskfs</p>
<hr />
<div>When a patch is submitted to Lustre, automated testing is run against a build of Lustre with the submitted patch. Some of these test groups must pass testing, enforced test groups, and others may fail, optional test groups.<br />
== Enforced Test Groups ==<br />
There are eight test groups that every patch submitted to Lustre must pass in order for a patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs<br />
!review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-part-4<br />
|-<br />
|sanity <br />
|sanity-quota<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|mmp <br />
<br />
|-<br />
|lnet-selftest <br />
|sanity-flr<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|replay-single <br />
|-<br />
|<br />
|replay-single <br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
| <br />
|sanity-pfl<br />
|-<br />
|<br />
|conf-sanity <br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|replay-ost-single <br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|insanity<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|insanity<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there are two optional test groups that do not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
The Lustre test suites that compose each optional test group are:<br />
{| class="wikitable"<br />
! style="text-align:left;" |review-dne-zfs-part-3<br />
!review-dne-zfs-part-4<br />
|-<br />
|conf-sanity <br />
|mmp<br />
|-<br />
|<br />
|replay-single<br />
|-<br />
| <br />
|sanity-pfl<br />
|-<br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|insanity<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3415Test Groups for Patch Testing2018-08-28T22:54:03Z<p>Jnunez: Update test groups and test suites in each</p>
<hr />
<div>When a patch is submitted to Lustre, automated testing is run against a build of Lustre with the submitted patch. Some of these test groups must pass testing, enforced test groups, and others may fail, optional test groups.<br />
== Enforced Test Groups ==<br />
There are eight test groups that every patch submitted to Lustre must pass in order for a patch to be considered for landing. If there is a failure in any one of these test sessions, a patch will not be allowed to land to the Lustre branch. <br />
The Lustre test suites that compose each test group are listed in the following table and run in the order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs<br />
!review-dne-part-1<br />
!review-dne-zfs-part-1<br />
!review-dne-part-2<br />
!review-dne-zfs-part-2<br />
!review-dne-part-3<br />
!review-dne-part-4<br />
|-<br />
|sanity <br />
|sanity-quota<br />
|sanity <br />
|sanity <br />
|runtests <br />
|runtests <br />
|conf-sanity <br />
|mmp <br />
<br />
|-<br />
|lnet-selftest <br />
|sanity-flr<br />
|sanityn <br />
|sanityn <br />
|ost-pools <br />
|ost-pools <br />
| <br />
|replay-single <br />
|-<br />
|racer <br />
|replay-single <br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
|sanity-hsm<br />
| <br />
|sanity-pfl<br />
|-<br />
|<br />
|conf-sanity <br />
|lustre-rsync-test<br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|sanity-scrub <br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|replay-ost-single <br />
|<br />
|<br />
|sanity-lfsck <br />
|sanity-lfsck <br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|insanity<br />
|<br />
|<br />
|sanity-sec <br />
|sanity-sec <br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|<br />
|<br />
|<br />
|mds-survey<br />
|mds-survey<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|<br />
|<br />
|<br />
|large-scale<br />
|large-scale<br />
|<br />
|insanity<br />
|}<br />
<br />
== Optional Test Groups ==<br />
In addition to the enforced test groups, there are two optional test groups that do not influence if a patch can land. These optional test groups will become enforced test groups for patch landing in the near future and should be reviewed for failures. <br />
<br />
The Lustre test suites that compose each optional test group are:<br />
{| class="wikitable"<br />
! style="text-align:left;" |review-dne-zfs-part-3<br />
!review-dne-zfs-part-4<br />
|-<br />
|conf-sanity <br />
|mmp<br />
|-<br />
|<br />
|replay-single<br />
|-<br />
| <br />
|sanity-pfl<br />
|-<br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|insanity<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Release_2.12.0&diff=3359Release 2.12.02018-06-25T21:57:53Z<p>Jnunez: Changed Tester for LNET Health</p>
