Questions about server hardware and software performance, or network performance.

learn more… | top users | synonyms (2)

1
vote
1answer
43 views

Performance impact enabling intel vt-x

I have a rather unusual question: What is the performance impact when you enable vt-x and you don't need it? I ask this because all of the new servers I receive have this enabled by default in the ...
0
votes
1answer
30 views

What is the best way to analyze data captured from sar?

I've got some sysstat data that has been captured from servers with SAR, and I'm unsure what is the best way to analyze that data. I've found ksar, but it seems to be quite old and out of date. I'd ...
0
votes
1answer
21 views

Improving I/O rates for EBS snapshot backed volumes

I'm working with a system that takes a set of 42 rotating daily EBS snapshots of each of its numerous (40) volumes for disaster recovery purposes. EBS volumes are aggregated into a RAID volume. A set ...
7
votes
1answer
122 views

Sluggish performance on NTFS drive with large number of files

I am looking at this setup: Windows Server 2012 1 TB NTFS drive, 4 KB clusters, ~90% full ~10M files stored in 10,000 folders = ~1,000 files/folder Files mostly quite small < 50 KB Virtual drive ...
-1
votes
1answer
38 views

Which raid array will be best practices with seven 1.2 tb hdd system

I have a server which have seven 1.2 tb hard disks. I have to create raid array but i don't decide which raid i use? First of all, first and most important matter is security. At any cost i must not ...
0
votes
1answer
21 views

Increase openfire memory to larger values

We use OpenFire for XMPP messages. We have some memory issues(OutOfMemoryError), and therefor we would like to increase memory. I know how to increase memory using VM options and we were able to ...
0
votes
0answers
26 views

lower tcp throughput than expected

I've conducted some tests which measured tcp throughput via wireless and wired connection. (a) was wired link between my desktop and my home router. (b) was wireless link between my desktop and my ...
2
votes
1answer
64 views

Why might 'mpstat' and 'pidstat' disagree about CPU load levels?

I'm monitoring a mysql process in ubuntu 12.04 using mpstat and pidstat, simultaneously. While debugging its CPU usage, I noticed something unusual. While both tools agree that CPU load is occurring, ...
0
votes
0answers
36 views

Reduce Connecting time to server for inital request

I am struggling with decreasing load time of inital html page request. It is consistently above 800 ms however other websites they load in less than 300 ms. In this load time GTMetrix shows more than ...
0
votes
0answers
26 views

Does decommissioning nodes on hadoop cluster hamper performance?

I have 120 node Hadoop cluster, I have removed around 14 nodes in 7 days (each day - 2 nodes were decommissioned) Now users are facing some performance issues, does this decommission really matters. ...
4
votes
4answers
1k views

RAID 10 - many slow disks vs fewer fast disks

I am looking to buy HDDs for a single server which will be used as development server. The server will use ESXi as hypervisor and will have some but not too many virtual machines (web server, database ...
0
votes
1answer
27 views

Speed: nginx serving static content even faster: fixed folder ; how can I

we run centos and nginx one of latest versions in 2016. We use 1 media directory with some underlying subdirectories. FTTB for php is 200ms which is very fast - but now I discovered that the JS CSS ...
1
vote
0answers
61 views

Slow gigabit speeds with Ookla speedtest software

We have 2 speedtest servers (RHEL 6.7) sitting on 10GB links with a 10GB pipe between the two. The servers are separated geographically by about 256 miles but traceroutes look very good, with 4 hops ...
1
vote
1answer
34 views

How can I determine which files have high I/O in Windows?

In trying to reduce the storage bottleneck on a Windows server (2008 R2) I need to find the files that have the highest I/O over a long period of time (aka 'hot' files) so I can move those to SSD ...
0
votes
0answers
27 views

Real memory usage on Linux and Private_Dirty

On Linux, is using Private_Dirty value from smaps a good way to measure real process memory usage? Thanks
1
vote
1answer
78 views

Hardware performance penalty for Hyper-V Generation 2 VMs

I have the following configuration: Windows Server 2012 R2 OS installed on baremetal with Hyper-V. OS is installed on RAID1 850 PRO drives. Windows Server 2012 R2 Guest OS Generation 2 VM is located ...
0
votes
0answers
21 views

Why in my index in a cold situation that slow?

