| … | |
… | |
| 47 | * without any syscalls. what's not to like? |
47 | * without any syscalls. what's not to like? |
| 48 | * d) ok, it's vastly more complex, but that's ok, really. |
48 | * d) ok, it's vastly more complex, but that's ok, really. |
| 49 | * e) why 3 mmaps instead of one? one would be more space-efficient, |
49 | * e) why 3 mmaps instead of one? one would be more space-efficient, |
| 50 | * and I can't see what benefit three would have (other than being |
50 | * and I can't see what benefit three would have (other than being |
| 51 | * somehow resizable/relocatable, but that's apparently not possible). |
51 | * somehow resizable/relocatable, but that's apparently not possible). |
|
|
52 | * (FIXME: newer kernels can use 2 mmaps only, need to look into this). |
| 52 | * f) hmm, it's practiclaly undebuggable (gdb can't access the memory, and |
53 | * f) hmm, it's practiclaly undebuggable (gdb can't access the memory, and |
| 53 | the bizarre way structure offsets are commuinicated makes it hard to |
54 | * the bizarre way structure offsets are communicated makes it hard to |
| 54 | * just print the ring buffer heads, even *iff* the memory were visible |
55 | * just print the ring buffer heads, even *iff* the memory were visible |
| 55 | * in gdb. but then, that's also ok, really. |
56 | * in gdb. but then, that's also ok, really. |
| 56 | * g) well, you cannot specify a timeout when waiting for events. no, |
57 | * g) well, you cannot specify a timeout when waiting for events. no, |
| 57 | * seriously, the interface doesn't support a timeout. never seen _that_ |
58 | * seriously, the interface doesn't support a timeout. never seen _that_ |
| 58 | * before. sure, you can use a timerfd, but that's another syscall |
59 | * before. sure, you can use a timerfd, but that's another syscall |
| 59 | * you could have avoided. overall, this bizarre omission smells |
60 | * you could have avoided. overall, this bizarre omission smells |
| 60 | * like a µ-optimisation by the io_uring author for his personal |
61 | * like a µ-optimisation by the io_uring author for his personal |
| 61 | * applications, to the detriment of everybody else who just wants |
62 | * applications, to the detriment of everybody else who just wants |
| 62 | * an event loop. but, umm, ok, if that's all, it could be worse. |
63 | * an event loop. but, umm, ok, if that's all, it could be worse. |
|
|
64 | * (FIXME: jens mentioned timeout commands, need to investigate) |
| 63 | * h) there is a hardcoded limit of 4096 outstanding events. okay, |
65 | * h) there is a hardcoded limit of 4096 outstanding events. okay, |
| 64 | * at least there is no arbitrary low system-wide limit... |
66 | * at least there is no arbitrary low system-wide limit... |
|
|
67 | * (FIXME: apparently, this was increased to 32768 in later kernels( |
| 65 | * i) unlike linux aio, you *can* register more then the limit |
68 | * i) unlike linux aio, you *can* register more then the limit |
| 66 | * of fd events, and the kernel will "gracefully" signal an |
69 | * of fd events, and the kernel will "gracefully" signal an |
| 67 | * overflow, after which you could destroy and recreate the kernel |
70 | * overflow, after which you could destroy and recreate the kernel |
| 68 | * state, a bit bigger, or fall back to e.g. poll. thats not |
71 | * state, a bit bigger, or fall back to e.g. poll. thats not |
| 69 | * totally insane, but kind of questions the point a high |
72 | * totally insane, but kind of questions the point a high |
| 70 | * performance I/O framework when it doesn't really work |
73 | * performance I/O framework when it doesn't really work |
| 71 | * under stress. |
74 | * under stress. |
|
|
75 | * (FIXME: iouring should no longer drop events, need to investigate) |
| 72 | * j) but, oh my! is has exactly the same bugs as the linux aio backend, |
76 | * j) but, oh my! is has exactly the same bugs as the linux aio backend, |
| 73 | * where some undocumented poll combinations just fail. |
77 | * where some undocumented poll combinations just fail. |
| 74 | * so we need epoll AGAIN as a fallback. AGAIN! epoll!! and of course, |
78 | * so we need epoll AGAIN as a fallback. AGAIN! epoll!! and of course, |
| 75 | * this is completely undocumented, have I mantioned this already? |
79 | * this is completely undocumented, have I mantioned this already? |
| 76 | * k) overall, the *API* itself is, I dare to say, not a total trainwreck. |
80 | * k) overall, the *API* itself is, I dare to say, not a total trainwreck. |
