Testing via localhost? #7
Comments
|
oops, read the doc! Pretty big differnce in up vs down tho. No simultaneous test? davet@milliways:~/git/obudpst$ ./udpst -4 -u localhost |
|
Hi Dave, thanks for running some tests!
I’ll reply to each point as we go...
Al
From: Dave Täht ***@***.***>
Sent: Monday, October 31, 2022 11:53 PM
To: BroadbandForum/obudpst ***@***.***>
Cc: Subscribed ***@***.***>
Subject: Re: [BroadbandForum/obudpst] Testing via localhost? (Issue #7)
oops, read the doc!
[acm] 😊 I think this is a weakness of many tools, we don’t document as well as we might for new users, especially when there are 30-40 options...
Downstream Summary Delivered(%): 98.82, Loss/OoO/Dup: 7967/0/0, OWDVar(ms): 0/6/19, RTTVar(ms): 0-7, Mbps(L3/IP): 1036.50
Downstream Minimum One-Way Delay(ms): -7 [w/clock difference], Round-Trip Time(ms): 0
Downstream Maximum Mbps(L3/IP): 2328.60, Mbps(L2/Eth): 2339.30, Mbps(L1/Eth): 2357.65, Mbps(L1/Eth+VLAN): 2360.70
Pretty big differnce in up vs down tho. No simultaneous test?
[acm] I see that: 2.3 Gig down vs 5.1 Gig up. One thing I see is that the received rate was continuing to climb in the upstream test: still climbing at 10 seconds. I think that using the * -A C * option might help. The Type C algorithm reaches 1Gbps faster than the default “B” and is more dynamic responding to impairments, so we may see a higher max for both upstream and downstream.
I’ll investigate this on other hosts.
Also, we don’t have a simultaneous test because we send status feedback messages (in the reverse direction of the load) that convey measurements or sending rate commands – all critical info to the load adjustment algorithm. If we were congesting *both* directions of transmission, lots of feedback status messages would be lost.
***@***.***:~/git/obudpst$ ./udpst -4 -u localhost
UDP Speed Test
Software Ver: 7.5.0, Protocol Ver: 9, Built: Oct 31 2022 20:39:49
Mode: Client, Payload Default[Max]: 1222[8972], Authentication: Available, SendMMsg(): Available
Upstream Test Int(sec): 10, DelayVar Thresh(ms): 30-90 [RTT], Trial Int(ms): 50, Ignore OoO/Dup: Disabled, Payload: zeroes,
SendRate Index: , Cong. Thresh: 3, High-Speed Delta: 10, SeqError Thresh: 10, Algo: B, IPv4 ToS: 0
Sub-Interval1<sec>: 1, Delivered(%): 100.00, Loss/OoO/Dup: 0/0/0, OWDVar(ms): 0/0/3, RTTVar(ms): 0-1, Mbps(L3/IP): 93.47
Sub-Interval2<sec>: 2, Delivered(%): 100.00, Loss/OoO/Dup: 1/0/0, OWDVar(ms): 0/0/6, RTTVar(ms): 0-2, Mbps(L3/IP): 284.74
Sub-Interval3<sec>: 3, Delivered(%): 100.00, Loss/OoO/Dup: 0/0/0, OWDVar(ms): 3/5/18, RTTVar(ms): 0-2, Mbps(L3/IP): 382.02
Sub-Interval4<sec>: 4, Delivered(%): 100.00, Loss/OoO/Dup: 0/0/0, OWDVar(ms): 4/5/17, RTTVar(ms): 0-2, Mbps(L3/IP): 639.91
Sub-Interval5<sec>: 5, Delivered(%): 99.36, Loss/OoO/Dup: 379/56/0, OWDVar(ms): 1/5/16, RTTVar(ms): 0-6, Mbps(L3/IP): 580.67
Sub-Interval6<sec>: 6, Delivered(%): 99.00, Loss/OoO/Dup: 828/0/0, OWDVar(ms): 0/11/24, RTTVar(ms): 0-4, Mbps(L3/IP): 945.22
Sub-Interval7<sec>: 7, Delivered(%): 96.78, Loss/OoO/Dup: 3045/0/0, OWDVar(ms): 7/12/18, RTTVar(ms): 0-0, Mbps(L3/IP): 1645.59
Sub-Interval8<sec>: 8, Delivered(%): 98.46, Loss/OoO/Dup: 1332/0/0, OWDVar(ms): 5/12/18, RTTVar(ms): 0-1, Mbps(L3/IP): 1949.57
Sub-Interval9<sec>: 9, Delivered(%): 99.59, Loss/OoO/Dup: 377/0/0, OWDVar(ms): 11/12/22, RTTVar(ms): 0-3, Mbps(L3/IP): 3216.76
Sub-Interval10<sec>: 10, Delivered(%): 99.95, Loss/OoO/Dup: 54/0/0, OWDVar(ms): 11/12/14, RTTVar(ms): 0-0, Mbps(L3/IP): 5058.65
Upstream Summary Delivered(%): 99.08, Loss/OoO/Dup: 6016/56/0, OWDVar(ms): 0/7/24, RTTVar(ms): 0-6, Mbps(L3/IP): 1479.66
Upstream Minimum One-Way Delay(ms): -12 [w/clock difference], Round-Trip Time(ms): 0
Upstream Maximum Mbps(L3/IP): 5058.65, Mbps(L2/Eth): 5069.67, Mbps(L1/Eth): 5088.57, Mbps(L1/Eth+VLAN): 5091.72
—
Reply to this email directly, view it on GitHub<https://urldefense.com/v3/__https:/github.com/BroadbandForum/obudpst/issues/7*issuecomment-1297988809__;Iw!!BhdT!lzpifzwPGhJkgMYpyD1XNP41aroFjn3vNp72IRXuEyILcS3WaJ_CdLZs5dgKe65kVxz8-q2TA6Qjwe6doMoIxg$>, or unsubscribe<https://urldefense.com/v3/__https:/github.com/notifications/unsubscribe-auth/ACILYGH3BRPANKHX4J3XV6LWGCH2TANCNFSM6AAAAAARTVZ2Z4__;!!BhdT!lzpifzwPGhJkgMYpyD1XNP41aroFjn3vNp72IRXuEyILcS3WaJ_CdLZs5dgKe65kVxz8-q2TA6Qjwe6vMRmcqQ$>.
You are receiving this because you are subscribed to this thread.Message ID: ***@***.******@***.***>>
|
First thing I tried
./udpst localhost
UDP Speed Test
Software Ver: 7.5.0, Protocol Ver: 8-9, Built: Oct 31 2022 20:39:49
Mode: Server, Payload Default[Max]: 1222[8972], Authentication: Available, SendMMsg(): Available
BIND ERROR: Address already in use (127.0.0.1:25000)
The text was updated successfully, but these errors were encountered: