This commit was manufactured by cvs2svn to create tag

'slurm-0-4-15-1'.

META

@@ -9,8 +9,8 @@
   Name:		slurm
   Major:	0
   Minor:	4
-  Micro:        6
-  Version:	0.4.6
+  Micro:        15
+  Version:	0.4.15
   Release:	1
   API_CURRENT:	6	
   API_AGE:	4

NEWS

@@ -1,9 +1,47 @@
 This file describes changes in recent versions of SLURM. It primarily
 documents those changes that are of interest to users and admins. 
 
+* Changes in SLURM 0.4.15
+========================
+ -- Added error checking to a bunch of Bridge API calls and more 
+    gracefully handle failure modes.
+
+* Changes in SLURM 0.4.14
+========================
+ -- job state is kept on warm start of slurm
+
+* Changes in SLURM 0.4.13
+========================
+ -- epilog fix for bgl plugin
+
+* Changes in SLURM 0.4.12
+========================
+ -- bug shot for new api calls.
+ -- added BridgeAPILogFile as an option for bluegene.conf file
+
+* Changes in SLURM 0.4.11
+========================
+ -- changed as many rm_get_partition() to rm_get_partitions_info as we could 
+    for time saving.
+
+* Changes in SLURM 0.4.10
+========================
+ -- redesign for BGL external wiring.
+ -- smap display bug fix for smaller systems.
+
+* Changes in SLURM 0.4.9
+========================
+ -- setpnum works now, have to include this in bluegene.conf
+
+* Changes in SLURM 0.4.8
+========================
+ -- Changed the prolog and the epilog to use the env var MPIRUN_PARTITION
+    instead of BGL_PARTITION_ID
+
 * Changes in SLURM 0.4.7
 ========================
- -- Remove some BGL specific headers that IBM now distributes.
+ -- Remove some BGL specific headers that IBM now distributes, NOTE
+    BGL driver 080 or greater required.
  -- Change autogen.sh to deal with problems running autoconf on one
     system and configure on another with different software versions.
 

auxdir/x_ac_bgl.m4

@@ -33,7 +33,7 @@ AC_DEFUN([X_AC_BGL],
          fi
 
          have_bgl_ar=yes
-         bgl_ldflags="$bgl_ldflags -Wl,-rpath $bgl_dir/lib -Wl,-L$bgl_dir/lib -Wl,-whole-archive -Wl,-lbglbridge -Wl,-no-whole-archive $bgl_dir/lib/bglbootload.a $bgl_dir/lib/bglsp440supt.a -lbgldb -lbglmachine -ltableapi -lexpat -lbglsp"
+         bgl_ldflags="$bgl_ldflags -Wl,-rpath $bgl_dir/lib -Wl,-L$bgl_dir/lib -Wl,-whole-archive -Wl,-lbglbridge -Wl,-no-whole-archive $bgl_dir/lib/bglbootload.a $bgl_dir/lib/bglsp440supt.a -lsaymessage -lbgldb -lbglmachine -ltableapi -lexpat -lbglsp"
       fi
 
       # Search for required DB2 library in the directory

doc/html/bluegene.html

@@ -99,7 +99,7 @@ <h3>User Tools</h3>
 The script that you submit to SLURM can contain multiple invocations of mpirun as
 well as any desired commands for pre- and post-processing.
 The mpirun command will get its <i>bglblock</i> or BGL partition information from the
-<i>BGL_PARTITION_ID</i> as set by SLURM. A sample script is shown below.
+<i>MPIRUN_PARTITION</i> as set by SLURM. A sample script is shown below.
 <pre>
 #!/bin/bash
 # pre-processing
@@ -185,11 +185,11 @@ <h3>System Administration</h3>
 and interfaces. 
 The value of <i>SchedulerType</i> should be set to "sched/builtin".
 The value of <i>Prolog</i> should be set to a program that will delay 
-execution until the bglblock identified by the BGL_PARTITION_ID environment 
+execution until the bglblock identified by the MPIRUN_PARTITION environment 
 variable is ready for use. It is recommended that you construct a script 
 that serves this function and calls the supplied program <i>slurm_prolog</i>.
 The value of <i>Epilog</i> should be set to a program that will wait
-until the bglblock identified by the BGL_PARTITION_ID environment
+until the bglblock identified by the MPIRUN_PARTITION environment
 variable has been freed. It is recommended that you construct a script
 that serves this function and calls the supplied program <i>slurm_epilog</i>.
 The prolog and epilog programs are used to insure proper synchronization 

