Date: Wed, 3 Dec 2003 13:51:27 -0800 (PST) From: Don Lewis <truckman@FreeBSD.org> To: kmarx@vicor.com Cc: mckusick@beastie.mckusick.com Subject: Re: 4.8 ffs_dirpref problem Message-ID: <200312032151.hB3LpReF032726@gw.catspoiler.org> In-Reply-To: <3FCD4396.1040100@vicor.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 2 Dec, Ken Marx wrote: > > > Don Lewis wrote: >> I went ahead and spun a new version of my patch with the new multiplier, >> one other tweak to the formula, and updated comments. > > Hi, Sorry for the delay. Tested, then realized a stupid mistake, > started over, panic'd the box, and finally tested. Panic was > a bit unsettling. Happened when I tried to call my dump routine > from the debugger. Might have been a typo for all I know(!?) - > was doing quickly to keep benchmark script from bailing due to > "Profiling timer expired" killing my timer. (That's another kettle > of wax, I guess.) > > Other than that, the newer hashkey stuff does seem to improve > the shallowness of the table. Below are some samples while doing > the 1.4gb untar commands on 98% and 99%+ full disk. Again, > running w/ 75% avgbfree, avgifree so as to hit the table harder. It looks good enough to me. I just committed it.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200312032151.hB3LpReF032726>