feat: initial commit — Ansible roles storage-01/gpu-01 opérationnels

ansible/roles/lm_studio/files/install-lmstudio-compat.sh

@@ -0,0 +1,57 @@
+#!/usr/bin/env bash
+# Install LM Studio on AlmaLinux 9.
+#
+# AlmaLinux 9 ships GCC 11 → libstdc++ provides up to GLIBCXX_3.4.29.
+# LM Studio bundles watcher.node (compiled with GCC 12) which requires
+# _ZNSt18condition_variable4waitERSt11unique_lockISt5mutexE@GLIBCXX_3.4.30.
+# That symbol exists in the system libstdc++ under GLIBCXX_3.4.11.
+#
+# Fix: ELF-patch watcher.node to rewrite the VERNEED entry from
+# GLIBCXX_3.4.30 → GLIBCXX_3.4.11 (same symbol, correct version tag).
+# Both vna_hash and the version string are updated in-place.
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# Ansible copy task places files in /tmp
+if [ -f "/tmp/patch-glibcxx-compat.py" ]; then
+    PATCHER="/tmp/patch-glibcxx-compat.py"
+else
+    PATCHER="${SCRIPT_DIR}/patch-glibcxx-compat.py"
+fi
+
+# --- Fetch installer metadata ---
+echo "[lmstudio-install] Fetching installer metadata..."
+INSTALL_SH=$(curl -fsSL https://lmstudio.ai/install.sh)
+VERSION=$(echo "$INSTALL_SH" | grep '^APP_VERSION=' | cut -d'"' -f2)
+ARTIFACT_URL_BASE=$(echo "$INSTALL_SH" | grep '^ARTIFACT_DOWNLOAD_URL=' | cut -d'"' -f2)
+
+ARTIFACT="${VERSION}-linux-x64.full.tar.gz"
+URL="https://${ARTIFACT_URL_BASE}/${ARTIFACT}"
+
+TMPDIR=$(mktemp -d)
+trap 'rm -rf "$TMPDIR"' EXIT
+
+echo "[lmstudio-install] Downloading ${ARTIFACT}..."
+curl -fsSL "$URL" -o "$TMPDIR/bundle.tar.gz"
+
+echo "[lmstudio-install] Extracting bundle..."
+tar xf "$TMPDIR/bundle.tar.gz" -C "$TMPDIR"
+
+# Patch watcher.node before bootstrap so the daemon never sees GLIBCXX_3.4.30
+echo "[lmstudio-install] Patching watcher.node (GLIBCXX_3.4.30 → GLIBCXX_3.4.11)..."
+find "$TMPDIR" -name 'watcher.node' | while read -r node; do
+    python3 "$PATCHER" "$node"
+done
+
+echo "[lmstudio-install] Running bootstrap..."
+LMS_BOOTSTRAP_INSTALL_SH=1 "$TMPDIR/llmster" bootstrap
+
+# Also patch the installed copy in ~/.lmstudio after bootstrap
+echo "[lmstudio-install] Patching installed watcher.node copies..."
+find "${HOME}/.lmstudio" -name 'watcher.node' 2>/dev/null | while read -r node; do
+    python3 "$PATCHER" "$node"
+done
+
+echo "[lmstudio-install] Installation complete."

