Re: ZFS/RAIDZ and SAMBA: abyssimal performance

看板FB_current作者時間12年前 (2013/04/27 13:01), 編輯推噓0(000)
留言0則, 0人參與, 最新討論串12/16 (看更多)
--Sig_/YHk9yyAq5=oq4ZJM6O=gADJ Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable Fleuriot Damien <ml@my.gd> wrote: >=20 > On Jan 4, 2013, at 4:19 PM, O. Hartmann <ohartman@zedat.fu-berlin.de> wro= te: >=20 > > Am 01/04/13 15:45, schrieb Garrett Cooper: > >> On Fri, Jan 4, 2013 at 6:06 AM, Fleuriot Damien <ml@my.gd> wrote: > >>=20 > >> ... > >>=20 > >>> And this is under [global] in /usr/local/etc/smb.conf: > >>> min receivefile size =3D 16384 > >>> aio read size =3D 16384 > >>> aio write size =3D 16384 > >>> aio write behind =3D yes > >>=20 > >> These are still pretty low, depending on what your networking/disk > >> setup is like; my important performance settings are: > >>=20 > >> socket options =3D SO_RCVBUF=3D64240 SO_SNDBUF=3D64240 TCP_NODE= LAY > >> IPTOS_LOWDELAY IPTOS_THROUGHPUT > >> write cache size =3D 65536 > >> aio read size =3D 65536 > >> aio write size =3D 65536 > >> directory name cache size =3D 0 > > Well, now I have peak values ~ 120 MB/s when copying. I applied Fleuriot > > Damien's values to /boot/loader.conf and yours to the smb.conf. > > Somewhere in the handbook this should be documented! it is to much > > efford to get SAMBA working properly with ZFS, if the tricks and > > problems are so widespread over several architectural aspects of the sy= stem. > >=20 > > It could save a lot of time for adminsitartors and those which try > > FreeBSD as a serving system instead of Linux. > >=20 > > Just for the record. I feel a bit confused about all the tricks and > > tweak now "published" for ZFS, its magic L2ARC, the kernel_vmem wizzardy > > thingis. The ZFS Wiki seems to be a bit outdated and confusing, it would > > be a great deal if all these things could be lined up a s a primer with > > a bit more explanations than "put this number there". > The problem, Oliver, is that these values are system dependant. While I agree that the values are system dependant the purpose of the tunables could still be documented together with a description of how to properly test that they have any effect at all and that it's an improvement compared to the defaults. Scarce ZFS tuning documentation is also a problem upstream which probably doesn't help. Fabian --Sig_/YHk9yyAq5=oq4ZJM6O=gADJ Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (FreeBSD) iEYEARECAAYFAlDnH04ACgkQBYqIVf93VJ1hgwCggdVXWRVaoZe0OM9MzxTjW5pW MhEAn0UzjXYE07C+3pzigW+dTO+i11Yv =fAK9 -----END PGP SIGNATURE----- --Sig_/YHk9yyAq5=oq4ZJM6O=gADJ--
文章代碼(AID): #1HUrkp5N (FB_current)
討論串 (同標題文章)
文章代碼(AID): #1HUrkp5N (FB_current)