wip on streamlining slurm integration #1165

JBlaschke · 2025-04-10T18:23:52Z

Long term we'll want to use https://github.com/JuliaParallel/NetworkInterfaceControllers.jl -- however to make progress right now, I just copied the slurm integration into src/extern.

The way this ends up being used (at the moment -- again we'll make it better) is to set REACTANT_COORDINATOR_BIND_ADDRESS. Eg. on Perlmutter we want to use the chn (Customer High-Speed Network) adaptor on the HSN:

export REACTANT_COORDINATOR_BIND_ADDRESS=\$(ip -f inet addr show hsn0 | grep chn | awk '/inet / {print \$2}' | cut -d/ -f1):75535

github-actions · 2025-04-10T18:24:25Z

src/Distributed.jl

+        port = ENV["REACTANT_COORDINATOR_BIND_ADDRESS"] |>
+            Base.Fix2(split, ":") |> last |> Base.Fix1(parse, Int)


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

port = ENV["REACTANT_COORDINATOR_BIND_ADDRESS"] |>

Base.Fix2(split, ":") |> last |> Base.Fix1(parse, Int)

port =

Base.Fix1(parse, Int)(last(Base.Fix2(split, ":")(ENV["REACTANT_COORDINATOR_BIND_ADDRESS"])))

someone doesn't like the pipe syntax....

github-actions · 2025-04-10T18:24:26Z

src/Distributed.jl

    end
+    node_list = ENV[_SLURM_NODELIST]
+    @debug "Setup coordinator: node_list=$(node_list)"
+    broker_addr = Hostlists.Hostlist(node_list) |> first


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

broker_addr = Hostlists.Hostlist(node_list) |> first

broker_addr = first(Hostlists.Hostlist(node_list))

github-actions · 2025-04-10T18:24:26Z

src/extern/hostlists.jl

+module Hostlists
+module SlurmHostlists
+
+import Libdl


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

import Libdl

using Libdl: Libdl

github-actions · 2025-04-10T18:24:26Z

src/extern/hostlists.jl

+const libslurm = Libdl.find_library(["libslurm"])
+if !("" == libslurm)
+    # We need to dlopen libslurm with RTLD_GLOBAL to make sure that all
+    # dependencies are loaded correctly.
+    Libdl.dlopen(libslurm, Libdl.RTLD_GLOBAL)
+end


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

const libslurm = Libdl.find_library(["libslurm"])

if !("" == libslurm)

# We need to dlopen libslurm with RTLD_GLOBAL to make sure that all

# dependencies are loaded correctly.

Libdl.dlopen(libslurm, Libdl.RTLD_GLOBAL)

end

const libslurm = Libdl.find_library(["libslurm"])

if !("" == libslurm)

# We need to dlopen libslurm with RTLD_GLOBAL to make sure that all

# dependencies are loaded correctly.

Libdl.dlopen(libslurm, Libdl.RTLD_GLOBAL)

end

const hostlist_t = Ptr{Nothing}

function slurm_hostlist_create(hostlist)

@ccall libslurm.slurm_hostlist_create(hostlist::Cstring)::hostlist_t

end

function slurm_hostlist_count(hl::hostlist_t)

@ccall libslurm.slurm_hostlist_count(hl::hostlist_t)::Cint

end

function slurm_hostlist_destroy(hl::hostlist_t)

@ccall libslurm.slurm_hostlist_destroy(hl::hostlist_t)::Cvoid

end

function slurm_hostlist_find(hl::hostlist_t, hostname)

@ccall libslurm.slurm_hostlist_find(hl::hostlist_t, hostname::Cstring)::Cint

end

function slurm_hostlist_push(hl::hostlist_t, hosts)

@ccall libslurm.slurm_hostlist_push(hl::hostlist_t, hosts::Cstring)::Cint

end

function slurm_hostlist_push_host(hl::hostlist_t, host)

@ccall libslurm.slurm_hostlist_push_host(hl::hostlist_t, host::Cstring)::Cint

end

function slurm_hostlist_ranged_string(hl::hostlist_t, n::Csize_t, buf)

@ccall libslurm.slurm_hostlist_ranged_string(

hl::hostlist_t, n::Csize_t, buf::Ptr{UInt8}

)::Cssize_t

end

function slurm_hostlist_shift(hl::hostlist_t)

@ccall libslurm.slurm_hostlist_shift(hl::hostlist_t)::Cstring

end

function slurm_hostlist_uniq(hl::hostlist_t)

