Lustre Debugging for Developers

Adding Debugging to the Source Code
The debug infrastructure provides a number of macros which can be used in the Lustre™ source to aid debugging or report serious errors. All of these macros depend on having the DEBUG_SUBSYSTEM variable set at the top of the file to indicate what code module the debugging is part of:


 * #define DEBUG_SUBSYSTEM S_PORTALS


 * LBUG: This is a panic style assertion in the kernel which will cause Lustre to dump its circular log to the file /tmp/lustre-log from where it can be retrieved after a reboot.
 * LASSERT: Validate that a given expression is true, otherwise call LBUG. The failed expression is printed onto the console, though the values that make up the expression are not printed.
 * LASSERTF: Similar to LASSERT but also allows a free-format message to be printed, like printf/printk
 * CDEBUG: CDEBUG is the basic and most commonly used debug macro, and takes just one more argument than a standard printf - the debug type. When the debug mask is set accordingly, this message will be added to the debug log. Later, when a troubleshooter retrieves that log, they can also filter based on this type.
 * CDEBUG(D_INFO, "This is my debug message: the number is %d\n", number);


 * CERROR: CERROR behaves similarly to CDEBUG, but prints the message in the debug log and to the console. This is appropriate for serious errors or fatal conditions:
 * CERROR("Something very bad has happened, and the return code is %d.\n", rc);


 * ENTRY and EXIT: ENTRY and EXIT take no arguments and simply add messages to aid in call tracing. One should attempt to cover all exit conditions when using these macros, to avoid confusion when the debug log reports that a function was entered but never exited.
 * LDLM_DEBUG and LDLM_DEBUG_NOLOCK: These macros are to be used when tracing MDS and VFS operations for locking. The purpose of these macros is to build a thin trace that shows the protocol exchanges between nodes.
 * DEBUG_REQ: prints a great deal of information about the given ptlrpc_request structure


 * OBD_FAIL_CHECK: this allows insertion of failure points into the Lustre code, useful for generating regression tests that can hit a very specific sequence of events. This works in conjunction with "sysctl -w lustre.fail_loc={fail_loc}" to set a specific failure point for which a given OBD_FAIL_CHECK will test for.
 * OBD_FAIL_TIMEOUT: like OBD_FAIL_CHECK, and if the given fail_loc is hit, wait for the specified number of seconds. Useful for simulating hung, blocked, or busy processes, or network delays
 * OBD_RACE: like OBD_FAIL_CHECK, and the first process to hit it sleeps until a second process hits the same OBD_RACE and then both continue on. Useful for having multiple processes executing the same code concurrently to provoke locking races
 * OBD_FAIL_ONCE: a flag set on a lustre.fail_loc breakpoint to cause the OBD_FAIL_CHECK condition to only be hit a single time. otherwise a fail_loc is permanent until cleared with "sysctl -w lustre.fail_loc=0"
 * OBD_FAIL_RAND: have the OBD_FAIL_CHECK fail randomly, on average every (1 / lustre.fail_val) times
 * OBD_FAIL_SKIP: have OBD_FAIL_CHECK succeed lustre.fail_val times, and then fail permanently, or once with OBD_FAIL_ONCE
 * OBD_FAIL_SOME: have OBD_FAIL_CHECK fail lustre.fail_val times, and then succeed

= Ptlrpc Request History = Each service always maintains request history, which is almost certainly very useful for first occurrence troubleshooting. The following email snippet describes the implementation.

Ptlrpc history works as follows...

"req_buffer_history_max" and remove its reqs from the service's request history. Request history is accessed/controlled via the following /proc files under the service directory...
 * 1) request_in_callback adds the new request to the service's request history.
 * 2) When a request buffer becomes idle add it to the service's request buffer history list.
 * 3) Cull buffers from the service's request buffer history if it has grown above

Note that requests in the history include "live" requests that are actually being handled. Each line in "req_history" looks like....
 * req_buffer_history_len            # of request buffers currently in the history
 * req_buffer_history_max          max # request buffers to keep
 * req_history                             the request history




 * seq:                 request sequence number
 * target NID:      destination NID of the incoming request
 * client ID:         client's PID and NID
 * xid:                  rq_xid
 * length:              size of the request message
 * phase:
 * New (waiting to be handled or couldn't be unpacked)
 * Interpret (unpacked and being handled)
 * Complete (handled)
 * svc specific:
 * Service-specific request printout. Currently the only service that does this is the OST, which prints the opcode if the message has been unpacked successfully.

= LWT Tracing = Also, Eric Barton has a very lightweight tracing facility called LWT. It prints fixed size requests into a buffer and is much faster than LDEBUG.

The records that are dumped contain:


 * Current CPU
 * Process counter
 * Pointer to file
 * Pointer to line in the file
 * 4 void * pointers

An lctl command dumps the logs to files.

This tracking facility has been very successful to debug difficult problems.

=Finding memory leaks=

Memory leaks can occur in a code where you allocate a memory, but forget to free it once its no longer required. Such problems can be found using the leak_finder.pl program. Before running this program, the debugging should be completely turned on to make sure all malloc and free entries are collected. This can be done as follows:

sysctl -w lnet.debug=+malloc

Dump the log into a user specified log file using lctl as shown in previous section. Run the leak finder after this on the just created log dump:

perl leak_finder.pl 

This provides output as shown below:

malloced  8bytes   at a3116744 called pathcopy (lprocfs_status.c:lprocfs_add_vars:80) freed     8bytes   at a3116744 called pathcopy (lprocfs_status.c:lprocfs_add_vars:80)

The tool will also give the following output to show the leaks found:

Leak:32bytes allocated at a23a8fc (service.c:ptlrpc_init_svc:144,debug file line 241)