Date: Sat, 24 Feb 2024 21:52:11 -0500 From: Mark Saad <nonesuch@longcount.org> To: freebsd-net@freebsd.org Subject: Re: NFS performance with 10GBase-T Message-ID: <9F370420-52DC-4895-B2B3-5254B6E470D0@longcount.org> In-Reply-To: <034cc6ea-26d8-4520-879a-672459832407@fsfe.org> References: <034cc6ea-26d8-4520-879a-672459832407@fsfe.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--Apple-Mail-E0DD2C68-F6FB-45A9-BD26-CE8E9A032E65 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable > On Feb 24, 2024, at 7:18 PM, Hannes Hauswedell <h2+lists2024@fsfe.org> wro= te: >=20 > =EF=BB=BFHi everyone, >=20 > I am coming here from > https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D2771971160 >=20 > TL;DR: >=20 > * I have a FreeBSD14 Server and Client with an Intel X540 (ix) adaptor eac= h. > * I am trying to improve the NFS throughput. > * I get 1160 MiB/s via nc, but only ~200 MiB/s via NFS. > * Increasing rsize and wsize to 1 MiB increases throughput to 395 MiB/s > * But a Linux client achieves 560-600 MiB/s with any rsize. > * The mtu is set to 9000 but this doesn't make a difference for the FreeBS= D client (it does make a difference for Linux). >=20 > I assume < 400 MiB/s is not the expected performance? Do you have any advi= ce on debugging this? >=20 > Thank you for your help, > Hannes >=20 Hi Hannes, The link didn=E2=80=99t work . Can you tell us more about the file system ,= what type of disks . Details about the server , hardware details. If you w= ant post a copy of your dmesg to https://dmesgd.nycbug.org/index.cgi that ca= n help too . Also what kinds of clients are you using ? Do you have any relevant network stats or a topology/ diagram of the shape o= f things ?=20 Mark saad | nonesuch@longcount.org= --Apple-Mail-E0DD2C68-F6FB-45A9-BD26-CE8E9A032E65 Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable <html><head><meta http-equiv=3D"content-type" content=3D"text/html; charset=3D= utf-8"></head><body dir=3D"auto"><div dir=3D"ltr"><br></div><div dir=3D"ltr"= ><br><blockquote type=3D"cite">On Feb 24, 2024, at 7:18 PM, Hannes Hauswedel= l <h2+lists2024@fsfe.org> wrote:<br><br></blockquote></div><blockquote= type=3D"cite"><div dir=3D"ltr">=EF=BB=BF<span>Hi everyone,</span><br><span>= </span><br><span>I am coming here from</span><br><span>https://bugs.freebsd.= org/bugzilla/show_bug.cgi?id=3D2771971160</span><br><span></span><br><span>T= L;DR:</span><br><span></span><br><span>* I have a FreeBSD14 Server and Clien= t with an Intel X540 (ix) adaptor each.</span><br><span>* I am trying to imp= rove the NFS throughput.</span><br><span>* I get 1160 MiB/s via nc, but only= ~200 MiB/s via NFS.</span><br><span>* Increasing rsize and wsize to 1 MiB i= ncreases throughput to 395 MiB/s</span><br><span>* But a Linux client achiev= es 560-600 MiB/s with any rsize.</span><br><span>* The mtu is set to 9000 bu= t this doesn't make a difference for the FreeBSD client (it does make a diff= erence for Linux).</span><br><span></span><br><span>I assume < 400 MiB/s i= s not the expected performance? Do you have any advice on debugging this?</s= pan><br><span></span><br><span>Thank you for your help,</span><br><span>Hann= es</span><br><span></span><br></div></blockquote><br><div>Hi Hannes,</div><d= iv> The link didn=E2=80=99t work . Can you tell us more about the file= system , what type of disks . Details about the server , hardware details. &= nbsp;If you want post a copy of your dmesg to <a href=3D"https://dmesgd= .nycbug.org/index.cgi">https://dmesgd.nycbug.org/index.cgi</a> that can= help too .</div><div><br></div><div>Also what kinds of clients are you usin= g ?</div><div><br></div><div>Do you have any relevant network stats or a top= ology/ diagram of the shape of things ? </div><div><br></div><div><div s= tyle=3D"display: block;" class=3D"">Mark saad | nonesuch@longcount.org</div>= </div></body></html>= --Apple-Mail-E0DD2C68-F6FB-45A9-BD26-CE8E9A032E65--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?9F370420-52DC-4895-B2B3-5254B6E470D0>