@ccall libslurm.slurm_hostlist_uniq(hl::hostlist_t)::Cvoid

end

not sure about this, but probably fine

github-actions · 2025-04-10T18:24:26Z

src/extern/hostlists.jl

+const hostlist_t = Ptr{Nothing}
+
+slurm_hostlist_create(hostlist) = @ccall libslurm.slurm_hostlist_create(hostlist::Cstring)::hostlist_t
+slurm_hostlist_count(hl::hostlist_t) = @ccall libslurm.slurm_hostlist_count(hl::hostlist_t)::Cint
+slurm_hostlist_destroy(hl::hostlist_t) = @ccall libslurm.slurm_hostlist_destroy(hl::hostlist_t)::Cvoid
+slurm_hostlist_find(hl::hostlist_t, hostname) = @ccall libslurm.slurm_hostlist_find(hl::hostlist_t, hostname::Cstring)::Cint
+slurm_hostlist_push(hl::hostlist_t, hosts) = @ccall libslurm.slurm_hostlist_push(hl::hostlist_t,hosts::Cstring)::Cint
+slurm_hostlist_push_host(hl::hostlist_t, host) = @ccall libslurm.slurm_hostlist_push_host(hl::hostlist_t, host::Cstring)::Cint
+slurm_hostlist_ranged_string(hl::hostlist_t, n::Csize_t, buf) = @ccall libslurm.slurm_hostlist_ranged_string(hl::hostlist_t, n::Csize_t, buf::Ptr{UInt8})::Cssize_t
+slurm_hostlist_shift(hl::hostlist_t) = @ccall libslurm.slurm_hostlist_shift(hl::hostlist_t)::Cstring
+slurm_hostlist_uniq(hl::hostlist_t) = @ccall libslurm.slurm_hostlist_uniq(hl::hostlist_t)::Cvoid
+
+mutable struct Hostlist
+    hlist::hostlist_t
+
+    function Hostlist(node_list::String)
+        slurm_hl = slurm_hostlist_create(node_list)
+        if slurm_hl == C_NULL
+            error("Could not allocate memory for hostlist.")


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

const hostlist_t = Ptr{Nothing}

slurm_hostlist_create(hostlist) = @ccall libslurm.slurm_hostlist_create(hostlist::Cstring)::hostlist_t

slurm_hostlist_count(hl::hostlist_t) = @ccall libslurm.slurm_hostlist_count(hl::hostlist_t)::Cint

slurm_hostlist_destroy(hl::hostlist_t) = @ccall libslurm.slurm_hostlist_destroy(hl::hostlist_t)::Cvoid

slurm_hostlist_find(hl::hostlist_t, hostname) = @ccall libslurm.slurm_hostlist_find(hl::hostlist_t, hostname::Cstring)::Cint

slurm_hostlist_push(hl::hostlist_t, hosts) = @ccall libslurm.slurm_hostlist_push(hl::hostlist_t,hosts::Cstring)::Cint

slurm_hostlist_push_host(hl::hostlist_t, host) = @ccall libslurm.slurm_hostlist_push_host(hl::hostlist_t, host::Cstring)::Cint

slurm_hostlist_ranged_string(hl::hostlist_t, n::Csize_t, buf) = @ccall libslurm.slurm_hostlist_ranged_string(hl::hostlist_t, n::Csize_t, buf::Ptr{UInt8})::Cssize_t

slurm_hostlist_shift(hl::hostlist_t) = @ccall libslurm.slurm_hostlist_shift(hl::hostlist_t)::Cstring

slurm_hostlist_uniq(hl::hostlist_t) = @ccall libslurm.slurm_hostlist_uniq(hl::hostlist_t)::Cvoid

mutable struct Hostlist

hlist::hostlist_t

function Hostlist(node_list::String)

slurm_hl = slurm_hostlist_create(node_list)

if slurm_hl == C_NULL

error("Could not allocate memory for hostlist.")

mutable struct Hostlist

hlist::hostlist_t

function Hostlist(node_list::String)

slurm_hl = slurm_hostlist_create(node_list)

if slurm_hl == C_NULL

error("Could not allocate memory for hostlist.")

end

hl = new(slurm_hl)

finalizer(delete, hl)

return hl

again, not sure but probably fine

github-actions · 2025-04-10T18:24:28Z

src/extern/hostlists.jl

+Base.convert(::Type{String}, hl::Hostlist) = join(hl.hlist, ",")
+Base.string(hl::Hostlist) = Base.convert(String, hl)
+function Base.push!(x::Hostlist, y::String)
+    push!(x.hlist, y)
+    x.hlist = x.hlist |> x->filter(!isempty, x) |> unique!
+    x
+end
+Base.length(x::Hostlist) = length(x.hlist)


