Date: Tue, 4 Aug 2015 23:17:58 +0200 From: Terje Elde <terje@elde.net> To: javocado <javocado@gmail.com> Cc: "freebsd-questions@freebsd.org" <freebsd-questions@freebsd.org> Subject: Re: pw operations slow under zfs load Message-ID: <3C5A26BE-DC2E-457C-A205-B572FC19325E@elde.net> In-Reply-To: <CAP1HOmSuohyh=mUQ=BChrsuysPQK=v3hdPAays-zn-zadZUKjA@mail.gmail.com> References: <CAP1HOmSuohyh=mUQ=BChrsuysPQK=v3hdPAays-zn-zadZUKjA@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 4. aug. 2015, at 23:07, javocado <javocado@gmail.com> wrote: > So, what's going on here? How does a busy pool with it's own set of drives= > (which operate off an HBA) affect the speed of operations involving the > boot volume (a UFS-formatted SSD connected to the mobo)? First thing that springs to mind is that it's not just a matter of simple IO= . There's also locking (see man-page for flock and/or lockf). Could this be a= s simple as whatever is causing the work-load on your ZFS-volume holding a s= hared lock, on something pw wants to grab an exclusive lock on, prior to doi= ng the actual change? Terje=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3C5A26BE-DC2E-457C-A205-B572FC19325E>