Revert "perf(pools): size image/rayon pools to the CFS quota"

This reverts the image-pool migration (commit 5629ba6). The bench
(bench_pool_concurrency / POOL-CONCURRENCY.md) measured the one pool it could
isolate — the thumbnail decode semaphore — and found flat throughput, p99 AND
peak RSS (137 MiB) from K=1..16: shrink-on-load already makes each decode
RAM-cheap, so sizing it to the CFS quota gains nothing measurable. Adding code
without a measured benefit isn't worth it.

Kept: the effective_parallelism() helper (it has a *measured* win in the Tokio
runtime — benches/RUNTIME.md) and the benchmark itself (reusable). The ffmpeg
video fan-out has a plausible a-priori case (one OS process per permit) but is
left as a future, deliberately-measured change rather than shipped on
speculation. Doc updated to record the decision.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez

benches/POOL-CONCURRENCY.md

@@ -56,15 +56,19 @@ taskset -c 0,1 ./target/release/examples/bench_pool_concurrency   # model a 2-co
    every core". The flat RSS is exactly that: each concurrent decode's transient
    buffer is small, so 16 in flight cost the same resident memory as 1.
 
-3. **So the pool migration is a correctness/consistency change, not a perf win.**
+3. **Decision: NOT migrated (reverted).** Because the only pool this bench could
-   It is still worth keeping: it has **no downside** (off-quota `effective ==
+   isolate showed zero measured benefit, the `effective_parallelism()` migration
-   available`, so no change), it unifies pool sizing with the runtime fix behind
+   of the image pools was reverted — adding code without a measured win isn't
-   one `effective_parallelism()` helper, and it protects the pools this bench did
+   worth it. The `effective_parallelism()` helper stays (it has a *measured*
-   *not* isolate — the transcode rayon pool (thread stacks) and the ffmpeg video
+   benefit in the Tokio runtime — see `RUNTIME`), so a future, deliberately
-   fan-out (one OS process per permit), where over-spawning per *host* core under
+   measured case can adopt it per-pool.
-   a tight quota is genuinely wasteful. But operators should not expect a
+   The one pool with a plausible a-priori argument is the **ffmpeg video
-   throughput jump from it; the real download/runtime wins are in `BLOB-PREFETCH`
+   fan-out** (one heavyweight OS process per permit — 32 ffmpeg processes for a
-   and `RUNTIME`.
+   2-core budget on a many-core host is self-evidently wasteful). That was left
+   on `available_parallelism()` too, to revisit *with* a measurement if a
+   high-host-core / low-quota deployment running video thumbnails ever warrants
+   it. The transcode rayon pool over-sizing only costs parked thread stacks
+   (negligible).
 
 4. **Honest caveat on scale.** This was run at a 2-core quota on a 4-core host
    (K_oversub = 8 ≈ 4×). On a 64-core host under a 2-core quota the host-count

src/common/di.rs

@@ -363,9 +363,9 @@ impl AppServiceFactory {
             if self.config.features.enable_video_thumbnails
                 && FfmpegVideoFrameService::is_available(&ffmpeg_path)
             {
-                // effective_parallelism respects the CFS quota (--cpus), not
+                let cpus = std::thread::available_parallelism()
-                // just affinity — so ffmpeg fan-out matches the real core budget.
+                    .map(|n| n.get())
-                let cpus = crate::common::runtime::effective_parallelism();
+                    .unwrap_or(4);
                 let concurrency = std::env::var("OXICLOUD_VIDEO_THUMBNAIL_CONCURRENCY")
                     .ok()
                     .and_then(|v| v.parse::<usize>().ok())

src/infrastructure/services/image_transcode_service.rs

@@ -31,14 +31,13 @@ pub const MAX_TRANSCODE_SIZE: u64 = 5 * 1024 * 1024;
 /// Minimum number of threads in the dedicated transcoding pool
 const MIN_TRANSCODE_THREADS: usize = 2;
 
-/// Compute the number of transcoding threads: half the available CPUs, with a
+/// Compute the number of transcoding threads: half the available CPUs,
-/// floor of `MIN_TRANSCODE_THREADS`. Sized by
+/// with a floor of `MIN_TRANSCODE_THREADS`.  `available_parallelism()`
-/// [`effective_parallelism`](crate::common::runtime::effective_parallelism),
+/// respects cgroup limits (Docker/K8s) and CPU affinity masks.
-/// which respects CPU affinity **and** the CFS quota (Docker/K8s `--cpus`) —
-/// unlike bare `available_parallelism()`, which ignores the quota and would
-/// over-size this CPU-bound pool under a container limit.
 fn transcode_thread_count() -> usize {
-    let cpus = crate::common::runtime::effective_parallelism();
+    let cpus = std::thread::available_parallelism()
+        .map(|n| n.get())
+        .unwrap_or(MIN_TRANSCODE_THREADS);
     (cpus / 2).max(MIN_TRANSCODE_THREADS)
 }
 

src/infrastructure/services/thumbnail_service.rs

@@ -107,11 +107,8 @@ const STREAM_TO_TEMP_TIMEOUT: Duration = Duration::from_secs(120);
 /// concurrency was halved to keep peak RAM in check. Decodes are now DCT-shrunk
 /// to the thumbnail size (~18–25 MB regardless of source resolution), so the RAM
 /// ceiling no longer forces throttling and we can saturate every core. Override
-/// with `OXICLOUD_THUMBNAIL_DECODE_CONCURRENCY`. Sized by
+/// with `OXICLOUD_THUMBNAIL_DECODE_CONCURRENCY`. `available_parallelism()`
-/// [`effective_parallelism`](crate::common::runtime::effective_parallelism),
+/// respects cgroup limits (Docker/K8s) and CPU affinity masks.
-/// which respects CPU affinity **and** the CFS quota (`--cpus`) — so under a
-/// container quota we don't over-permit concurrent CPU-heavy decodes onto cores
-/// the scheduler can't give us.
 fn max_concurrent_decodes() -> usize {
     if let Some(n) = std::env::var(DECODE_CONCURRENCY_ENV)
         .ok()
@@ -120,7 +117,10 @@ fn max_concurrent_decodes() -> usize {
     {
         return n;
     }
-    crate::common::runtime::effective_parallelism().max(2)
+    let cpus = std::thread::available_parallelism()
+        .map(|n| n.get())
+        .unwrap_or(4);
+    cpus.max(2)
 }
 
 /// Thumbnail service for generating and caching image thumbnails