mirror of
https://github.com/torlando-tech/pyxis.git
synced 2026-09-27 01:48:00 +00:00
Torlando
32a09938d8
Three findings on the transient-stall bail, all valid: - Reload invalidation: a bail recorded BYPASS, but NomadNetCacheFlow::service() accepts only MISS as a successful invalidation, so a bail during an admitted reload reported 'Page cache invalidation failed' instead of falling through to a live fetch. The bail now records MISS. - Open-resource leak: the bail cleared read_open_/write_open_ (and abandoned an open directory enumeration) without calling endRead()/abortWrite()/endList(), leaking SD handles. The bail now releases each in-flight resource via the seam's own teardown (bounded best-effort; a still-transient close is accepted rather than re-pinning the op). - Tick-vs-time: the not-ready UNAVAILABLE path returns immediately (no bus wait), so a pure 500-tick budget could expire during a legitimate SD mount window and disable caching for the whole session. The bail is now gated on BOTH the tick floor AND a 10s wall-time window (service() takes a monotonic ms clock; production passes millis(), 0 is a safe default for tests). Regression tests: reload-invalidation bail -> NEED_LIVE (flow), flat-clock does not bail, healable transient keeps authority, list-open (RECOVERY_END) stall bails and releases the handle (cache).
66 lines
7.4 KiB
C++
66 lines
7.4 KiB
C++
#include <iostream>
|
|
#include <map>
|
|
#include <vector>
|
|
#include <cstring>
|
|
#include "NomadNetCache.h"
|
|
#include "NomadNetCacheFlow.h"
|
|
using namespace UI::LXMF::NomadNet;
|
|
struct Mem:NomadNetStorage{std::map<std::string,std::vector<uint8_t>>f;std::string a;size_t p=0;bool w=false;bool list_busy=false;bool isAvailable()const override{return true;}StorageResult beginRead(const char*n,uint32_t&s)override{auto i=f.find(n);if(i==f.end())return StorageResult::MISS;a=n;p=0;s=i->second.size();return StorageResult::OK;}StorageResult readChunk(uint8_t*o,size_t c,size_t&n)override{auto&v=f[a];n=std::min(c,v.size()-p);memcpy(o,v.data()+p,n);p+=n;return StorageResult::OK;}StorageResult endRead()override{return StorageResult::OK;}StorageResult beginWrite(const char*n)override{a=n;f[a].clear();w=true;return StorageResult::OK;}StorageResult writeChunk(const uint8_t*d,size_t z,size_t&n)override{n=z;f[a].insert(f[a].end(),d,d+z);return StorageResult::OK;}StorageResult commitWrite()override{w=false;return StorageResult::OK;}StorageResult abortWrite()override{w=false;return StorageResult::OK;}StorageResult remove(const char*n)override{return f.erase(n)?StorageResult::OK:StorageResult::MISS;}StorageResult rename(const char*x,const char*y)override{auto i=f.find(x);if(i==f.end())return StorageResult::MISS;f[y]=i->second;f.erase(i);return StorageResult::OK;}StorageResult stat(const char*,uint32_t&)override{return StorageResult::MISS;}StorageResult beginList(const char*)override{return list_busy?StorageResult::BUSY:StorageResult::OK;}StorageResult nextList(char*,size_t,bool&d)override{d=true;return StorageResult::OK;}StorageResult endList()override{return StorageResult::OK;}};
|
|
int main(){int f=0;auto ck=[&](bool x,const char*n){if(!x){f++;std::cerr<<"FAIL "<<n<<"\n";}};Mem s;NomadNetCache c(s);NomadNetCacheFlow flow(c);CacheKey k{"0123456789abcdef0123456789abcdef","/page/index.mu",RequestDataClass::NIL};
|
|
ck(flow.begin(k,100,false)==CacheFlowState::LOOKUP,"lookup first");for(int i=0;i<10&&flow.state()==CacheFlowState::LOOKUP;i++)flow.service();ck(flow.state()==CacheFlowState::NEED_LIVE,"miss needs live");std::vector<uint8_t>b={'o','k'};CacheEligibility e{true,true,false,false,false,false,RequestDataClass::NIL};ck(flow.acceptLive(b,e,100),"valid live accepted");ck(flow.pageReady()&&flow.status()=="Page loaded (live)","render ready before commit");for(int i=0;i<20;i++)flow.service();
|
|
NomadNetCacheFlow hit(c);ck(hit.begin(k,101,false)==CacheFlowState::LOOKUP,"second lookup");for(int i=0;i<10&&hit.state()==CacheFlowState::LOOKUP;i++)hit.service();ExternalVector<uint8_t>out;ck(hit.state()==CacheFlowState::READY&&hit.takePage(out)&&std::equal(out.begin(),out.end(),b.begin(),b.end())&&hit.status()=="Cached page; current reachability not checked","hit without peer and without internal-vector copy");
|
|
// A new lookup arriving while unrelated cache work is active must wait for
|
|
// cancellation cleanup, admit its own lookup, and still use the available hit.
