Dmitrii Kuvaiskii
Dmitrii Kuvaiskii
Indeed, TDEngine seems to require `timer_create()` syscall and may fail arbitrarily if the syscall is not implemented: https://github.com/taosdata/TDengine/blob/d290daa197b08564c7b1b587b3cde8cda96e70c1/source/os/src/osTimer.c#L111-L113 (The code quality is... dubious. The author knows that `timer_create()` may return...
@qijiax Gramine currently supports only classic alarm/timer syscalls: - [`alarm`](https://man7.org/linux/man-pages/man2/alarm.2.html) - [`setitimer`](https://man7.org/linux/man-pages/man2/setitimer.2.html) - Only `ITIMER_REAL` type is supported! These syscalls are far less powerful than `timer_create()` unfortunately. But if TDEngine...
I'm not aware of anyone working on `timer_create()`, at least from the Intel side. If possible, you may also want to take a look at `timerfd_create()` syscall -- maybe it...
@BraunPhilipp If you haven't seen it yet, I recently created a comprehensive technical document on Gramine implemented and unimplemented features. It is still a [pending PR](https://github.com/gramineproject/gramine/pull/1194), but you can read...
@BraunPhilipp Replied there.
> we have discovered that the `ra_tls_set_measurement_callback` function gets ignored if the `gramine` main package is missing What does that mean? This function doesn't do anything special: https://github.com/gramineproject/gramine/blob/ce7556d14996cba3d58f9a8858ca170a91b46e68/tools/sgx/ra-tls/ra_tls_verify_common.c#L234-L237 So how...
> ... `gramine-ratls-epid` needs to directly depend on `libcjson1`, though cjson might have changed between 1.4 and current master (@dimakuv is this accurate?). This is accurate. We removed the need...
@llly Good observation and good idea, thanks. @kailun-qin implemented a new LibOS upcall `get_vma_info()`, which PALs can call to learn current VMA information (page protections, and I think currently that's...
@llly Hm, I may be missing something. Now that I look at your example: > We've seen a workload that calls `mmap(RW)` to allocate some pages then calls `mprotect(RW)` on...
Thank you @llly, then I misunderstood your initial request. Yes, now it totally makes sense to me.