Date: Tue, 13 Jun 2017 15:47:08 +0300 From: Slawa Olhovchenkov <slw@zxy.spb.ru> To: "Caza, Aaron" <Aaron.Caza@ca.weatherford.com> Cc: "freebsd-hackers@freebsd.org" <freebsd-hackers@freebsd.org> Subject: Re: [EXTERNAL] Re: FreeBSD10 Stable + ZFS + PostgreSQL + SSD performance drop < 24 hours Message-ID: <20170613124708.GB18123@zxy.spb.ru> In-Reply-To: <f3599715fd104d73acd0846ebc468315@DM2PR58MB013.032d.mgd.msft.net> References: <79528bf7a85a47079756dc508130360b@DM2PR58MB013.032d.mgd.msft.net> <20170610163642.GA18123@zxy.spb.ru> <f3599715fd104d73acd0846ebc468315@DM2PR58MB013.032d.mgd.msft.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Jun 13, 2017 at 06:24:34AM +0000, Caza, Aaron wrote: > Slawa - thanks again for your suggestion but, unfortunately, same behavior: np, thanks for check! > (Server is Intel Core i5-2500K w 16GB ram and 2x Intel 520 120GB SSDs): > > PostgreSQL test results immediately after reboot: > Timing is on. > count > ---------- > 21568508 > (1 row) > > Time: 53855.000 ms > test$ uptime > 7:51PM up 2 mins, 1 user, load averages: 2.46, 0.88, 0.34 > test$ uname -a > FreeBSD xyz.com 10.3-STABLE FreeBSD 10.3-STABLE #0 r307264M: Mon Jun 12 17:48:24 MDT 2017 aaronc@WFT:XYZ amd64 > > PostgreSQL test results after ~5 hours: > Timing is on. > count > ---------- > 21568508 > (1 row) > > Time: 737626.512 ms > test$ uname -a > FreeBSD xyz.com 10.3-STABLE FreeBSD 10.3-STABLE #0 r307264M: Mon Jun 12 17:48:24 MDT 2017 aaronc@WFT:XYZ amd64 > test$ uptime > 1:06AM up 5:16, 1 user, load averages: 2.21, 2.59, 2.04 > > Perhaps if I was on stable/11 this would be of some benefit. > Thanks for the response. I happened across r307264; however, my understanding is that it applies to the FreeBSD 11 and I'm using FreeBSD 10. This commit (ZFS ARC comression support) was MFC on stable/11 and stable/10, so you don't need check stable/11.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20170613124708.GB18123>