[dtrace-discuss] UDP socket buffer overflow monitor

Hi All, I want to monitor the frequency of the socket buffer (receive) overflow during a data transfer over UDP. Is there a way to do this using dtrace or any other solaris tool? Thank you, Vishal -- This message posted from opensolaris.org ___

Re: [dtrace-discuss] UDP socket buffer overflow monitor

[b]More precisely, I want to monitor the number of packets that are in the socket buffer during the data transfer.[/b] This will give me a better picture of the state of the socket buffer than just finding out the frequency of buffer overflow. Can this be done using dtrace. Thank you. -- This

[dtrace-discuss] dtrace udp socket buffer

Hi, Is there a way to determine the number of packets/bytes read from the socket buffer per read using dtrace? Thanks, Vish -- This message posted from opensolaris.org ___ dtrace-discuss mailing list dtrace-discuss@opensolaris.org

Re: [dtrace-discuss] dtrace udp socket buffer

Also, I need to find out the time that was taken to read those many packets from the buffer. Thanks, Vish -- This message posted from opensolaris.org ___ dtrace-discuss mailing list dtrace-discuss@opensolaris.org

[dtrace-discuss] sched provider

Hi All, I used the following script from the dtrace manual to measure how long a particular process runs on the cpu. Modified it to look at the exact timestamps: [i] sched:::on-cpu { self-ts = timestamp; printf(on=%d\n, self-ts) } sched:::off-cpu /self-ts/ { printf(off=%d\n, timestamp) self-ts

[dtrace-discuss] UDP Packet processing

Hi, I have a simple socket application which receives UDP packets and writes them to a disk. What I am trying to do is to figure out the average time that a UDP packet spends on the CPU before being written to the disk. The CPU time would essentially boil down to the packet processing

[dtrace-discuss] CPU time and IO time

Hi, I am trying to characterize some benchmark programs using dtrace. The first step is to determine the time that a program spends on the CPU (doing computations), and the time it spends doing IO. The cpu time can be easily determined using the on-cpu and off-cpu probes. I am having

[dtrace-discuss] File name not being displayed.

I found the script below in the dtrace manual: #pragma D option quiet BEGIN { printf(%10s %58s %2s %7s\n, DEVICE, FILE, RW, MS); } io:::start { start[args[0]-b_edev, args[0]-b_blkno] = timestamp; } io:::done /start[args[0]-b_edev, args[0]-b_blkno]/ { this-elapsed = timestamp -

Re: [dtrace-discuss] File name not being displayed.

Hi Pramod, I am using the ZFS filesystem on OpenSolaris. The thing is that the file that my program is reading is 2.5 GB in size, which is greater than the RAM size. Will caching still take place? And when I run the script, I can see that the number of reads that it

[dtrace-discuss] disk service time using dtrace

Hi, I am trying to figure out the service time distribution for disk reads using dtrace. I am using Solaris Community edition, with UFS as the filesystem. I have written simple scripts which use fbt, but am not getting any consistency in my results. The biggest hindrance seems to be