<hr />
<div>(Draft version - work in progress)<br />
<br />
== Current Schedule ==<br />
<br />
* June 30 2018 - Feature Cut-off (Only features will patches already in review at this point still considered)<br />
* July 31 2018 - Feature Freeze (Final date for features to land for 2.12)<br />
* Sep 30 2018 - Code Freeze<br />
* Oct 31 2018 - Release 2.12.0<br />
<br />
(Note: these are very rough guidelines. For more accurate details on the schedule please refer to LWG call minutes)<br />
<br />
== Scope ==<br />
<br />
=== Test Matrix ===<br />
* Servers: RHEL 7.5<br />
* Clients RHEL 7.5, SLES 12 SP3, Ubuntu 18.04<br />
* OFED: inkernel<br />
* E2FSProgs: v1.42.13.wc6<br />
* Interoperability: 2.11, Latest 2.10.X Servers/Clients<br />
<br />
=== Features ===<br />
<br />
The following features are under active development and could be possible for landing during the 2.12 release cycle<br />
<br />
{| class="wikitable sortable"<br />
|-<br />
! Feature !! Developers !! Reviewers !! Testers !! Docs !! Confirmed in 2.12<br />
|-<br />
<br />
| [https://jira.hpdd.intel.com/browse/LU-9120 LNet Network Health] || Amir Shehata || Sonia Sharma, Dmitry Eremin || TBD || Amir Shehata, [https://jira.hpdd.intel.com/browse/LUDOC-396 LUDOC-396] || TBD<br />
|-<br />
| [https://jira.hpdd.intel.com/browse/LU-4684 DNE Directory Restriping] || Lai Siyao || Andreas Dilger, Alex Zhuravlev || Sarah Liu || Lai Siyao, [https://jira.hpdd.intel.com/browse/LUDOC-395 LUDOC-395] || TBD<br />
|-<br />
| [https://jira.hpdd.intel.com/browse/LU-9538 Lazy Size on MDT] || Yingjin Qian || Alex Zhuravlev Lai Siyao || Rahul Deshmukh || Yingjin Qian, [https://jira.hpdd.intel.com/browse/LUDOC-402 LUDOC-402] || TBD<br />
|-<br />
|}<br />
<br />
=== General Work and Maintenance ===<br />
<br />
From the [https://jira.hpdd.intel.com/browse/LU Lustre project page] in the [https://jira.hpdd.intel.com Lustre issue tracker], we can see a dashboard for the project. On that page under the "Versions: Unreleased" section, there are links to future releases and all of the issues that are either targeted to be addressed in that release, or are already addressed for the release. Here is a shortcut to Lustre 2.12.0's issue summary page:<br />
<br />
* [https://jira.hpdd.intel.com/projects/LU/versions/13495 Lustre 2.12.0 Issues]<br />
<br />
Any issue that contains "Lustre 2.12.0" in the "Fix Version/s" field of a ticket is intended to be fixed for version 2.12.0. The Lustre 2.12.0 Issues list is fluid, and will be updated on a continual basis as resources and priorities change.<br />
<br />
If you would like to own one or more tasks for the release but are not currently listed in the drop-down list of developers in JIRA then please email [mailto:peter.a.jones@intel.com Peter Jones] to get that setup<br />
<br />
A convenience search filter is supplied for anyone looking for work that needs to be done for 2.12.0:<br />
<br />
* [https://jira.hpdd.intel.com/issues/?filter=15115 Lustre 2.12.0 Unassigned Issues]<br />
<br />
In addition, a search filter is available for anyone looking to start Lustre development with some simple development tasks, or anyone with a few minutes/hours available to improve Lustre:<br />
<br />
* [https://jira.hpdd.intel.com/issues/?jql=resolution=Unresolved%20AND%20labels=easy Lustre easy-to-fix issues]<br />
<br />
[[Category: Releases]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Groups_for_Patch_Testing&diff=3260Test Groups for Patch Testing2018-06-07T22:03:33Z<p>Jnunez: List of test suites run for each test group required for patch landings.</p>
<hr />
<div>There are seven mandatory test groups that every patch submitted to Lustre, community release, must pass in order for a patch to be considered for landing. In addition, there are two optional test groups that do not influence if a patch can land. These optional test groups will become madatory for patch landing soon and should be reviewed. The Lustre test suites that compose each test group are listed in the following table and run in the exact order below every time they are executed.<br />
<br />
{| class="wikitable"<br />
! style="text-align:left;" | review-ldiskfs<br />
!review-zfs-part-1<br />
!review-zfs-part-2<br />
!review-dne-part-1<br />
!review-dne-part-2<br />
!review-dne-part-3<br />
!review-dne-part-4<br />
|-<br />
|sanity <br />
|runtests<br />
|replay-single <br />
|sanity <br />
|runtests <br />
