From mboxrd@z Thu Jan 1 00:00:00 1970 References: <20160222131359.GA2152@polynum.com> <9660a4b83c4716e542067787ef079dc9@proxima.alt.za> <89408094bbaa48f7f464c9c1ea4d9df4@hemiola.co.uk> <20160222151234.GB2988@polynum.com> <2c7afb1f-f7be-4e55-af95-a0f084b63b90@email.android.com> <20160222152701.GA2923@polynum.com> From: Kenny Lasse Hoff Levinsen Content-Type: text/plain; charset=us-ascii In-Reply-To: Message-Id: <5E146D30-0932-4D66-800D-1F99AA7F5892@gmail.com> Date: Mon, 22 Feb 2016 17:28:11 +0100 To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net> Content-Transfer-Encoding: quoted-printable Mime-Version: 1.0 (1.0) Subject: Re: [9fans] rtl8169 gbe slow Topicbox-Message-UUID: 87e5b190-ead9-11e9-9d60-3106f5b1d025 Go http client + go http server on a vps (14.2ms ping) show same issues: 182= s to download 100MB from remote using a 9front VM, 7s local, vs. 30s and 1s f= or the linux host. So yeah, hget/webfs has nothing to do with it. Fun sidenote: more floating point code in note handlers, this time duffzero w= hen calling os.Exit. *sigh*. Best regards, Kenny Levinsen On 22. feb. 2016, at 16.46, David du Colombier <0intro@gmail.com> wrote: >> No. Is it possible to change the string for hget? >=20 > You can change the string in /sys/src/cmd/hget.c. > But this issue is not related to hget, since it doesn't happen when > using hget on Linux or 9vx. >=20 > It seems related to the Plan 9 TCP stack, or how the network > infrastructure behaves with it. >=20 > --=20 > David du Colombier >=20