We have a table CREATE TABLE mytable ( ... myfield bigint, ... ) and an index CREATE INDEX fk_fk18edb1cf49a32f88_idx ON mytable USING btree (myfield); and a simple query SELECT count(*) ...
0
votes
0answers
48 views

Disk performance drops in VMWare ESXi 4.1 / 5 Linux Guest

I'm benchmarking disk write performance using this command: dd if=/dev/zero of=/mnt/test.dmp bs=1M count=256 conv=fdatasync After a random time and random number of attempts, the file system ...
1
vote
0answers
27 views

iperf actual send rate always lower than the expected target bandwidth until some equilibrium reached. Why?

I did an UDP iperf 2.0.5-Ubuntu test between two VMs on the same hypervisor. As can be seen in the iperf output below I started my first test with "-b 686M" flag. However, iperf reported that it was ...
2
votes
1answer
84 views

Is this btrfs snapshot removal performance normal?

I have several boxes running Debian 8, dovecot and btrfs. I'm using btrfs snapshots for short term backup. For this purpose I keep 14 snapshots of the mail subvolume. Performance is OK until it comes ...
1
vote
1answer
38 views

Intermittent Server Performance Degradation Troubleshooting

I have been troubleshooting an intermittent server performance issue for too long and I am running out of ideas. I am looking for any suggestions as to how I might be able to identify the cause of ...
2
votes
1answer
45 views

How to reduce “Connecting” time incurred for a request

I am trying to optimize speed of website and during this process I have found that. A connecting time of around 620ms is incurred everytime I request a page. Please see screenshot below for detailed ...
1
vote
0answers
11 views

Limiting Oracle instances resources with Cgroups?

Is it possible to limit the amount of resources (I/O, CPU and Memory) a Oracle instance can consume using only cgroups? (no containers or virtualization) The reason I wanna do that is because I want ...
1
vote
0answers
20 views

Performance concern with hosting large clustered DBs on VPS cloud servers

I wonder if anybody else bumped into this issue? You get a couple of beefy 12-core VPS instances in some cloud like DigitalOcean and set up a database on them in "active-passive" cluster ...
0
votes
0answers
15 views

Are changes since snapshots still stored as changelogs?

It's been four years. Is the accepted answer of this question about VMWare still accurate? In other words (in case for some reason that link ever breaks), is this still true? When you create a ...
0
votes
0answers
59 views

ncftp vs common ftp speed

I have very different download speeds with this two ftp clients. Ncftp with standard configuration downlaods at 7MB, while ftp does it at 80MB (connection between dedicated server and FTP Backup ...
1
vote
0answers
41 views

httpd processes cpu spike to 100%+ every xx seconds

My first post, unfortunately due to an issue on my dedicated (Linux Centos 6) server running some personal and one commercial website. Server version: Apache/2.4.18 (Unix) Server built: Mar 7 2016 ...
-1
votes
1answer
28 views

Getting file size before download on a proxy server [closed]

We're working on building a multithreaded proxy file server in C, where we receive a request and retrieve it from another location using the libcurl library. The library gives you the option of ...
1
vote
2answers
52 views

Disk IO Rate: What causes it and what does it mean to me?

I just got a mail from Linode saying that my account "has exceeded the notification threshold (1000) for disk io rate by averaging 1017.36 for the last 2 hours. " My question is just out of curious: ...
3
votes
1answer
114 views

FTP transfers slow on a long fat pipe

We've recently gotten new internet - 100Mb/s fibre - and have been complaining bitterly to our new ISP about transfer speeds to some FTP servers in the USA (300ms away). To one server in particular, ...
0
votes
0answers
11 views

How can I get a nginx & php server to use much more system resources?

I'm running a local setup. Crunching some largish 100mb json files via php running on nginx. I'm also doing some mysql stuff, checking through tables with about 90k rows, matching data from the json ...
0
votes
0answers
122 views

MongoDB high page faults every 15 minutes, delayed readers

We have a relatively small MongoDB production replicaset. We do about 100 operations per second -- balanced reads and writes. Every 15 minutes or so we see a spike in response time on reads, and in ...
0
votes
0answers
59 views

Mongodb, we can't go over 100 insert/sec on 200iops HDD

Thanks in advance for your help, we get a strange behaviour in mongodb. So we have a cluster of 20 shards, each composed of 1 master and 2 slaves. This database has a heavy load of write only. However ...
1
vote
1answer
30 views

how to identify and report bad RDS hardware

Recently we [finally] migrated all of our production hardware from the deprecated default networking into VPCs including EC2 and RDS nodes. Everything went pretty well except when we started to run ...
0
votes
1answer
277 views

Why is zfs/btrfs recommended for an lxd host?

