Search Results

Search found 13249 results on 530 pages for 'performance tuning'.

Page 95/530 | < Previous Page | 91 92 93 94 95 96 97 98 99 100 101 102  | Next Page >

• CORAID using only 1 of the 2 available NICs for AoE traffic

  - by Peter Carrero

  We got 6 CORAID shelves in my workplace. On 2 of them I see AoE traffic on only 1 of the 2 NICs that are attached to the SAN switch. We got jumbo frames enabled on all devices. Both NICs show up when I issue the aoe-interfaces command. This wouldn't bother me too much if the throughput performance observed on the "bad" shelves using bonnie++ wasn't half of the result of the "good" shelves. The "good" shelves are older SR1521 model and they have ReiserFS on their LUNS - not that I think it makes a difference - and the "bad" shelves are newer SR2421 model and have JFS. Any help as to what is going on and how to rectify this would be greatly appreciated. BTW: even the lower performing shelves outperform another iSCSI device we got, but that is another story... Thanks.

  Read the article

• Install 64-bit Ubuntu or 32-bit?

  - by nitbuntu

  I'll be receiving a new notebook in a few days and was planning on running Ubuntu on it as it's compatible and the notebook has no OS pre-installed. The specifications are: Core 2 Duo, T6600, 4 GB RAM, Intel integrated graphics. I know a year or two ago, running a 64-bit version of Ubuntu was not advised due to much of the applications and plugins (e.g. Flash) only running on 32-bit. Is this still the case? Would I get better performance with 64-bit Ubuntu since I have 4 GB of RAM? Are there any downsides anymore?

  Read the article

• Do Seagate Momentus XT SSD Hybrid drives perform better than a good hard drive + flash on ReadyBoost

  - by Chris W. Rea

  Seagate has released a product called the Momentus XT Solid State Hybrid Drive. At a glance, this looks exactly like what Windows ReadyBoost attempts to do with software at the OS level: Pairing the benefits of a large hard drive together with the performance of solid-state flash memory. Does the Momentus XT out-perform a similar ad-hoc pairing of a decent hard drive with similar flash memory storage under Windows ReadyBoost? Other than the obvious "a hardware implementation ought to be faster than a software implementation", why would ReadyBoost not be able to perform as well as such a hybrid device?

  Read the article

• eSata plugged into Sata socket via adaptor cable very slow

  - by Jon

  Why would an external eSata Drive (xSonic with 500Gb notebook Hard Drive) run ok on a Silicon Image based PCI-E to eSata adaptor at about 35MB/s, But then run really slow when plugged into NForce4 Sata socket via cable? I have another version of the problem with Really slow 1MB/s!!! performance on a ASUS P5K Pro Motherboard with E8400 CPU. This time the same card is plugged into a PCI-E socket. The same eSata drive is plugged into the Esata port on the card. All this is running on Windows XP Pro 32bit. Any suggestions on how to diagnose the problems??

  Read the article

• How to monitor current output/receive queue length in Linux

  - by IZhen

  I want to check the capacity and performance of my network. Besides checking the txkB/s and rxkB/s via Sar, I'd also like to see the average queue length of the network interface(so that the average queueing time in the interface can be calculated). It seems that netstat can give a per socket queue length, is it possible to get a per interface statics(a bit like Network Interface\Output Queue Length in Windows)? A related and kind of reverse questions is How do I view the TCP Send and Receive Queue sizes on Windows? Thanks

  Read the article

• Full Screen Flash is choppy (nVidia GeForce 8200M)

  - by Joel Martinez

  I have a new compaq presario laptop (I asked SU for advice before I bought it :-) ). It has a nVidia GeForce 8200M video card. When I try to play a flash video full screen, it plays really choppy. This is a brand new computer and is well more powerful than my previous computer so I know it's not a matter of the full screen being too processor intensive to play, or a bandwidth problem. Even playing HD hulu videos full screen was fine on my previous laptop. Any advice on how to get better performance here? edit: World Of Warcraft is able to play at a great framerate, so this machine should definitely be able to handle a simple little flash video ;-)

  Read the article

• Nginx & Passenger - failed (11: Resource temporarily unavailable) while connecting to upstream

