diff options
| author | Samuel Thibault <samuel.thibault@ens-lyon.org> | 2011-01-09 23:34:42 +0100 |
|---|---|---|
| committer | Samuel Thibault <samuel.thibault@ens-lyon.org> | 2011-01-09 23:34:42 +0100 |
| commit | f3df65ce34153357d28bee621bdf49b61e68b182 (patch) | |
| tree | 25ac416b157b010ca2f942dac5c5ba0b38a924ac /open_issues/multiprocessing.mdwn | |
| parent | 09184ae09c44c052a207aa5c6dc8ce9cf61a343f (diff) | |
| parent | 3bbe62327128ce85829a4cb2fb429bd8f21b4d75 (diff) | |
Merge branch 'master' of flubber:~hurd-web/hurd-web
Diffstat (limited to 'open_issues/multiprocessing.mdwn')
| -rw-r--r-- | open_issues/multiprocessing.mdwn | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/open_issues/multiprocessing.mdwn b/open_issues/multiprocessing.mdwn index 7b4f2611..224c0826 100644 --- a/open_issues/multiprocessing.mdwn +++ b/open_issues/multiprocessing.mdwn @@ -11,7 +11,7 @@ License|/fdl]]."]]"""]] [[!tag open_issue_hurd]] We would expect that fine-grained, compartmentalized systems, that is, -microkernel-based multi-server systems in particular, would be ideal condidates +microkernel-based multi-server systems in particular, would be ideal candidates for applying multiprocessing. That is, however, only true from a first and inexperienced point of view: there are many difficulties. @@ -19,14 +19,14 @@ inexperienced point of view: there are many difficulties. IRC, #hurd, August / September 2010 <marcusb> silver_hook: because multi-server systems depend on inter-process - communication, and inter-process communication is many times more expensive - across cpus - <marcusb> silver_hook: so you either force interrelated work on the same cpu, - or suffer heavy penalties. and in a typical fine-grained object system, all - objects are interconnected! - <marcusb> silver_hook: resources in today's systems, even in a single node with - one cpu, but more so in a network, are very non-uniform. scheduling these - resources efficiently is a huge problem. restricting the resource + communication, and inter-process communication is many times more + expensive across cpus + <marcusb> silver_hook: so you either force interrelated work on the same + cpu, or suffer heavy penalties. and in a typical fine-grained object + system, all objects are interconnected! + <marcusb> silver_hook: resources in today's systems, even in a single node + with one cpu, but more so in a network, are very non-uniform. scheduling + these resources efficiently is a huge problem. restricting the resource distribution policies in the way microkernel systems tend to do is posing serious research challenges |