etc/bluegene.conf.example

@@ -5,17 +5,30 @@
 # LinuxImage:     LinuxImage used for creation of all bglblocks.
 # MloaderImage:   MloaderImage used for creation of all bglblocks.
 # RamDiskImage:   RamDiskImage used for creation of all bglblocks.
-# ChangeNumpsets: Script to reset a created bglblock's Numpsets value.
-#                 Will be removed when an API is available for this.
-#                 Default value uses half of available I/O nodes.
+# Numpsets:       The Numpsets used for creation of all bglblocks 
+#                 equals this value multiplied by the number of 
+#                 base partitions in the bglblock.
+#
+# BridgeAPILogFile : Pathname of file in which to write the BGL 
+#                    Bridge API logs.
+# BridgeAPIVerbose:  How verbose the BGL Bridge API logs should be
+#                    0: Log only error and warning messages
+#                    1: Log level 0 and information messasges
+#                    2: Log level 1 and basic debug messages
+#                    3: Log level 2 and more debug message
+#                    4: Log all messages
+# 
 # NOTE: The bgl_serial value is set at configuration time using the 
 #       "--with-bgl-serial=" option. Its default value is "BGL".
 #
 BlrtsImage=/bgl/BlueLight/ppcfloor/bglsys/bin/rts_hw.rts
 LinuxImage=/bgl/BlueLight/ppcfloor/bglsys/bin/zImage.elf
 MloaderImage=/bgl/BlueLight/ppcfloor/bglsys/bin/mmcs-mloader.rts
 RamDiskImage=/bgl/BlueLight/ppcfloor/bglsys/bin/ramdisk.elf
-#ChangeNumpsets=/etc/slurm/change_numpsets
+Numpsets=8
+#
+BridgeAPILogFile=/var/log/slurm/bridgeapi.log
+BridgeAPIVerbose=0
 
 #
 # Define the static partitions (bglblocks)

src/partition_allocator/Makefile.am

@@ -16,7 +16,7 @@ INCLUDES = -I$(top_srcdir) $(BGL_INCLUDES)
 # 	$(top_builddir)/src/api/libslurm.la
 
 # partition_allocator_LDFLAGS = -export-dynamic -lm $(CMD_LDFLAGS) $(BGL_LDFLAGS)
-# CPPFLAGS = -DBUILD_EXE
+# CPPFLAGS = -DBUILD_EXE 
 
 # making a .la
 noinst_LTLIBRARIES = libpartition_allocator.la 

src/partition_allocator/partition_allocator.c

@@ -92,8 +92,7 @@ static void _switch_config(pa_node_t* source, pa_node_t* target, int dim,
 			int port_src, int port_tar);
 /* */
 static void _set_external_wires(int dim, int count, pa_node_t* source, 
-			 pa_node_t* target_1, pa_node_t* target_2, 
-			 pa_node_t* target_first, pa_node_t* target_second);
+			 pa_node_t* target_1, pa_node_t* target_2);
 /* */
 static char *_set_internal_wires(List nodes, int size, int conn_type);
 
@@ -474,7 +473,7 @@ void pa_init(node_info_msg_t *node_info_ptr)
 	_create_pa_system();
 
 	pa_system_ptr->fill_in_value = (pa_node_t *) 
-		xmalloc(sizeof(pa_node_t) * pa_system_ptr->num_of_proc);
+		xmalloc(sizeof(pa_node_t) * 128);
 
 	init_grid(node_info_ptr);
 
