1
vote
0answers
17 views

Multipath tcp application level performance measurement

I am working on a project related to Multipath tcp and I want to measure the goodput and the RTT at the application level. I don't want to use a traditional tool(netperf, iperf, ...) and I want to ...
1
vote
0answers
40 views

IRQ not handled by all CPUs

I have a problem about balancing irq. I took irq numbers from /etc/interrupts and assigned each irq to each of 24 CPUs as this tutorial says for i in {143..166};do cat /proc/irq/${i}/smp_affinity; ...
0
votes
0answers
11 views

configuring server for single process using all resources [duplicate]

i'm attempting to configure a server that will be used for data scraping using phantomjs (if you're not familiar it's a headless browser - it's webkit, controllable via javascript, without a gui ...
2
votes
1answer
50 views

Server load avg. hitting 16-20, but all resources under 90% usage?

As you can see in the image shared below, the server load peaked to almost 20 but the CPU, RAM, DISK IO and Network I/O remained well under their full capacity. My question is: 1). What caused the ...
0
votes
2answers
260 views

Linux : SSD performance tweaking queue

I've allready applied well known mountpoint options for ssd, enabled stuff in LVM for ssd optimisation as well. Now i've ran into a possible challenge. Would it be possible to gather information on ...
0
votes
1answer
180 views

rmem_max more than rmem_default

I just installed centos 6.3 freshly and noticed the following: [root@localhost user1]# cat /etc/redhat-release CentOS release 6.3 (Final) [root@localhost user1]# [root@localhost user1]# cat ...
3
votes
1answer
206 views

How to identify which MySQL queries take a lot of time?

My MySQL server is consuming a lot of memory. Memory footprint 1. Memory consumption in descending order (top 4) MySQL's memory consumption in particular - Why is there so many number of mysqld ...
2
votes
1answer
3k views

Improving OpenVPN Performance

I've been trying to improve my OpenVPN performance and this is my current setup: cat /etc/openvpn/server.conf port 443 #- port proto tcp #- protocol dev tun #tun-mtu 1500 tun-mtu-extra 32 #mssfix ...
5
votes
2answers
117 views

ZFS Equivalent of lvdisplay snap_percent

I've been using LVM snapshots for backing up MySQL databases. FLUSH TABLES WITH READ LOCK is issued and then lvcreate --snapshot --size 4G etc. Because the database is live while the snapshot is ...
4
votes
3answers
2k views

Understanding RedHat's recommended tuned profiles

We are going to roll out tuned (and numad) on ~1000 servers, the majority of them being VMware servers either on NetApp or 3Par storage. According to RedHats documentation we should choose the ...
1
vote
1answer
185 views

TCP RWIN, MSS and MTU [closed]

I have been doing some reading into TCP Receive Window (RWIN), Maximum Segment Size (MSS) and Maximum Transmission Unit (MTU). Right off the bat I have some questions and I need a power user's help! ...
1
vote
1answer
2k views

How do I increase UDP Recv-Q

I have a gigabit connection that is not fully utilized but I am getting packet receiving loss. When I do netstat, it shows the Recv-Q sometimes maxes out at 262656 during heavy traffic. Proto Recv-Q ...
0
votes
1answer
216 views

Why am I getting a Sudden Drop in throughput and sluggishness with no CPU increase

Occasionally, during random parts of the day, I get a 10 minute period of extreme sluggishness where my requests are taking 50-1000 times longer then they normally do. Note: I am on Apache/2.2.16 ...
1
vote
2answers
135 views

Visualize overloaded nic in linux (kernel time)?

I have a linux server that keeps getting its NIC overloaded and I need to visualize how and why this is occurring based on connections and CPU utilization. How do I do this? For example; for me to ...
1
vote
0answers
253 views

Copying cause big iowait

I have dedicated server with 3 HDD. System disk, backup disk (same as system disk) and data disk. When I copy lot of data with cp (say, between backup disk and data disk) load average goes sky high. ...
0
votes
0answers
409 views

Ubuntu 12.04 64bit - What would cause high System CPU %sys during high MySQL loads?

