Date: Thu, 27 May 2021 09:09:54 -0400 From: mike tancsa <mike@sentex.net> To: Steven Hartland <killing@multiplay.co.uk> Cc: Alan Somers <asomers@freebsd.org>, freebsd-fs <freebsd-fs@freebsd.org> Subject: Re: speeding up zfs send | recv (update) Message-ID: <56a05357-6fb7-fa77-98a2-8ea8d3b07fcb@sentex.net> In-Reply-To: <CAHEMsqa%2BsOpHCz2XHMMTj8ujeN-J5j8z-NK8EThDP=6Wzt_L-g@mail.gmail.com> References: <866d6937-a4e8-bec3-d61b-07df3065fca9@sentex.net> <CAOtMX2gifUmgqwSKpRGcfzCm_=BX_szNF1AF8WTMfAmbrJ5UWA@mail.gmail.com> <f6ea3387-faf8-4c63-d1e7-906fa397b00b@sentex.net> <CAHEMsqYf4JOL22R3%2B13kqSOaDMydnpsq9Z2mR4EFBg7u78FjSQ@mail.gmail.com> <17763650-53b9-c2af-e14e-5d66f6ae69a1@sentex.net> <CAHEMsqa%2BsOpHCz2XHMMTj8ujeN-J5j8z-NK8EThDP=6Wzt_L-g@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 5/27/2021 5:00 AM, Steven Hartland wrote: > With spinning rust that has other things processing your seek times is > likely the limiting factor. > > Have a look at gstat -pd while the send it happening. > > Thanks, I think I am just running into the limitations of the rusty hardware.=C2=A0=C2=A0 I do notice on my other pool which has more spindle= s with a pair of vdevs, its a bit faster on the sends.=C2=A0 Perhaps adding anothe= r vdev of disks will help squeeze out a bit more performance for now. =C2=A0=C2=A0=C2=A0 ---Mike
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?56a05357-6fb7-fa77-98a2-8ea8d3b07fcb>