fix buffer overflow when handling slot type in a jobspec

resource/evaluators/edge_eval_api.cpp

@@ -149,6 +149,11 @@ unsigned int evals_t::qualified_count () const
     return m_qual_count;
 }
 
+unsigned int evals_t::qualified_granules () const
+{
+    return m_eval_egroups.size ();
+}
+
 unsigned int evals_t::total_count () const
 {
     return m_total_count;

resource/evaluators/edge_eval_api.hpp

@@ -73,6 +73,7 @@ class evals_t {
     // This can throw out_of_range exception
     const eval_egroup_t &at (unsigned int i) const;
     unsigned int qualified_count () const;
+    unsigned int qualified_granules () const;
     unsigned int total_count () const;
     int64_t cutline () const;
     int64_t set_cutline (int64_t cutline);

resource/evaluators/scoring_api.cpp

@@ -180,6 +180,14 @@ unsigned int scoring_api_t::qualified_count (const subsystem_t &s,
     return res_evals->qualified_count ();
 }
 
+unsigned int scoring_api_t::qualified_granules (const subsystem_t &s,
+                                                const std::string &r)
+{
+    handle_new_keys (s, r);
+    auto res_evals = (*m_ssys_map[s])[r];
+    return res_evals->qualified_granules ();
+}
+
 unsigned int scoring_api_t::total_count (const subsystem_t &s,
                                          const std::string &r)
 {

resource/evaluators/scoring_api.hpp

@@ -58,6 +58,7 @@ class scoring_api_t {
     const eval_egroup_t &at (const subsystem_t &s, const std::string &r,
                              unsigned int i);
     unsigned int qualified_count (const subsystem_t &s, const std::string &r);
+    unsigned int qualified_granules (const subsystem_t &s, const std::string &r);
     unsigned int total_count (const subsystem_t &s, const std::string &r);
     unsigned int best_k (const subsystem_t &s, const std::string &r);
     unsigned int best_i (const subsystem_t &s, const std::string &r);

resource/traversers/dfu_impl.cpp

@@ -449,17 +449,29 @@ int dfu_impl_t::cnt_slot (const std::vector<Resource> &slot_shape,
                           scoring_api_t &dfu_slot)
 {
     unsigned int qc = 0;
+    unsigned int qg = 0;
     unsigned int fit = 0;
     unsigned int count = 0;
     unsigned int qual_num_slots = UINT_MAX;
     const subsystem_t &dom = m_match->dom_subsystem ();
 
     // qualifed slot count is determined by the most constrained resource type
+    // both in terms of the amounts available as well as the number of edges into
+    // that resource because that represent the match granularity.
+    // Say you have 128 units of memory available across two memory resource
+    // vertices each with 64 units of memory and you request 1 unit of memory.
+    // In this case, you don't have 128 slots available because the match
+    // granularity is 64 units. Instead, you have only 2 slots available each
+    // with 64 units, and your request will get 1 whole resource vertex.
     qual_num_slots = UINT_MAX;
     for (auto &slot_elem : slot_shape) {
         qc = dfu_slot.qualified_count (dom, slot_elem.type);
+        qg = dfu_slot.qualified_granules (dom, slot_elem.type);
         count = m_match->calc_count (slot_elem, qc);
+        // constraint check against qualified amounts
         fit = (count == 0)? count : (qc / count);
+        // constraint check against qualified granules
+        fit = (fit > qg)? qg : fit;
         qual_num_slots = (qual_num_slots > fit)? fit : qual_num_slots;
         dfu_slot.rewind_iter_cur (dom, slot_elem.type);
     }

t/Makefile.am

@@ -51,6 +51,7 @@ TESTS = \
     t3014-resource-var-aware.t \
     t3015-resource-basic-jgf.t \
     t3016-resource-power-jgf.t \
+    t3017-resource-granule.t \
     t4000-match-params.t \
     t4001-match-allocate.t \
     t4002-match-reserve.t \

