Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 26 May 2016 12:48:22 +0200
From:      Fabian Keil <freebsd-listen@fabiankeil.de>
To:        FreeBSD Filesystems <freebsd-fs@freebsd.org>
Subject:   Re: zfs receive stalls whole system
Message-ID:  <20160526124822.374b2dea@fabiankeil.de>
In-Reply-To: <20160517123627.699e2aa5@fabiankeil.de>
References:  <0C2233A9-C64A-4773-ABA5-C0BCA0D037F0@ultra-secure.de> <20160517102757.135c1468@fabiankeil.de> <c090ab7bbff2fffe2a49284f9be70183@ultra-secure.de> <20160517123627.699e2aa5@fabiankeil.de>

next in thread | previous in thread | raw e-mail | index | archive | help
--Sig_/c7iMMeIVRTkG76+IpJ0qpz5
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

Fabian Keil <freebsd-listen@fabiankeil.de> wrote:

> rainer@ultra-secure.de wrote:
>=20
> > Am 2016-05-17 10:27, schrieb Fabian Keil: =20
> > > Rainer Duffner <rainer@ultra-secure.de> wrote:
> > >    =20
> > >> I have two servers, that were running FreeBSD 10.1-AMD64 for a long=
=20
> > >> time, one zfs-sending to the other (via zxfer). Both are NFS-servers=
=20
> > >> and MySQL-slaves, the sender is actively used as NFS-server, the=20
> > >> recipient is just a warm-standby, in case something serious happens=
=20
> > >> and we don=E2=80=99t want to wait for a day until the restore is bac=
k in=20
> > >> place. The MySQL-Slaves are actively used as read-only servers (at t=
he=20
> > >> application level, Python=E2=80=99s SQL-Alchemy does that, apparentl=
y).
> > >>=20
> > >> They are HP DL380G8 (one CPU, hexacore) with over 128 GB RAM (I thin=
k=20
> > >> one has 144, the other has 192).
> > >> While they were running 10.1, they used HP P420 RAID-controllers wit=
h=20
> > >> individual 12 RAID0 volumes that I pooled into 6-disk RAIDZ2 vdevs.
> > >> I use zfsnap to do hourly, daily and weekly snapshots.   =20
> > > [...]   =20
> > >> Now, when I do a zxfer, sometimes the whole system stalls while the=
=20
> > >> data is sent over, especially if the delta is large or if something=
=20
> > >> else is reading from the disk at the same time (backup agent).
> > >>=20
> > >> I had this before, on 10.0 (I believe, we didn=E2=80=99t have this i=
n 9.1=20
> > >> either, IIRC) and it went away in 10.1.   =20
> > >=20
> > > Do you use geli for swap device(s)?   =20
> >=20
> >=20
> > Yes, I do.
> > /dev/mirror/swap.eli		none	swap	sw		0	0
> >=20
> > Bad idea? =20
>=20
> It can cause deadlocks and poor performance when paging.
>=20
> This was recently fixed in ElectroBSD and I intend to submit
> the patch in a couple of days after a bit more stress testing.

Done: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D209759

Fabian

--Sig_/c7iMMeIVRTkG76+IpJ0qpz5
Content-Type: application/pgp-signature
Content-Description: OpenPGP digital signature

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2

iEYEARECAAYFAldG1HcACgkQBYqIVf93VJ0TDgCeKKfOKu3Say8K0QDsWuAPmhPA
s3AAoJPlCDWMXyVZJOBsOQulUU94U+hS
=f3f2
-----END PGP SIGNATURE-----

--Sig_/c7iMMeIVRTkG76+IpJ0qpz5--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20160526124822.374b2dea>