Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Route\s+cache\s+performance\s+under\s+stress\s*$/: 364 ]

Total 364 documents matching your query.

321. Re: Route cache performance under stress (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Sat, 14 Jun 2003 23:36:28 -0700 (PDT)
No please do. There is an updated rtstat already. I am, but I have to do this by hand. It seems your email client has caught the disease that turns all tabs into spaces :(
/archives/netdev/2003-06/msg01347.html (10,825 bytes)

322. Re: Route cache performance under stress (score: 1)
Author: Robert Olsson <Robert.Olsson@xxxxxxxxxxx>
Date: Tue, 17 Jun 2003 19:03:37 +0200
A starting point... Kernel hack enclosed and companion app from: ftp://robur.slu.se/pub/Linux/net-development/fibstat Just some hash metrics yet. Output below is from our DoS tests: lookup_total ==
/archives/netdev/2003-06/msg01428.html (17,264 bytes)

323. Re: Route cache performance under stress (score: 1)
Author: Florian Weimer <fw@xxxxxxxxxxxxx>
Date: Tue, 17 Jun 2003 22:58:31 +0200
Zebra doesn't send BGP keepalives while updating the kernel's view of the routing table. If a configuration change results massive routing table updates (e.g. changed LOCAL_PREF), it's quite likely t
/archives/netdev/2003-06/msg01463.html (11,721 bytes)

324. Re: Route cache performance under stress (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Sun, 18 May 2003 02:31:51 -0700 (PDT)
[ Please don't CC: sim@xxxxxxxxxxxxx any more, his address bounces at least for me (maybe his site rejects ECN, it is the most likely problem if it works for other people) ] Well, what would change y
/archives/netdev/2003-05/msg00572.html (10,630 bytes)

325. Re: Route cache performance under stress (score: 1)
Author: Jamal Hadi <hadi@xxxxxxxxxxxxxxxx>
Date: Mon, 19 May 2003 13:36:06 -0400 (EDT)
Florian, I actually asked you to run some tests last time you showed up on netdev but never heard back. Maybe we can get some results now that the complaining is still continuing. Note, we cant just
/archives/netdev/2003-05/msg00580.html (9,658 bytes)

326. Re: Route cache performance under stress (score: 1)
Author: Ralph Doncaster <ralph@xxxxxxxxx>
Date: Mon, 19 May 2003 15:18:14 -0400 (EDT)
When I looked at the route-cache code, efficient wasn't the word the came to mind. Whether the problem is in the route-cache or not, getting task. I've tried 2.2 and 2.4 (up to 2.4.20) with 3c905CX c
/archives/netdev/2003-05/msg00582.html (13,447 bytes)

327. Re: Route cache performance under stress (score: 1)
Author: Jamal Hadi <hadi@xxxxxxxxxxxxxxxx>
Date: Mon, 19 May 2003 18:37:43 -0400 (EDT)
Took Linux kernel off the cc list. I just tested a small userland apps which does some pseudo routing in userland. With NAPI i am able to do 148Kpps without it same hardware, about 32Kpps. I cant tes
/archives/netdev/2003-05/msg00584.html (14,426 bytes)

328. Re: Route cache performance under stress (score: 1)
Author: Simon Kirby <sim@xxxxxxxxxxxxx>
Date: Mon, 19 May 2003 18:10:53 -0700
Was the hash distribution broken before even in the truly random case? If so, the patch would likely help. If not, it shouldn't really affect the DoS case or the normal traffic case, because I doubt
/archives/netdev/2003-05/msg00586.html (10,697 bytes)

329. Re: Route cache performance under stress (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Mon, 19 May 2003 18:14:05 -0700 (PDT)
I bet you have been, the weakness in the hash has been very well publicized and the script kiddies aren't using the truly random version of the attacks anymore. Just google for juno-z.101f.c, this (o
/archives/netdev/2003-05/msg00587.html (9,836 bytes)

330. Re: Route cache performance under stress (score: 1)
Author: Jamal Hadi <hadi@xxxxxxxxxxxxxxxx>
Date: Mon, 19 May 2003 21:23:08 -0400 (EDT)
Also used to attack CISCOs by them kiddies btw. We stand much better than any CISCO doing caching. cheers, jamal
/archives/netdev/2003-05/msg00588.html (10,161 bytes)