ansible/roles/lm_studio/files/patch-glibcxx-compat.py

@@ -0,0 +1,147 @@
+#!/usr/bin/env python3
+"""
+Patch ELF .so/.node files that require GLIBCXX_3.4.30 to use GLIBCXX_3.4.29
+instead. Required for AlmaLinux 9 / RHEL 9 which ships GCC 11 (max GLIBCXX_3.4.29).
+
+Both the version string AND the vna_hash in .gnu.version_r are updated so the
+dynamic linker finds the version correctly at runtime.
+"""
+import sys
+import struct
+
+
+def elf_hash(name: str) -> int:
+    """ELF version symbol hash (not GNU hash — used in .gnu.version_r)."""
+    h = 0
+    for c in name:
+        h = ((h << 4) + ord(c)) & 0xFFFFFFFF
+        g = h & 0xF0000000
+        if g:
+            h ^= g >> 24
+        h &= (~g) & 0xFFFFFFFF
+    return h
+
+
+def patch_file(path: str) -> bool:
+    with open(path, 'rb') as f:
+        data = bytearray(f.read())
+
+    old_ver = b'GLIBCXX_3.4.30'
+    new_ver = b'GLIBCXX_3.4.11'
+
+    if old_ver not in data:
+        print(f'  skip (no GLIBCXX_3.4.30): {path}')
+        return False
+
+    # ----- ELF header -----
+    if data[:4] != b'\x7fELF':
+        print(f'  skip (not ELF): {path}')
+        return False
+
+    ei_class = data[4]  # 1=32-bit, 2=64-bit
+    ei_data  = data[5]  # 1=LE, 2=BE
+    endian   = '<' if ei_data == 1 else '>'
+
+    if ei_class == 2:
+        # 64-bit ELF
+        e_shoff_fmt = f'{endian}Q'
+        ehdr_size   = 64
+        shdr_size   = 64
+        shdr_fmt    = f'{endian}IIQQQQIIQQ'  # 64-byte shdr
+        (e_shoff,)  = struct.unpack_from(f'{endian}Q', data, 40)
+        (e_shentsize, e_shnum, e_shstrndx) = struct.unpack_from(f'{endian}HHH', data, 58)
+        shdr_type_off = 4
+        shdr_off_off  = 24   # sh_offset within shdr
+        shdr_link_off = 48   # sh_link within shdr
+    else:
+        # 32-bit ELF
+        (e_shoff,)  = struct.unpack_from(f'{endian}I', data, 32)
+        (e_shentsize, e_shnum, e_shstrndx) = struct.unpack_from(f'{endian}HHH', data, 46)
+        shdr_type_off = 4
+        shdr_off_off  = 16
+        shdr_link_off = 28
+
+    SHT_GNU_verneed = 0x6FFFFFFE
+
+    patched = False
+    # Target GLIBCXX_3.4.11 — that's where condition_variable::wait actually lives
+    # in AlmaLinux 9's libstdc++.so.6 (same byte length: 14 chars each)
+    old_hash = elf_hash('GLIBCXX_3.4.30')
+    new_hash = elf_hash('GLIBCXX_3.4.11')
+    old_hash_bytes = struct.pack(f'{endian}I', old_hash)
+    new_hash_bytes = struct.pack(f'{endian}I', new_hash)
+
+    for i in range(e_shnum):
+        shdr_base = e_shoff + i * e_shentsize
+        sh_type   = struct.unpack_from(f'{endian}I', data, shdr_base + shdr_type_off)[0]
+
+        if sh_type != SHT_GNU_verneed:
+            continue
+
+        # sh_offset and sh_link (index of associated string table section)
+        if ei_class == 2:
+            sh_offset = struct.unpack_from(f'{endian}Q', data, shdr_base + 24)[0]
+            sh_size   = struct.unpack_from(f'{endian}Q', data, shdr_base + 32)[0]
+            sh_link   = struct.unpack_from(f'{endian}I', data, shdr_base + 40)[0]
+            sh_info   = struct.unpack_from(f'{endian}I', data, shdr_base + 44)[0]
+        else:
+            sh_offset = struct.unpack_from(f'{endian}I', data, shdr_base + 16)[0]
+            sh_size   = struct.unpack_from(f'{endian}I', data, shdr_base + 20)[0]
+            sh_link   = struct.unpack_from(f'{endian}I', data, shdr_base + 24)[0]
+            sh_info   = struct.unpack_from(f'{endian}I', data, shdr_base + 28)[0]
+
+        # String table section referenced by sh_link
+        strtab_shdr = e_shoff + sh_link * e_shentsize
+        if ei_class == 2:
+            strtab_off = struct.unpack_from(f'{endian}Q', data, strtab_shdr + 24)[0]
+        else:
+            strtab_off = struct.unpack_from(f'{endian}I', data, strtab_shdr + 16)[0]
+
+        # Walk Elf64_Verneed / Elf64_Vernaux entries
+        # Elf64_Verneed: vn_version(2)+vn_cnt(2)+vn_file(4)+vn_aux(4)+vn_next(4) = 16 bytes
+        # Elf64_Vernaux: vna_hash(4)+vna_flags(2)+vna_other(2)+vna_name(4)+vna_next(4) = 16 bytes
+        vneed_pos = sh_offset
+        for _ in range(sh_info):  # sh_info = number of Verneed entries
+            vn_cnt  = struct.unpack_from(f'{endian}H', data, vneed_pos + 2)[0]
+            vn_aux  = struct.unpack_from(f'{endian}I', data, vneed_pos + 8)[0]   # +8 (after vn_file)
+            vn_next = struct.unpack_from(f'{endian}I', data, vneed_pos + 12)[0]
+
+            vaux_pos = vneed_pos + vn_aux
+            for _ in range(vn_cnt):
+                vna_hash  = struct.unpack_from(f'{endian}I', data, vaux_pos)[0]
+                vna_name  = struct.unpack_from(f'{endian}I', data, vaux_pos + 8)[0]
+                vna_next  = struct.unpack_from(f'{endian}I', data, vaux_pos + 12)[0]
+
+                # Read the version name from the string table
+                name_off  = strtab_off + vna_name
+                name_end  = data.index(b'\x00', name_off)
+                ver_name  = bytes(data[name_off:name_end])
+
+                if ver_name == old_ver:
+                    # Patch hash
+                    struct.pack_into(f'{endian}I', data, vaux_pos, new_hash)
+                    # Patch string (same byte length — safe in-place)
+                    data[name_off:name_off + len(old_ver)] = new_ver
+                    patched = True
+
+                if vna_next == 0:
+                    break
+                vaux_pos += vna_next
+
+            if vn_next == 0:
+                break
+            vneed_pos += vn_next
+
+    if patched:
+        with open(path, 'wb') as f:
+            f.write(data)
+        print(f'  patched (hash+string): {path}')
+        return True
+    else:
+        print(f'  skip (GLIBCXX_3.4.30 not in verneed): {path}')
+        return False
+
+
+if __name__ == '__main__':
+    for path in sys.argv[1:]:
+        patch_file(path)

