The tag has no wiki summary.

learn more… | top users | synonyms

0
votes
0answers
7 views

Aggregate syscall time on OSX / strace -c equivalent [on hold]

I have been using strace -c on my linux box a lot. It gives me an overall idea, on which system call the program spending too much time, (reading/writing/network connection) Eg: ...
1
vote
0answers
68 views

Apache Timeout / Deadlock When MaxClients Reached

I'm running Apache 2.2, preform MPM, on Debian Squeeze with mod_php (PHP 5.3), listening on several ports (with memcached running on the same machine). Over the past 6 weeks or so, I've been ...
0
votes
1answer
39 views

Intentionally stop a process from responding

Is there any way to intentionally prevent a process from responding - ie. not close or kill it, but stop it dead in it's track, so it immediately stops processing anything? I've often found myself ...
1
vote
0answers
93 views

strace not showing anything for thread at 100% 'system' CPU

I'm having difficulty with my Python app going to 100% 'system' CPU time across multiple threads for up to 10+ seconds. My (limited) understanding is that 'system' CPU time is time spent in the ...
0
votes
0answers
102 views

Linux high iowait without block device activity

I'm having a hard time figure out the reason cause high iowait on my server. top: %Cpu(s): : 30.0 us, 5.4 sy, 0.0 ni, 53.9 id, 10.1 wa, 0.0 hi, 0.7 si, 0.0 st iostat: Device: ...
1
vote
2answers
609 views

tail -f not following log file in Docker container

I am seeing some strange behavior running the tail -f command inside a Docker container in CoreOS. There are a number of variables I can think of that may be contributing to the problem but I am not ...
0
votes
1answer
115 views

strange strace output of httpd process of apache running django with mod_wsgi

I have about 12 httpd processes running for an RHEL aws box that no one is hitting in the browser (shared team dev box). These processes together are consuming over 1.8 GB on the dev box, and I have ...
0
votes
0answers
68 views

SystemTap - filter own syscalls (system-wide trace)

I want to write simple strace-like script using SystemTap. Main goal is to catch only some system calls (like open, close, read, write etc.) for all processes in system. (Can't do that with strace ...
0
votes
0answers
151 views

Why doesn't Linux strace show activity on a particular socket from java

This has been confusing me for a while now. I have a Java app (specifically, Glassfish, 3.1.2.2). I want to see how it handles the main HTTP socket that is used to for serving HTTP requests. I can ...
0
votes
0answers
99 views

Strace php script - ERESTART_RESTARTBLOCK (To be restarted)

I am trying to troubleshoot a WordPress installation that is loading the front page very slow. I straced the index.php file with the -T option to see where the delay occurs and it pauses 2 times for ...
3
votes
1answer
277 views

Apache stops communicating with memcache after creating too many vhosts

I've noticed a very peculiar problem with Apache. I have a very high number of virtual hosts set up - it's around 501. Problems started occuring after vhost number 493. First 493 vhosts work as ...
1
vote
2answers
153 views

TCP packet which is absent in strace log

Can somebody give me ideas about following situation (Linux 2.6.18-348.4.1.el5 ): At some point tcpdump shows [FIN, ACK] packet sent from server port to local client strace log shows no socket ...
4
votes
1answer
540 views

strace shows long time reading from mysql socket - mysql takes long time to execute query?

My Apache server takes long time to process request. I attached strace to it and can see the two following delays: 1) Very critical (143 seconds to process) 1335 0.000037 write(16, ...
0
votes
1answer
209 views

upstart - supervisord fork count > 2 (can;t get supervisord to start on boot)

i'm trying to use upstart so that supervisord starts automatically at boot. my supervisord is in a virtual environment. I've configured it to run in foreground mode with -n param and it works if ...
0
votes
2answers
113 views

process works under strace but not normally

I have a process - a perl script - that does: while true check a POP account on a server on the lan process any email found write logs - messages found, actions taken, errors sleep ...
0
votes
1answer
37 views

How to watch a file, who accesses or uses [duplicate]

I am looking forward a way to watch a file to get following information Which process does open, read, write it? When? Result. (e.g. can they write on it, or can they read it, etc.) Strace helps ...
0
votes
1answer
100 views

Tracing system calls is slow on a KVM VPS?