|conf-sanity <br />
|mmp <br />
<br />
|-<br />
|lnet-selftest <br />
|sanity <br />
|conf-sanity <br />
|sanityn <br />
|ost-pools <br />
| <br />
|replay-single <br />
|-<br />
|racer <br />
|sanityn <br />
|recovery-small <br />
|recovery-small <br />
|sanity-hsm<br />
| <br />
|sanity-pfl<br />
|-<br />
|<br />
|sanity-quota <br />
|replay-ost-single <br />
|lustre-rsync-test<br />
|sanity-scrub <br />
|<br />
|sanity-flr<br />
|-<br />
|<br />
|ost-pools <br />
|insanity <br />
|<br />
|sanity-lfsck <br />
|<br />
|sanity-dom<br />
|-<br />
|<br />
|sanity-lfsck<br />
|lustre-rsync-test<br />
|<br />
|sanity-sec <br />
|<br />
|sanity-quota<br />
|-<br />
|<br />
|sanity-hsm<br />
|large-scale <br />
|<br />
|mds-survey<br />
|<br />
|replay-ost-single<br />
|-<br />
|<br />
|sanity-flr<br />
|mds-survey<br />
|<br />
|large-scale<br />
|<br />
|insanity<br />
|}<br />
<br />
The optional test groups that are run for each patch are:<br />
{| class="wikitable"<br />
! style="text-align:left;" |review-dne-zfs-part-1<br />
!review-dne-zfs-part-2<br />
|-<br />
|sanity <br />
|runtests<br />
|-<br />
|sanityn <br />
|ost-pools<br />
|-<br />
|recovery-small <br />
|sanity-hsm<br />
|-<br />
|lustre-rsync-test<br />
|sanity-scrub<br />
|-<br />
|<br />
|sanity-lfsck<br />
|-<br />
|<br />
|sanity-sec<br />
|-<br />
|<br />
|mds-survey<br />
|-<br />
|<br />
|large-scale<br />
|}</div>Jnunezhttp://wiki.lustre.org/index.php?title=Testing&diff=3259Testing2018-06-07T21:23:54Z<p>Jnunez: Added new page for test groups</p>
<hr />
<div>* [[Testing HOWTO | Run Lustre Tests HOWTO]]<br />
* [[Test Descriptions | Test Framework and Descriptions of Unit, Regression, and Feature Tests]]<br />
* [[Testing Setup To Induce Race Conditions | Testing setup to induce otherwise hard to hit race conditions]]<br />
* [[Test Groups for Patch Testing | Test Groups for Patch Testing]]<br />
* [[Test Configuration Variables | Test Configuration and Environment Variables]]<br />
----<br />
Intel HPDD's testing results database for patches: [https://testing.hpdd.intel.com/ Maloo]<br />
<br />
Intel HPDD Wiki pages related to testing:<br />
* [https://wiki.hpdd.intel.com/display/PUB/Testing+a+Lustre+filesystem Testing a Lustre filesystem]<br />
* [https://wiki.hpdd.intel.com/display/PUB/Lustre+Test+Tools+Environment+Variables Lustre Test Tools Environment Variables]<br />
* [https://wiki.hpdd.intel.com/display/PUB/Auster Auster]<br />
----<br />
wiki.old.lustre.org pages related to testing:<br />
* [http://wiki.old.lustre.org/index.php/Acceptance_Small_%28acc-sm%29_Testing_on_Lustre Acceptance Small (acc-sm) Testing on Lustre]<br />
* [http://wiki.old.lustre.org/index.php/Testing_Lustre_Code Testing Lustre Code]<br />
<br />
[[Category:Testing]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Release_2.12.0&diff=3121Release 2.12.02018-04-05T17:33:24Z<p>Jnunez: Updated Tester for LNet Health</p>
<hr />
<div>(Draft version - work in progress)<br />
<br />
== Current Schedule ==<br />
<br />
* July 31 2018 - Feature Freeze (need to discuss more at LWG)<br />
* Sep 30 2018 - Code Freeze<br />
* Oct 31 2018 - Release 2.12.0<br />
<br />
(Note: these are very rough guidelines. For more accurate details on the schedule please refer to LWG call minutes)<br />
<br />
== Scope ==<br />
<br />
=== Test Matrix ===<br />
* Servers: RHEL 7.4 (likely need something more current?)<br />
* Clients RHEL 7.4, SLES 12 SP3, Ubuntu 16.04<br />
* OFED: inkernel<br />
* E2FSProgs: v1.42.13.wc6<br />
* Interoperability: 2.11, Latest 2.10.X Servers/Clients<br />
<br />
=== Features ===<br />
<br />
The following features are under active development and could be possible for landing during the 2.12 release cycle<br />
<br />
{| class="wikitable sortable"<br />
|-<br />
! Feature !! Developers !! Reviewers !! Testers !! Docs !! Confirmed in 2.12<br />
|-<br />
<br />
| [https://jira.hpdd.intel.com/browse/LU-9120 LNet Network Health] || Amir Shehata || Sonia Sharma, Dmitry Eremin || Saurabh Tandan || Amir Shehata, [https://jira.hpdd.intel.com/browse/LUDOC-396 LUDOC-396] || TBD<br />
|-<br />
| [https://jira.hpdd.intel.com/browse/LU-4684 DNE Directory Restriping] || Lai Siyao || Andreas Dilger, Alex Zhuravlev || Sarah Liu || Lai Siyao, [https://jira.hpdd.intel.com/browse/LUDOC-395 LUDOC-395] || TBD<br />
|-<br />
|}<br />
<br />
=== General Work and Maintenance ===<br />
<br />
