Portal silo thread starvation backs up routing dispatch legs (60+ waiting for a pool slot before their subscribe) #5366

2026-09-22 15:59:28Z memex-portal-deployment-86dbb4d55c-gcrcd crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [c911059d#6 started 2026-09-22T15:59:28.4181589Z]: 64 route dispatches in flight (reporting threshold 64); ordered channels queued 0 over 0 stream destination(s), deepest per-channel queue 0, routing pool subscribing 0, waiting for a pool slot 62; oldest leg in flight 24 ms — dispatch → MeshWeaverInstance/36d61c0097aa (delivery gqHP_lBv3ka6d3gaf0MSww). Latest dispatch target nerijus.vasiliauskas/_Install/EntityViews — the address that happened to cross the threshold, NOT a diagnosis. A slot is held from dispatch until the leg terminates, INCLUDING the unbounded wait for a ThreadPool thread before the leg's own timeouts start, so a CPU-starved silo raises this with nothing stuck. A CHANNEL is (destination, stream), so a deepest queue of 1 or more means legs of the SAME stream are blocked behind one another (head-of-line within one channel); 0 means nothing is waiting on anything, so read it as load. Many channels over FEW destinations is a multiplexer hub draining in parallel, which is load too — before issue #5009 those legs shared one channel and read as head-of-line. 🚨 THE TWO POOL GAUGES ANSWER DIFFERENT QUESTIONS AND ONLY ONE SEES THE WAIT NAMED ABOVE — issue #5018. 'subscribing' counts legs inside their SUBSCRIBE PROLOGUE only, so a leg still waiting for a ThreadPool thread and a leg already past its subscribe BOTH read 0 there; 'waiting for a pool slot' is the gauge that sees the pre-subscribe wait. High while subscribing is below the pool's cap is a THREAD shortage; both near zero means the legs are past their subscribe and the wait is downstream I/O. 🚨 READ THE OLDEST LEG FIRST: it is the only load-vs-leak discriminator available from a SINGLE line — every leg young is load the silo is absorbing, one leg minutes old is a slot that never came back and the label names it — whereas the episode stamp below needs a SECOND line to say anything. 🚨 Deepest is sampled AT THE CROSS…[truncated]
2026-09-22 15:59:28Z memex-portal-deployment-86dbb4d55c-gcrcd crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [c911059d#7 started 2026-09-22T15:59:28.4359709Z]: 64 route dispatches in flight (reporting threshold 64); ordered channels queued 0 over 0 stream destination(s), deepest per-channel queue 0, routing pool subscribing 0, waiting for a pool slot 62; oldest leg in flight 42 ms — dispatch → MeshWeaverInstance/36d61c0097aa (delivery gqHP_lBv3ka6d3gaf0MSww). Latest dispatch target Indexing/_Policy — the address that happened to cross the threshold, NOT a diagnosis. A slot is held from dispatch until the leg terminates, INCLUDING the unbounded wait for a ThreadPool thread before the leg's own timeouts start, so a CPU-starved silo raises this with nothing stuck. A CHANNEL is (destination, stream), so a deepest queue of 1 or more means legs of the SAME stream are blocked behind one another (head-of-line within one channel); 0 means nothing is waiting on anything, so read it as load. Many channels over FEW destinations is a multiplexer hub draining in parallel, which is load too — before issue #5009 those legs shared one channel and read as head-of-line. 🚨 THE TWO POOL GAUGES ANSWER DIFFERENT QUESTIONS AND ONLY ONE SEES THE WAIT NAMED ABOVE — issue #5018. 'subscribing' counts legs inside their SUBSCRIBE PROLOGUE only, so a leg still waiting for a ThreadPool thread and a leg already past its subscribe BOTH read 0 there; 'waiting for a pool slot' is the gauge that sees the pre-subscribe wait. High while subscribing is below the pool's cap is a THREAD shortage; both near zero means the legs are past their subscribe and the wait is downstream I/O. 🚨 READ THE OLDEST LEG FIRST: it is the only load-vs-leak discriminator available from a SINGLE line — every leg young is load the silo is absorbing, one leg minutes old is a slot that never came back and the label names it — whereas the episode stamp below needs a SECOND line to say anything. 🚨 Deepest is sampled AT THE CROSSING, so like the in-fligh…[truncated]
2026-09-22 15:59:31Z memex-portal-deployment-86dbb4d55c-gcrcd crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [c911059d#8 started 2026-09-22T15:59:31.6083662Z]: 64 route dispatches in flight (reporting threshold 64); ordered channels queued 0 over 0 stream destination(s), deepest per-channel queue 0, routing pool subscribing 0, waiting for a pool slot 61; oldest leg in flight 3 ms — dispatch → Training/_Entitlements/thomas.pepin (delivery AEwXYakJk02bTjcC3pkxng). Latest dispatch target lucas.mebold/_Install/OgCard — the address that happened to cross the threshold, NOT a diagnosis. A slot is held from dispatch until the leg terminates, INCLUDING the unbounded wait for a ThreadPool thread before the leg's own timeouts start, so a CPU-starved silo raises this with nothing stuck. A CHANNEL is (destination, stream), so a deepest queue of 1 or more means legs of the SAME stream are blocked behind one another (head-of-line within one channel); 0 means nothing is waiting on anything, so read it as load. Many channels over FEW destinations is a multiplexer hub draining in parallel, which is load too — before issue #5009 those legs shared one channel and read as head-of-line. 