  - by Toby Hede

  I have an Nginx and Passenger setup that is proving problematic. At relatively low loads the server seems to get backed up and start churning results like this into the error.log: connect() to unix:/passenger_helper_server failed (11: Resource temporarily unavailable) while connecting to upstream My passenger setup is: passenger_min_instances 2; passenger_pool_idle_time 1200; passenger_max_pool_size 20; I have done some digging, and it looks like the CPU gets pegged. Memory usage seems fine passenger_memory_stats shows at most about 700MB being used, but CPU approaches 100%. is this enough to cause this type of error? Should i bring the pool size down? Are there other configuration settings I should be looking at? Any help appreciated Other pertinent information: Amazon EC2 Small Instance Ubuntu 10.10 Nginx (latest stable) Passenger (latest stable) Rails 3.0.4

  Read the article

• Configuring apache and php to handle many connections

  - by Marc

  My preliminary setup is like this. Two QuadCore 8GB servers running debian 6, with php and apache, One QuadCore 16GB server running debian 6, with mysql My plan is to have one 8Gb server to act as a proxy server, using vertx java to handle connections. I will let vertx use HttpClient to send web requests to the second 8GB server. This would have apache installed and use php to deliver any information that it gets from the mysql server on the third, 16GB server. The main reason I want this setup is to have things separated, so the "proxy" will be the only way to access the system, as the other two server will only be reachable from the local network. I can have the vertx proxy handle 5000+ concurrent connections, but, I don't know how to configure apache to handle all the requests coming from the proxy. Php will connect over mysqli with persistent connection pool of 500-800 connections, the mysql server seems not to have any issues on this part. In previous projects, the apache part was always causing issues, no matter how I set it up. I might not fully understand how to setup apache, since normally apache should handle many concurrent connections, but it does seem to now.

  Read the article

• Lot of FIN_WAIT2, CLOSE_WAIT , LAST_ACK and TIME_WAIT in Haproxy

  - by Tux

  We are running haproxy in production for around 10k+ concurrent users . But we are seeing lot of FIN_WAIT2, CLOSE_WAIT , LAST_ACK and TIME_WAIT in the netstat output. This output is on a 8G ubuntu-12.04 node. 8046 CLOSE_WAIT 1 CLOSING 1 established) 40869 ESTABLISHED 1212 FIN_WAIT1 7575 FIN_WAIT2 1 Foreign 2252 LAST_ACK 7 LISTEN 143 SYN_RECV 4920 TIME_WAIT Can someone please tell me what tweaking i need to do. Please note that all these connections are persistent connections . tcp_fin_timeout = 30 tcp_keepalive_time = 1800 Right now, the application is working fine. But wondering will be there any issues as we add more users to this haproxy node.

  Read the article

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

  - by Wawrzek

  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 ~]# blockdev --report /dev/cciss/c0d9 RO RA SSZ BSZ StartSec Size Device rw 256 512 4096 0 3906963632 /dev/cciss/c0d9 [root@machine ~]# blockdev --report /dev/cciss/c0d9p1 RO RA SSZ BSZ StartSec Size Device rw 256 512 2048 1 3906959039 /dev/cciss/c0d9p1 We have a lot of small files, so yes the block size is smaller than normal. The device is a logical driver on an HP P410 raid controller, simple disk without any raid - RAID 0 on one disk to be precise. (Please note that above configuration is a feature not a bug). Therefore, I have the following questions. Can the above discrepancy in the block size affect disk performance? Can I control the block size using hpacucli?

  Read the article

• High CPU usage on Linux machine

  - by user305210

  I have a piece of java code running on two different machines, but on one of the linux machines, the code uses alot of CPU (close to 100% cpu usage). On the other machine the same code uses less cpu (under 3 to 4%). The machine where cpu usage is high, is a more powerful machine, more CPU and and more memory. This has started happening recently and performance on the machine with high cpu usage has degraded significantly. I am wondering if anyone has any ideas why something like this could happen, possible causes behind this etc. any guesses? No recent changes in hardware were made, no recent code updates... Thank you.

  Read the article

• Ultra Low Latency Linux Distribution or Kernel

  - by Zanler

  I'd like to know if there are any linux distributions that are focused on low latency networking. The area I'm working in is algorithmic trading, and extremely low latency comms between machines is a must. The current h/w we're using is 10g ethernet, we're looking into things like infiniband RDMA and Voltaire VMA I've googled around, and have only been able to find tidbtits of kernel patches, command line options and hardware suggestions. I'm looking for a complete solution, specially built kernel, kernel bypass features, essentially all the goodies rolled up into one package - does such a thing even exist? I ask as a lot of this stuff seems to be a black art, people keep secret what they know works etc.