From the [https://jira.hpdd.intel.com/browse/LU Lustre project page] in the [https://jira.hpdd.intel.com Lustre issue tracker], we can see a dashboard for the project. On that page under the "Versions: Unreleased" section, there are links to future releases and all of the issues that are either targeted to be addressed in that release, or are already addressed for the release. Here is a shortcut to Lustre 2.12.0's issue summary page:<br />
<br />
* [https://jira.hpdd.intel.com/projects/LU/versions/13495 Lustre 2.12.0 Issues]<br />
<br />
Any issue that contains "Lustre 2.12.0" in the "Fix Version/s" field of a ticket is intended to be fixed for version 2.12.0. The Lustre 2.12.0 Issues list is fluid, and will be updated on a continual basis as resources and priorities change.<br />
<br />
If you would like to own one or more tasks for the release but are not currently listed in the drop-down list of developers in JIRA then please email [mailto:peter.a.jones@intel.com Peter Jones] to get that setup<br />
<br />
A convenience search filter is supplied for anyone looking for work that needs to be done for 2.12.0:<br />
<br />
* [https://jira.hpdd.intel.com/issues/?filter=15115 Lustre 2.12.0 Unassigned Issues]<br />
<br />
In addition, a search filter is available for anyone looking to start Lustre development with some simple development tasks, or anyone with a few minutes/hours available to improve Lustre:<br />
<br />
* [https://jira.hpdd.intel.com/issues/?jql=resolution=Unresolved%20AND%20labels=easy Lustre easy-to-fix issues]<br />
<br />
[[Category: Releases]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Test_Descriptions&diff=3117Test Descriptions2018-04-04T22:26:10Z<p>Jnunez: Add sanity-dom, sanity-flr and sanity-pfl to list of Lustre test suites</p>
<hr />
<div>== Lustre Test Framework ==<br />
<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
! Description<br />
|-<br />
|data-sort-value="acceptance-small"| [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/acceptance-small.sh acceptance-small.sh (acc-sm)]<br />
|The acceptance-small.sh script is a wrapper around auster that runs the test group '[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/test-groups/regression regression]' unless tests are specified on the command line.<br />
|-<br />
|data-sort-value="auster"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/auster auster]<br />
|auster is used to run the Lustre tests. It can be used to run groups of tests, individual tests, or sub-tests. Provides setup and cleanup. <br />
|-<br />
|data-sort-value="functions"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/functions.sh functions.sh]<br />
|Provides functions for the run_*.sh tests, such as run_dd.sh or run_dbench.sh<br />
|-<br />
|data-sort-value="test-framework"|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/test-framework.sh test-framework.sh]<br />
|Provides the fundamental functions needed by tests to create, setup, verify, start, stop, and reformat a Lustre filesystem. <br />
|}<br />
<br />
See the [[TestingLustreCode]] page for details on how to run these test scripts.<br />
<br />
== Lustre Unit, Feature, and Regression Tests ==<br />
<br />
{| class="wikitable"<br />
|+Status Key<br />
|-<br />
|<span style="color:green">Active</span><br />
|Test suite has been run on Maloo or committed to in last year.<br />
|-<br />
|<span style="color:blue">Inactive</span><br />
|Test suite has not been run on Maloo or committed to in over a year.<br />
|-<br />
|<span style="color:red">Deprecated</span><br />
|Test suite has been removed or replaced.<br />
|}<br />
<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Status<br />
!Test Description<br />
|-<br />
|data-sort-value="conf-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/conf-sanity.sh conf-sanity]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify the configuration tools, and runs Lustre with multiple different setups to ensure correct operation in unusual system configurations. <br />
|-<br />
|data-sort-value=dne-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/dne_sanity.sh dne_sanity]<br />
|<span style="color:blue">Inactive</span><br />
|Run sanity parallel on different directories at the same time.<br />
|-<br />
|data-sort-value="insanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/insanity.sh insanity]<br />
|<span style="color:green">Active</span><br />
|A set of tests that verify the multiple concurrent failure conditions. <br />
|-<br />
