Date: Sat, 07 Jun 2008 12:03:32 +0200 From: Ivan Voras <ivoras@freebsd.org> To: freebsd-hackers@freebsd.org Subject: Re: Is there any way to increase the KVM? Message-ID: <g2dmdo$98u$1@ger.gmane.org> In-Reply-To: <20080607060521.GB3462@garage.freebsd.pl> References: <6a7033710805302252v43a7b240x66ca3f5e3dd5fda4@mail.gmail.com> <20080603135308.GC3434@garage.freebsd.pl> <6a7033710806032317g4dbe8845h26a1196016b9c440@mail.gmail.com> <86zlq140x0.fsf@ds4.des.no> <6a7033710806041053g4a5c2fdftd7202b708bff363c@mail.gmail.com> <20080605062728.GA4278@garage.freebsd.pl> <g28rhe$32m$1@ger.gmane.org> <20080607060521.GB3462@garage.freebsd.pl>
next in thread | previous in thread | raw e-mail | index | archive | help
This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig0277BEE0C5A9F610F420C647 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: quoted-printable Pawel Jakub Dawidek wrote: > On Thu, Jun 05, 2008 at 04:00:13PM +0200, Ivan Voras wrote: >> At the risk of sounding repetitive, can you try a simple test on your >> ZFS pools, to see if you can panic the kernel? Do this: >> >> * install blogbench and bonnie++ from ports/benchmarks >> * run: >> blogbench -c 100 -d . -i 30 -r 50 -W 10 -w 10 >> bonnie++ -d . -s 16G -n 80 >> in parallel, until completion or crash. It shouldn't take too long t= o >> complete the above benchmarks, so you probably won't invest too much >> time in it even if it doesn't crash. >=20 > Both completed successfully (i386, 1GB of RAM, dual core CPU). Perfect! > Can you now go and revert all the FUD you spread? You probably need to > invest much more time than that. Right, I'm just an evil guy trying to badmouth the system that's a large = chunk of my bread and butter because I'm bored. :) What should I say,=20 "sorry for posting bug reports?" and "sorry for writing docs on which=20 features of (current) ZFS to avoid to sidestep crashes?" Actually I have a suspicion it's the second one (in ZFS wiki pages)=20 you'd like cleared up, but keep in mind you were off the lists for a=20 time and you are the principal source of information on our ZFS=20 implementation. At the time there was a lot of incorrect information=20 floating about in the mailing lists, where people (me included) were=20 doing voodoo computing - trying every knob there was to see if it made a = difference - and I tried to document whatever seemed to work to avoid=20 answering repetitive questions posted on the lists. I will be among the first to try the new patches (depending on the time=20 zone, probably, and we're pretty close there) and, unfortunately, I will = complain and ask guidance if things don't work. On the other hand, if=20 they do work, I'll a) add big honking banners with bells and whistles=20 proclaiming that it finally works in (HEAD | RELENG_7), optionally=20 praising you to heaven for bringing it to completion[*], and b) buy you=20 a BIGNUM of beers next time we meet. [*] really, no sarcasm intended. It *was* an enormous job and if it=20 works, you'd earn it! In the time I spent trying to make it work I saw=20 from first-hand experience how great the whole idea of ZFS is and how=20 useful it is in daily operation. --------------enig0277BEE0C5A9F610F420C647 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.5 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iD8DBQFISlz1ldnAQVacBcgRArQ1AJ9h6cuhdJ7KGdd+BBSJt0/4bMKgnwCg7ZYR qD4K5rfpUUU9/d6X7xF0KBM= =2roW -----END PGP SIGNATURE----- --------------enig0277BEE0C5A9F610F420C647--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?g2dmdo$98u$1>