Results 1 to 3 of 3

Thread: TCP Optimizer issue

  1. #1
    Junior Member
    Join Date
    Jan 2006
    Posts
    2

    Exclamation TCP Optimizer issue

    Ok I used the tcp optimizer except for RWIN values being too high this is a great software.. I have posted the test results below for the rwin values and you will notice NOT a single speed tests was faster at the 256960 versus 128480. All tests were faster with 128480 and I have also read this same thing with other users that have 10+ mb connections like me. So I'll let the results speak for themselves. Also I tried results with the mostly recommended setting of 64240 setting and I did see less stalling during the speedtest vs 128480 but at 256960 much more stalling and lower results. Maybe TCP Optimizer should consider making the highest value more closer to 128480 and nowhere as near as high as the 10mb default setting is.

    --------------------------------------------------------------------------

    rwin at 128480

    Dallas, Tx
    Download Speed: 8202 kbps (1025.3 KB/sec transfer rate)
    Upload Speed: 955 kbps (119.4 KB/sec transfer rate)

    Seattle, WA
    Download Speed: 7478 kbps (934.8 KB/sec transfer rate)
    Upload Speed: 953 kbps (119.1 KB/sec transfer rate)

    San Francisco, CA
    Download Speed: 5196 kbps (649.5 KB/sec transfer rate)
    Upload Speed: 950 kbps (118.8 KB/sec transfer rate)

    Los Angeles, CA
    Download Speed: 8148 kbps (1018.5 KB/sec transfer rate)
    Upload Speed: 953 kbps (119.1 KB/sec transfer rate)

    Atlanta, GA
    Download Speed: 9557 kbps (1194.6 KB/sec transfer rate)
    Upload Speed: 956 kbps (119.5 KB/sec transfer rate)

    Service: isdndslcablewirelesssatellite Speed (advertised) kbit/s: Operating System: win95win98win98SEwinMEwinNTwin2kwinXPMacLinuxFBSDSolaris Connection: normalwinpoetwinXPpppoerouterpppoeraspppoeenternetpppoA


    1. Your Tweakable Settings:
    Receive Window (RWIN): 128480
    Window Scaling: 1
    Path MTU Discovery: ON
    RFC1323 Window Scaling: ON
    RFC1323 Time Stamping: OFF
    Selective Acks: ON
    MSS requested: 1460
    TTL:
    (less any hops behind firewall)
    65
    TTL remaining: 49
    TOS/TOS subfield: 0
    TOS/Flags:

    2. Test 84681 byte download
    Actual data bytes sent: 84681
    Actual data packets: 59
    Max packet sent (MTU): 1500
    Max packet recd (MTU): 1500
    Retransmitted data packets: 0
    sacks you sent: 1
    pushed data pkts: 12
    data transmit time: 0.519 secs
    our max idletime: 1226.0 ms
    transfer rate: 47001 bytes/sec
    transfer rate: 376 kbits/sec
    This is not a speed test!
    transfer efficiency: 100%


    3. ICMP (ping) check
    Minimum ping: 46.27 ms
    Maximum ping: 50.10 ms
    Ping stability:
    46.66 46.28 50.10 47.22 46.93 46.27 46.33 46.27 46.34 47.92




    Notes and recommendations:
    RWIN is in range
    Looking good

    Notes and recommendations:
    Good data stream (no/few rexmits)
    1 second+ stall detected (FAQ #1606)

    Notes and recommendations:
    Looking good

    ------------------------------------------------------------------
    rwin at 256960

    Dallas, Tx
    Download Speed: 8523 kbps (1065.4 KB/sec transfer rate)
    Upload Speed: 955 kbps (119.4 KB/sec transfer rate)

    Seattle, WA
    Download Speed: 7420 kbps (927.5 KB/sec transfer rate)
    Upload Speed: 953 kbps (119.1 KB/sec transfer rate)

    San Francisco, CA
    Download Speed: 5071 kbps (633.9 KB/sec transfer rate)
    Upload Speed: 952 kbps (119 KB/sec transfer rate)

    Los Angeles, CA
    Download Speed: 5224 kbps (653 KB/sec transfer rate)
    Upload Speed: 951 kbps (118.9 KB/sec transfer rate)

    Atlanta, GA
    Download Speed: 9566 kbps (1195.8 KB/sec transfer rate)
    Upload Speed: 956 kbps (119.5 KB/sec transfer rate)

