[Asterisk-Users] CPU load (was: dimensioning: Where is the CPU vs Asterisk load table)
Erick Perez ha scritto: -And the most important I read was: Keep load under 5 in single CPUs and 10 in dual CPUs (didn't mention dual cores in the article). That seemed to me a lot, so i googled around a little trying to understand the true meaning of those numbers : I'll sum up here what I've found, sparing you the formulae (look for linux load average neil gunther) First of all the sampling of cpu load gives more weight to recent samples, so is better to look at the third value, average in the last 15 minutes, without being scared by high punctual values. Following what the gurus says the value should be kept below 3, or below the number of cpus, given what we are measuring (the number of process ready and waiting to be executed), those values means to me a rule of thumb and make no one wait to do his job. It's not a lot of meaning, is it ? What I suppose we want to say is when I start hearing the calls bad ?, like gamers don't care about FPS but want to know which graphic card I have to buy to frag aliens smoothly ?. I'm not a C programmer so I don't know asterisk internals, what I'll say now maybe is totally nonsense, I leave the sensate replies to the community. If I have an asterisk process waiting, is sensate to state that if it waits too long, when his turn comes he'll drop the packets as the timestamp on them is too old and sound quality will start decreasing ? If this is the case, isn't the important measure not how many are waiting but how long are they waiting ? Since the upper bound to load should be low enough so they don't have to drop . (as a fast reply I can say that I made some calls while my dual 3.0 Ghz was under load 5, and they sounded good, alaw no transcoding) ___ --Bandwidth and Colocation provided by Easynews.com -- Asterisk-Users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
RE: [Asterisk-Users] CPU load (was: dimensioning: Where is the CPU vsAsterisk load table)
-Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Simone Cittadini Sent: Friday, January 13, 2006 12:00 PM Erick Perez ha scritto: -And the most important I read was: Keep load under 5 in single CPUs and 10 in dual CPUs (didn't mention dual cores in the article). That seemed to me a lot, so i googled around a little trying to understand the true meaning of those numbers : I'll sum up here what I've found, sparing you the formulae (look for linux load average neil gunther) First of all the sampling of cpu load gives more weight to recent samples, so is better to look at the third value, average in the last 15 minutes, without being scared by high punctual values. Following what the gurus says the value should be kept below 3, or below the number of cpus, given what we are measuring (the number of process ready and waiting to be executed), those values means to me a rule of thumb and make no one wait to do his job. It's not a lot of meaning, is it ? What I suppose we want to say is when I start hearing the calls bad ?, like gamers don't care about FPS but want to know which graphic card I have to buy to frag aliens smoothly ?. I'm not a C programmer so I don't know asterisk internals, what I'll say now maybe is totally nonsense, I leave the sensate replies to the community. If I have an asterisk process waiting, is sensate to state that if it waits too long, when his turn comes he'll drop the packets as the timestamp on them is too old and sound quality will start decreasing ? If this is the case, isn't the important measure not how many are waiting but how long are they waiting ? Since the upper bound to load should be low enough so they don't have to drop . (as a fast reply I can say that I made some calls while my dual 3.0 Ghz was under load 5, and they sounded good, alaw no transcoding) ___ # What is the relation between I/O wait and load average? by Jeff Layton Linux follows the standard of traditional UNIX and computes its load average as the average number of runnable or running processes (R state), and the number of processes in un-interruptible sleep (D state) over the specified interval. Some other operating systems calculate their load averages simply by looking at processes in R state. On those systems, load average is synonymous with the run queue -- high load averages mean that the box is CPU bound. This is not the case with Linux. On Linux the load average is a measurement of the amount of work being done by the machine (without being specific as to what that work is). This work could reflect a CPU intensive application (compiling a program or encrypting a file), or something I/O intensive (copying a file from disk to disk, or doing a database full table scan), or a combination of the two. Mimmus ___ --Bandwidth and Colocation provided by Easynews.com -- Asterisk-Users mailing list To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
[Asterisk-Users] CPU load
Hi! Here comes a newbi question. I now that transcoding of codecs take a lot of cpu load. But if I want to receive all traffic as IAX and then want to send it out as SIP. Is it the same? Requires a lot of CPU and RAM? Regards Anders Svensson ___ --Bandwidth and Colocation sponsored by Easynews.com -- Asterisk-Users mailing list Asterisk-Users@lists.digium.com http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] CPU load
Anders Svensson a écrit : Hi! Here comes a newbi question. I now that transcoding of codecs take a lot of cpu load. But if I want to receive all traffic as IAX and then want to send it out as SIP. Is it the same? Requires a lot of CPU and RAM? I don't think so. Transcoding means that you are swapping a codec for another (i.e. iLBC - g.729), not swapping protocols. That being said, it might be better to have either SIP or IAX both ways so that you can support REINVITES (or IAX equivalent, 'transfer') and shorten the media path as much as possible. ___ --Bandwidth and Colocation sponsored by Easynews.com -- Asterisk-Users mailing list Asterisk-Users@lists.digium.com http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
[Asterisk-Users] CPU load about at max when it should be idle.