  Read the article

• virtual machines: optimal host os to run Windows XP guest os?

  - by user61132

  My department doesn't have the budget to upgrade my ailing Dell D620 laptop. However, I do have the option to buy my own personal computer, then use my company-issued ISO image to run Windows XP as my guest os using virtualbox or vmware. Therefore, last month, I bought an Acer AX3910-U3012 desktop that had Windows 7 as the host os (and 8G RAM). In short, I was disappointed with the performance while trying to run WinXP as the guest os. (It didn't perform much better than my laptop.) Just wondering what the optimal host os would be for running Windows XP as the guest os? (No, I can't use my company-issued ISO image to build the os for my personal computer.) FWIW, I'm willing to spend up to $2k if it's REALLY worth it, but would prefer to spend no more than $1k. Also, in an effort to cut costs, I'd prefer buy a desktop instead of a laptop. Thanks for any/all feedback.

  Read the article

• Database Server Hardware components (order of importance), CPU speed VS CPU cache vs RAM vs DISK

  - by nulltorpedo

  I am new to database world and would like to know what are crucial hardware specs when it comes to database performance. I have searched the internet and found this so far (In order of decreasing importance): 1) Hard Disk: Get an SSD basically (much more IOPS than spinners) 2) Memory: Get as much as you can afford 3) CPU: For the same $ spent, prefer larger cache size over speed. Are these findings sensible? EDIT: I would like to focus on CPU speed VS CPU cache size. EDIT2: The database is used to store some combination of ints and int arrays with few text fields. There are a lot of Select queries looking for existing entries. If entry is not found, then insert it. I would say most of processing would be trying to find a match across a table with 200 columns and 20k rows. The insert statements are very few. EDIT3: Also, we have a lot of views (basically select queries).

  Read the article

• AIX network parameters to close TCP sockets of unplugged devices

  - by ADD Geek

  Hi there We have an AIX box, running what we call in banking "ATM Switch" not the ATM networking switch, but the bank ATM driver. where we have some ATM machines connected to two server processes. The problem is, when we disconnect any of these machines, the netstat -na| grep <port number> command shows that the socket established for this disconnected device is still established, we have to manually send a command from the software to make the socket aware that it is not live anymore. Is there a parameter on tcp level to make this connection aware within a minute or two that this device is not connected anymore? we had the following parameters set with root privileges: no -o tcp_keepidle=1000 no -o tcp_keepcnt=2 no -o tcp_keepintvl=150 no -o tcp_finwait2=100 it was originally having the default values. but even after we changed these parameters and restarted the server processes, the problem was still there.

  Read the article

• Freebsd or Linux? as BGP router over 100mbps

  - by Yucong Sun

  I am building a server to act as a BGP border router for my 100mbps uplink in ISP. I needs these feature: 1) Dual stack BGP peering/routing (at least 100Mbps, maybe more). 2) Potential full internet BGP feed. 3) Some basic ACL functionality. The hardware is L3426/8G ram. NIC will be on-board dual port Broadcom 5716. I've worked with Linux extensively before and it seems to be able to handle 100mbps, but I heard FreeBSD is faster on networking stuff. Which one should I use? And do we have some performance benchmark numbers out there? Cheers.

  Read the article

• Can I monitor active user count on my iis sites?

  - by Dejan.S

  We are having problems with performance on our server that host our websites that the processor gets upp to 90%. I would like to monitor the amount of users active on your sites that are published on the iis. My question, is this possible? is there any software for this? EDIT current (like this second) visitor count on all the active websites on our iis REASON FOR THIS if i can get the visitor amount on the days the CPU is not overloaded and and compare it to the days it is then i atleast know that this CAN be a reason why this is happening and i can take it from there. Otherwise i can focus on the code on the sites, or maybe google crawler is causing this, there are manythings that can cause this you know? for me this is just a simple way of troubleshooting.

  Read the article

• Nginx Slower than Apache??

