Opened 8 years ago

Last modified 2 years ago

#5464 assigned enhancement

Decentralized measurement for network load balancing

Reported by: mikeperry Owned by: arma
Priority: Medium Milestone:
Component: Core Tor/Torflow Version:
Severity: Normal Keywords: SponsorZ-large performance
Cc: arma, aagbsn, isis@…, robgjansen, gk, starlight@… Actual Points:
Parent ID: #5992 Points:
Reviewer: Sponsor:

Description

EigenSpeed could provide a lot of security improvements to the Tor network in the face of all sorts of amplification attacks. It just sort of sucks because the passive version could not measure fast relays, and so we've never used it.

However, an active version based on CapProbe, PacketPair, etc could possibly measure capacity in as little as a handful of UDP packets, enabling distributed active lightweight measurements. We could also blend in circuit failure rate information.

As an alternative, we could also try using the passive EigenSpeed for slow relays and the bw authorities only for the faster ones...

The big problem is that this is basically a research effort. We're going to need to try at least a couple different versions of these designs and compare them to each other, and then compare them to the current bandwidth authorities, to make sure everything is as performant and abuse tolerant as possible.

Child Tickets

Change History (17)

comment:1 Changed 8 years ago by mikeperry

comment:2 Changed 8 years ago by mikeperry

Cc: aagbsn added
Owner: mikeperry deleted
Status: newassigned
Summary: Evaluate Active EigenSpeed/Hybrid EigenspeedEvaluate Active EigenSpeed vs Hybrid EigenSpeed vs Existing Bw Auths

comment:3 Changed 8 years ago by mikeperry

Owner: set to arma

arma: I am going to assign this to you since you're our Research Rangler. Maybe if you poke people about it, they will actually listen.

comment:4 Changed 8 years ago by mikeperry

FYI, there are a ton of lightweight capacity measurement mechanisms published since CapProbe that claim to be improvements. Examples include: Packet Twins, TRIO, and "ThroughputIndex" (fully passive).

If you check the CapProbe citation lists, there's also a ton of new work on measuring capacity in overlay networks that directly cites CapProbe:
http://ksubrick.ist.psu.edu/showciting?doi=10.1.1.76.8001

The challenge for us is to find not only the best one of these for Tor's current and future transports, but to also blend in latency (#4708), circuit failure (#1984), tcp socket exhaustion (#4709), feedback (#1976), and resilience to gaming.

comment:5 Changed 7 years ago by mikeperry

Keywords: SponsorZ-large performance added

If we have to do both the research and the implementation ourselves, this is a large project. It is also closely related to network performance and security.

comment:6 Changed 7 years ago by mikeperry

Summary: Evaluate Active EigenSpeed vs Hybrid EigenSpeed vs Existing Bw AuthsDecentralized measurement for network load balancing

comment:7 Changed 7 years ago by mikeperry

Parent ID: #5456#5992

Going to re-parent this to #5992. We may not strictly need this to defend against path bias, anyway.

comment:8 Changed 7 years ago by mikeperry

FYI: I broke off the circuit failure stuff for path bias into #7509/#7281.

comment:9 Changed 6 years ago by isis

Cc: isis@… added

comment:10 Changed 6 years ago by robgjansen

Cc: robgjansen added

comment:11 in reply to:  1 Changed 5 years ago by gk

Cc: gk added

Replying to mikeperry:

Eigenspeed paper: http://www.usenix.org/event/iptps09/tech/full_papers/snader/snader.pdf
http://www.usenix.org/event/iptps09/tech/full_papers/snader/snader_html/

Who knows what black hole the source has disappeared into, though...

The code for EigenSpeed is here: https://bitbucket.org/hatswitch/eigenspeed. Nikita sent me an old patch when asked about the code used in "Improving Security and Performance in the Tor Network through Tunable Path Selection". Not sure if that one is helpful though...

comment:12 Changed 3 years ago by cass

Severity: Normal

This ticket is tagged SponsorZ, but it looks like progress stalled two years ago. Is this still a thing that needs funding?

comment:13 Changed 3 years ago by cypherpunks

comment:14 Changed 3 years ago by nickm

Parent ID: #5992
Priority: MediumHigh

comment:15 Changed 3 years ago by nickm

Parent ID: #5992

comment:16 Changed 3 years ago by starlight

Cc: starlight@… added

comment:17 Changed 2 years ago by teor

Priority: HighMedium

Priorities and Severities in torflow are meaningless, setting them all to Medium/Normal.

Note: See TracTickets for help on using tickets.