diff options
Diffstat (limited to 'Documentation/RCU/torture.txt')
-rw-r--r-- | Documentation/RCU/torture.txt | 22 |
1 files changed, 13 insertions, 9 deletions
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index d896685a9100..a4948591607d 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt | |||
@@ -7,7 +7,7 @@ The CONFIG_RCU_TORTURE_TEST config option is available for all RCU | |||
7 | implementations. It creates an rcutorture kernel module that can | 7 | implementations. It creates an rcutorture kernel module that can |
8 | be loaded to run a torture test. The test periodically outputs | 8 | be loaded to run a torture test. The test periodically outputs |
9 | status messages via printk(), which can be examined via the dmesg | 9 | status messages via printk(), which can be examined via the dmesg |
10 | command (perhaps grepping for "rcutorture"). The test is started | 10 | command (perhaps grepping for "torture"). The test is started |
11 | when the module is loaded, and stops when the module is unloaded. | 11 | when the module is loaded, and stops when the module is unloaded. |
12 | 12 | ||
13 | However, actually setting this config option to "y" results in the system | 13 | However, actually setting this config option to "y" results in the system |
@@ -44,6 +44,10 @@ test_no_idle_hz Whether or not to test the ability of RCU to operate in | |||
44 | a kernel that disables the scheduling-clock interrupt to | 44 | a kernel that disables the scheduling-clock interrupt to |
45 | idle CPUs. Boolean parameter, "1" to test, "0" otherwise. | 45 | idle CPUs. Boolean parameter, "1" to test, "0" otherwise. |
46 | 46 | ||
47 | torture_type The type of RCU to test: "rcu" for the rcu_read_lock() | ||
48 | API, "rcu_bh" for the rcu_read_lock_bh() API, and "srcu" | ||
49 | for the "srcu_read_lock()" API. | ||
50 | |||
47 | verbose Enable debug printk()s. Default is disabled. | 51 | verbose Enable debug printk()s. Default is disabled. |
48 | 52 | ||
49 | 53 | ||
@@ -51,14 +55,14 @@ OUTPUT | |||
51 | 55 | ||
52 | The statistics output is as follows: | 56 | The statistics output is as follows: |
53 | 57 | ||
54 | rcutorture: --- Start of test: nreaders=16 stat_interval=0 verbose=0 | 58 | rcu-torture: --- Start of test: nreaders=16 stat_interval=0 verbose=0 |
55 | rcutorture: rtc: 0000000000000000 ver: 1916 tfle: 0 rta: 1916 rtaf: 0 rtf: 1915 | 59 | rcu-torture: rtc: 0000000000000000 ver: 1916 tfle: 0 rta: 1916 rtaf: 0 rtf: 1915 |
56 | rcutorture: Reader Pipe: 1466408 9747 0 0 0 0 0 0 0 0 0 | 60 | rcu-torture: Reader Pipe: 1466408 9747 0 0 0 0 0 0 0 0 0 |
57 | rcutorture: Reader Batch: 1464477 11678 0 0 0 0 0 0 0 0 | 61 | rcu-torture: Reader Batch: 1464477 11678 0 0 0 0 0 0 0 0 |
58 | rcutorture: Free-Block Circulation: 1915 1915 1915 1915 1915 1915 1915 1915 1915 1915 0 | 62 | rcu-torture: Free-Block Circulation: 1915 1915 1915 1915 1915 1915 1915 1915 1915 1915 0 |
59 | rcutorture: --- End of test | 63 | rcu-torture: --- End of test |
60 | 64 | ||
61 | The command "dmesg | grep rcutorture:" will extract this information on | 65 | The command "dmesg | grep torture:" will extract this information on |
62 | most systems. On more esoteric configurations, it may be necessary to | 66 | most systems. On more esoteric configurations, it may be necessary to |
63 | use other commands to access the output of the printk()s used by | 67 | use other commands to access the output of the printk()s used by |
64 | the RCU torture test. The printk()s use KERN_ALERT, so they should | 68 | the RCU torture test. The printk()s use KERN_ALERT, so they should |
@@ -124,7 +128,7 @@ The following script may be used to torture RCU: | |||
124 | modprobe rcutorture | 128 | modprobe rcutorture |
125 | sleep 100 | 129 | sleep 100 |
126 | rmmod rcutorture | 130 | rmmod rcutorture |
127 | dmesg | grep rcutorture: | 131 | dmesg | grep torture: |
128 | 132 | ||
129 | The output can be manually inspected for the error flag of "!!!". | 133 | The output can be manually inspected for the error flag of "!!!". |
130 | One could of course create a more elaborate script that automatically | 134 | One could of course create a more elaborate script that automatically |