Date: Sat, 17 Jun 2017 01:49:18 -0500 From: Adam Vande More <amvandemore@gmail.com> To: "Caza, Aaron" <Aaron.Caza@ca.weatherford.com> Cc: "freebsd-hackers@freebsd.org" <freebsd-hackers@freebsd.org> Subject: Re: FreeBSD10 Stable + ZFS + PostgreSQL + SSD performance drop < 24 hours Message-ID: <CA%2BtpaK2oZJswsTNpqUdGgDdpq-5NNSa6mbS96N7pNr%2BbbqAYjw@mail.gmail.com> In-Reply-To: <4561529b83ce4270b09aa0e3b12f299f@BLUPR58MB002.032d.mgd.msft.net> References: <4561529b83ce4270b09aa0e3b12f299f@BLUPR58MB002.032d.mgd.msft.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, Jun 17, 2017 at 12:16 AM, Caza, Aaron <Aaron.Caza@ca.weatherford.com > wrote: > > Regarding this issue, I've now conducted testing using merely a FreeBSD > 10.3 Stable amd64 GENERIC kernel and using dd to read a large file. The > following is a log, taken hourly, of the degradation which occurred at just > over 9 hours of uptime. As the original is quite large, I've removed some > sections; however, these can be supplied if desired. > Supplied are the initial dmesg and zpool status, logged only on startup, > followed by uptime, uname -a, and zfs-stats -a output, each of which are > logged hourly. > What does this say? # zpool get all
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CA%2BtpaK2oZJswsTNpqUdGgDdpq-5NNSa6mbS96N7pNr%2BbbqAYjw>