128GB RAM, 32cores Xeon RAID 10 SSD. Mysql version is the latest 5.5 for Ubuntu 12.04 . We have a lot of queries - about 1800+ per second. During high MySQL load - 2700+% load on a 32 CPU system - ...
2
votes
3answers
454 views

Disk write speed much slower than read speed

I have a VPS server (WiredTree), running CentOS. After experiencing some performance issues I created a simple benchmark for disk read/write speed using the following script: echo Write to disk dd ...
-2
votes
1answer
197 views

Which will give more free RAM to linux? [closed]

Trying to avoid some issues so I've been trying to learn vm. in kernel tuning but still a little confused even after googling. The lower background_ratio is the sooner the flushes? the lower ...
1
vote
1answer
398 views

VM Tuning to enhance performance

vm.bdflush = 100 1200 128 512 15 5000 500 1884 2 vm.dirty_ratio = 20 vm.dirty_background_ratio = 10 vm.swappiness = 10 vm.min_free_kbytes = 300000 That means that the MOST dirty data that can be in ...
1
vote
0answers
82 views

Getting the virtual memory address for (major) page faults

On a Linux (Cent OS 5) system, I have a process that accesses a large amount of memory mapped files. The process is generating a large amount of page faults because the aggregated size of the mapped ...
-5
votes
1answer
209 views

CFQ vs Deadline - performance benefits [closed]

Running CPanel and wondering what would be the best for web hosting? deadline is more balanced over CFQ right so would allow for more I/O activities right
3
votes
1answer
2k views

Disabling CPU management

If I add the following processor.max_cstate=0 to the kernel command line for boot up, does that disable all CPU power management and throttling? I also found: ...
7
votes
2answers
2k views

CPU0 is swamped with eth1 interrupts

I've got an Ubuntu VM, running inside Ubuntu-based Xen XCP. It hosts a custom FCGI-based HTTP service, behind nginx. Under load from ab the first CPU core is saturated, and the rest is under-loaded. ...
0
votes
1answer
87 views

MySQL Threads or what is this

http://i.stack.imgur.com/dZFqI.png How can I reduce that number? I have a quad core machine. Do I need to edit thread_pool_size and by reducing them do I get better performance? Should a lot of ...
1
vote
1answer
326 views

Doubled up RAM to 32 GB - now how to speed up a “LAPP” server?

I run a small Facebook game at a CentOS 6.3 quad core machine with PostgreSQL 8.4.3 + few PHP scripts (doing mostly select queries) + 1 Perl daemon and even though the server worked ok, I've suggested ...
2
votes
1answer
72 views

Server hanging when serving random file on page load

I'm optimising a website, and the problem I'm facing with now is server related. During page load, there are about 40-50 requests sent to server (depending on the page), and in every case, server ...
2
votes
1answer
459 views

Different block sizes for partition and underlying logical disk on HP Raid Controller (Linux)

Following links collected in this thread I started to check blockdev and found the following output indicating different sizes for partition c0d9p1 and the underlying device (c0d9): [root@machine ~]# ...
0
votes
1answer
260 views

Linux kernel 3 TCP IP tuning

I found several resources about tuning linux TCP/IP stack parameters in /etc/sysctl.conf for high bandwidth connections, but all refer to kernel 2.6. Does anyone have suggestions about how to tune ...
0
votes
2answers
57 views

How can I decide up the nature of performed IO?

I am using Linux (3.2.12-3.2.4). I have few "syncer" processes which updates lots and lots SQLite db files in a loop. The database sizes vary from 1 MB to few GB. I have a "searcher" process which ...
0
votes
2answers
970 views

How to turn linux to keep 'cache' high?

We are running a heavy service on Debian. Our service generates lots of file i/o and its performance relies on how well Linux kernel caches files. Our system has 64GB memory. Total file size is 500GB ...
5
votes
1answer
763 views

How do I test the effect of ionice (against a device using the cfq scheduler)?

I'm trying to construct an experiment to measure the effect of ionice. What I'd like to do is to (per another answer on serverfault) cause frequent enough I/O that a sufficiently "niced" process is ...
3
votes
1answer
279 views

How long is the “defined grace period” for the idle scheduling class of the CFQ io scheduler?