I run a website on a KVM VPS and I noticed that processes appear to run extremely slowly when being traced. For example, I ran ls on my home directory, which contains 72 files and directories. With ...
1
vote
0answers
281 views

Apache web server maxing out due to processes stuck at D status

I have a Apache 2.2.3 web server running on a 8 core VM with 8G Ram. During a load test, the web server stopped responding and load average went up to 1000. When I run Top command, I see a large ...
3
votes
2answers
358 views

MySQL hangs if connection comes from outside the LAN

I have a MySQL Server operating just fine if I access him from his local LAN (192.168.100.0/24). If I try to access hin from another LAN (192.168.113.0/24 in this case) it hangs for a really long time ...
0
votes
0answers
49 views

MySQL sandbox strace option

Latest MySQL Sandbox version uses environment variable SBDEBUG to start mysql instances in debug mode, but i can't pass mysql --debug option. export SBDEBUG=d:t:O,/tmp/client.trace cd ...
1
vote
1answer
102 views

Debugging high CPU load when adding new domain inside server's control panel

When adding a new domain inside my server's control panel it takes much longer than usual since some time. CPU shows 100% usage on one core and strace reports something like this: poll([{fd=7, ...
0
votes
2answers
570 views

Troubleshooting SUDO Slowness with STRACE

I'm having trouble with sudo on some systems. It is taking anywhere from 15-30 seconds to complete a sudo command or to even login to the system. I ran an strace and can see where the delay is ...
1
vote
1answer
242 views

mongodb mystery crashes with sigkill under strace

I have a mongodb instance that seems to crash roughly once a day. I don't see any useful information in the mongo log file. All is well and then the process is just crashed with no additional ...
0
votes
1answer
282 views

strace vs. log4cxx performance hit?

I need to debug some issue on a production server, and I'm trying to decide whether to use strace or the log4cxx logging library; one crucial characteristic I need to know before, is which of the two ...
4
votes
0answers
434 views

mysql client slow login strace

I am experiencing an issue with slow connections/logins to a loaded mysql server, even when connecting via the unix socket file (CentOS 6.3). Queries are completing very quickly -- (0.00 sec) in this ...
4
votes
5answers
20k views

Find out what high CPU usage apache process is actually doing?

Currently having a few issues with our server where, intermittently, we seem to get apache processes which just run and run, taking up 100% CPU. When running top, we see the following: PID USER ...
1
vote
3answers
526 views

Mysql killing the CPU with gettimeofday

I have a problem with mysql killing the CPU on a Debian Squeeze 64. This is a development machine on a VPS so I stopped all the other services, including apache2. The mysql version is 5.1.49. This is ...
0
votes
1answer
67 views

Trying to diagnose bottleneck for apache

I am trying to diagnose bottleneck for a apache(v 2.0.52) server using strace. It looks like call to poll is slowing the process. Below is one example poll([{fd=10, events=POLLIN}], 1, 120000) = 0 ...
0
votes
1answer
77 views

Interfacing strace with Process Name instead of PID

How do I implement a wrapper script pstrace in bash that changees the interface of [sudo] strace -c -p [PID] to [sudo] pstrace -c -p [PROCESS-NAME] similar to how killall [PROCESS-NAME] is ...
0
votes
2answers
1k views

Apache strace to hunt down a memory leak

We have a server with a memory issue: the server keeps allocating itself memory and doesn't release it. We're running Apache. I set MaxReqsPerClient to a really low value just so the threads don't ...
2
votes
1answer
1k views

How to resolve high CPU + excessive stat(“/etc/localtime”) and clock_gettime(CLOCK_REALTIME) calls

I've been experiencing really high CPU on a ruby on rails app (see stack below) and have been trying to diagnose the possible causes to no avail. Stack: ruby 1.9.3 rails 3.2.6 Apache/2.2.21 ...
2
votes
4answers
2k views

Apache process consumes too much CPU

I have an ubuntu apache/php server running php doing appx 100 hits/sec and a PHP cron running in the background. I get occasionally high CPU load on one of the Apache processes which stays high ...
1
vote
3answers
303 views

WSGI cannot access a file, but permissions are correct

I am debugging a problem where MoinMoin on CentOS is throwing a permissions error, but I can't track down where the problematic file / directory is. I ran strace -vp <pid> on the apache pid; ...
1
vote
0answers
480 views

Tracking down an elusive and slow anon_inode from lsof and Apache strace

Experiencing an intermittent issue with a LAMP application wherein Apache forks to its ServerLimit and grinds to a (near) halt. An strace on any httpd process shows numerous, slow epoll_wait calls. ...
0
votes
1answer
62 views

monitor processes in citrix

Where I work, We've been having trouble with certain applications mysteriously crashing/hanging in citrix; the primary culprits are IE8 and a certain .net-based industry specific app that we use. ...
3
votes
1answer
253 views

Why does strace open, read 512 bytes, and THEN fstat libncurses?