t/data/resource/commands/granule/cmds01.in

@@ -0,0 +1,8 @@
+# 5x cluster[1]->rack[1]->node[1]->socket[1]->slot[4]->core[1]
+#                                                    ->memory[1]
+match allocate @TEST_SRCDIR@/data/resource/jobspecs/granule/test001.yaml
+match allocate @TEST_SRCDIR@/data/resource/jobspecs/granule/test001.yaml
+match allocate @TEST_SRCDIR@/data/resource/jobspecs/granule/test001.yaml
+match allocate @TEST_SRCDIR@/data/resource/jobspecs/granule/test001.yaml
+match allocate @TEST_SRCDIR@/data/resource/jobspecs/granule/test001.yaml
+quit

t/data/resource/expected/granule/001.R.out

@@ -0,0 +1,72 @@
+      ---------------core32[1:x]
+      ---------------core33[1:x]
+      ---------------core34[1:x]
+      ---------------core35[1:x]
+      ---------------memory4[2:x]
+      ---------------memory5[2:x]
+      ---------------memory6[2:x]
+      ---------------memory7[2:x]
+      ------------socket1[1:s]
+      ---------node1[1:s]
+      ------rack0[1:s]
+      ---tiny0[1:s]
+INFO: =============================
+INFO: JOBID=1
+INFO: RESOURCES=ALLOCATED
+INFO: SCHEDULED AT=Now
+INFO: =============================
+      ---------------core14[1:x]
+      ---------------core15[1:x]
+      ---------------core16[1:x]
+      ---------------core17[1:x]
+      ---------------memory0[2:x]
+      ---------------memory1[2:x]
+      ---------------memory2[2:x]
+      ---------------memory3[2:x]
+      ------------socket0[1:s]
+      ---------node1[1:s]
+      ------rack0[1:s]
+      ---tiny0[1:s]
+INFO: =============================
+INFO: JOBID=2
+INFO: RESOURCES=ALLOCATED
+INFO: SCHEDULED AT=Now
+INFO: =============================
+      ---------------core32[1:x]
+      ---------------core33[1:x]
+      ---------------core34[1:x]
+      ---------------core35[1:x]
+      ---------------memory4[2:x]
+      ---------------memory5[2:x]
+      ---------------memory6[2:x]
+      ---------------memory7[2:x]
+      ------------socket1[1:s]
+      ---------node0[1:s]
+      ------rack0[1:s]
+      ---tiny0[1:s]
+INFO: =============================
+INFO: JOBID=3
+INFO: RESOURCES=ALLOCATED
+INFO: SCHEDULED AT=Now
+INFO: =============================
+      ---------------core14[1:x]
+      ---------------core15[1:x]
+      ---------------core16[1:x]
+      ---------------core17[1:x]
+      ---------------memory0[2:x]
+      ---------------memory1[2:x]
+      ---------------memory2[2:x]
+      ---------------memory3[2:x]
+      ------------socket0[1:s]
+      ---------node0[1:s]
+      ------rack0[1:s]
+      ---tiny0[1:s]
+INFO: =============================
+INFO: JOBID=4
+INFO: RESOURCES=ALLOCATED
+INFO: SCHEDULED AT=Now
+INFO: =============================
+INFO: =============================
+INFO: No matching resources found
+INFO: JOBID=5
+INFO: =============================

