Test Descriptions

Lustre Test Framework

Name	Description
acceptance-small.sh (acc-sm)	The acceptance-small.sh script is a wrapper around auster that runs the test group 'regression' unless tests are specified on the command line.
auster	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.
functions.sh	Provides functions for the run_*.sh tests, such as run_dd.sh or run_dbench.sh
test-framework.sh	Provides the fundamental functions needed by tests to create, setup, verify, start, stop, and reformat a Lustre filesystem.

See the TestingLustreCode page for details on how to run these test scripts, and Testing HOWTO for a worked multi-node setup example.

Test suites are grouped into test groups under lustre/tests/test-groups. The regression group defines the suites run against every patch; a suite's presence in that group is the practical definition of "actively tested". See Test Groups for Patch Testing for more detail.

Lustre Unit, Feature, and Regression Tests

Status Key

Active	Test suite is present in the source tree and is run in AutoTest or has been committed to recently. Suites listed in lustre/tests/test-groups/regression are run for every patch.
Inactive	Test suite is still present in the source tree but is not part of a routine test group and has not been committed to recently.
Removed	Test suite has been deleted from the source tree or replaced by another suite. Retained here so that references in older bug reports, patches, and Maloo results remain interpretable.

Note: Status reflects the state of the Lustre master branch. To confirm what exists for a particular release, check lustre/tests/ in that branch.