|data-sort-value="large-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/large-scale.sh large-scale]<br />
|<span style="color:green">Active</span><br />
|Large-scale tests that verify version-based recovery features. <br />
|-<br />
|data-sort-value="large-lun" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/large-lun.sh large-lun]<br />
|<span style="color:green">Active</span><br />
|Large LUN test<br />
|-<br />
|data-sort-value="lfsck" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lfsck.sh lfsck]<br />
|<span style="color:red">Deprecated</span><br />
|Replaced by sanity-lfsck. <br />
|-<br />
|data-sort-value="lfsck-performance" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lfsck-performance.sh lfsck-performance]<br />
|<span style="color:green">Active</span><br />
|lfsck performance test for the cases: lfsck with load, lfsck during create, backup/restore, simulate upgrade from 1.8.<br />
|-<br />
|data-sort-value="liblustre" | liblustre<br />
|<span style="color:red">Deprecated</span><br />
|Run tests linked to liblustre client library <br />
|-<br />
|data-sort-value="lustre-rsync-test" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lustre-rsync-test.sh lustre-rsync-test]<br />
|<span style="color:green">Active</span><br />
|Verifies the lustre_rsync (replication) feature. <br />
|-<br />
|data-sort-value="metadata-updates" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/metadata-updates.sh metadata-updates]<br />
|<span style="color:green">Active</span><br />
| Tests that metadata updates are properly completed when multiple clients create/delete files and modify the attributes of files.<br />
|-<br />
|data-sort-value="mmp" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/mmp.sh mmp]<br />
|<span style="color:green">Active</span><br />
|Tests for multiple mount protection (MMP) feature.<br />
|-<br />
|data-sort-value="ost-pools" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/ost-pools.sh ost-pools]<br />
|<span style="color:green">Active</span><br />
|Tests that exercises the OST pools feature.<br />
|-<br />
|data-sort-value="performance-sanity" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/performance-sanity.sh performance-sanity]<br />
|<span style="color:green">Active</span><br />
|Performance mdsrate tests (small file create/open/delete, large file create/open/delete, lookup rate 10M file dir, lookup rate 10M file 10 dir, getattr small file, and getattr large files). <br />
|-<br />
|data-sort-value="parallel-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale.sh parallel-scale]<br />
|<span style="color:green">Active</span><br />
|Runs functional tests (connectathon, cascading_rw, write_disjoint, write_append_truncate, parallel_grouplock, statahead), performance tests (IOR, compilebench and metabench), and a stress test (simul). <br />
|-<br />
|data-sort-value="parallel-scale-cifs" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-cifs.sh parallel-scale-cifs]<br />
|<span style="color:green">Active</span><br />
|Tests Lustre exported via Samba and runs concurrent load compilebench, dbench, fsx, and iozone on Samba clients. The test assumes that Samba server and clients have necessary packages installed.<br />
|-<br />
|data-sort-value="parallel-scale-nfs" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfs.sh parallel-scale-nfs]<br />
|<span style="color:green">Active</span><br />
| Called by parallel-scale-nfsv3.sh and parallel-scale-nfsv4.sh with a version specified.<br />
|-<br />
|data-sort-value="parallel-scale-nfsv3" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfsv3.sh parallel-scale-nfsv3]<br />
|<span style="color:green">Active</span><br />
|Provide setup nfs within auster framework<br />
|-<br />
|data-sort-value="parallel-scale-nfsv4" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/parallel-scale-nfsv4.sh parallel-scale-nfsv4]<br />
|<span style="color:green">Active</span><br />
|Provide setup nfs within auster framework<br />
|-<br />
|data-sort-value="posix" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/posix.sh posix]<br />
|<span style="color:green">Active</span><br />
|Automate POSIX compliance testing. Assuming that the POSIX source already installed, on the system, setup loop back ext4 filesystem, then install, build and run POSIX binaries on ext4. Run POSIX again Lustre and compare results from ext4 and Lustre.<br />
|-<br />
|data-sort-value="racer" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/racer.sh racer]<br />
