What on earth is this? http://www.cyberciti.biz/faq/rhel-centos-debian-ubuntu-jumbo-frames-configuration/ I was under the impression that Ethernet frames can never be more than 1500 bytes. Or is it some kind of stupid linux hack? Or does it have any meaning? Is there real value in this? I don't get it. -Girish
Jumbo frames. Ethernet frames with more than 1500 bytes of payload/ Fewer frames get corrupted, means less processing overhead per frame. Outside of that, the remaining advantage is fewer frames going over the line. It's not recommended on the same LAN as systems not using jumbo frames.
This is not correct. The relatively recent (2005) IEEE 802.3as spec extends Ethernet frame length only to 2048 bytes, mainly to accommodate VLAN stacking and various encap methods. It does not define a standard for jumbo frame length. Jumbo frame support is widely implemented but it's still not standard. Perhaps because there is no standard, switches differ on jumbo MTU. Most support 9216 bytes or more, but some top out at 9000. dn
But the same amount of data(!) needs to be transmitted, and only if no collision(s) and retransmission(s) occurs! Anybody on the same LAN segment - who wants to transmit, I know only a few HP routers which can handle efficiently jumbo frames (internally) - IF enabled. Ask yourself, what would happen with this jumbo frames outside a LAN segment? How would the rest of routers/switches/repeaters - like hubs/etc. would handle jumbo frames? mufurcz
Use NICs capable of TCP checksumming and the appropriate drivers, that A router in between jumbo and non-jumbo will break frames down to non-jumbo sizes if need be. Even a wee Cisco 3750G we tested with does so with minimal CPU hit (maybe it's done in hardware on those, I don't know) We had problems when using is on the same segment with 1518 MTUs. Much of what we read recommened against it but that's like sticking a "DO NOT PUSH" sign above a big red button for me. :) Anyhow to sum it up: jumbo is cool when used correctly. The throughput difference can be quite impressive, we had a considerable boost in speed on 4x GigE iSCSI RAID chassis to the front end box and with NFS. gg
Huh? Haven't seen a network in YEARS that didn't use a switch for interconnect - the 'segments' with most switches have two hosts - machine & switch. If you're running 1GB or 10GB, the switches you're using have backbones well capable of running any framesize you can configure. Lee
Yes, there's value in it. NFS can benefit greatly if you can stuff a single read/write block into a single ethernet frame (rather than splitting it across 3 or 4). It's also helpful for wringing maximum throughput out of your network at higher speeds. Think about the interrupt rate to send 1Gb/s with 1500B frames and compare that to 6000B frames. Even if your card is totally insane, you've just got 4 times more data out of one interrupt. Check the manpages for the various network drivers... On Dec 29, 2007 11:41 PM, Girish Venkatachalam -- GDB has a 'break' feature; why doesn't it have 'fix' too?
On Dec 29, 2007 11:41 PM, Girish Venkatachalam Can be. http://sd.wareonearth.com/~phil/net/jumbo/ http://en.wikipedia.org/wiki/Jumbo_frames DS
Jumbo frames are very real. A simple google search will enlighten you :)
This should help you: http://sd.wareonearth.com/~phil/net/jumbo/ On Dec 30, 2007 12:11 PM, Girish Venkatachalam -- Karthik http://guilt.bafsoft.net
| Matthew Wilcox | [PATCH] Fix boot-time hang on G31/G33 PC |
| Vu Pham | Re: [Scst-devel] Integration of SCST in the mainstream Linux kernel |
| Greg Kroah-Hartman | [PATCH 004/196] Chinese: add translation of SubmittingPatches |
| Rafael J. Wysocki | [Bug #11799] xorg can not start up with stolen memory |
git: | |
| Li Frank-B20596 | why not TortoiseGit |
| Jon Smirl | ! [rejected] master -> master (non-fast forward) |
| Junio C Hamano | Re: If you would write git from scratch now, what would you change? |
| Wincent Colaiuta | Possible to make a totally empty repository for remote access? |
| Richard Stallman | Real men don't attack straw men |
| Chris | Prolific USB-Serial Controller |
| Douglas A. Tutty | OBSD's perspective on SELinux |
| Nick Guenther | Re: how to clear dmesg outpout |
| Volker Armin Hemmann | build error with 2.6.27.6+reiser4+ehci-hub patch. ERROR: "mii_ethtool_gset" [drive... |
| Wenji Wu | A Linux TCP SACK Question |
| Evgeniy Polyakov | [resend take 2 0/4] Distributed storage. |
| YOSHIFUJI Hideaki / | [GIT PULL] [IPV6] COMPAT: Fix SSM applications on 64bit kernels. |
