Date: Fri, 27 Aug 2010 20:34:18 -0700 From: Artem Belevich <fbsdlist@src.cx> To: jhell <jhell@dataix.net> Cc: freebsd-current@freebsd.org, Martin Matuska <mm@freebsd.org> Subject: Re: [CFT] Improved ZFS metaslab code (faster write speed) Message-ID: <AANLkTi=LQOQvs4RXih3UdOvPRFt4mzr862nc2ZY6mXdH@mail.gmail.com> In-Reply-To: <4C78655C.3010200@DataIX.net> References: <4C713EF5.8080402@FreeBSD.org> <AANLkTi=8x1EenWyqGz6AQWKDUq5JiMJbX_jbVbX43DKx@mail.gmail.com> <4C714FC0.90005@FreeBSD.org> <AANLkTim_BH4WrQUY-X491c%2BfLaP2FKMcS1k-DN5tLG-9@mail.gmail.com> <20100828081917.ee931f7f.nork@FreeBSD.org> <AANLkTi=hbL3wfTvmfBhPkpJ7orh_WuhagGPoXaS_hcTW@mail.gmail.com> <4C78655C.3010200@DataIX.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Aug 27, 2010 at 6:24 PM, jhell <jhell@dataix.net> wrote: > On 08/27/2010 19:50, Artem Belevich wrote: >> Another "me too" here. >> >> 8-stable/amd64 + v15 (zpool still uses v14) + metaslab + >> abe_stat_rrwlock + A.Gapon's vm_paging_needed() + uma defrag patches. >> >> The box survived few days of pounding on it without any signs of trouble= . >> > > =A0 =A0 =A0 =A0I must have missed the uma defrag patches but according to= the code Here is the UMA patch I was talking about: http://unix.derkeiler.com/Mailing-Lists/FreeBSD/hackers/2010-08/msg00188.ht= ml > those patches should not have any effect on your implimentation of ZFS > on your system because vfs.zfs.zio.use_uma defaults to off unless you > have manually turned this on or the patch reverts that facility back to > its original form. Hmm. Indeed. Kmem_malloc carves memory allocations directly from kmem. Yet the difference in max ARC size with the patch applied is there. http://unix.derkeiler.com/Mailing-Lists/FreeBSD/hackers/2010-08/msg00257.ht= ml Perhaps reduced UMA fragmentation helps those subsystem that do use UMA (including ZFS which always uses uma for various housekeeping data). --Artem
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTi=LQOQvs4RXih3UdOvPRFt4mzr862nc2ZY6mXdH>