Sign up ×
Server Fault is a question and answer site for system and network administrators. It's 100% free, no registration required.

We host our web-service on a dedicated server. During high-load period, the server returns a time-out error instead of a page very frequently. We have around 170,000 daily requests. However, server has a lot of free memory and the CPU is not loaded at the moment.

I cannot understand why the server works poor.

I have profiled the problem case with tcpdump utility. These are the good and bad sessions traced by tcpdump. The request is the same in both experiments. Good - server returns response. Bad - no response, time-out error.

Do you see why the problem happens from these data? How can I move further to get closer to the source of the error?

I've replaced my real ip address with

---- Bad ----
12:23:36.366292 IP > S 2125316338:2125316338(0) win 8192 <mss 1460,nop,wscale 2,nop,nop,sackOK>
12:23:39.362394 IP > S 2125316338:2125316338(0) win 8192 <mss 1460,nop,wscale 2,nop,nop,sackOK>
12:23:45.365567 IP > S 2125316338:2125316338(0) win 8192 <mss 1460,nop,nop,sackOK>

---- Good ----
12:27:07.632229 IP > S 3581365570:3581365570(0) win 8192 <mss 1460,nop,wscale 2,nop,nop,sackOK>
12:27:10.620946 IP > S 3581365570:3581365570(0) win 8192 <mss 1460,nop,wscale 2,nop,nop,sackOK>
12:27:10.620969 IP > S 2654770980:2654770980(0) ack 3581365571 win 5840 <mss 1460,nop,nop,sackOK,nop,wscale 6>
12:27:10.838747 IP > . ack 1 win 4380
12:27:10.957143 IP > P 1:213(212) ack 1 win 4380
12:27:10.957152 IP > . ack 213 win 108
12:27:10.965543 IP > P 1:630(629) ack 213 win 108
12:27:10.965621 IP > F 630:630(0) ack 213 win 108
12:27:11.183540 IP > . ack 631 win 4222
12:27:11.185657 IP > F 213:213(0) ack 631 win 4222
12:27:11.185663 IP > . ack 214 win 108

Details on the service.

This is a weather reporting service. It is written in Perl, backed by MySQL. The script uses several modules (from CPAN and our own).

The code is relatively simple. The script downloads the weather from another server, converts data format and returns XML response. The weather is cached in MyISAM DB. There is a world locations data-base (INNODB) that can also be requested via the script.

These are the metrics taken during the high-load period.

Average traffic: 2.5MBit/sec

Average packets number: 3300 packets/sec

Hoster: SuperbHosting

OS: Ubuntu

Server parameters: E6300 CONROE 1.86GHZ 2 X 1MB CACHE 1066 1GB DDR2 667MHZ

This is a link to apache configuration file we use

This is server-status report at the moment of high-load There are only 10 Child Servers running out of 120, so enough space for new requests.

Top program snapshot during high-load period.

top - 13:21:29 up 15 days, 18:36,  1 user,  load average: 0.18, 0.19, 0.21
Tasks: 137 total,   1 running, 136 sleeping,   0 stopped,   0 zombie
Cpu(s):  1.8%us,  1.2%sy,  0.0%ni, 92.8%id,  0.7%wa,  0.0%hi,  3.5%si,  0.0%st
Mem:   1033904k total,   590620k used,   443284k free,     6892k buffers
Swap:  3028212k total,    82556k used,  2945656k free,    64156k cached

 4252 mysql     20   0  162m  48m 3352 S    1  4.8 279:01.27 mysqld
14503 www-data  20   0 43280  14m 3824 S    1  1.4   0:00.16 apache2
14577 www-data  20   0 43012  13m 3500 S    1  1.4   0:00.06 apache2
14401 www-data  20   0 45076  17m 4340 S    0  1.8   0:00.46 apache2
14414 www-data  20   0 45516  18m 4344 S    0  1.8   0:00.47 apache2
14420 www-data  20   0 45624  18m 4372 S    0  1.8   0:00.61 apache2
14421 www-data  20   0 45488  18m 4352 S    0  1.8   0:00.42 apache2
14496 www-data  20   0 44820  17m 4328 S    0  1.7   0:00.18 apache2
14510 www-data  20   0 45216  17m 4300 S    0  1.8   0:00.62 apache2
    1 root      20   0  2844  456  404 S    0  0.0   0:05.24 init
    2 root      15  -5     0    0    0 S    0  0.0   0:00.00 kthreadd
    3 root      RT  -5     0    0    0 S    0  0.0   0:00.24 migration/0
    4 root      15  -5     0    0    0 S    0  0.0  32:28.85 ksoftirqd/0
    5 root      RT  -5     0    0    0 S    0  0.0   0:00.77 watchdog/0
    6 root      RT  -5     0    0    0 S    0  0.0   0:00.15 migration/1
    7 root      15  -5     0    0    0 S    0  0.0   0:03.07 ksoftirqd/1
    8 root      RT  -5     0    0    0 S    0  0.0   0:00.63 watchdog/1
share|improve this question

migrated from Jan 20 '10 at 4:35

This question came from our site for professional and enthusiast programmers.