🚨 THE TWO POOL GAUGES ANSWER DIFFERENT QUESTIONS AND ONLY ONE SEES THE WAIT NAMED ABOVE — issue #5018. 'subscribing' counts legs inside their SUBSCRIBE PROLOGUE only, so a leg still waiting for a ThreadPool thread and a leg already past its subscribe BOTH read 0 there; 'waiting for a pool slot' is the gauge that sees the pre-subscribe wait. High while subscribing is below the pool's cap is a THREAD shortage; both near zero means the legs are past their subscribe and the wait is downstream I/O. 🚨 READ THE OLDEST LEG FIRST: it is the only load-vs-leak discriminator available from a SINGLE line — every leg young is load the silo is absorbing, one leg minutes old is a slot that never came back and the label names it — whereas the episode stamp below needs a SECOND line to say anything. 🚨 Deepest is sampled AT THE CROSSING, so li…[truncated]
2026-09-22 15:59:38Z memex-portal-deployment-86dbb4d55c-gcrcd crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [4a24a311#1 started 2026-09-22T15:59:38.1064443Z]: 64 route dispatches in flight (reporting threshold 64); ordered channels queued 0 over 0 stream destination(s), deepest per-channel queue 0, routing pool subscribing 0, waiting for a pool slot 601; oldest leg in flight 6501 ms — dispatch → lucas.mebold/_Install/Publish (delivery QLGXV_H98UWIOiYwgVbioQ). Latest dispatch target roland.buergi/_Install/GraphViews — the address that happened to cross the threshold, NOT a diagnosis. A slot is held from dispatch until the leg terminates, INCLUDING the unbounded wait for a ThreadPool thread before the leg's own timeouts start, so a CPU-starved silo raises this with nothing stuck. A CHANNEL is (destination, stream), so a deepest queue of 1 or more means legs of the SAME stream are blocked behind one another (head-of-line within one channel); 0 means nothing is waiting on anything, so read it as load. Many channels over FEW destinations is a multiplexer hub draining in parallel, which is load too — before issue #5009 those legs shared one channel and read as head-of-line. 🚨 THE TWO POOL GAUGES ANSWER DIFFERENT QUESTIONS AND ONLY ONE SEES THE WAIT NAMED ABOVE — issue #5018. 'subscribing' counts legs inside their SUBSCRIBE PROLOGUE only, so a leg still waiting for a ThreadPool thread and a leg already past its subscribe BOTH read 0 there; 'waiting for a pool slot' is the gauge that sees the pre-subscribe wait. High while subscribing is below the pool's cap is a THREAD shortage; both near zero means the legs are past their subscribe and the wait is downstream I/O. 🚨 READ THE OLDEST LEG FIRST: it is the only load-vs-leak discriminator available from a SINGLE line — every leg young is load the silo is absorbing, one leg minutes old is a slot that never came back and the label names it — whereas the episode stamp below needs a SECOND line to say anything. 🚨 Deepest is sampled AT THE CROSSING, so…[truncated]
2026-09-22 15:59:41Z memex-portal-deployment-86dbb4d55c-gcrcd crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [4a24a311#2 started 2026-09-22T15:59:41.3383667Z]: 64 route dispatches in flight (reporting threshold 64); ordered channels queued 0 over 0 stream destination(s), deepest per-channel queue 0, routing pool subscribing 0, waiting for a pool slot 63; oldest leg in flight 9732 ms — dispatch → ICloud/_Issue/1785 (delivery uzklUCiVkkCpKjxbzblUcQ). Latest dispatch target jacky.enciso/_Install/GoogleMaps — the address that happened to cross the threshold, NOT a diagnosis. A slot is held from dispatch until the leg terminates, INCLUDING the unbounded wait for a ThreadPool thread before the leg's own timeouts start, so a CPU-starved silo raises this with nothing stuck. A CHANNEL is (destination, stream), so a deepest queue of 1 or more means legs of the SAME stream are blocked behind one another (head-of-line within one channel); 0 means nothing is waiting on anything, so read it as load. Many channels over FEW destinations is a multiplexer hub draining in parallel, which is load too — before issue #5009 those legs shared one channel and read as head-of-line. 🚨 THE TWO POOL GAUGES ANSWER DIFFERENT QUESTIONS AND ONLY ONE SEES THE WAIT NAMED ABOVE — issue #5018. 'subscribing' counts legs inside their SUBSCRIBE PROLOGUE only, so a leg still waiting for a ThreadPool thread and a leg already past its subscribe BOTH read 0 there; 'waiting for a pool slot' is the gauge that sees the pre-subscribe wait. High while subscribing is below the pool's cap is a THREAD shortage; both near zero means the legs are past their subscribe and the wait is downstream I/O. 🚨 READ THE OLDEST LEG FIRST: it is the only load-vs-leak discriminator available from a SINGLE line — every leg young is load the silo is absorbing, one leg minutes old is a slot that never came back and the label names it — whereas the episode stamp below needs a SECOND line to say anything. 🚨 Deepest is sampled AT THE CROSSING, so like the in-…[truncated]