cancel
Showing results for 
Search instead for 
Did you mean: 
cancel
1460
Views
5
Helpful
3
Replies

6513 SUP720 CPU high due to VLC player multicast streams

sajism220
Level 1
Level 1

Hi


We are running one linux PC with 3 VLC streams for our company Add, last couple days I notices that our multicast source router, where this VLC PC connected is running on high cpu utilization, and I did the following troubleshooting


After I disconneted this PC form network, the CPU process is normal.


The PC is running on Linux, what could be the probelm.

A-DISTT1#sh processes cpu sorted | exclude 0.00%
CPU utilization for five seconds: 92%/91%; one minute: 25%; five minutes: 22%
PID Runtime(ms)   Invoked      uSecs   5Sec   1Min   5Min TTY Process
395    97350452 389572702        249  0.15%  0.74%  0.69%   0 PIM Process     
155   2974377924264655218          0  0.15%  0.96%  1.57%   0 IP Input        
396    57168908  68962609        828  0.15%  0.39%  0.26%   0 MLSM Process    
   3       12376      2411       5133  0.07%  0.41%  0.47%   1 SSH Process     
350   121028320 392568888        308  0.07%  0.53%  0.53%   0 Port manager pe


A-DISTT2#sh processes cpu sorted | exclude 0.00%
CPU utilization for five seconds: 45%/33%; one minute: 38%; five minutes: 23%
PID Runtime(ms)   Invoked      uSecs   5Sec   1Min   5Min TTY Process
155   347591256 330574202       1051 10.87%  2.20%  1.46%   0 IP Input        
395   154942084 526796334        294  0.47%  0.70%  0.53%   0 PIM Process     
397    34611708  35864894        965  0.15%  0.09%  0.09%   0 MLSM Stat Proces
396    39788256 153516402        259  0.15%  0.21%  0.16%   0 MLSM Process    

A-DISTT1#sh processes cpu history
                                                             
    2222222111112222211111222222222211111111112222211111111111
    5577777999991111166666333332222299999555556666633333555552
100                                                          
90                                                          
80                                                          
70                                                          
60                                                          
50                                                          
40                                                          
30 *******                                   *****          
20 ***********************************************     *****
10 **********************************************************
   0....5....1....1....2....2....3....3....4....4....5....5....
             0    5    0    5    0    5    0    5    0    5   
               CPU% per second (last 60 seconds)
                                                             
    2159989999899998899999999999999889997999989999999999999999
    6247377575427883157615748084586688842776862785125887682872
100    *  ****  ***  *** ** * * ***  **  ****  ***  ****** **
90    ******* ****  ******************* *********************
80    ********************************* *********************
70    *******************************************************
60    *******************************************************
50   ************************************#************#***#**
40   *##*##****###****#*#####*####**#****###****#*##*##*####*
30 * *#######*#########################*####*################
20 # *#######################################################
10 ##########################################################
   0....5....1....1....2....2....3....3....4....4....5....5....
             0    5    0    5    0    5    0    5    0    5   
               CPU% per minute (last 60 minutes)
              * = maximum CPU%   # = average CPU%
                                                                         
    9224236422232233272499999999999999999999999999999999999999999999999999
    8770918257566815646499999999999999999999999999999999999899999999999999
100 *                   **************************************************
90 *                   **************************************************
80 *                   **************************************************
70 *     *          *  **************************************************
60 *     *          *  **************************************************
50 *     *          *  **************************************************
40 *  *  **   *   * * **#################################################
30 *********************#################################################
20 #*******************##################################################
10 ######################################################################
   0....5....1....1....2....2....3....3....4....4....5....5....6....6....7.
             0    5    0    5    0    5    0    5    0    5    0    5    0
                   CPU% per hour (last 72 hours)
                  * = maximum CPU%   # = average CPU%


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


A-DISTT2#sh processes cpu history
                                                             
    111                                                      
    1114444444444333339999911111888884444466666444444444422222
100                                                          
90                                                          
80                                                          
70                                                          
60                                                          
50                                                          
40                                                          
30                                                          
20                                                          
10 ***               *****     *****     *****              
   0....5....1....1....2....2....3....3....4....4....5....5....
             0    5    0    5    0    5    0    5    0    5   
               CPU% per second (last 60 seconds)
                                                             
       9989999999999999999999979999999998889998899998999899999
    9798707677387474683822447660644006864779868968758886289656
100    ** **** ** * ** *    **  *    ***   ***  **** *** *****
90    ** ******************** ********* *************** *****
80    *******************************************************
70    *******************************************************
60    *******************************************************
50    ******************************************#************
40    ##*#####*###***##***###*####**###***###*####**###***##*
30    #######################################################
20    #######################################################
10 ***#######################################################
   0....5....1....1....2....2....3....3....4....4....5....5....
             0    5    0    5    0    5    0    5    0    5   
               CPU% per minute (last 60 minutes)
              * = maximum CPU%   # = average CPU%
                                                                         
    9922417242123212422199999999999999999999999999999999999999999999999999
    9733570000945192502989999999999999999999999999999999999999999999899999
100 **                  **************************************************
90 **                  **************************************************
80 **                  **************************************************
70 **    *             **************************************************
60 **    *             **************************************************
50 **  * *         *   **************************************************
40 **  * * *   *   *   *#################################################
30 #*  * * *   *   *   *#################################################
20 #********************#################################################
10 ###########*##########################################################
   0....5....1....1....2....2....3....3....4....4....5....5....6....6....7.
             0    5    0    5    0    5    0    5    0    5    0    5    0
                   CPU% per hour (last 72 hours)
                  * = maximum CPU%   # = average CPU%