The ionice man page says A program running with idle io priority will only get disk time when no other program has asked for disk io for a defined grace period. Where is this "grace period" ...
0
votes
1answer
200 views

adding new scheduling policy to the kernel

i'm working on a redhat 8 linux and i want to add new policy for scheduling the processes , could you help me with : 1) where to define the new policy 2) how does the process of assigning a policy for ...
0
votes
2answers
97 views

Server configurations for hosting MySQL database

I have a web application which uses a MySQL database hosted on a virtual server. I've been using this server when I started the application and when the database was really small. Now it has grown and ...
3
votes
3answers
477 views

httperf hangs when using --hog

I'm using httperf from a large ec2 instance with ubuntu 10.04 (no other software installed). When I test without --hog the tests run however when I use --hog the tests never end
3
votes
2answers
332 views

Tuning MySQL and Linux to reduce maximum response time specifically

We have a MySQL-based application that is very response time sensitive. A MySQL stored procedure needs to respond on average in less than 10 milliseconds and the maximum acceptable response time is 50 ...
4
votes
1answer
486 views

Ubuntu HTTP latency falling into strange quantiles

I have an Ubuntu 10.10 server with plenty of RAM, bandwidth and CPU. I'm seeing a strange, repeatable pattern in the distribution of latencies when serving static files from both Apache and nginx. ...
0
votes
1answer
535 views

Improving TCP performance over a network with small packet loss

I’m trying to improve my TCP throughput over a “high delay network”, with some packet drops, between Linux machines. I set tcp_mem, tcp_wmem and tcp_rmem to “8192 20530752 20530752”. I set rmem_max, ...
-1
votes
1answer
209 views

Linux script to check settings and recommend tuning changes? [closed]

I'm searching for a script to run on our linux server and recommend various tuning changes we might consider making, as well as their suggested values for consideration. Any ideas if something like ...
0
votes
3answers
1k views

How to speed up apache

We have a server with 8Cores, 16GB of RAM and RAID 0 SAS 10K drives. Our goal is to use this to serve a fairly simple php application quickly. We have tested all other components and we think we have ...
0
votes
2answers
792 views

MySQL Memory usage

Our MySQL server seems to be using a lot of memory. I've tried looking for slow queries and queries with no index and have halved the peak CPU usage and Apache memory usage but the MySQL memory stays ...
6
votes
1answer
4k views

Interpreting ethtool Coalesce output

Other than tx and rx being the transmit and recieve, can anyone explain what the fields mean in ethtool -c's (Coalescing output) and what effect they have on how coalescing works? Coalesce parameters ...
0
votes
1answer
244 views

ionice or chrt for Bonnie benchmark

I am running Bonnie benchmark on an embedded device and I am getting variable results for every run. I am contemplating using ionice and / or chrt to get around it. Can you suggest which option is ...
1
vote
3answers
965 views

Filesystem/Options for intensive random I/O

I'm planning to (privately) deploy a server that will be hammered with random I/Os in files ranging from 100MB to 50GB. The requests will range from 128 KB to 4MB. The profile will be 50:50 concerning ...
3
votes
3answers
1k views

Linux's best filesystem to work with 10000's of files without overloading the system I/O

It is known that certain AMD64 Linuxes are subject of being unresponsive under heavy disk I/O (see Gentoo forums: AMD64 system slow/unresponsive during disk access (Part 2)), unfortunately have such ...
4
votes
7answers
2k views

Linux tool/command to check file system performance

What is the simplest way to check read/write performance to a specific location (e.g. a mounted iSCSI device). I suspect I can't use hdparm because that's lower level. Am I right?
0
votes
3answers
551 views

Extreme fine tuning MySQL performance wise on a Linux server

I would like to know all of the key points where MySQL can be fine tuned performance wise on a Linux server through my.cnf or through other methods, libraries and tools. Tips and tricks and shady ...
8
votes
2answers
729 views

Linux RAID-0 performance doesn't scale up over 1 GB/s

I have trouble getting the max throughput out of my setup. The hardware is as follow : dual Quad-Core AMD Opteron(tm) Processor 2376 16 GB DDR2 ECC RAM dual Adaptec 52245 RAID controllers 48 1 TB ...
3
votes
1answer
302 views

What are some current and relevant benchmark tools for Linux?

I'm specifically interested in benchmarks that approximate or target real in the wild usage scenarios. My main areas of focus are latency, network performance (incoming data over sockets). ...
0
votes
1answer
513 views

Webserver: Performance impact when storing session files on /dev/shm

I have a website runing on a typical setup: Linux, Apache, PHP, MySQL. However, what's not typical about it, is that it's getting tons of traffic (400,000+ visits a day) and so, efficiency is becoming ...