Routing pool starved of slots by ThreadPool contention during a 3-minute burst on portal pods #5226

2026-09-22 10:56:03Z memex-portal-deployment-5bb495d47b-jntbn crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [bc4ebfb4#5 started 2026-09-22T10:56:03.8268997Z]: 64 route dispatches in flight (reporting threshold 64); ordered channels queued 14 over 1 stream destination(s), deepest per-channel queue 1, routing pool subscribing 0, waiting for a pool slot 58; oldest leg in flight 4 ms — dispatch → baisakhi.das/_Install/Mail (delivery iRXCHTAUAEaV0lU6GXYt6A). Latest dispatch target cache/-dk5L69WpUeM0KjZtV-P7Q — 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 i…[truncated]
2026-09-22 10:56:08Z memex-portal-deployment-58f7cdffc5-d5tld crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [eabb02b3#2 started 2026-09-22T10:56:08.7809483Z]: 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 0; oldest leg in flight 2482 ms — dispatch → ClientFReporting/Fund (delivery hG_thswS3kKhEUT1ai1NXQ). Latest dispatch target RemoteControl/Screen — 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-flight count i…[truncated]
2026-09-22 10:56:08Z memex-portal-deployment-5bb495d47b-jntbn crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [bc4ebfb4#6 started 2026-09-22T10:56:08.8463795Z]: 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 3 ms — dispatch → ThreeBody/_Access/baisakhi.das_Access (delivery gahFiBcDL0m9lQFXHnwmYg). Latest dispatch target christoph.hofstetter/_Install/Collaboration — 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 TH…[truncated]
2026-09-22 10:56:08Z memex-portal-deployment-5bb495d47b-jntbn crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [bc4ebfb4#7 started 2026-09-22T10:56:08.8652245Z]: 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 1, waiting for a pool slot 62; oldest leg in flight 4 ms — dispatch → OpenStreetMap/_Entitlements/amit.kumar (delivery FpBkrIU7HEySZ9_rwuqvyg). Latest dispatch target AppleMaps/_Entitlements/thomas.pepin — 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 CROS…[truncated]
2026-09-22 10:56:13Z memex-portal-deployment-58f7cdffc5-d8zph crit: MeshWeaver.Hosting.Orleans.RoutingGrain[0]
      [ROUTE] Routing back-pressure [c6ae8f43#2 started 2026-09-22T10:56:13.4457107Z]: 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 1, waiting for a pool slot 0; oldest leg in flight 388 ms — dispatch → BusinessRules/Scope (delivery tQuD4PtpzEijqPFAT6zRJg). Latest dispatch target AppleWeather/Weather/_Activity/compile-state — 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 l…[truncated]