Updated SRPT documentation.

git-svn-id: http://svn.code.sf.net/p/scst/svn/trunk@1024 d57e44dd-8a1f-0410-8b47-8ef2f437770f

srpt/README.ofed

@@ -53,6 +53,7 @@ Unload any loaded InfiniBand drivers:
 Remove any distro-provided InfiniBand drivers:
 
   rm -rf /lib/modules/$(uname -r)/kernel/drivers/infiniband
+  rm -rf /lib/modules/$(uname -r)/kernel/drivers/net/mlx4
 
 Now locate the file Makefile.lib and patch it such that it supports
 the variable PRE_CFLAGS:

srpt/Testing.txt

@@ -0,0 +1,58 @@
+The following tests must be run at least before releasing a new SRPT version:
+
+* Make sure that SRPT compiles and installs without triggering any
+  compiler warning. Use the following command to compile and install SRPT:
+
+  for d in scst srpt; do make -C $d -s clean && make -C $d -s install; done 
+
+* Verify the output of run-regression-tests for kernel versions starting at
+  2.6.23 up to and including the latest released kernel.
+
+* Verify that SRPT compiles, installs and works fine when following the
+  instructions in README.ofed for the latest released OFED distribution and
+  at the latest released CentOS, Ubuntu and openSUSE distributions.
+
+* Verify that module loading and unloading works fine.
+
+* Verify that rejecting logins does not trigger a memory leak, e.g. as follows:
+  * Run the following command on the target system:                              
+      ${SCST_TRUNK}/scripts/monitor-memory-usage | tee memlog.txt  
+  * Run the following command on the initiator system:                           
+      for ((i=0;i<100000;i++)); do echo 'id_ext=0002c9030003cca2,ioc_guid=0002c9030003cca2,pkey=ffff,dgid=fe800000000000000002c9030003cca3,service_id=0002c9030003cca3' >/sys/class/infiniband_srp/srp-mlx4_0-1/add_target ; done                
+
+* Verify that an I/O stress test runs fine by running the following command
+  on an initiator system after having created two partitions:
+
+fio <<EOF
+[global]
+bs=1M
+direct=1
+ioengine=sync
+verify=meta
+rw=write
+verify_fatal=1
+verify_async=1
+loops=10
+
+[partition1]
+filename=/dev/sdb1
+
+[partition2]
+filename=/dev/sdb2
+EOF
+
+* Verify that a SCSI reset works properly by running the following command
+  on an initiator system:
+
+    sg_reset -d ${initiator_device}
+
+* Run the following command on a target system:
+
+    while true; do /etc/init.d/scst stop; sleep 3; /etc/init.d/scst start; sleep 5; done
+
+  and the following commands on an initiator system:
+
+    target_id="id_ext=0002c9030003cca2,ioc_guid=0002c9030003cca2,dgid=fe800000000000000002c9030003cca3,pkey=ffff,service_id=0009030003cca2,ioc_guid=0002c9030003cca2,dgid=fe800000000000000002c9030003cca3,pkey=ffff,service_id=0002c9030003cca2"
+    while true; do date; rmmod ib_srp; modprobe ib_srp; echo "${target_id}" > /sys/class/infiniband_srp/srp-mlx4_0-1/add_target; sleep 2; done
+
+  and verify that nothin unexpected happens.

srpt/ToDo

@@ -4,33 +4,18 @@
 
 
 2. The SRPT driver directly uses the internal state of the SCST core target
-   state machine (scmnd->state), which is bad, bad, bad and generally not
-   acceptable. Only dev handler are allowed to use them. This should be fixed.
+   state machine (scmnd->state field / SCST_CMD_STATE_* values), which is bad,
+   bad, bad and generally not acceptable. Only dev handler are allowed to use
+   them. This should be fixed: the SRPT driver should keep its internal state
+   in an SRPT-specific variable. For an example, see also the "Q2T_STATE_"
+   constants in the qla2x00t driver, and especially the function
+   q2t_do_ctio_completion().
 
 
-3. Fix the race condition between srpt_refresh_port_work() and 
-   srpt_remove_one(). Although the probability that this happens is very low,
-   at least in theory it is possible that srpt_refresh_port_work() gets
-   called for a port after srpt_remove_one() called kfree() on the data
-   structure that contains the work_struct passed to srpt_refresh_port_work().
-   It's not clear to me whether or not letting srpt_remove_one() wait until
-   srpt_refresh_work() finished can result in a deadlock.
-
-
-4. Find out from which threads the srpt_devices list can be accessed and
-   whether it has to be protected by a spinlock or mutex.
-
-
-5. Fix the issue that 'rmmod ib_srpt' under load hangs.
-
-
-6. The initiator names supplied to the SCST core contain the target port name,
+3. The initiator names supplied to the SCST core contain the target port name,
    which is wrong. Nobody identifies a man by the door through which he entered.
    Instead, a man has a name by which he is identified through his whole life.
 
 
-7. Analyze and document the implications of
+4. Analyze and document the implications of
    sdev->mr = ib_get_dma_mr(sdev->pd, IB_ACCESS_LOCAL_WRITE).
-
-
-8. Enable and test the LUN_RESET task management function.