|<span style="color:green">Active</span><br />
|Tests for filesystem race conditions by concurrently creating, moving, deleting, etc. a set of files. <br />
|-<br />
|data-sort-value="recovery-double-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-double-scale.sh recovery-double-scale]<br />
|<span style="color:green">Active</span><br />
|Failover test for all pair-wise combinations of node failures. <br />
|-<br />
|data-sort-value="recovery-mds-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-mds-scale.sh recovery-mds-scale]<br />
|<span style="color:green">Active</span><br />
|The server failover test: for a duration of 24 hours, repeatedly fail over a random facet (MDS or OST) at 10 minute intervals and verify that no application errors occur. <br />
|-<br />
|data-sort-value="recovery-random-scale" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-random-scale.sh recovery-random-scale]<br />
|<span style="color:green">Active</span><br />
|Verifies client failure not affecting other clients. <br />
|-<br />
|data-sort-value="recovery-small" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/recovery-small.sh recovery-small]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify RPC replay after communications failure. <br />
|-<br />
|data-sort-value="replay-dual" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-dual.sh replay-dual]<br />
|<span style="color:green">Active</span><br />
|A set of unit tests that verify the recovery from two clients after server failure. <br />
|-<br />
|data-sort-value="replay-ost-single" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-ost-single.sh replay-ost-single]<br />
|<span style="color:green">Active</span><br />
| A set of unit tests that verify recovery after OST failure. <br />
|-<br />
|data-sort-value="replay-single" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-single.sh replay-single]<br />
|<span style="color:green">Active</span><br />
| A set of unit tests that verify recovery after MDS failure. <br />
|-<br />
|data-sort-value="replay-vbr" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/replay-vbr.sh replay-vbr]<br />
|<span style="color:green">Active</span><br />
|Verifies version-based recovery feature. <br />
|-<br />
|data-sort-value="runtests" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/runtests runtests]<br />
|<span style="color:green">Active</span><br />
|Simple basic regression test that verifies data persistence across write, unmount, and remount. This is one of the few tests that verifies data integrity across a full filesystem shutdown and remount, unlike many tests which at most only verify the existence/size of files. <br />
|-<br />
|[http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity.sh sanity]<br />
|<span style="color:green">Active</span><br />
|A set of regression tests that verify operation under normal operating conditions. This tests a large number of unusual operations that have previously caused functional or data correctness issues with Lustre. Some of the tests are Lustre specific, and hook into the Lustre fault injection framework using the "lctl set_param fail_loc=X" command to activate triggers in the code to simulate unusual operating conditions that would otherwise be difficult or impossible to simulate. <br />
|-<br />
|data-sort-value="sanityn" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanityn.sh sanityn]<br />
|<span style="color:green">Active</span><br />
|Tests that verify operations from two clients under normal operating conditions. This is done by mounting the same filesystem twice on a single client, in order to allow a single script/program to execute and verify filesystem operations on multiple "clients" without having to be a distributed program itself.<br />
|-<br />
|data-sort-value="sanity-benchmark" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-benchmark.sh sanity-benchmark]<br />
|<span style="color:green">Active</span><br />
|Test basic functionality of the filesystem using simple benchmarks. Runs dbench, bonnie++, iozone, fsx, and pios.<br />
|-<br />
|data-sort-value="sanity-dom" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-dom.sh sanity-dom]<br />
|<span style="color:green">Active</span><br />
|Sanity test the Data on MDT feature.<br />
|-<br />
|data-sort-value="sanity-flr" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-flr.sh sanity-flr]<br />
|<span style="color:green">Active</span><br />
