Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add restart_file configuration variable, remove ENV variable, enable restarted progress logging #2777

Merged
merged 2 commits into from
Mar 20, 2024
Merged

Add restart_file configuration variable, remove ENV variable, enable restarted progress logging #2777

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bbb65cb
Add `restart_file` configuration variable, remove ENV variable
nefrathenrici Mar 11, 2024
3b135c1
Enable progress estimate for restarted simulations
nefrathenrici Mar 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion .buildkite/pipeline.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,7 +370,6 @@ steps:
artifact_paths: "restart_mpi_baroclinic_wave_rhoe/*"
env:
CLIMACORE_DISTRIBUTED: "MPI"
RESTART_FILE: "mpi_make_restart/day5.0.hdf5"
agents:
slurm_ntasks: 2
slurm_mem: 16G
Expand Down
3 changes: 3 additions & 0 deletions config/default_configs/default_config.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -274,3 +274,6 @@ log_progress:
deep_atmosphere:
help: "Do not assume that the atmosphere is shallow, where the vertical columns are cylindrical"
value: false
restart_file:
help: "Path to HDF5 file to use as simulation starting point"
value: ~
3 changes: 2 additions & 1 deletion config/mpi_configs/restart_mpi_baroclinic_wave_rhoe.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
job_id: "restart_mpi_baroclinic_wave_rhoe"
t_end: "20days"
initial_condition: "DryBaroclinicWave"
initial_condition: "DryBaroclinicWave"
restart_file: "mpi_make_restart/day5.0.hdf5"
9 changes: 5 additions & 4 deletions src/callbacks/callbacks.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,6 +231,7 @@ end
import Dates
function print_walltime_estimate(integrator)
(; walltime_estimate, dt, t_end) = integrator.p
t_start = integrator.sol.prob.tspan[1]
wte = walltime_estimate

# Notes on `ready_to_report`
Expand Down Expand Up @@ -258,11 +259,11 @@ function print_walltime_estimate(integrator)

if wte.n_calls == wte.n_next && ready_to_report
t = integrator.t
n_steps_total = ceil(Int, t_end / dt)
n_steps = ceil(Int, t / dt)
n_steps_total = ceil(Int, (t_end - t_start) / dt)
n_steps = ceil(Int, (t - t_start) / dt)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think above we need n_steps_total = ceil(Int, (t_end - t_start) / dt)

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

But I think that might be all we need

wall_time_ave_per_step = wte.∑Δt_wall / n_steps
wall_time_ave_per_step_str = time_and_units_str(wall_time_ave_per_step)
percent_complete = round(t / t_end * 100; digits = 1)
percent_complete = round((t - t_start) / t_end * 100; digits = 1)
n_steps_remaining = n_steps_total - n_steps
wall_time_remaining = wall_time_ave_per_step * n_steps_remaining
wall_time_remaining_str = time_and_units_str(wall_time_remaining)
Expand All @@ -272,7 +273,7 @@ function print_walltime_estimate(integrator)
simulation_time = time_and_units_str(Float64(t))
sypd = round(
simulated_years_per_day(
EfficiencyStats((zero(t), t), wte.∑Δt_wall),
EfficiencyStats((t_start, t), wte.∑Δt_wall),
);
digits = 3,
)
Expand Down
2 changes: 1 addition & 1 deletion src/callbacks/get_callbacks.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ function get_callbacks(config, sim_info, atmos, params, Y, p, t_start)
(; dt, output_dir) = sim_info

callbacks = ()
if parsed_args["log_progress"] && !sim_info.restart
if parsed_args["log_progress"]
@info "Progress logging enabled."
callbacks = (
callbacks...,
Expand Down
13 changes: 7 additions & 6 deletions src/solver/type_getters.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -296,9 +296,11 @@ function get_spaces_restart(Y)
return (; center_space, face_space)
end

function get_state_restart(comms_ctx)
@assert haskey(ENV, "RESTART_FILE")
reader = InputOutput.HDF5Reader(ENV["RESTART_FILE"], comms_ctx)
function get_state_restart(config::AtmosConfig)
(; parsed_args, comms_ctx) = config
restart_file = parsed_args["restart_file"]
@assert !isnothing(restart_file)
reader = InputOutput.HDF5Reader(restart_file, comms_ctx)
Y = InputOutput.read_field(reader, "Y")
t_start = InputOutput.HDF5.read_attribute(reader.file, "time")
return (Y, t_start)
Expand Down Expand Up @@ -472,7 +474,7 @@ function get_sim_info(config::AtmosConfig)

sim = (;
output_dir,
restart = haskey(ENV, "RESTART_FILE"),
restart = !isnothing(parsed_args["restart_file"]),
job_id,
dt = FT(time_to_seconds(parsed_args["dt"])),
start_date = DateTime(parsed_args["start_date"], dateformat"yyyymmdd"),
Expand Down Expand Up @@ -723,9 +725,8 @@ function get_simulation(config::AtmosConfig)

if sim_info.restart
s = @timed_str begin
(Y, t_start) = get_state_restart(config.comms_ctx)
(Y, t_start) = get_state_restart(config)
spaces = get_spaces_restart(Y)
@warn "Progress estimates do not support restarted simulations"
end
@info "Allocating Y: $s"
else
Expand Down
Loading