Hello Everyone, I am using this box for asterisk, and it seems that as of the last kernel build I made, when I start asterisk it pins the cpu at 50 percent and the system at 50 percent. When I shut down asterisk, it goes 100% idle. Anyone seen this before? This is a P4-3.0, and I only have 1-2 calls at a time max. Greg top - 13:05:04 up 5 min, 1 user, load average: 0.94, 0.48, 0.19 Tasks: 43 total, 2 running, 41 sleeping, 0 stopped, 0 zombie Cpu(s): 41.3% us, 50.3% sy, 0.0% ni, 0.0% id, 0.0% wa, 8.0% hi, 0.3% si Mem:496936k total,67916k used, 429020k free, 3588k buffers Swap: 1494004k total,0k used, 1494004k free,39304k cached PID USER PR NI VIRT RES SHR S %CPU %MEMTIME+ COMMAND 1 root 16 0 1504 512 1352 S 0.0 0.1 0:00.49 init 2 root 34 19 000 S 0.0 0.0 0:00.00 ksoftirqd/0 3 root 5 -10 000 S 0.0 0.0 0:00.00 events/0 4 root 14 -10 000 S 0.0 0.0 0:00.00 khelper 5 root 5 -10 000 S 0.0 0.0 0:00.00 kblockd/0 38 root 20 0 000 S 0.0 0.0 0:00.00 pdflush 39 root 15 0 000 S 0.0 0.0 0:00.00 pdflush 41 root 15 -10 000 S 0.0 0.0 0:00.00 aio/0 40 root 25 0 000 S 0.0 0.0 0:00.00 kswapd0 42 root 15 0 000 S 0.0 0.0 0:00.00 cifsoplockd 329 root 6 -10 000 S 0.0 0.0 0:00.00 ata/0 334 root 16 0 000 S 0.0 0.0 0:00.00 kseriod 335 root 16 0 000 S 0.0 0.0 0:00.00 i2oevtd ___ Asterisk-Users mailing list Asterisk-Users@lists.digium.com http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
[Asterisk-Users] CPU load 100% when SIP register
Hi,I'm running CVS-head for quite some time now, and util last saturday without serous problems.Last saturday however I updated * again, and now the cpu load goes to a 100%.It seems that the sip register is the problem.when I comment out all sip registers there is no problem, but enabling just one register the cpu goes skyhigh.I've seen there were some modifications to the chan_sip.c.Can anyone confirm the problem?RegardsAndre ___ Asterisk-Users mailing list Asterisk-Users@lists.digium.com http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
RE: [Asterisk-Users] CPU load
What processor? What distro? What kernel(SMP, non-SMP)? What are you doing specifically with your Asterisk system? My personal experience is that I've had high-load crashes anywhere from 6.0 to 8.0 on a SMP P4 Single-processor with HT enabled. The load isn't the best indicator of when a crash is going to occur. when I had high-load crashes it was usually a sudden spike in processor load from under 1.0 to over 6.0 that was then followed quickly by a machine crash. I still haven't found out what causes the spike, but it is rare enough that I cannot test it easily and it isn't too much of a concern. MATT--- -Original Message- From: PBXtech [mailto:[EMAIL PROTECTED] Sent: Thursday, March 04, 2004 12:16 PM To: [EMAIL PROTECTED] Subject: [Asterisk-Users] CPU load At what point in the CPU load does asterisk start to fail? ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] CPU load
On Thursday 04 March 2004 11:16, PBXtech wrote: At what point in the CPU load does asterisk start to fail? CPU load does not measure what you think it does. It is simply the measurement of the average number of processes in a short wait status (i.e. waiting only for CPU time, not for disk access, keyboard input, network, etc.). How CPU load affects the processes running depends strongly on what your processes are actually doing (e.g. the codecs used, concurrency, echo cancellation, etc.) and the resources available (e.g. CPU speed, CPU number, amount of memory, etc.). There is no simple characterization to be had of what CPU load corresponds to poor performance of Asterisk or any other process. In fact, you're far more likely to run into other resource constraints before the amount of time a process spends waiting for the CPU begins to cause performance problems. -Tilghman ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] CPU load
PBXtech wrote: At what point in the CPU load does asterisk start to fail? At the point you start getting blocked calls. Jeremy McNamara ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users