Updating a lot of control files with more information in their
description and also some hard data numbers.
Signed-off-by: Michael Rubin <mrubin@google.com>
git-svn-id: http://test.kernel.org/svn/autotest/trunk@2162 592f7852-d20e-0410-864c-8624ca9c26a4
diff --git a/client/tests/aiostress/control b/client/tests/aiostress/control
index c59c1c9..16e059f 100644
--- a/client/tests/aiostress/control
+++ b/client/tests/aiostress/control
@@ -2,19 +2,23 @@
NAME = "aio stress"
TEST_CATEGORY = "Stress"
TEST_CLASS = "Kernel"
-TIME = "MEDIUM"
+TIME = "SHORT"
TEST_TYPE = "client"
DOC = """\
aio-stress
will open or create each file on the command line, and start a series
-of aio to it.
+of aio to it.
aio is done in a rotating loop. first file1 gets 8 requests, then
file2, then file3 etc. As each file finishes writing, it is switched
to reads
io buffers are aligned in case you want to do raw io
+
+This test takes less than a minute. It ends up writing and reading less
+than a few Megs. It is a sequential workload. This test stresses the aio
+interface not the disk, or kernel.
"""
job.run_test('aiostress')
diff --git a/client/tests/bonnie/control b/client/tests/bonnie/control
index 1699827..2717a80 100644
--- a/client/tests/bonnie/control
+++ b/client/tests/bonnie/control
@@ -10,6 +10,12 @@
tribute to Bonnie Raitt, who knows how to use one.
For more info, see http://www.textuality.com/bonnie/
+
+This benchmark configuration run generates sustained write traffic
+of 35-50MB/s of .1MB writes to just one disk. It appears to have a
+sequential and a random workload. It gives profile measurements for:
+throughput, %CPU rand seeks per second. Not sure if the the CPU numbers
+are trustworthy.
"""
job.run_test('bonnie')
diff --git a/client/tests/dbench/control b/client/tests/dbench/control
index 44885cc..d04e2e1 100644
--- a/client/tests/dbench/control
+++ b/client/tests/dbench/control
@@ -9,6 +9,9 @@
More information on dbench can be found here:
http://samba.org/ftp/tridge/dbench/README
+
+Currently it needs to be updated in its configuration. It is a great test for
+the higher level I/O systems but barely touches the disk right now.
"""
job.run_test('dbench')
diff --git a/client/tests/disktest/control b/client/tests/disktest/control
index fb94845..af1d5fb 100644
--- a/client/tests/disktest/control
+++ b/client/tests/disktest/control
@@ -4,6 +4,8 @@
Pattern test of the disk, using unique signatures for each block and each
iteration of the test. Designed to check for data corruption issues in the
disk and disk controller.
+
+It writes 50MB/s of 500KB size ops.
'''
TIME = 'MEDIUM'
TEST_CATEGORY = 'Kernel'
diff --git a/client/tests/fs_mark/control b/client/tests/fs_mark/control
index ad5a1d3..081d41f 100644
--- a/client/tests/fs_mark/control
+++ b/client/tests/fs_mark/control
@@ -6,7 +6,13 @@
TIME = 'MEDIUM'
EXPERIMENTAL = "True"
DOC='''
-Details of fs_mark can be found at:
+Detect barrier issues in file systems.
+
+If a file system have write barrier not protecting synchronous write,
+the number of synchronous (single threaded) operations/sec will exceed the
+calculated number of synchronous operations/sec of the underlying drive.
+
+Details of fs_mark can be found at:
http://devresources.linux-foundation.org/dev/doubt/fs_mark/index.html
'''
job.run_test('fs_mark', dir='/mnt')
diff --git a/client/tests/fsfuzzer/control b/client/tests/fsfuzzer/control
index f243021..8c8c7e8 100644
--- a/client/tests/fsfuzzer/control
+++ b/client/tests/fsfuzzer/control
@@ -8,5 +8,14 @@
DOC='''
fsfuzzer is a file system fuzzer tool. This test simply runs fsfuzzer.
+
+Fuzzing is slang for fault injection via random inputs. The goal is to
+find bugs in software without reading code or designing detailed test
+cases. Here fsfuzz will inject random errors into the files systems
+mounted. Evidently it has found many errors in many systems.
+
+WARNING: Currently this test may not work, and it may break subsequent
+other test runs.
'''
+
job.run_test('fsfuzzer')
diff --git a/client/tests/fsstress/control b/client/tests/fsstress/control
index 36d98f7..0ddd06b 100644
--- a/client/tests/fsstress/control
+++ b/client/tests/fsstress/control
@@ -6,6 +6,12 @@
TIME = 'MEDIUM'
EXPERIMENTAL = "True"
DOC='''
-Information about fsstress can be found at http://www.cs.duke.edu/ari/fstress/
+A benchmark that tries to capture both transactional DB workloads and
+random web server ones. It writes about 24MB/s but has many small writes a
+second. It does a lot of this randomly but lets you go back to replay the
+randomness
+
+More information about fsstress can be found at
+http://www.cs.duke.edu/ari/fstress/
'''
job.run_test('fsstress')
diff --git a/client/tests/iozone/control b/client/tests/iozone/control
index ff40eb6..17d9be2 100644
--- a/client/tests/iozone/control
+++ b/client/tests/iozone/control
@@ -6,8 +6,13 @@
TEST_CATEGORY = "Benchmark"
DOC = """
-Runs the standard IOzone filesystem benchmark. For more information see
-http://www.iozone.org
+Iozone is useful for performing a broad filesystem analysis of a vendors
+computer platform. The benchmark tests file I/O performance for the following
+operations:
+ Read, write, re-read, re-write, read backwards, read strided, fread,
+ fwrite, random read, pread ,mmap, aio_read, aio_write
+
+For more information see http://www.iozone.org
"""
job.run_test('iozone')