|Sanity test the File Level Redundancy feature.<br />
|-<br />
|data-sort-value="sanity-gss" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-gss.sh sanity-gss]<br />
|<span style="color:green">Active</span><br />
|Verifies GSSAPI features. A mechanism-agnostic test suite for just the GSSAPI code itself using the gssnull security flavor, which in turn uses the null GSSAPI mechanism.<br />
|-<br />
|data-sort-value="sanity-hsm" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-hsm.sh sanity-hsm]<br />
|<span style="color:green">Active</span><br />
|Sanity test for HSM feature.<br />
|-<br />
|data-sort-value="sanity-krb5" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-krb5.sh sanity-krb5]<br />
|<span style="color:green">Active</span><br />
|Verifies Kerberos features.<br />
|-<br />
|data-sort-value="sanity-lfsck" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-lfsck.sh sanity-lfsck]<br />
|<span style="color:green">Active</span><br />
|Sanity test for lfsck<br />
|-<br />
|data-sort-value="sanity-pfl" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-pfl.sh sanity-pfl]<br />
|<span style="color:green">Active</span><br />
|Sanity test for the Progressive File Layout feature.<br />
|-<br />
|data-sort-value="sanity-quota" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-quota.sh sanity-quota]<br />
|<span style="color:green">Active</span><br />
|A set of tests that verify filesystem quotas. <br />
|-<br />
|data-sort-value="sanity-scrub" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-scrub.sh sanity-scrub]<br />
|<span style="color:green">Active</span><br />
|Verifies OI scrub functionality.<br />
|-<br />
|data-sort-value="sanity-sec" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sanity-sec.sh sanity-sec]<br />
|<span style="color:green">Active</span><br />
|Verifies Lustre identity features. , including UID/GID mapping<br />
|-<br />
|data-sort-value="scrub-performance" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/scrum-performance.sh scrub-performance]<br />
|<span style="color:green">Active</span><br />
|Test OI scrub performance<br />
|}<br />
<br />
== Benchmark Scripts ==<br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Status<br />
!Script Description<br />
|-<br />
|data-sort-value="lnet-selftest" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/lnet-selftest.sh lnet-selftest]<br />
|<span style="color:green">Active</span><br />
|LNET self-test is a kernel module that runs over LNET and the Lustre network drivers (LNDs). It is designed to test the connection ability of the Lustre network, run regression tests of the Lustre network, and test performance of the Lustre network.<br />
|-<br />
|data-sort-value="obdfilter-survey" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/obdfilter-survey.sh obdfilter-survey]<br />
|<span style="color:green">Active</span><br />
|This survey script does sequential I/O with varying numbers of threads and objects (files) by using lctl to drive the echo_client connected to local or remote obdfilter instances, or remote obdecho instances. It can be used to characterize the performance of the following Lustre components.<br />
|-<br />
|data-sort-value="sgpdd-survey" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/sgpdd-survey.sh sgpdd-survey]<br />
|<span style="color:green">Active</span><br />
|This survey may be used to characterize the performance of a SCSI device. It simulates an OST serving multiple stripe files. The data gathered by it can help set expectations for the performance of a Lustre OST exporting the device.<br />
|}<br />
<br />
== Auxiliary Tests and Benchmarks Tools == <br />
{| class="wikitable sortable" cellpadding="15"<br />
! style="text-align:left;" | Name<br />
!Script Description<br />
|-<br />
|data-sort-value="bonnie" | [http://www.coker.com.au/bonnie++/ bonnie++]<br />
|Bonnie++ benchmark for creation, reading, and deleting many small files.<br />
|-<br />
|data-sort-value="dbench" | [https://dbench.samba.org/ dbench]<br />
|Dbench benchmark for simulating N clients to produce the filesystem load.<br />
|-<br />
|data-sort-value="fsx" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/fsx.c fsx]<br />
|The file system exerciser was developed outside of Lustre and is intended to stress test unusual IO and file operations. It does buffered and mmap reads and writes with random size and offset, truncate, open, close on a file. It verifies data integrity after each step. A lustre-developed extension allows fsx to run against multiple mountpoints to verify distributed IO operation correctness. (Source [https://wiki.hpdd.intel.com/display/PUB/Auster HPDD Wiki Auster])<br />