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

Base.convert(::Type{String}, hl::Hostlist) = join(hl.hlist, ",")

Base.string(hl::Hostlist) = Base.convert(String, hl)

function Base.push!(x::Hostlist, y::String)

push!(x.hlist, y)

x.hlist = x.hlist |> x->filter(!isempty, x) |> unique!

x

end

Base.length(x::Hostlist) = length(x.hlist)

Base.convert(::Type{String}, hl::Hostlist) = join(hl.hlist, ",")

Base.string(hl::Hostlist) = Base.convert(String, hl)

function Base.push!(x::Hostlist, y::String)

push!(x.hlist, y)

x.hlist = (x -> unique!(filter(!isempty, x)))(x.hlist)

return x

end

Base.length(x::Hostlist) = length(x.hlist)

github-actions · 2025-04-10T18:24:28Z

src/extern/hostlists.jl

+end
+Base.length(x::Hostlist) = length(x.hlist)
+
+export string, push!, length


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

export string, push!, length

export string, push!, length

github-actions · 2025-04-10T18:24:28Z

src/extern/hostlists.jl

+
+export string, push!, length
+
+Base.show(io::IO, x::Hostlist) = print(io, string(x))


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

Base.show(io::IO, x::Hostlist) = print(io, string(x))

Base.show(io::IO, x::Hostlist) = print(io, string(x))

github-actions · 2025-04-10T18:24:28Z

src/extern/hostlists.jl

+function __init__()
+    if "" == SlurmHostlists.libslurm
+        @debug "libslurm.so not found, using SimpleHostlists"
+        global const Hostlists.Hostlist = SimpleHostlists.Hostlist


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

global const Hostlists.Hostlist = SimpleHostlists.Hostlist

const global Hostlists.Hostlist = SimpleHostlists.Hostlist

github-actions · 2025-04-10T18:24:28Z

src/extern/hostlists.jl

+        global const Hostlists.Hostlist = SimpleHostlists.Hostlist
+    else
+        @debug "libslurm.so found, using SlurmHostlists"
+        global const Hostlists.Hostlist = SlurmHostlists.Hostlist


[JuliaFormatter] _{reported by reviewdog 🐶}

Suggested change

global const Hostlists.Hostlist = SlurmHostlists.Hostlist

const global Hostlists.Hostlist = SlurmHostlists.Hostlist

JBlaschke added 2 commits April 10, 2025 11:18

wip on streamlinging slurm integration

b923047

add slurm bindings

930ae84

github-actions bot reviewed Apr 10, 2025

View reviewed changes

JBlaschke and others added 9 commits April 10, 2025 14:25

Merge remote-tracking branch 'origin/main' into jpb/hostlists

04ee9c8

Merge remote-tracking branch 'origin/main' into jpb/hostlists

13bed0a

Merge remote-tracking branch 'origin/main' into jpb/hostlists

6ef42d5

Merge branch 'main' into jpb/hostlists

9e0ac66

Merge remote-tracking branch 'origin/main' into jpb/hostlists

620de2e

Merge remote-tracking branch 'origin/main' into jpb/hostlists

9eeea06

Merge remote-tracking branch 'origin/main' into jpb/hostlists

123d885

Merge remote-tracking branch 'origin/main' into jpb/hostlists

da5c484

Merge branch 'main' into jpb/hostlists

3f482ad

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

wip on streamlining slurm integration #1165

wip on streamlining slurm integration #1165

Uh oh!

JBlaschke commented Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

JBlaschke Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

JBlaschke Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

JBlaschke Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Uh oh!

Uh oh!

		port = ENV["REACTANT_COORDINATOR_BIND_ADDRESS"] \|>
		Base.Fix2(split, ":") \|> last \|> Base.Fix1(parse, Int)

	broker_addr = Hostlists.Hostlist(node_list) \|> first
	broker_addr = first(Hostlists.Hostlist(node_list))


		export string, push!, length

		Base.show(io::IO, x::Hostlist) = print(io, string(x))

	global const Hostlists.Hostlist = SimpleHostlists.Hostlist
	const global Hostlists.Hostlist = SimpleHostlists.Hostlist

	global const Hostlists.Hostlist = SlurmHostlists.Hostlist
	const global Hostlists.Hostlist = SlurmHostlists.Hostlist

wip on streamlining slurm integration #1165

Are you sure you want to change the base?

wip on streamlining slurm integration #1165

Uh oh!

Conversation

JBlaschke commented Apr 10, 2025

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

JBlaschke Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

JBlaschke Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

JBlaschke Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions bot Apr 10, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!