    Service: isdndslcablewirelesssatellite Speed (advertised) kbit/s: Operating System: win95win98win98SEwinMEwinNTwin2kwinXPMacLinuxFBSDSolaris Connection: normalwinpoetwinXPpppoerouterpppoeraspppoeenternetpppoA


    1. Your Tweakable Settings:
    Receive Window (RWIN): 256960
    Window Scaling: 2
    Path MTU Discovery: ON
    RFC1323 Window Scaling: ON
    RFC1323 Time Stamping: OFF
    Selective Acks: ON
    MSS requested: 1460
    TTL:
    (less any hops behind firewall)
    65
    TTL remaining: 49
    TOS/TOS subfield: 0
    TOS/Flags:

    2. Test 86141 byte download
    Actual data bytes sent: 86141
    Actual data packets: 60
    Max packet sent (MTU): 1500
    Max packet recd (MTU): 1500
    Retransmitted data packets: 0
    sacks you sent: 1
    pushed data pkts: 10
    data transmit time: 0.453 secs
    our max idletime: 1714.0 ms
    transfer rate: 38807 bytes/sec
    transfer rate: 310 kbits/sec
    This is not a speed test!
    transfer efficiency: 100%


    3. ICMP (ping) check
    Minimum ping: 45.46 ms
    Maximum ping: 51.26 ms
    Ping stability:
    51.26 45.63 46.35 46.52 46.80 47.13 45.46 47.10 46.09 45.99




    Notes and recommendations:
    Choose RWIN between 94900 and 251120 (FAQ #586)
    download/use DRTCP .. (FAQ #578)
    Read the tweak FAQ

    Notes and recommendations:
    Good data stream (no/few rexmits)
    1 second+ stall detected (FAQ #1606)

    Notes and recommendations:
    Looking good

  2. #2
    Elite Member trogers's Avatar
    Join Date
    Jan 2005
    Location
    Bangkok, Thailand
    Posts
    12,323

    No Pertfect Setting

    I am located in South East Asia and frequently surf to Europe amd USA.

    From numerous trials and errors of tweaking, I have saved and used 3 different settings with the use of Cablenut Aduster to suit network traffic conditions for Light, Medium and Heavy.

    Tweaking is by TCP Optimizer and then Cablenut Adjuster.

    Testing site is fixed at this link:

    http://nitro.ucsc.edu/

    My bandwidth is PPPoE 1024/512 Kbps.

    Here are the summarized readings of the 3 different settings and test results carried out within the last 15 mintues.

    Light Traffic Setting

    TCP options string = 020405a40103030201010402
    MTU = 1484
    MTU is somewhat optimized for broadband. If you're not on a PPPoE DSL connection that limits packet size, consider increasing your MTU to 1500 for optimal throughput.
    MSS = 1444
    Maximum useful data in each packet = 1444, which equals MSS.
    Default Receive Window (RWIN) = 255552
    RWIN Scaling (RFC1323) = 2 bits (scale factor of 4)
    Unscaled Receive Window = 63888

    For optimum performance, consider changing RWIN to a multiple of MSS.
    Other values for RWIN that might work well with your current MTU/MSS:
    508288 (MSS x 44 * scale factor of 8)
    254144 (MSS x 44 * scale factor of 4)
    127072 (MSS x 44 * scale factor of 2)
    63536 (MSS x 44)
    bandwidth * delay product (Note this is not a speed test):

    Your RcvWindow limits you to: 10222.08 kbps (1277.76 KBytes/s) @ 200ms
    Your RcvWindow limits you to: 4088.832 kbps (511.104 KBytes/s) @ 500ms
    MTU Discovery (RFC1191) = ON
    Time to live left = 46 hops

    TTL value is ok.
    Timestamps (RFC1323) = OFF
    Selective Acknowledgements (RFC2018) = ON
    IP type of service field (RFC1349) = 11110000 (240)

    TCP/Web100 Network Diagnostic Tool v5.3.3d
    click START to begin
    Checking for Middleboxes . . . . . . . . . . . . . . . . . . Done
    running 10s outbound test (client to server) . . . . . 403.17Kb/s
    running 10s inbound test (server to client) . . . . . . 65.16kb/s
    Your PC is connected to a Cable/DSL modem
    Information: Other network traffic is congesting the link

    ------ Web100 Detailed Analysis ------
    Cable modem/DSL/T1 link found.
    Link set to Full Duplex mode
    Information: throughput is limited by other network traffic.
    Good network cable(s) found
    Normal duplex operation found.

