David Xu wrote: > Julian Elischer wrote: > >> >> John Baldwin wrote: >> >>> On Thursday 19 January 2006 21:56, Julian Elischer wrote: >>> >>> >>>> some progrsss.. >>>> as the first few lines show, it's not quite perfect yet but it's >>>> most of >>>> the way there.. >>>> (Like proc 1 isn't init) >>>> >>> >>> >>> >>> One other note, watch out for the AIO daemons. They have to be >>> kernel procs and not kthreads because they borrow the vmspace of the >>> user process when performing AIO on another process' behalf. >>> >>> >>> >> yeah I found that and the patches account for that. >> >> However I would like to suggest that we change the way that aio works.. >> >> My suggestion is that when a process does AIO, that we "fork a >> ksegroup" and attach it to the >> process, and assign it a (or some) worker thread to do the aio work. >> The userland process would >> be oblivious of the extra (kernel) threads in that kseg and they >> would be independently schedulable. >> They would however automatically have full access to the correct >> address space. >> > These threads should be invisible to userland debugger, and other code > current unknown, for example, signal code ? The idea seems simply but we > may in fact encounter problem, because you inject unknown threads to a > process. :-) If the userland doesn't know about them, how would it affect it? As a kernel thread it wouldn't take part in signals, other than to abort when the process exits. it WOULD accumulate cpu time for the process.. but that is just fair. currently I think that aio is "free". Anyhow I'm not ready to try do it now.. As the current patches leave the status-quo for aio. > I still prefer current model, also the aiod threads can be reused for > multiple > processes. that is both a positive and a negative when it comes to accounting.Received on Mon Jan 23 2006 - 23:59:13 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:51 UTC