about summary refs log tree commit diff
path: root/specials
diff options
context:
space:
mode:
Diffstat (limited to 'specials')
-rw-r--r--specials/slurm-container.scm27
1 files changed, 23 insertions, 4 deletions
diff --git a/specials/slurm-container.scm b/specials/slurm-container.scm
index f50ce28..8765c3d 100644
--- a/specials/slurm-container.scm
+++ b/specials/slurm-container.scm
@@ -196,11 +196,24 @@ which slurmd cannot decode (it never loads the JWT key)."
                ;; (a job that is ready to run still waits for the next
                ;; cycle), which for a workflow that submits its steps a
                ;; few seconds apart becomes the dominant cost of a whole
-               ;; run: 6 one-second jobs took ~3 minutes. These settings
-               ;; are for a throwaway test container, not a deployment.
-               "SchedulerParameters=sched_interval=5,sched_min_interval=1,bf_interval=5,bf_max_job_start=40\n"
+               ;; run: 6 one-second jobs took ~3 minutes. With capacity
+               ;; for 30 jobs the cycle length is what decides whether a
+               ;; 40-job scatter starts in one go or trickles, so the
+               ;; cycle is a second and one cycle may start them all.
+               ;; These settings are for a throwaway test container, not a
+               ;; deployment.
+               "SchedulerParameters=sched_interval=1,sched_min_interval=1,bf_interval=1,bf_max_job_start=60\n"
                "SelectType=select/cons_tres\n"
                "SelectTypeParameters=CR_Core\n"
+               ;; One job = one core = 1 GiB reserved. Without a
+               ;; DefMemPerCPU a job that requests no memory is allocated
+               ;; the node's whole memory, which queues the next job
+               ;; behind it however many cores are free.
+               "DefMemPerCPU=1024\n"
+               ;; The conf, not slurmd's own probe, decides the node's
+               ;; size: the container sees the host's cores and memory,
+               ;; and slurmd refuses to start when the two disagree.
+               "SlurmdParameters=config_overrides\n"
                "ReturnToService=2\n"
                "MpiDefault=none\n"
                "\n"
@@ -219,7 +232,13 @@ which slurmd cannot decode (it never loads the JWT key)."
                ;; multi-job workflow.
                "MinJobAge=86400\n"
                "\n"
-               "NodeName=slurm-container NodeAddr=127.0.0.1 CPUs=2 RealMemory=1024 State=UNKNOWN\n"
+               ;; 30 CPUs because that is what the scatter needs: measured
+               ;; with CPUs=2, a 30-job probe ran 2 at a time and ravanan's
+               ;; 40-job LOCO workflow (20 chromosomes x kinship+gwa) took
+               ;; 102 s cold against 14.3 s single-machine. RealMemory is
+               ;; generous because the container uses the host's RAM; the
+               ;; per-job share is DefMemPerCPU above, not this number.
+               "NodeName=slurm-container NodeAddr=127.0.0.1 CPUs=30 RealMemory=65536 State=UNKNOWN\n"
                "PartitionName=debug Nodes=slurm-container Default=YES MaxTime=INFINITE State=UP\n")))
 
 ;; The JWT key is fixed, not random: `scontrol token` cannot mint one