    Web100 reports the Round trip time = 479.6 msec; the Packet size = 1444 Bytes; and
    There were 5 packets retransmitted, 38 duplicate acks received, and 18 SACK blocks received
    The connection was idle 0 seconds (0%) of the time
    This connection is network limited 99.98% of the time.
    Excessive packet loss is impacting your performance, check the auto-negotiate function on your local PC and network switch

    Web100 reports TCP negotiated the optional Performance Settings to:
    RFC 2018 Selective Acknowledgment: ON
    RFC 896 Nagle Algorithm: ON
    RFC 3168 Explicit Congestion Notification: OFF
    RFC 1323 Time Stamping: OFF
    RFC 1323 Window Scaling: ON
    Information: Network Middlebox is modifying MSS variable
    Server IP addresses are preserved End-to-End
    Client IP addresses are preserved End-to-End

    Medium Traffic Setting

    TCP options string = 020405a40103030101010402
    MTU = 1484
    MTU is somewhat optimized for broadband. If you're not on a PPPoE DSL connection that limits packet size, consider increasing your MTU to 1500 for optimal throughput.
    MSS = 1444
    Maximum useful data in each packet = 1444, which equals MSS.
    Default Receive Window (RWIN) = 127776
    RWIN Scaling (RFC1323) = 1 bits (scale factor of 2)
    Unscaled Receive Window = 63888

    For optimum performance, consider changing RWIN to a multiple of MSS.
    Other values for RWIN that might work well with your current MTU/MSS:
    508288 (MSS x 44 * scale factor of 8)
    254144 (MSS x 44 * scale factor of 4)
    127072 (MSS x 44 * scale factor of 2)
    63536 (MSS x 44)
    bandwidth * delay product (Note this is not a speed test):

    Your RcvWindow limits you to: 5111.04 kbps (638.88 KBytes/s) @ 200ms
    Your RcvWindow limits you to: 2044.416 kbps (255.552 KBytes/s) @ 500ms
    MTU Discovery (RFC1191) = ON
    Time to live left = 48 hops

    TTL value is ok.
    Timestamps (RFC1323) = OFF
    Selective Acknowledgements (RFC2018) = ON
    IP type of service field (RFC1349) = 11110000 (240)

    TCP/Web100 Network Diagnostic Tool v5.3.3d
    click START to begin
    Checking for Middleboxes . . . . . . . . . . . . . . . . . . Done
    running 10s outbound test (client to server) . . . . . 431.20Kb/s
    running 10s inbound test (server to client) . . . . . . 413.53kb/s
    Your PC is connected to a Cable/DSL modem
    Information: Other network traffic is congesting the link

    ------ Web100 Detailed Analysis ------
    Cable modem/DSL/T1 link found.
    Link set to Full Duplex mode
    Information: throughput is limited by other network traffic.
    Good network cable(s) found
    Normal duplex operation found.

    Web100 reports the Round trip time = 404.89 msec; the Packet size = 1444 Bytes; and
    There were 39 packets retransmitted, 230 duplicate acks received, and 130 SACK blocks received
    The connection was idle 0 seconds (0%) of the time
    This connection is network limited 99.98% of the time.

    Web100 reports TCP negotiated the optional Performance Settings to:
    RFC 2018 Selective Acknowledgment: ON
    RFC 896 Nagle Algorithm: ON
    RFC 3168 Explicit Congestion Notification: OFF
    RFC 1323 Time Stamping: OFF
    RFC 1323 Window Scaling: ON
    Information: Network Middlebox is modifying MSS variable
    Server IP addresses are preserved End-to-End
    Client IP addresses are preserved End-to-End

    Heavy Traffic Setting

    TCP options string = 020405a40103030001010402
    MTU = 1484
    MTU is somewhat optimized for broadband. If you're not on a PPPoE DSL connection that limits packet size, consider increasing your MTU to 1500 for optimal throughput.
    MSS = 1444
    Maximum useful data in each packet = 1444, which equals MSS.
    Default Receive Window (RWIN) = 63888
    RWIN Scaling (RFC1323) = 0 bits
    Unscaled Receive Window = 63888