Note that for maximum performance, it's recommended to have /var/lib/lxd on a btrfs filesystem or setup ZFS or LVM and configure LXD to use a ZFS pool or LVM VG. Source Why is that? I.e. How ...
0
votes
1answer
29 views

Managing sudden peak in traffic for event ticketing system

I am going to be managing an event ticketing system for a specific event. I think we will probably be expecting generally low traffic, although there's likely to be a few sudden peaks of traffic (to ...
0
votes
1answer
29 views

Which bandwith can i expect, when i´m running a SATA SSD on a SAS interface?

So, i know this question had been asked before. I consider to buy a SSD for my Server, because i kinda hate the SAS HDDs in there. I thought: If i connect a SSD, which, in fact, handles way more ...
2
votes
1answer
73 views

Fastest triggering of realtime anti virus scan

I have the problem, that in each backup of my mail system (File based archive on Windows Server 2012 R2), errors occur while backing up virus-infected e-mail attachment files. This is caused by the ...
2
votes
0answers
30 views

Finding or estimating sequential vs random distribution of existing system (VMware / SAN)

IOMeter testing says the IOPs of the storage subsystem can range from hundreds of IOPs for 100% random loads to tens of thousands IOPs for 100% sequential loads. Is there any way I can measure or ...
0
votes
0answers
20 views

Oprofile events are not available

I run an Intel(R) Xeon(R) CPU E5520 @ 2.27GHz and I've just started to use Oprofile. I want to measure some events like the BUS_REQ_OUTSTANDING and BUS_TRAN_BRD but are not available. Is ...
2
votes
1answer
64 views

Filesystem Performance for LUKS Encrypted Volumes?

As you can format a LUKS volume with any filesystem you want, are certain filesystems better-suited to IO performance against an encrypted filesystem? Specifically, I'm wondering about a loop device ...
0
votes
0answers
31 views

Bad performance on ocfs2 with many files

i am managing a small science server infrastructure with an ocfs2 storage. On the storage are about 9.000.000 files consuming 4,7 TB. The files itself a really small around 500KiB-1Mb. The problem is ...
0
votes
0answers
29 views

Server Specs for browser game that hugs cpu

Our team have developed a web browser game, our servers are using nginx and php-fpm to host the website. the game consist of two parts an api and the game itself. both applications reside on its own ...
0
votes
0answers
32 views

Comparing 1x Xeon multi core vs 4x UltraSparc IV

I'm in the process of reviewing specs for hardware running an Oracle server. The new hardware will be running using Xeon processor compared to the old servers (Solaris) running on UltraSparc IV. So ...
0
votes
2answers
56 views

Guest OS 100% utilization, 'Total Run Time' is about 60%

I have ran CPU stress test on linux HyperV VM. Linux reports 100% CPU utilization, but "Hyper-V Hypervisor Virtual Processor(*)\%Total Run Time" metric shows about 60-70%. Is it possible to obtain "...
11
votes
1answer
275 views

OpenVPN low performance. Do I have MTU problems? Dumps inside

I have problems with an OpenVPN tunnel which does not reach line speed. The gateway is a Debian Jessy virtual server hosted at OVH. The client is either my freebsd 10.2 homeserver (Intel I3 Ivy Bridge)...
1
vote
3answers
133 views

How can I determine the performance penalty of VT-d vs. baremetal?

I am looking to configure my server in a slight odd way to create a private cloud setup. I have to take the HBA that my storage disks are tied to and pass it into a VM (probably xen) to allow the ...
1
vote
0answers
116 views

What's your experience with the AWS NAT Gateway performance?

In December/2015 Amazon launched their VPC NAT Gateway service which is basically a managed alternative to creating your own (and it looks very good in comparison to NAT instances). I was just about ...
1
vote
1answer
16 views

Linux top in RES what does the 't' suffix stand for

When monitoring my system with top, I noticed that under RES some values have a 't' suffix, but I can't see any indication of what this means. PID USER PR NI VIRT RES SHR S %CPU %...
4
votes
1answer
131 views

SQL Azure insert query ten times slower on V12 than V11?

I noticed performance degradation about two weeks ago impacting one of our applications with an SQL Azure backend. It's running on V12 on tier S1 90% of the time, sometimes scaling to S2, S3 or P1. ...