|-<br />
|data-sort-value="iozone" | [http://www.iozone.org/ iozone]<br />
|Iozone benchmark for generating and measuring a variety of file operations.<br />
|-<br />
|data-sort-value="oos.sh" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/oos.sh oos.sh]<br />
|Script used to check out-of-space detection in sanity.sh test 64b.<br />
|-<br />
|data-sort-value="oos2.sh" | [http://git.whamcloud.com/fs/lustre-release.git/blob/HEAD:/lustre/tests/oos2.sh oos2.sh]<br />
|Script used to check out-of-space detection with multiple writers in sanityn.sh test 15.<br />
|-<br />
|data-sort-value="pios" | pios<br />
|pios is a parallel IO simulator. It can simulate shared file per process and file per process IO. Used in sanity-benchmark. pios-1.2-wc1 is available from the Intel HPDD build of the toolkit repo for various distributions, e.g. RHEL6 x86_64 https://build.hpdd.intel.com/job/toolkit/arch=x86_64,distro=el6/lastSuccessfulBuild/artifact/_topdir/RPMS/x86_64/<br />
|}<br />
<br />
[[Category:Testing]]</div>Jnunezhttp://wiki.lustre.org/index.php?title=Release_2.12.0&diff=3116Release 2.12.02018-04-04T21:54:26Z<p>Jnunez: Added Tester for DNE Restriping feature.</p>
<hr />
<div>(Draft version - work in progress)<br />
<br />
== Current Schedule ==<br />
<br />
* July 31 2018 - Feature Freeze (need to discuss more at LWG)<br />
* Sep 30 2018 - Code Freeze<br />
* Oct 31 2018 - Release 2.12.0<br />
<br />
(Note: these are very rough guidelines. For more accurate details on the schedule please refer to LWG call minutes)<br />
<br />
== Scope ==<br />
<br />
=== Test Matrix ===<br />
* Servers: RHEL 7.4 (likely need something more current?)<br />
* Clients RHEL 7.4, SLES 12 SP3, Ubuntu 16.04<br />
* OFED: inkernel<br />
* E2FSProgs: v1.42.13.wc6<br />
* Interoperability: 2.11, Latest 2.10.X Servers/Clients<br />
<br />
=== Features ===<br />
<br />
The following features are under active development and could be possible for landing during the 2.12 release cycle<br />
<br />
{| class="wikitable sortable"<br />
|-<br />
! Feature !! Developers !! Reviewers !! Testers !! Docs !! Confirmed in 2.12<br />
|-<br />
<br />
| [https://jira.hpdd.intel.com/browse/LU-9120 LNet Network Health] || Amir Shehata || Sonia Sharma, Dmitry Eremin || TBD || Amir Shehata, [https://jira.hpdd.intel.com/browse/LUDOC-396 LUDOC-396] || TBD<br />
|-<br />
| [https://jira.hpdd.intel.com/browse/LU-4684 DNE Directory Restriping] || Lai Siyao || Andreas Dilger, Alex Zhuravlev || Sarah Liu || Lai Siyao, [https://jira.hpdd.intel.com/browse/LUDOC-395 LUDOC-395] || TBD<br />
|-<br />
|}<br />
<br />
=== General Work and Maintenance ===<br />
<br />
From the [https://jira.hpdd.intel.com/browse/LU Lustre project page] in the [https://jira.hpdd.intel.com Lustre issue tracker], we can see a dashboard for the project. On that page under the "Versions: Unreleased" section, there are links to future releases and all of the issues that are either targeted to be addressed in that release, or are already addressed for the release. Here is a shortcut to Lustre 2.12.0's issue summary page:<br />
<br />
* [https://jira.hpdd.intel.com/projects/LU/versions/13495 Lustre 2.12.0 Issues]<br />
<br />
Any issue that contains "Lustre 2.12.0" in the "Fix Version/s" field of a ticket is intended to be fixed for version 2.12.0. The Lustre 2.12.0 Issues list is fluid, and will be updated on a continual basis as resources and priorities change.<br />
<br />
If you would like to own one or more tasks for the release but are not currently listed in the drop-down list of developers in JIRA then please email [mailto:peter.a.jones@intel.com Peter Jones] to get that setup<br />
<br />
A convenience search filter is supplied for anyone looking for work that needs to be done for 2.12.0:<br />
<br />
* [https://jira.hpdd.intel.com/issues/?filter=15115 Lustre 2.12.0 Unassigned Issues]<br />
<br />
In addition, a search filter is available for anyone looking to start Lustre development with some simple development tasks, or anyone with a few minutes/hours available to improve Lustre:<br />
<br />
* [https://jira.hpdd.intel.com/issues/?jql=resolution=Unresolved%20AND%20labels=easy Lustre easy-to-fix issues]<br />
<br />
[[Category: Releases]]</div>Jnunez