ansible/roles/lm_studio/files/run-llmster.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+# LM Studio service wrapper.
+#
+# Lets lms server start handle daemon launch (passkey setup, etc.),
+# optionally auto-loads a model (LMS_MODEL + LMS_CONTEXT_LENGTH),
+# then monitors the llmster process and exits when it dies so systemd
+# can restart the service.
+set -e
+
+LMS="${HOME}/.lmstudio/bin/lms"
+LMS_PORT="${LMS_PORT:-1234}"
+LMS_BIND="${LMS_BIND:-0.0.0.0}"
+LMS_MODEL="${LMS_MODEL:-}"
+LMS_CONTEXT_LENGTH="${LMS_CONTEXT_LENGTH:-65536}"
+LMS_GPU_OFFLOAD="${LMS_GPU_OFFLOAD:-max}"
+
+echo "Starting LM Studio server (port ${LMS_PORT}, bind ${LMS_BIND})..."
+"$LMS" server start --port "$LMS_PORT" --bind "$LMS_BIND"
+
+if [[ -n "$LMS_MODEL" ]]; then
+    echo "Unloading any previously loaded models..."
+    "$LMS" unload --all 2>/dev/null || true
+    echo "Auto-loading model ${LMS_MODEL} (context ${LMS_CONTEXT_LENGTH}, gpu ${LMS_GPU_OFFLOAD})..."
+    "$LMS" load "$LMS_MODEL" --context-length "$LMS_CONTEXT_LENGTH" --gpu "$LMS_GPU_OFFLOAD"
+fi
+
+# llmster bind sur 127.0.0.1 après chargement du backend Vulkan.
+# socat proxy sur l'IP LAN (non-conflictuel avec le loopback) → llmster.
+if [[ "$LMS_BIND" != "127.0.0.1" ]]; then
+    LAN_IP=$(ip -4 addr show scope global | grep -oP '(?<=inet\s)\d+(\.\d+){3}' | head -1)
+    if [[ -n "$LAN_IP" ]]; then
+        echo "Starting socat proxy ${LAN_IP}:${LMS_PORT} → 127.0.0.1:${LMS_PORT}..."
+        socat TCP-LISTEN:"${LMS_PORT}",fork,bind="${LAN_IP}",reuseaddr TCP:127.0.0.1:"${LMS_PORT}" &
+        SOCAT_PID=$!
+        echo "socat PID: ${SOCAT_PID}"
+    fi
+fi
+
+echo "Server started. Monitoring llmster daemon..."
+while pgrep -u "$(id -un)" -x llmster > /dev/null 2>&1; do
+    sleep 15
+done
+
+echo "llmster daemon stopped unexpectedly, exiting..."
+exit 1