Name	Status	Test Description
conf-sanity	Active	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.
dne_sanity	Inactive	Run sanity parallel on different directories at the same time.
dom-performance	Active	Performance comparison for the Data-on-MDT feature. Runs small-file workloads against DoM and non-DoM layouts so the two can be compared directly.
ha	Active	Long-running HA/failover harness. Drives configurable client workloads while repeatedly failing over server nodes, and reports any application-visible errors. Used for extended stability runs rather than per-patch testing.
insanity	Active	A set of tests that verify the multiple concurrent failure conditions.
large-scale	Active	Large-scale tests that verify version-based recovery features.
large-lun	Active	Large LUN test
lfsck	Removed	Replaced by sanity-lfsck. No longer present in the source tree.
lfsck-performance	Active	lfsck performance test for the cases: lfsck with load, lfsck during create, backup/restore, simulate upgrade from 1.8.
liblustre	Removed	Ran tests linked against the liblustre client library. The liblustre userspace client was removed from Lustre, and this suite went with it.
lockorder	Active	Exercises lock ordering across two mountpoints using createmany/statmany/unlinkmany to surface lock inversion and deadlock conditions.
lustre-rsync-test	Active	Verifies the lustre_rsync (replication) feature.
metadata-updates	Removed	Tested that metadata updates were properly completed when multiple clients create/delete files and modify file attributes. Removed in Lustre 2.16.0 by LU-16250; multi-client metadata coverage now lives in sanityn and racer.
mmp	Active	Tests for multiple mount protection (MMP) feature.
ost-pools	Active	Tests that exercises the OST pools feature.
performance-sanity	Active	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).
parallel-scale	Active	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).
parallel-scale-cifs	Active	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.
parallel-scale-nfs	Active	Called by parallel-scale-nfsv3.sh and parallel-scale-nfsv4.sh with a version specified.
parallel-scale-nfsv3	Active	Provide setup nfs within auster framework
parallel-scale-nfsv4	Active	Provide setup nfs within auster framework
pjdfstest	Active	POSIX compliance testing using the pjdfstest suite. Sets up a loopback ext4 filesystem, runs pjdfstest against both ext4 and Lustre, and compares the two reports so that failures attributable to the Linux VFS can be separated from Lustre-specific failures. Added to review and full testing by LU-12662. Requires the pjdfstest binary (default /bin/pjdfstest, test directory /usr/share/pjdfstest). See POSIX Compliance Testing.
posix	Removed	Former POSIX compliance wrapper built on the TET/VSX (LSB-VSX) suite. Replaced by pjdfstest.
racer	Active	Tests for filesystem race conditions by concurrently creating, moving, deleting, etc. a set of files.
recovery-double-scale	Active	Failover test for all pair-wise combinations of node failures.
recovery-mds-scale	Active	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.
recovery-oss-scale	Active	For a duration of 24 hours, repeatedly fail over a random OSS at 10 minute intervals while client load runs, and verify that no application errors occur.
recovery-random-scale	Active	Verifies client failure not affecting other clients.
recovery-small	Active	A set of unit tests that verify RPC replay after communications failure.
replay-dual	Active	A set of unit tests that verify the recovery from two clients after server failure.
replay-ost-single	Active	A set of unit tests that verify recovery after OST failure.
replay-single	Active	A set of unit tests that verify recovery after MDS failure.
replay-single-lmv	Inactive	Variant of replay-single that exercises MDS recovery through the LMV layer with multiple MDTs configured.
replay-vbr	Active	Verifies version-based recovery feature.
runtests	Active	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.
sanity	Active	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.
sanityn	Active	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.
sanity-benchmark	Active	Test basic functionality of the filesystem using simple benchmarks. Runs dbench, bonnie++, iozone, fsx, and pios.
sanity-compr	Active	Sanity tests for the compression feature, covering compressed component layouts, read/write correctness against compressed extents, and interaction with PFL layouts.
sanity-dom	Active	Sanity test the Data on MDT feature.
sanity-ec	Active	Sanity tests for erasure coding, covering parity component layouts and verification of the parity flag on components.
sanity-flr	Active	Sanity test the File Level Redundancy feature.
sanity-gss	Removed	Verified GSSAPI features using the gssnull security flavor. Removed in Lustre 2.16.0 by LU-16262; Kerberos/GSS coverage is provided by sanity-krb5 and shared-secret key coverage by sanity-sec.
sanity-hsm	Active	Sanity test for HSM feature.
sanity-krb5	Active	Verifies Kerberos features.
sanity-lfsck	Active	Sanity test for lfsck
sanity-lnet	Active	Sanity test for lnet
sanity-lsnapshot	Active	Sanity tests for Lustre snapshots (lctl snapshot_create/mount/umount/destroy) on ZFS backends. Part of the regression test group.
sanity-pcc	Active	A set of tests verifying basic functionality of the Persistent Client Cache feature.
sanity-pfl	Active	Sanity tests for the Progressive File Layout feature.
sanity-quota	Active	A set of tests that verify filesystem quotas.
sanity-scrub	Active	Verifies OI scrub functionality.
sanity-selinux	Active	Verifies SELinux support on Lustre clients, including security label storage and retrieval and enforcement of SELinux policy on Lustre files. Requires an SELinux policy permitting transitions from unconfined_t to user_t and guest_t for some tests.
sanity-sec	Active	Verifies Lustre security and identity features, including nodemaps, UID/GID mapping, root squash, filesets, shared secret key (SSK) flavors, and client-side encryption.
scrub-performance	Active	Test OI scrub performance.

Benchmark Scripts

Name	Status	Script Description
lnet-selftest	Active	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.
mds-survey	Active	Wrapper around the mds-survey tool, which characterizes metadata performance of an MDT by driving the echo client against the MDD layer, independent of the network and client stack. Skipped if the mds-survey binary is not installed.
obdfilter-survey	Active	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.
sgpdd-survey	Active	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.

Auxiliary Tests and Benchmarks Tools

Name	Script Description
bonnie++	Bonnie++ benchmark for creation, reading, and deleting many small files.
dbench	Dbench benchmark for simulating N clients to produce the filesystem load.
fsx	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 Auster)
iozone	Iozone benchmark for generating and measuring a variety of file operations.
oos.sh	Script used to check out-of-space detection in sanity.sh test 64b.
oos2.sh	Script used to check out-of-space detection with multiple writers in sanityn.sh test 15.
ost_oos.sh	Standalone out-of-space check against a single OST. Mounts a local filesystem via llmount.sh, fills the mountpoint past its free space with dd, and verifies that the out-of-space condition is reported correctly. Run directly rather than through auster.
run-llog.sh	Driver for the llog_test kernel module unit tests, which exercise the Lustre log (llog) implementation used for configuration logs and changelogs. Skips if no MGS is available. Run directly rather than through auster.
pios	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/