|
|
CacheKey other{"fedcba9876543210fedcba9876543210","/page/other.mu",RequestDataClass::NIL};
|
|
ck(c.beginCommit(other,b,101,43200)==CacheResult::PENDING,"overlap commit admitted");
|
|
NomadNetCacheFlow overlap(c);ck(overlap.begin(k,102,false)==CacheFlowState::LOOKUP,"overlap lookup waits");
|
|
for(int i=0;i<200&&overlap.state()==CacheFlowState::LOOKUP;++i)overlap.service();
|
|
ExternalVector<uint8_t>overlap_out;
|
|
ck(overlap.state()==CacheFlowState::READY&&overlap.takePage(overlap_out)&&std::equal(overlap_out.begin(),overlap_out.end(),b.begin(),b.end()),"busy cache retries requested lookup and preserves hit");
|
|
NomadNetCacheFlow fields(c);k.request_data=RequestDataClass::FIELDS;fields.begin(k,101,false);fields.service();ck(fields.state()==CacheFlowState::NEED_LIVE,"request data bypass");
|
|
k.request_data=RequestDataClass::NIL;NomadNetCacheFlow reload(c);reload.begin(k,101,true);while(reload.state()==CacheFlowState::INVALIDATE)reload.service();ck(reload.state()==CacheFlowState::NEED_LIVE,"reload bypass invalidates without history-side effects");
|
|
NomadNetCacheFlow malformed(c);malformed.begin(k,101,false);while(malformed.state()==CacheFlowState::LOOKUP)malformed.service();CacheEligibility bad{true,false,false,true,false,false,RequestDataClass::NIL};ck(!malformed.acceptLive(b,bad,101)&&malformed.state()==CacheFlowState::FAILED,"malformed not committed");
|
|
NomadNetCacheFlow cancelled(c);cancelled.begin(k,101,false);cancelled.cancel();cancelled.service();ck(cancelled.state()==CacheFlowState::CANCELLED&&!cancelled.pageReady(),"navigation cancels lookup");
|
|
// Reload during startup recovery remains in explicit invalidation until the old generation is physically gone.
|
|
NomadNetCache recovering(s);NomadNetCacheFlow recovering_reload(recovering);k.request_data=RequestDataClass::NIL;
|
|
ck(recovering_reload.begin(k,102,true)==CacheFlowState::INVALIDATE,"reload during recovery waits for invalidation admission");
|
|
for(int i=0;i<200&&recovering_reload.state()==CacheFlowState::INVALIDATE;++i)recovering_reload.service();
|
|
ck(recovering_reload.state()==CacheFlowState::NEED_LIVE,"reload starts exactly one live fetch only after terminal invalidation");
|
|
ck(recovering.beginLookup(k,102)==CacheResult::PENDING,"post reload invalidation lookup");for(int i=0;i<50&&recovering.busy();++i)recovering.service();
|
|
ck(recovering.lastResult()!=CacheResult::HIT,"reload during recovery removed stale generation");
|
|
// The device symptom: boot-time recovery pinned by a permanently BUSY SD
|
|
// seam (SPI mutex starved). Before the fix the flow sat in LOOKUP forever
|
|
// and the UI froze at "Checking SD page cache..."; now the stall budget
|
|
// expires and the flow falls through to a live fetch.
|
|
{
|
|
Mem hang;hang.list_busy=true;NomadNetCache hc(hang);NomadNetCacheFlow hf(hc);
|
|
CacheKey hk{"fedcba9876543210fedcba9876543210","/page/hang.mu",RequestDataClass::NIL};
|
|
ck(hf.begin(hk,1000,false)==CacheFlowState::LOOKUP,"hang lookup admitted");
|
|
uint64_t hclock=0;int serviced=0;
|
|
while(hf.state()==CacheFlowState::LOOKUP&&serviced<200000){hf.service(++hclock);++serviced;}
|
|
ck(hf.state()==CacheFlowState::NEED_LIVE,"pinned recovery no longer freezes the lookup");
|
|
ck(serviced<200000,"lookup reached live in bounded service ticks");
|
|
ck(hc.recoveryComplete()==false,"bailed recovery is not authoritative");
|
|
// F3: a flat (non-advancing) clock must NOT bail — the wall-time window has to
|
|
// elapse, so 500 fast no-progress ticks alone keep the cache (session) alive.
|
|
{
|
|
Mem hangf;hangf.list_busy=true;NomadNetCache hcf(hangf);NomadNetCacheFlow hff(hcf);
|
|
CacheKey hkf{"fedcba9876543210fedcba9876543210","/page/hangf.mu",RequestDataClass::NIL};
|
|
hff.begin(hkf,1000,false);
|
|
uint64_t flat=0;for(int i=0;i<600&&hff.state()==CacheFlowState::LOOKUP;++i){hff.service(flat);++flat;}
|
|
ck(hff.state()==CacheFlowState::LOOKUP,"flat clock keeps a fast-ticking cache from bailing");
|
|
}
|
|
// F1: a bail during an admitted RELOAD invalidation must fall through to a
|
|
// live fetch (NEED_LIVE), not report a hard "Page cache invalidation failed".
|
|
{
|
|
Mem hangr;hangr.list_busy=true;NomadNetCache hcr(hangr);NomadNetCacheFlow hfr(hcr);
|
|
CacheKey hkr{"fedcba9876543210fedcba9876543210","/page/hangr.mu",RequestDataClass::NIL};
|
|
hfr.begin(hkr,1000,true);
|
|
uint64_t rclock=0;int svc=0;
|
|
while((hfr.state()==CacheFlowState::INVALIDATE)&&svc<200000){hfr.service(++rclock);++svc;}
|
|
ck(hfr.state()==CacheFlowState::NEED_LIVE,"reload invalidation bail falls through to live");
|
|
ck(hfr.state()!=CacheFlowState::FAILED,"reload invalidation bail is not a hard failure");
|
|
}
|
|
}
|
|
std::cout<<(f?"failed":"passed")<<"\n";return f?1:0;}
|