t/data/resource/expected/granule/002.R.out

@@ -0,0 +1,72 @@
+      ---------------core0[1:x]
+      ---------------core1[1:x]
+      ---------------core2[1:x]
+      ---------------core3[1:x]
+      ---------------memory0[2:x]
+      ---------------memory1[2:x]
+      ---------------memory2[2:x]
+      ---------------memory3[2:x]
+      ------------socket0[1:s]
+      ---------node0[1:s]
+      ------rack0[1:s]
+      ---tiny0[1:s]
+INFO: =============================
+INFO: JOBID=1
+INFO: RESOURCES=ALLOCATED
+INFO: SCHEDULED AT=Now
+INFO: =============================
+      ---------------core18[1:x]
+      ---------------core19[1:x]
+      ---------------core20[1:x]
+      ---------------core21[1:x]
+      ---------------memory4[2:x]
+      ---------------memory5[2:x]
+      ---------------memory6[2:x]
+      ---------------memory7[2:x]
+      ------------socket1[1:s]
+      ---------node0[1:s]
+      ------rack0[1:s]
+      ---tiny0[1:s]
+INFO: =============================
+INFO: JOBID=2
+INFO: RESOURCES=ALLOCATED
+INFO: SCHEDULED AT=Now
+INFO: =============================
+      ---------------core0[1:x]
+      ---------------core1[1:x]
+      ---------------core2[1:x]
+      ---------------core3[1:x]
+      ---------------memory0[2:x]
+      ---------------memory1[2:x]
+      ---------------memory2[2:x]
+      ---------------memory3[2:x]
+      ------------socket0[1:s]
+      ---------node1[1:s]
+      ------rack0[1:s]
+      ---tiny0[1:s]
+INFO: =============================
+INFO: JOBID=3
+INFO: RESOURCES=ALLOCATED
+INFO: SCHEDULED AT=Now
+INFO: =============================
+      ---------------core18[1:x]
+      ---------------core19[1:x]
+      ---------------core20[1:x]
+      ---------------core21[1:x]
+      ---------------memory4[2:x]
+      ---------------memory5[2:x]
+      ---------------memory6[2:x]
+      ---------------memory7[2:x]
+      ------------socket1[1:s]
+      ---------node1[1:s]
+      ------rack0[1:s]
+      ---tiny0[1:s]
+INFO: =============================
+INFO: JOBID=4
+INFO: RESOURCES=ALLOCATED
+INFO: SCHEDULED AT=Now
+INFO: =============================
+INFO: =============================
+INFO: No matching resources found
+INFO: JOBID=5
+INFO: =============================

t/data/resource/jobspecs/granule/test001.yaml

@@ -0,0 +1,26 @@
+version: 1
+resources:
+  - type: node
+    count: 1
+    with:
+      - type: socket
+        count: 1
+        with:
+          - type: slot
+            count: 4
+            label: default
+            with:
+              - type: core
+                count: 1
+              - type: memory
+                count: 1
+
+# a comment
+attributes:
+  system:
+    duration: 3600
+tasks:
+  - command: app
+    slot: default
+    count:
+      per_slot: 1

t/t3017-resource-granule.t

@@ -0,0 +1,39 @@
+#!/bin/sh
+
+test_description='Test Scheduling Correctness on Vertex Granularity'
+
+. $(dirname $0)/sharness.sh
+
+cmd_dir="${SHARNESS_TEST_SRCDIR}/data/resource/commands/granule"
+exp_dir="${SHARNESS_TEST_SRCDIR}/data/resource/expected/granule"
+grugs="${SHARNESS_TEST_SRCDIR}/data/resource/grugs/tiny.graphml"
+query="../../resource/utilities/resource-query"
+
+#
+# Selection Policy -- High ID first (-P high)
+#     The resource vertex with higher ID is preferred among its kind
+#     (e.g., node1 is preferred over node0 if available)
+#
+
+cmds001="${cmd_dir}/cmds01.in"
+test001_desc="memory granularity keeps last jobspec from being matched (pol=hi)"
+test_expect_success "${test001_desc}" '
+    sed "s~@TEST_SRCDIR@~${SHARNESS_TEST_SRCDIR}~g" ${cmds001} > cmds001 &&
+    ${query} -L ${grugs} -S CA -P high -t 001.R.out < cmds001 &&
+    test_cmp 001.R.out ${exp_dir}/001.R.out
+'
+
+## Selection Policy -- Low ID first (-P low)
+##     The resource vertex with lower ID is preferred among its kind
+##     (e.g., node0 is preferred over node1 if available)
+##
+
+cmds002="${cmd_dir}/cmds01.in"
+test002_desc="memory granularity keeps last jobspec from being matched (pol=hi)"
+test_expect_success "${test002_desc}" '
+    sed "s~@TEST_SRCDIR@~${SHARNESS_TEST_SRCDIR}~g" ${cmds002} > cmds002 &&
+    ${query} -L ${grugs} -S CA -P low -t 002.R.out < cmds002 &&
+    test_cmp 002.R.out ${exp_dir}/002.R.out
+'
+
+test_done