Should be in Serverfault – Chathuranga Chandrasekara Jan 18 '10 at 10:46

5 Answers 5

Your MySQL server seems to be working hard at times (but not in your screenshot), because of the high CPU time. Check which queries are run by issuing SHOW PROCCESSLIST; in the MySQL prompt.

Also try to activate the server-status page in Apache. With ExtendedStatus On it will give you information about which pages are loading at that time and you can see how many open "slots" you have left in Apache.

The default in Apache mpm-prefork is to have about 250 processes at most, meaning you can handle 250 simultaneous file downloads. This can cause a lot of trouble if you have many visitors, especially if you have KeepAlive activated. You will see in your server-status page if this is your problem.

share|improve this answer
Emil, thank you much for the response! 1. This is the process-list from MySQL, unfortunately, it does not tell me anything, just a bunch of processes that sleep. Is there any sign of a trouble? What was the indication of MySQL working hard in the "top" output for you? I will try to investigate server-status now, and then get back with results. – par Jan 18 '10 at 11:04
The high CPU time means it has worked hard, but if there are only sleeping threads there seems to be some other bottleneck. – Emil Vikström Jan 18 '10 at 11:56
Ah! you mean this time "279:01.27", thanks, I have only noticed 1% CPU consumption at the moment. MySQL has probably worked hard when I run reports on it. – par Jan 18 '10 at 14:27
I have found out that when the response is missing the REQUEST is not logged by Apache. Is it because the request does not reach the server somehow? How could it happen? I have updated the question with server-status report taken right after time-out error. There are only 10 Child Servers running out of 120, so enough space for new requests. I'm lost :-( – par Jan 18 '10 at 18:35
Hi, Emil! I have profiled server network traffic with tcpdump. See the update to the question. Can you tell from the dumps why the server does not respond? – par Jan 19 '10 at 10:08

There are a whole host (<--pun) of reasons why Apache might be unresponsive. As a starting point I'd look at server-status assuming you have mod_status enabled and see how many processes are running and whether they look busy or not. This page is a good first place to look through things you could try if it turns out that you have child process issues.

share|improve this answer

The top screenshot shows your MySQL server is not working hard at all! (Sorry Emil - but you need to read that more carefully or learn some more about top).

And there's only 8 apache processes listed.

And the load average is 0.2 with 93% cpu idle - this machine is sitting doing nothing.

Half the config is missing from the link posted, but it looks like its pre-forked.

My first guess is that the MaxServers is set to some wacky value like 10 (depending on what your application looks like, it should be in the region of 100-200).

You might also want to check for stupid stuff like reverse lookups on incoming connections or mod_ident installed (OK these aren't always stupid - but should be used with extreme caustion).

Certainly installing mod_status and enabling the extended status will give a much better picture of what's going on here.


share|improve this answer
symcbean, thank you much, a good answer. I have posted the link to the whole Apache config, I just checked the link again, it is complete. I have added the service descripton. Basically this is Perl+MySQL=XML We do not change MaxServers in the configuration file. Ah, unfortunately I don't know anything about "reverse lookups on incoming connections". mod_ident is certainly not installed. I have installed mod_status and profiled with it. See the link to snapshot in the question body. – par Jan 20 '10 at 9:43
Still don't know where the problem is coming from :-( – par Jan 20 '10 at 9:45

Karl B is right apache status page will help you a lot. Check if the request is not logged in errorlog. It could be that the number of active request has reached the maximum number specified in apache configuration file. See if MaxClients is bigger than:

sudo netstat -tnp|egrep -c 'apache|http'
share|improve this answer
The number of MaxClients is 120. At the moment of error, there are 37 active clients. And no error messages in the error-log. So this version is excluded. – par Jan 20 '10 at 9:38

Can you try flood ping (ping -f) the server? I would guess there is some hardware problem regarding the network connection as you server does not seem to answer the SYN packets fast enough.

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.