+1 -1

build.zig.zon

reviewed

··· 1 1 .{ 2 2 .name = .zat, 3 3 - .version = "0.3.0-alpha.19", 3 3 + .version = "0.3.0-alpha.20", 4 4 .fingerprint = 0x8da9db57ee82fbe4, 5 5 .minimum_zig_version = "0.16.0", 6 6 .dependencies = .{

+3 -3

devlog/008-the-io-migration.md

reviewed

··· 222 222 223 223 the logs showed nothing unusual. chain breaks (expected after restarts when cursor positions are stale), normal reconnection cycles, then sudden death. 13 restarts in 12 hours. 224 224 225 225 - we had a separate observation that was shaping our thinking: a minimal repro ([`repro_evented.zig`](https://tangled.org/zzstoatzz.io/zlay/tree/main/scripts/repro_evented.zig)) that spawns a single fiber and returns GPFs immediately under ReleaseSafe. the crash lands in `fiber.zig:contextSwitch` → `Uring.zig:mainIdle`. so we had a confirmed fiber context-switch bug under one build mode, and a mystery SIGSEGV under another. the natural conclusion: same bug, different manifestation. ReleaseFast just hides it longer because the optimizer arranges code differently. 225 225 + we had a separate observation that was shaping our thinking: a minimal repro ([`repro_evented.zig`](https://tangled.org/zzstoatzz.io/zlay/blob/main/scripts/repro_evented.zig)) that spawns a single fiber and returns GPFs immediately under ReleaseSafe. the crash lands in `fiber.zig:contextSwitch` → `Uring.zig:mainIdle`. so we had a confirmed fiber context-switch bug under one build mode, and a mystery SIGSEGV under another. the natural conclusion: same bug, different manifestation. ReleaseFast just hides it longer because the optimizer arranges code differently. 226 226 227 227 we spent time investigating the fiber machinery, reading disassembly of the context switch, checking for upstream fixes (fiber.zig was unchanged across 32 dev builds). we considered patching the context switch ourselves. we checked upstream Uring networking implementation status — still fully stubbed. we read the zig team's position on Evented — "experimental," "important followup work to be done." 228 228 ··· 269 269 270 270 under ReleaseFast, there's a `lea` that loads the SwitchMessage stack address into `%rsi` before the asm. under ReleaseSafe, that `lea` appears to be missing — `%rsi` holds a stale value from a prior function call. the ReleaseSafe prologue adds stack probing (`__zig_probe_stack`) and a canary (`fs:0x28`), which change the code layout surrounding the inline asm. we think this is why the register allocation differs, but we're not certain — there may be something else going on. 271 271 272 272 - we've written this up as a [bug report](https://tangled.org/zzstoatzz.io/zlay/tree/main/scripts/fiber_gpf_issue.md) with a standalone reproduction. 272 272 + we've written this up as a [bug report](https://tangled.org/zzstoatzz.io/zlay/blob/main/scripts/fiber_gpf_issue.md) with a standalone reproduction. 273 273 274 274 this is a real problem for the ecosystem. ReleaseSafe is the mode designed for production services that want optimization with safety checks. TigerBeetle uses it. the zig compiler's own nightlies recently switched to it. Ghostty and Bun use ReleaseFast, but both have noted they'd prefer ReleaseSafe if the performance cost were lower. for `Io.Evented` to be a viable production backend, it needs to work with ReleaseSafe. 275 275 ··· 287 287 288 288 the thing that found it was switching to ReleaseSafe. not to fix the crash — we'd already reverted to Threaded for that — but because reverting happened to re-enable the build mode that had the safety checks. the bounds check caught the real bug on the first handshake that split on `\r\n`. 289 289 290 290 - there are two bugs here and they're both real. the websocket off-by-one was the production crash. the ReleaseSafe GPF is a separate issue that blocks Evented from running with safety checks. we'd consider [filing the latter upstream](https://tangled.org/zzstoatzz.io/zlay/tree/main/scripts/fiber_gpf_issue.md). in the meantime, ReleaseFast works, and we know what to look for when it doesn't. 290 290 + there are two bugs here and they're both real. the websocket off-by-one was the production crash. the ReleaseSafe GPF is a separate issue that blocks Evented from running with safety checks. we'd consider [filing the latter upstream](https://tangled.org/zzstoatzz.io/zlay/blob/main/scripts/fiber_gpf_issue.md). in the meantime, ReleaseFast works, and we know what to look for when it doesn't. 291 291 292 292 zat is v0.3.0-alpha. the Io parameter is the only breaking change.