@@ -985,7 +984,7 @@ static int _create_config_even(pa_node_t *grid)
 
 #if HAVE_BGL
 	int y,z;
-	pa_node_t *target_2, *target_first, *target_second;
+	pa_node_t *target_2;
 	for(x=0;x<DIM_SIZE[X];x++) {
 		for(y=0;y<DIM_SIZE[Y];y++) {
 			for(z=0;z<DIM_SIZE[Z];z++) {
@@ -999,31 +998,23 @@ static int _create_config_even(pa_node_t *grid)
 					target_2 = &grid[x+2][y][z];
 				else
 					target_2 = target_1;
-				target_first = &grid[0][y][z];
-				if (DIM_SIZE[X] > 1)
-					target_second = &grid[1][y][z];
-				else
-					target_second = target_first;
 				_set_external_wires(X, x, source, 
-						target_1, target_2, 
-						target_first, target_second);
+						target_1, target_2);
 
 				if(y<(DIM_SIZE[Y]-1)) 
 					target_1 = &grid[x][y+1][z];
 				else 
 					target_1 = &grid[x][0][z];
 
 				_set_external_wires(Y, y, source, 
-						    target_1, NULL, 
-						    NULL, NULL);
+						    target_1, NULL);
 				if(z<(DIM_SIZE[Z]-1)) 
 					target_1 = &grid[x][y][z+1];
 				else 
 					target_1 = &grid[x][y][0];
 
 				_set_external_wires(Z, z, source, 
-						    target_1, NULL, 
-						    NULL, NULL);
+						    target_1, NULL);
 			}
 		}
 	}
@@ -1051,8 +1042,7 @@ static int _create_config_even(pa_node_t *grid)
 		target_1 = &grid[x+1];
 
 		_set_external_wires(X, x, source, 
-				    target_1, NULL, 
-				    NULL, NULL);
+				    target_1, NULL);
 	}
 #endif
 	return 1;
@@ -1434,8 +1424,7 @@ static void _switch_config(pa_node_t* source, pa_node_t* target, int dim,
 }
 