331. Re: Route cache performance under stress (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Mon, 19 May 2003 18:24:10 -0700 (PDT)
I have to assume that the source address selection operates differently for attacking cisco equiptment, our hashes being identical would really be unbelievable :-)
/archives/netdev/2003-05/msg00589.html (9,934 bytes)

332. Re: Route cache performance under stress (score: 1)
Author: Pekka Savola <pekkas@xxxxxxxxxx>
Date: Tue, 20 May 2003 08:01:32 +0300 (EEST)
Yes, but pretty much nobody is using Cisco without CEF, except in the last mile, low-end devices. -- Pekka Savola "You each name yourselves king, yet the Netcore Oy kingdom bleeds." Systems. Networks
/archives/netdev/2003-05/msg00590.html (10,187 bytes)

333. Re: Route cache performance under stress (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Mon, 19 May 2003 23:46:24 -0700 (PDT)
I found a description of this thing on Cisco's web site. Amusingly it seems to contradict itself, it says that the CEF FIB is fully populated and has a 1-to-1 correspondance to the routing table yet
/archives/netdev/2003-05/msg00593.html (10,281 bytes)

334. Re: Route cache performance under stress (score: 1)
Author: Jamal Hadi <hadi@xxxxxxxxxxxxxxxx>
Date: Tue, 20 May 2003 07:47:44 -0400 (EDT)
so not a GSR thing only feature. At the edges though, wouldnt it be important to do more sexy things than just route based on a destination address? cheers, jamal
/archives/netdev/2003-05/msg00602.html (9,384 bytes)

335. Re: Route cache performance under stress (score: 1)
Author: Pekka Savola <pekkas@xxxxxxxxxx>
Date: Tue, 20 May 2003 14:55:10 +0300 (EEST)
Indeed. For example, policy-based routing (e.g. source address dependent routing) has been claimed to be in the CEF path now (previously it was in the slow path), but I certainly would "like" to be s
/archives/netdev/2003-05/msg00603.html (9,863 bytes)

336. Re: Route cache performance under stress (score: 1)
Author: Jamal Hadi <hadi@xxxxxxxxxxxxxxxx>
Date: Tue, 20 May 2003 08:04:00 -0400 (EDT)
It seems to be done at interupt level sort of like Linux fast switching (not to be confused with CISCO fast switching); however, unlike Linux fast switching which looks up based on dst cache, they do
/archives/netdev/2003-05/msg00604.html (11,380 bytes)

337. Re: Route cache performance under stress (score: 1)
Author: Simon Kirby <sim@xxxxxxxxxxxxx>
Date: Tue, 20 May 2003 17:09:36 -0700
Hmm, I see no difference. I've been using juno-z.101f.c to spam a test box (PIII 800 Mhz, 3C996B/BCM5701), and the box easily chokes when I hit it with my pimpin' 466 MHz Celery (running at 542 MHz)
/archives/netdev/2003-05/msg00626.html (11,413 bytes)

338. Re: Route cache performance under stress (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Tue, 20 May 2003 17:13:58 -0700 (PDT)
Look at the vc[] table and how it uses this in rndip().
/archives/netdev/2003-05/msg00627.html (9,630 bytes)

339. Re: Route cache performance under stress (score: 1)
Author: "David S. Miller" <davem@xxxxxxxxxx>
Date: Tue, 20 May 2003 17:36:07 -0700 (PDT)
Note: It may make sense that we have options to totaly remove the cache lookups if necessary - noone has proved a need for it at this point. There is a need, thinking otherwise is quite a narrow view
/archives/netdev/2003-05/msg00628.html (12,508 bytes)

340. Re: Route cache performance under stress (score: 1)
Author: Jamal Hadi <hadi@xxxxxxxxxxxxxxxx>
Date: Wed, 21 May 2003 09:03:19 -0400 (EDT)
IPIs to synchronize? For packets that are being forwarded or even host bound, why start at routing? This should be done much further below. Not sure how to deal with packets originating from the host
/archives/netdev/2003-05/msg00647.html (15,402 bytes)


This search system is powered by Namazu