    For optimum performance, consider changing RWIN to a multiple of MSS.
    Other values for RWIN that might work well with your current MTU/MSS:
    508288 (MSS x 44 * scale factor of 8)
    254144 (MSS x 44 * scale factor of 4)
    127072 (MSS x 44 * scale factor of 2)
    63536 (MSS x 44)
    bandwidth * delay product (Note this is not a speed test):

    Your RcvWindow limits you to: 2555.52 kbps (319.44 KBytes/s) @ 200ms
    Your RcvWindow limits you to: 1022.208 kbps (127.776 KBytes/s) @ 500ms
    MTU Discovery (RFC1191) = ON
    Time to live left = 46 hops

    TTL value is ok.
    Timestamps (RFC1323) = OFF
    Selective Acknowledgements (RFC2018) = ON
    IP type of service field (RFC1349) = 11110000 (240)

    TCP/Web100 Network Diagnostic Tool v5.3.3d
    click START to begin
    Checking for Middleboxes . . . . . . . . . . . . . . . . . . Done
    running 10s outbound test (client to server) . . . . . 447.32Kb/s
    running 10s inbound test (server to client) . . . . . . 158.10kb/s
    Your PC is connected to a Cable/DSL modem
    Information: Other network traffic is congesting the link

    ------ Web100 Detailed Analysis ------
    Cable modem/DSL/T1 link found.
    Link set to Full Duplex mode
    Information: throughput is limited by other network traffic.
    Good network cable(s) found
    Normal duplex operation found.

    Web100 reports the Round trip time = 285.15 msec; the Packet size = 1444 Bytes; and
    There were 7 packets retransmitted, 81 duplicate acks received, and 34 SACK blocks received
    The connection stalled 1 times due to packet loss
    The connection was idle 0.52 seconds (5.2%) of the time
    This connection is network limited 99.98% of the time.
    Excessive packet loss is impacting your performance, check the auto-negotiate function on your local PC and network switch

    Web100 reports TCP negotiated the optional Performance Settings to:
    RFC 2018 Selective Acknowledgment: ON
    RFC 896 Nagle Algorithm: ON
    RFC 3168 Explicit Congestion Notification: OFF
    RFC 1323 Time Stamping: OFF
    RFC 1323 Window Scaling: OFF
    Information: Network Middlebox is modifying MSS variable
    Server IP addresses are preserved End-to-End
    Client IP addresses are preserved End-to-End

    When I log onto the net, the first thing I will do is to carry out a test and then may readjust my Tweak setting and reboot to suit traffic conditions.

    This will enable me to have a few hours of satisfactory browsing speed.

    When speed slows, I carry out another test and make tweak adjustments and reboot accordingly.

    There is no perfect setting.

  3. #3
    Administrator Philip's Avatar
    Join Date
    May 1999
    Location
    Jacksonville, Florida, United States
    Posts
    10,558
    Blog Entries
    6
    256960 RWIN is much more suitable for a 10Mbps connection. Try to test by downloading multiple large files from fast, but distant servers and you will get different results than any "speed test". Web-based speed tests usualy use smaller test files, and have bandwidth limits that you are hitting with a 10MBps pipe...

    The bandwidth-delay product is the ultimate law that governs and is the upper bound of your possible speed. If you use the maximum anticipated latency and maximum possible throughput in the equation, you WILL get the approximate RWIN range you should be using. The TCP Optimizer reccomendations are based on this calculation, but they go a step further - optimizing the unscaled RWIN value to a high number as well.

Similar Threads

  1. TCP Optimizer WOW
    By queen in forum Broadband Tweaks Help
    Replies: 32
    Last Post: 02-20-08, 03:09 PM
  2. TCP Optimizer version 2.0.2 Beta
    By Philip in forum Broadband Tweaks Help
    Replies: 25
    Last Post: 11-15-05, 04:22 PM
  3. TCP Optimizer version 2.0.1 released
    By Philip in forum Broadband Tweaks Help
    Replies: 16
    Last Post: 10-12-05, 07:56 AM
  4. TCP Optimizer version 2.0.2 RC2 (10/06/2005)
    By Philip in forum Broadband Tweaks Help
    Replies: 8
    Last Post: 10-07-05, 08:47 AM
  5. TCP Optimizer version 2.0.2 RC1 (10/03/2005)
    By Philip in forum Broadband Tweaks Help
    Replies: 5
    Last Post: 10-06-05, 03:18 PM

Bookmarks

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •