git/list[1] front-page[2] threads[3] people[4] search[5] about
 

Re: What to expect after 0.99.8

From
Linus Torvalds <torvalds@osdl.org>
Date
Oct 5, 2005, 00:10 UTC
Message-ID
<Pine.LNX.4.64.0510041706330.31407@g5.osdl.org>
In-Reply-To
<7vu0fx9c1c.fsf@assigned-by-dhcp.cox.net>
On Tue, 4 Oct 2005, Junio C Hamano wrote:
Show 6 quoted lines
> 
> I vaguely recall there was an interesting regression in recent
> kernel history when the implementation of the pipe buffer was
> changed, with which, writing the same amount of data with
> different number of writes made things behave differently and
> making the worst case buffer size less than traditional 4K.

Just for performance reasons, I ended up doing merging anyway, so in fact regardless of how you write the current pipe buffer size is up to 16 pages.

I think you can safely assume that pretty much any file descriptor you use has at least 1kB of buffer. Even 4kB is likely a "safe assumption", and in reality, most of them end up having even more.

With something like ssh, you probably end up having even deeper ones, since you end up having the local pty or socket to ssh, and then ssh has the TCP buffer to the network..

			Linus
Previous: Junio C HamanoNext: H. Peter Anvin
Message 25 of 39 in “What to expect after 0.99.8”
  1. Junio C HamanoOct 3, 2005
  2. A Large Angry SCMOct 3, 2005
  3. Junio C HamanoOct 3, 2005
  4. Enable and fix support for base less merges.Fredrik Kuivinen, Oct 3, 2005
  5. Josef WeidendorferOct 3, 2005
  6. Junio C HamanoOct 4, 2005
  7. Josef WeidendorferOct 4, 2005
  8. Junio C HamanoOct 4, 2005
  9. Random documentation fixesJonas Fonseca, Oct 3, 2005
  10. Daniel BarkalowOct 3, 2005
  11. Martin CoxallOct 3, 2005
  12. Nick HengeveldOct 3, 2005
  13. Daniel BarkalowOct 3, 2005
  14. Junio C HamanoOct 3, 2005
  15. Daniel BarkalowOct 3, 2005
  16. Junio C HamanoOct 3, 2005
  17. Linus TorvaldsOct 3, 2005
  18. Dan AloniOct 4, 2005
  19. Daniel BarkalowOct 4, 2005
  20. Matthias UrlichsOct 4, 2005
  21. H. Peter AnvinOct 4, 2005
  22. Matthias UrlichsOct 4, 2005
  23. H. Peter AnvinOct 4, 2005
  24. Junio C HamanoOct 4, 2005
  25. Linus TorvaldsOct 5, 2005
  26. H. Peter AnvinOct 5, 2005
  27. Daniel BarkalowOct 4, 2005
  28. H. Peter AnvinOct 4, 2005
  29. Daniel BarkalowOct 4, 2005
  30. Alan ChandlerOct 3, 2005
  31. H. Peter AnvinOct 3, 2005
  32. Greg KHOct 4, 2005
  33. H. Peter AnvinOct 5, 2005
  34. Matthias UrlichsOct 3, 2005
  35. Chuck LeverOct 4, 2005
  36. Junio C HamanoOct 4, 2005
  37. Fredrik KuivinenOct 4, 2005
  38. Fredrik KuivinenOct 5, 2005
  39. Junio C HamanoOct 5, 2005

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.