Re: RELENG_4 -> 5 -> 6: significant performance regression
- From: Mike Jakubik <mikej@xxxxxxxxxx>
- Date: Thu, 27 Apr 2006 15:47:37 -0400
Bartosz Fabianowski wrote:
You wrote that Giant is needed in 6.0 and now you write it has been
removed.
In 4.x, every UFS write requires the Giant lock. In 6.x, Giant is not normally required, making file system operations faster. When you enable QUOTA, you basically get back to the 4.x behavior where Giant is needed for each write. This is why in 6.x UFS will normally be faster but if you enable QUOTA, you lose the newly gained performance again.
Why isn't QUOTA mpsafe then?
_______________________________________________
freebsd-stable@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "freebsd-stable-unsubscribe@xxxxxxxxxxx"
- Follow-Ups:
- Re: RELENG_4 -> 5 -> 6: significant performance regression
- From: Kris Kennaway
- Re: RELENG_4 -> 5 -> 6: significant performance regression
- References:
- RELENG_4 -> 5 -> 6: significant performance regression
- From: Dmitry Pryanishnikov
- Re: RELENG_4 -> 5 -> 6: significant performance regression
- From: Kris Kennaway
- Re: RELENG_4 -> 5 -> 6: significant performance regression
- From: ml@xxxxxxxx
- Re: RELENG_4 -> 5 -> 6: significant performance regression
- From: Kris Kennaway
- Re: RELENG_4 -> 5 -> 6: significant performance regression
- From: ml@xxxxxxxx
- Re: RELENG_4 -> 5 -> 6: significant performance regression
- From: Bartosz Fabianowski
- RELENG_4 -> 5 -> 6: significant performance regression
- Prev by Date: Re: RELENG_4 -> 5 -> 6: significant performance regression
- Next by Date: Re: RELENG_4 -> 5 -> 6: significant performance regression
- Previous by thread: Re: RELENG_4 -> 5 -> 6: significant performance regression
- Next by thread: Re: RELENG_4 -> 5 -> 6: significant performance regression
- Index(es):
Relevant Pages
|
|