 static void _set_external_wires(int dim, int count, pa_node_t* source, 
-		pa_node_t* target_1, pa_node_t* target_2, 
-		pa_node_t* target_first, pa_node_t* target_second)
+		pa_node_t* target_1, pa_node_t* target_2)
 {
 	_switch_config(source, source, dim, 0, 0);
 	_switch_config(source, source, dim, 1, 1);
@@ -1445,47 +1434,46 @@ static void _set_external_wires(int dim, int count, pa_node_t* source,
 		_switch_config(source, source, dim, 4, 4);			
 		return;
 	}
+
 	if(count==0) {
-		/* First Node */
+		/* First Even Node */
 		/* 4->3 of next */
 		_switch_config(source, target_1, dim, 4, 3);
-		/* 2->5 of next */
-		_switch_config(source, target_1, dim, 2, 5);
-		/* 3->4 of next even */
-		_switch_config(source, target_2, dim, 3, 4);
-		if(DIM_SIZE[dim]<4) {
-			/* 5->2 of next even */
-			_switch_config(source, target_2, dim, 5, 2);
-
-		}
-
+		/* 5->2 of next */
+		_switch_config(source, target_1, dim, 5, 2);
+		/* 2->5 of next even */
+		_switch_config(source, target_2, dim, 2, 5);	
+
 	} else if(!(count%2)) {
 		if(count<DIM_SIZE[dim]-2) {
 			/* Not Last Even Node */
-			/* 3->4 of next even */
-			_switch_config(source, target_2, dim, 3, 4);
-			/* 2->5 of next */
-			_switch_config(source, target_1, dim, 2, 5);
-			/* 5->2 of next */
-			_switch_config(source, target_1, dim, 5, 2);
+			/* 3->4 of next */
+			_switch_config(source, target_1, dim, 3, 4);
+			/* 4->3 of next */
+			_switch_config(source, target_1, dim, 4, 3);
+			/* 2->5 of next even */
+			_switch_config(source, target_2, dim, 2, 5);
+			/* 5->2 of next even */
+			_switch_config(source, target_2, dim, 5, 2);
+
 		} else {
 			/* Last Even Node */
 			/* 3->4 of next */
 			_switch_config(source, target_1, dim, 3, 4);
-			/* 5->2 of next */
-			_switch_config(source, target_1, dim, 5, 2);
-			/* 2->5 of first */
-			_switch_config(source, target_first, dim, 2, 5);
+			/* 2->5 of previous */
+			/********** fix me: on the full system this is needed ******/ 
+			//_switch_config(source, target_1, dim, 2, 5);	
+			/********** fix me: not this ******/ 
+			_switch_config(source, target_1, dim, 4, 3);
 		}
 	} else {
 		if(count<DIM_SIZE[dim]-2) {
 			/* Not Last Odd Node */
-			/* 4->3 of next odd */
-			_switch_config(source, target_2, dim, 4, 3);
+			/* 5->2 of next odd */
+			_switch_config(source, target_2, dim, 5, 2);
 		} else {
 			/* Last Odd Node */
-			/* 5->2 of second */
-			_switch_config(source, target_second, dim, 5, 2);
+			/* nothing */
 		}	
 	}	
 }
@@ -1891,42 +1879,33 @@ int main(int argc, char** argv)
 	List results;
 //	List results2;
 //	int i,j;
-	DIM_SIZE[X]=8;
+	DIM_SIZE[X]=4;
 	DIM_SIZE[Y]=1;
 	DIM_SIZE[Z]=1;
 	pa_init(NULL);
-	loc = find_bp_loc("R171");
-	printf("The loc is %d%d%d\n",loc[X],loc[Y],loc[Z]);
-	if((loc = find_bp_loc("R178")))
-		printf("The loc is %d%d%d\n",loc[X],loc[Y],loc[Z]);
-	else
-		printf("This doesn't exsist!\n");
-	exit(0);
 
-/* 	request->rotate = true; */
-/* 	request->elongate = true; */
-/* 	request->force_contig = true; */
-/* 	request->co_proc = true; */
-/* 	request->geometry[0]=-1; */
-
-	results = list_create(NULL);
-	request->geometry[0] = -1;
-	request->size = 1; //atoi(argv[1]);
-	request->conn_type = TORUS;
-	new_pa_request(request);
-	print_pa_request(request);
-	allocate_part(request, results);
+
 
 	results = list_create(NULL);
-	request->geometry[0] = 5;
+	request->geometry[0] = 4;
 	request->geometry[1] = 1;
 	request->geometry[2] = 1;
-	request->size = -1; //atoi(argv[1]);
-	request->conn_type = MESH;
+	request->size = 4;
+	request->conn_type = TORUS;
 	new_pa_request(request);
 	print_pa_request(request);
 	allocate_part(request, results);
 
+	/* results = list_create(NULL); */
+/* 	request->geometry[0] = 5; */
+/* 	request->geometry[1] = 1; */
+/* 	request->geometry[2] = 1; */
+/* 	request->size = -1; //atoi(argv[1]); */
+/* 	request->conn_type = MESH; */
+/* 	new_pa_request(request); */
+/* 	print_pa_request(request); */
+/* 	allocate_part(request, results); */
+
 	int dim,j;
 	int x,y,z;
 	int startx=0;
@@ -1955,11 +1934,11 @@ int main(int argc, char** argv)
 			}
 		}
 	}
-	list_destroy(results);
+	/* list_destroy(results); */
 
-	pa_fini();
+/* 	pa_fini(); */
 
-	delete_pa_request(request);
+/* 	delete_pa_request(request); */
 
 	return 0;
 }