Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!harbinger.cc.monash.edu.au!nntp.coast.net!howland.reston.ans.net!newsjunkie.ans.net!newsfeeds.ans.net!venger.snds.com!hill.ucr.edu!grif From: grif@hill.ucr.edu (Michael Griffith) Newsgroups: comp.unix.bsd.freebsd.misc,comp.os.linux.development.system Subject: Re: async or sync metadata [was: FreeBSD v. Linux] Date: 11 Feb 1996 03:39:24 GMT Organization: UC Riverside, Dept. of Computer Science Lines: 36 Message-ID: <4fjodc$o8j@venger.snds.com> References: <4er9hp$5ng@orb.direct.ca> <4f9skh$2og@dyson.iquest.net> <DMI5Mt.768@pe1chl.ampr.org> <4fi6gq$3tr@dyson.iquest.net> NNTP-Posting-Host: hill.ucr.edu Cc: Xref: euryale.cc.adfa.oz.au comp.unix.bsd.freebsd.misc:13587 comp.os.linux.development.system:17086 In article <4fi6gq$3tr@dyson.iquest.net>, John S. Dyson <root@dyson.iquest.net> wrote: |In article <DMI5Mt.768@pe1chl.ampr.org>, |Rob Janssen <pe1chl@wab-tis.rabobank.nl> wrote: |>It seems to be very hard to get this misconception out of the BSD people's |>heads... |>Sync metadata writes may seem to improve things, but actually it just |>causes your fsck's to return no errors while the files are still |>corrupted. Not necessarily better. |> |FreeBSD does support async mounts for those who want to maximize the |performance, getting both much quicker metadata perf, and the extremely |fast sequential perf associated with FreeBSD. You can get both. Since, |in my normal workstation usage async vs. sync appears to make no significant |difference, most of my filesystems are mounted sync. My news partition is |mounted async which appears to help by about 50%. I also mount filesystems |that |are being restored async, which helps perhaps 10:1. For transient files, mfs |is useful (like for /tmp), and for compiles, the -pipe option of gcc is | useful. Very hard indeed. Here it is one more time: sync metadata with async data is not just slower, it is LESS SAFE. This behavour should not be the default on any reasonable system. If you want real safety, then both data and meta need to be synchronous (i.e. no buffer cache for writes). This real safety comes with an huge performance hit (as in MSDOS). -- Michael A. Griffith (grif@cs.ucr.edu) | http://www.cs.ucr.edu/~grif/ Department of Computer Science | PGP public key available. University of California, Riverside | "My freedom of speech implies (909) 787-3803 | your freedom to be offended."