I've got the following strace output that I'm going through to teach myself a little more about the flow of programs. Here's the section that's confusing me: 16:08:02 open("/lib/libncurses.so.5", ...
3
votes
2answers
635 views

trace opening on a certain file

I know how to strace a certain program to see all the files it reads. I know how to see what processes are using a certain file at the moment. But is there a way to log all file opens. I want ...
2
votes
1answer
4k views

Java process (OpenDS) consumes all cpu (futex flood) - how to debug futex?

Today I noticed that my LDAP server (OpenDS) consumes 100% CPU on every available core. Fast diagnose showed me that there is a lot of ETIMEDOUT during the futex lock. How Can I debug it to figure ...
4
votes
1answer
856 views

Strace Apache process output showing 24 seconds wait?What can be the reason?

Performed strace on one one of the apache children and its showing 24 seconds between two system calls.How can i determine what is the cause of this behavior.It looks like both children are taking ...
3
votes
2answers
1k views

Why is my cron daemon is being killed every few minutes?

As of about a week ago, my cron daemon refuses to stay running. I'm using Debian 6 x64 on an OpenVZ virtual machine. Running something like pgrep cron shows that the daemon isn't running. I start the ...
10
votes
4answers
529 views

How would you simplify this command?

I'm quite new to strace / netstat / etc. I'm using this command to get a trace of the apache process handling my request (telnet), is there a way to simplify it a bit? sudo strace -o /tmp/strace -f ...
1
vote
2answers
2k views

puppet hanging or long time on rt_sigprocmask(SIG_BLOCK, NULL, [], 8) = 0

In our setup, we manage our servers using puppet. Since a few days I saw the puppet client running very slow. When stracing the puppet process I get loads of rt_sigprocmask(SIG_BLOCK, NULL, [], 8) ...
1
vote
0answers
1k views

“yum clean” hangs - what to try next?

I run a number of CentOS servers. I was recently doing the occasional yum update but this failed on a handful of the servers. On most I have been able to move forward by doing: # yum clean all # rm ...
1
vote
1answer
599 views

Cant run programs under strace

I'm trying to run this simple program ls under strace and it wouldnt let me. Can you guys think of why this be the case? [jeffjose@skipper ~]$ strace ls strace: ptrace(PTRACE_TRACEME, ...): ...
1
vote
1answer
160 views

Long page loads - problems with DNS lookup?

I've noticed my web server takes a long time to load pages recently. Using Firebug, I realised it takes around 4s for the DNS lookup: Connecting: 304ms Sending: 0ms Waiting: 3.45s Receiving: 0ms I ...
1
vote
1answer
902 views

which pid to use to strace my apache

My apache2 is using running slowly. A single PHP file is takes long time to process. The server is live. I dont want to restart it. So I thought I attach strace to it and check whats happening. So ...
0
votes
1answer
80 views

secure rollback of updates

I'm again and again wondering why there isn't (or did I just not find it?) any tool which can reliably and effortlessly rollback changes done by updates. Let me take an update with apt on Debian as ...
2
votes
1answer
1k views

Attaching strace to 100% CPU Apache process - output

I am having a problem with Apache2 spawning processes that use 100% CPU. Attaching strace to one of such processes produces no output sometimes and sometimes gives this: 2672 17:18:07 poll([{fd=14, ...
0
votes
2answers
1k views

Using strace effectively

Right now I'm dealing with a client's php based site that is somehow clogging up all of the available processes he has with his shared hosting provider. I'd like to prove to him exactly what and how ...
1
vote
2answers
173 views

How to analyze system calls when your disk is in read only and strace output is “Bus error”?

We have a HW problem with the disks, that made all the mount points to be read only. Output of dmesg: end_request: I/O error, dev sda, sector 15574609 sd 0:0:0:0: SCSI error: return code = 0x00040000 ...