You can analysis by seeing the packet drops


A-DISTT1#sh int | in up | drop

Vlan120 is up, line protocol is up
  Input queue: 0/75/1452/1452 (size/max/drops/flushes); Total output drops: 0
  Input queue: 0/75/0/0 (size/max/drops/flushes); Total output drops: 0


source and destination and where the packet drop is ocurring


A-DISTT1#sh buffers input-interface vlan 120 header


Buffer information for Big buffer at 0x45A30684
  data_area 0x826A144, refcount 1, next 0x5026A528, flags 0x200
  linktype 7 (IP), enctype 1 (ARPA), encsize 14, rxtype 1
  if_input 0x47B08364 (Vlan120), if_output 0x0 (None)
  inputtime 00:00:00.000 (elapsed never)
  outputtime 21w5d (elapsed 21:33:01.704), oqnumber 65535
  datagramstart 0x826A1BA, datagramsize 1358, maximum size 1740
  mac_start 0x826A1BA, addr_start 0x826A1BA, info_start 0x0
  network_start 0x826A1C8, transport_start 0x826A1DC, caller_pc 0x41FFDF6C

  source: 192.168.120.200, destination: 239.232.3.2, id: 0xFA3C, ttl: 1,
  TOS: 0 prot: 17, source port 39598, destination port 5000


Buffer information for Big buffer at 0x45A5FA00
  data_area 0x8324744, refcount 1, next 0x5027A814, flags 0x200
  linktype 7 (IP), enctype 1 (ARPA), encsize 14, rxtype 1
  if_input 0x47B08364 (Vlan120), if_output 0x0 (None)
  inputtime 00:00:00.000 (elapsed never)
  outputtime 17w5d (elapsed 4w0d), oqnumber 65535
  datagramstart 0x83247BA, datagramsize 1358, maximum size 1740
  mac_start 0x83247BA, addr_start 0x83247BA, info_start 0x0
  network_start 0x83247C8, transport_start 0x83247DC, caller_pc 0x41FFDF6C

  source: 192.168.120.200, destination: 239.232.3.3, id: 0x156B, ttl: 1,
  TOS: 0 prot: 17, source port 50428, destination port 5000


A-DISTT2#sh buffers input-interface vlan 120 header


Buffer information for Big buffer at 0x45A76AF0
  data_area 0x839B744, refcount 1, next 0x502883FC, flags 0x200
  linktype 7 (IP), enctype 1 (ARPA), encsize 14, rxtype 1
  if_input 0x52C86C6C (Vlan120), if_output 0x0 (None)
  inputtime 00:00:00.000 (elapsed never)
  outputtime 14w5d (elapsed 21:21:01.044), oqnumber 65535
  datagramstart 0x839B7BA, datagramsize 1358, maximum size 1740
  mac_start 0x839B7BA, addr_start 0x839B7BA, info_start 0x0
  network_start 0x839B7C8, transport_start 0x839B7DC, caller_pc 0x41FFDF6C

  source: 192.168.120.200, destination: 239.232.3.2, id: 0xDDD3, ttl: 1,
  TOS: 0 prot: 17, source port 46214, destination port 5000


Buffer information for Big buffer at 0x45A77208
  data_area 0x839D344, refcount 1, next 0x502827C4, flags 0x200
  linktype 7 (IP), enctype 1 (ARPA), encsize 14, rxtype 1
  if_input 0x52C86C6C (Vlan120), if_output 0x0 (None)
  inputtime 00:00:00.000 (elapsed never)
  outputtime 14w5d (elapsed 16:51:56.084), oqnumber 65535
  datagramstart 0x839D3BA, datagramsize 1358, maximum size 1740
  mac_start 0x839D3BA, addr_start 0x839D3BA, info_start 0x0
  network_start 0x839D3C8, transport_start 0x839D3DC, caller_pc 0x41FFDF6C

  source: 192.168.120.200, destination: 239.232.3.3, id: 0xF9AD, ttl: 1,
  TOS: 0 prot: 17, source port 39010, destination port 5000

3 Replies 3

rsimoni
Cisco Employee
Cisco Employee

Hi there,

the issue is that the mcast streams sourced by the PC have TTL=1

source: 192.168.120.200, destination: 239.232.3.2, id: 0xFA3C, ttl: 1,

...

  source: 192.168.120.200, destination: 239.232.3.3, id: 0x156B, ttl: 1,

...

  source: 192.168.120.200, destination: 239.232.3.2, id: 0xDDD3, ttl: 1,

...

  source: 192.168.120.200, destination: 239.232.3.3, id: 0xF9AD, ttl: 1,

Those packets cannot be handled in hardware, and therefore require CPU assistance > High CPU, as packets with TTL=1 cannot be routed and must be sent to the CPU for it to generate the TTL expired ICMP message.

Easiest solution is to configure your VLC streams to use a TTL>1 in order to avoid TTL expiration in vlan120.

Problem is pretty common on all Cisco switches, not only on cat6k.

regards,

Riccardo

Hi there,

please share with us your comments or flag this question as answered.

Riccardo

along with the above comments, for future reference you might start adding the following line to the interface

storm-control multicast level 10.00 (10 being a %, change to your preference)

good practice for multicast storm control.

Jude

Getting Started

Find answers to your questions by entering keywords or phrases in the Search bar above. New here? Use these resources to familiarize yourself with the community: