Hi! I found a bug in cons_res/select_p_select_nodeinfo_set_all.
If a node is part of two (or more) partitions the code will only count the number of cores/cpus in the partition that has the most running jobs on that node.
Patch attached to fix the problem.I also added an new function to bitstring to count the number of bits in an range (bit_set_count_range) and made a minor improvement of (bit_set_count) while reviewing the range version.
Best regards, Magnus -- Magnus Jonsson, Developer, HPC2N, Umeå Universitet
diff -ru site/src/common/bitstring.c amd64_ubuntu1004/src/common/bitstring.c
--- site/src/common/bitstring.c 2013-03-08 20:29:51.000000000 +0100
+++ amd64_ubuntu1004/src/common/bitstring.c 2013-03-12 14:07:20.000000000 +0100
@@ -69,6 +69,7 @@
strong_alias(bit_not, slurm_bit_not);
strong_alias(bit_or, slurm_bit_or);
strong_alias(bit_set_count, slurm_bit_set_count);
+strong_alias(bit_set_count_range, slurm_bit_set_count_range);
strong_alias(bit_clear_count, slurm_bit_clear_count);
strong_alias(bit_nset_max_count,slurm_bit_nset_max_count);
strong_alias(int_and_set_count, slurm_int_and_set_count);
@@ -662,15 +663,45 @@
_assert_bitstr_valid(b);
bit_cnt = _bitstr_bits(b);
- for (bit = 0; bit < bit_cnt; bit += word_size) {
- if ((bit + word_size - 1) >= bit_cnt)
- break;
+ for (bit = 0; (bit + word_size) <= bit_cnt; bit += word_size) {
count += hweight(b[_bit_word(bit)]);
}
for ( ; bit < bit_cnt; bit++) {
if (bit_test(b, bit))
count++;
}
+ return count;
+}
+
+/*
+ * Count the number of bits set in a range of bitstring.
+ * b (IN) bitstring to check
+ * start (IN) first bit to check
+ * end (IN) last bit to check+1
+ * RETURN count of set bits
+ */
+int
+bit_set_count_range(bitstr_t *b, int start, int end)
+{
+ int count = 0;
+ bitoff_t bit, bit_cnt;
+ const int word_size = sizeof(bitstr_t) * 8;
+
+ _assert_bitstr_valid(b);
+ _assert_bit_valid(b,start);
+
+ end = MIN(end,_bitstr_bits(b));
+ for ( bit = start; bit < end && bit < ((start+word_size-1)/word_size) * word_size; bit++) {
+ if (bit_test(b, bit))
+ count++;
+ }
+ for (; (bit + word_size) <= end ; bit += word_size) {
+ count += hweight(b[_bit_word(bit)]);
+ }
+ for ( ; bit < end; bit++) {
+ if (bit_test(b, bit))
+ count++;
+ }
return count;
}
diff -ru site/src/common/bitstring.h amd64_ubuntu1004/src/common/bitstring.h
--- site/src/common/bitstring.h 2013-03-08 20:29:51.000000000 +0100
+++ amd64_ubuntu1004/src/common/bitstring.h 2013-03-12 14:09:18.000000000 +0100
@@ -172,6 +172,7 @@
void bit_not(bitstr_t *b);
void bit_or(bitstr_t *b1, bitstr_t *b2);
int bit_set_count(bitstr_t *b);
+int bit_set_count_range(bitstr_t *b, int start, int end);
int bit_clear_count(bitstr_t *b);
int bit_nset_max_count(bitstr_t *b);
int int_and_set_count(int *i1, int ilen, bitstr_t *b2);
diff -ru site/src/common/slurm_xlator.h amd64_ubuntu1004/src/common/slurm_xlator.h
--- site/src/common/slurm_xlator.h 2013-03-08 20:29:51.000000000 +0100
+++ amd64_ubuntu1004/src/common/slurm_xlator.h 2013-03-12 12:32:50.000000000 +0100
@@ -93,6 +93,7 @@
#define bit_not slurm_bit_not
#define bit_or slurm_bit_or
#define bit_set_count slurm_bit_set_count
+#define bit_set_count_range slurm_bit_set_count_range
#define bit_clear_count slurm_bit_clear_count
#define bit_nset_max_count slurm_bit_nset_max_count
#define bit_and_set_count slurm_bit_and_set_count
diff -ru site/src/plugins/select/cons_res/select_cons_res.c amd64_ubuntu1004/src/plugins/select/cons_res/select_cons_res.c
--- site/src/plugins/select/cons_res/select_cons_res.c 2013-03-11 11:13:31.000000000 +0100
+++ amd64_ubuntu1004/src/plugins/select/cons_res/select_cons_res.c 2013-03-12 13:30:06.000000000 +0100
@@ -2230,7 +2230,7 @@
struct part_res_record *p_ptr;
struct node_record *node_ptr = NULL;
int i=0, n=0, c, start, end;
- uint16_t tmp, tmp_16 = 0;
+ uint16_t tmp, tmp_16 = 0, tmp_part;
static time_t last_set_all = 0;
uint32_t node_threads, node_cpus;
select_nodeinfo_t *nodeinfo = NULL;
@@ -2275,20 +2275,17 @@
for (p_ptr = select_part_record; p_ptr; p_ptr = p_ptr->next) {
if (!p_ptr->row)
continue;
+ tmp_part = 0;
for (i = 0; i < p_ptr->num_rows; i++) {
if (!p_ptr->row[i].row_bitmap)
continue;
- tmp = 0;
- for (c = start; c < end; c++) {
- if (bit_test(p_ptr->row[i].row_bitmap,
- c))
- tmp++;
- }
+ tmp = bit_set_count_range(p_ptr->row[i].row_bitmap,
+ start,end);
/* get the row with the largest cpu
count on it. */
- if (tmp > tmp_16)
- tmp_16 = tmp;
+ tmp_part = MAX(tmp,tmp_part);
}
+ tmp_16 += tmp_part;
}
/* The minimum allocatable unit may a core, so scale
smime.p7s
Description: S/MIME Cryptographic Signature
