# The binary that matches orders One name in a matching engine can be the simulator, a test, or a function production never compiles. Context is the production build. [Book a demo](https://byteask.cal.com/pratyush/book-a-demo) [See the evidence](https://byteask.ai/industries/trading-hft#evidence) ## The build gives the context ByteAsk Context indexes the functions and calls your compile commands select. The examples below show what was captured for this domain. validate(order); Text search Every validate in the tree, including the simulator and the tests The build Overload, namespace, virtual, or compiled out by the flags The index The one those compile commands keep, with its callers and its tests An example of the split. Not a captured resolution from a matching engine. [How ByteAsk Context works](https://byteask.ai/context) ## A deadlock in a running service orderd, stopped in gdb. Two threads, two mutexes, taken in opposite orders. When the process is already stopped in your gdb, it joins that session. The deadlock is found and fixed. **ByteAsk**AI pair-debugger done ❯ byteask "my gdb is stopped on the deadlock in orderd, take a look" ● Joined the bridge in your gdb. orderd is stopped. ▸ Two threads are stuck in __lll_lock_wait with no progress since 09:31. ▸ T7 (match) is blocked in OrderBook::cancel at order_book.cpp:214. ▸ T7 holds book_mtx_ and waits on risk_mtx_, owned by LWP 71154. ▸ T12 holds risk_mtx_ and waits on book_mtx_, owned by LWP 71149. ▸ That is a lock-order inversion between cancel() and on_fill(). ✎ order_book.cpp -std::lock_guard bk(book_mtx_); -std::lock_guard rk(risk_mtx_); +std::scoped_lock lk(book_mtx_, risk_mtx_); ▸ The same change is applied in risk_engine.cpp:87. $ ninja -C build && ./build/stress --orders 5000000 --threads 16 ✓ 5000000 orders, 0 stalls ▸ I want to run detach in your gdb. Approve? [y/n] ▸ Approved. Sent to your gdb. ✓The diff is ready for review. **gdb**your gdb, bridge armed detached (gdb) source ~/.byteask/byteask_gdb_bridge.py your session · 09:36 (gdb) byteask-bridge ByteAsk bridge armed. The AI can attach now. [byteask] (gdb) info threads Id Target Id Frame * 1 LWP 71142 "orderd" epoll_wait () 2 LWP 71143 "io" io_uring_enter () 7 LWP 71149 "match" __lll_lock_wait () 9 LWP 71151 "md_feed" recvmsg () 12 LWP 71154 "risk" __lll_lock_wait () [byteask] (gdb) thread 7 [Switching to thread 7 (LWP 71149 "match")] [byteask] (gdb) bt #0 __lll_lock_wait () #1 ___pthread_mutex_lock () #2 std::mutex::lock () at bits/std_mutex.h #3 OrderBook::cancel (this=0x55d1a3f2c8e0, id=88213004) at order_book.cpp:214 [byteask] (gdb) frame 3 #3 OrderBook::cancel (this=0x55d1a3f2c8e0, id=88213004) at order_book.cpp:214 [byteask] (gdb) p risk_mtx_._M_mutex.__data.__owner $1 = 71154 ← held by T12 [byteask] (gdb) thread 12 [Switching to thread 12 (LWP 71154 "risk")] [byteask] (gdb) bt #0 __lll_lock_wait () #1 ___pthread_mutex_lock () #2 std::mutex::lock () at bits/std_mutex.h #3 RiskEngine::on_fill (this=0x55d1a3f30120, fill=...) at risk_engine.cpp:87 [byteask] (gdb) p book_mtx_._M_mutex.__data.__owner $2 = 71149 ← held by T7 · cycle confirmed [byteask] (gdb) detach Detaching from program: /srv/orderd, process 71142 [Inferior 1 (process 71142) detached] (gdb) ## The source behind the answer Nasdaq TotalView-ITCH 5.0 Specification §1.3 Add Order Message · p.13 | Field | Offset | Length | | --- | --- | --- | | Message Type | 0 | 1 | | Stock Locate | 1 | 2 | | Tracking Number | 3 | 2 | | Timestamp | 5 | 6 | | Buy/Sell Indicator | 19 | 1 | | Shares | 20 | 4 | | Stock | 24 | 8 | Retrieved with `hft_ref` on 2026-09-11. Excerpt from the captured reference result. ## On your build [Book a demo](https://byteask.cal.com/pratyush/book-a-demo) [On-prem and air-gapped](https://byteask.ai/enterprise) --- HTML version: https://byteask.ai/industries/trading-hft