diff options
Diffstat (limited to 'hurd/translator/tmpfs/discussion.mdwn')
| -rw-r--r-- | hurd/translator/tmpfs/discussion.mdwn | 93 |
1 files changed, 93 insertions, 0 deletions
diff --git a/hurd/translator/tmpfs/discussion.mdwn b/hurd/translator/tmpfs/discussion.mdwn index 0409f046..1d441c7d 100644 --- a/hurd/translator/tmpfs/discussion.mdwn +++ b/hurd/translator/tmpfs/discussion.mdwn @@ -283,3 +283,96 @@ License|/fdl]]."]]"""]] <mcsim> what kind of log do you mean? <antrik> vmstat 1 I mean <mcsim> ah... + + +## IRC, freenode, #hurd, 2012-02-01 + + <mcsim> I run fsx with this command: fsx -N3000 foo/bar -S4 + -l$((1024*1024*8)). And after 70 commands it breaks. + <mcsim> The strangeness is at address 0xc000 there is text, which was + printed in fsx with vfprintf + <mcsim> I've lost log. Wait a bit, while I generate new + <jkoenig_> mcsim, what's fsx / where can I find it ? + <mcsim> fsx is filesystem exersiser + <mcsim> http://codemonkey.org.uk/projects/fsx/ + <jkoenig_> ok thanks + <mcsim> i use it to test tmpfs + <mcsim> here is fsx that compiles on linux: http://paste.debian.net/154390/ + and Makefile for it: http://paste.debian.net/154392/ + <jkoenig_> mcsim, hmm, I get a failure with ext2fs too, is it expected? + <mcsim> yes + <mcsim> i'll show you logs with tmpfs. They slightly differ + <mcsim> here: http://paste.debian.net/154399/ + <mcsim> pre last operation is truncate + <mcsim> and last is read + <mcsim> during pre-last (or last) starting from address 0xa000, every + 0x1000 bytes appears text + <mcsim> skipping zero size read + <mcsim> skipping zero size read + <mcsim> truncating to largest ever: 0x705f4b + <mcsim> signal 2 + <mcsim> testcalls = 38 + <mcsim> this text is printed by fsx, by function prt + <mcsim> I've mistaken: this text appears even from every beginning + <mcsim> I know that this text appears exactly at this moment, because I + added check of the whole file after every step. And this error appeared + only after last truncation. + <mcsim> I think that the problem is in defpager (I'm fixing it), but I + don't understand where defpager could get this text + <jkoenig_> wow I get java code and debconf templates + <mcsim> So, my question is: is it possible for defpager to get somehow this + text? + <jkoenig_> possibly recycled, non-zeroed pages? + <mcsim> hmmm... probably you're right + <jkoenig_> 0x1000 bytes is consistent with the page size + <mcsim> Should I clean these pages in tmpfs? + <mcsim> or in defpager? + <mcsim> What is proper way? + <jkoenig_> mcsim, I'd say defpager should do it, to avoid leaking + information, I'm not sure though. + <jkoenig_> maybe tmpfs should also not assume the pages have been blanked + out. + <mcsim> if i do it in both, it could have big influence on performance. + <mcsim> i'll do it only in defpager so far. + <mcsim> jkoenig_: Thank you a lot + <jkoenig_> mcsim, no problem. + + +## IRC, freenode, #hurd, 2012-02-08 + + <tschwinge> mcsim: You pushed another branch with cleaned-up patches? + <mcsim> yes. + <tschwinge> mcsim: Anyway, any data from your report that we could be + interested in? (Though it's not in English.) + <mcsim> It's completely in ukrainian an and mostly describes some aspects + of hurd's work. + <tschwinge> mcsim: OK. So you ran out of time to do the benchmarking, + etc.? + <tschwinge> Comparing tmpfs to ext2fs with RAM backend, etc., I mean. + <mcsim> tschwinge: I made benchmarking and it turned out that tmpfs up to 6 + times faster than ext2fs + <mcsim> tschwinge: is it possible to have a review of work, I've already + done, even if parallel writing doesn't work? + <tschwinge> mcsim: Do you need this for university or just a general review + for inclusion in the Git master branch? + <mcsim> general review + <tschwinge> Will need to find someone who feels competent to do that... + <mcsim> the branch that should be checked is tmpfs-final + <pinotree> cool, i guess you tested also special types of files like + sockets and pipes? (they are used in eg /run, /var/run or similar) + <mcsim> Oh. I accidentally created this branch. It is my private + branch. I'll delete it now and merge everything to mplaneta/tmpfs/master + <mcsim> pinotree: Completely forgot about them :( I'll do it by all means + <pinotree> mcsim: no worries :) + <mcsim> tschwinge: Ready. The right branch is mplaneta/tmpfs/master + + +## IRC, freenode, #hurd, 2012-03-07 + + <pinotree> did you test it with sockets and pipes? + <mcsim> pinotree: pipes work and sockets seems to work too (I've created + new pfinet device for them and pinged it). + <pinotree> try with simple C apps + <mcsim> Anyway all these are just translators, so there shouldn't be any + problems. + <mcsim> pinotree: works |