[lkml]   [2004]   [Jun]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH] Staircase Scheduler v6.3 for 2.6.7-rc2
Hash: SHA1
Pavel Machek wrote:
| Hi!
|>This is an update of the scheduler policy mechanism rewrite using the
|>infrastructure of the current O(1) scheduler. Slight changes from the
|>original design require a detailed description. The change to the
|>design has enabled all known corner cases to be abolished and cpu
|>distribution to be much better maintained. It has proven to be stable
in my
|>testing and is ready for more widespread public testing now.
|> - Interactive by design rather than have interactivity bolted on.
|> - Good scalability.
|> - Simple predictable design.
|> - Maintain appropriate cpu distribution and fairness.
|> - Low scheduling latency for normal policy tasks.
|> - Low overhead.
|> - Making renicing processes actually matter for CPU distribution
(nice 0 gets
|>20 times what nice +20 gets)
|> - Resistant to priority inversion
| How do you solve priority inversion?

I don't solve it. It is relatively resistant to priority inversion by
tasks traversing all the priorities lower than itself rather than
sitting at one priority. It does this more strictly when interactive is
disabled which I recommend for server and multiuser setups.

| Can you do "true idle threads" now? (I.e. nice +infinity?)

Not safely, no. I have a batch(idle) implementation that is relatively
safe but can be abused (it's in my -ck patchset only). At some stage if
the codebase settles down enough I'll try and introduce semaphore
tracking for batch processes that will elevate them to normal scheduling
~ to prevent DoSing.

Version: GnuPG v1.2.4 (GNU/Linux)
Comment: Using GnuPG with Thunderbird -
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at
Please read the FAQ at
 \ /
  Last update: 2005-03-22 14:04    [from the cache]
©2003-2014 Jasper Spaans. hosted at Digital Ocean