  - by ichilton

  Hi, I've just setup 2x identical Rackspace Cloud instances and am doing some comparisons and benchmarks to compare Apache and Nginx. I'm testing with a 3.4k png file and initially 512MB server instances but have now moved to 1024MB server instances. I'm very surprised to see that whatever I try, Apache seems to consistently outperform Nginx....what am I doing wrong? Nginx: Server Software: nginx/0.8.54 Server Port: 80 Document Length: 3400 bytes Concurrency Level: 100 Time taken for tests: 2.320 seconds Complete requests: 1000 Failed requests: 0 Write errors: 0 Total transferred: 3612000 bytes HTML transferred: 3400000 bytes Requests per second: 431.01 [#/sec] (mean) Time per request: 232.014 [ms] (mean) Time per request: 2.320 [ms] (mean, across all concurrent requests) Transfer rate: 1520.31 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 0 11 15.7 3 120 Processing: 1 35 76.9 20 1674 Waiting: 1 31 73.0 19 1674 Total: 1 46 79.1 21 1693 Percentage of the requests served within a certain time (ms) 50% 21 66% 39 75% 40 80% 40 90% 98 95% 136 98% 269 99% 334 100% 1693 (longest request) And Apache: Server Software: Apache/2.2.16 Server Port: 80 Document Length: 3400 bytes Concurrency Level: 100 Time taken for tests: 1.346 seconds Complete requests: 1000 Failed requests: 0 Write errors: 0 Total transferred: 3647000 bytes HTML transferred: 3400000 bytes Requests per second: 742.90 [#/sec] (mean) Time per request: 134.608 [ms] (mean) Time per request: 1.346 [ms] (mean, across all concurrent requests) Transfer rate: 2645.85 [Kbytes/sec] received Connection Times (ms) min mean[+/-sd] median max Connect: 0 1 3.7 0 27 Processing: 0 3 6.2 1 29 Waiting: 0 2 5.0 1 29 Total: 1 4 7.0 1 29 Percentage of the requests served within a certain time (ms) 50% 1 66% 1 75% 1 80% 1 90% 17 95% 19 98% 26 99% 27 100% 29 (longest request) I'm currently using worker_processes 4; and worker_connections 1024; but i've tried and benchmarked different values and see the same behaviour on all - I just can't get it to perform as well as Apache and from what i've read previously, i'm shocked about this! Can anyone give any advice? Thanks, Ian

  Read the article

• SQL Server Instancing: Should I use multiple instances or databases?

  - by Spence

  I have a reasonable server connected to a SAN which will be running SQL servers for multiples of the same application. There are no security issues with one application being able to read anothers database. We are unfortunately in 32 bit windows as well. I'm of the opinion that it would be better to use one instance on the server, enable AWE so that the server instance can use almost all of the ram we have and then run each of the databases in the one instance. However I've been overruled by the gods of the IT department on this one, so I'm really curious to hear your thoughts on this. From a performance point of view, am I incorrect that one instance of SQL is better than two? I know that we could do some failover stuff, but doing that on one blade only seems like overkill to me..

  Read the article

• Programs minimized for long time takes long time to "wake up"

  - by bart

  I'm working in Photoshop CS6 and multiple browsers a lot. I'm not using them all at once, so sometimes some applications are minimized to taskbar for hours or days. The problem is, when I try to maximize them from the taskbar - it sometimes takes longer than starting them! Especially Photoshop feels really weird for many seconds after finally showing up, it's slow, unresponsive and even sometimes totally freezes for minute or two. It's not a hardware problem as it's been like that since always on all on my PCs. Would I also notice it after upgrading my HDD to SDD and adding RAM (my main PC holds 4 GB currently)? Could guys with powerful pcs / macs tell me - does it also happen to you? I guess OSes somehow "focus" on active software and move all the resources away from the ones that run, but are not used. Is it possible to somehow set RAM / CPU / HDD priorities or something, for let's say, Photoshop, so it won't slow down after long period of inactivity?

  Read the article

• Simultaneous read/write to RAID array slows server to a crawl

  - by Jeff Leyser

  Fairly beefy NFS/SMB server (32GB RAM, 2 Xeon quad cores) with LSI MegaRAID 8888ELP controlling 12 drives configured into 3 different arrays. 5 2TB drives are grouped into a RAID 6 array. As expected, write performance to the array is slow. However, sustained, simultaneous read/write to the array (wether through NFS or done locally) seems to practically block any other access to anything else on the controller. For example, if I do: cp /home/joe/BigFile /home/joe/BigFileCopy where BigFile is 20G, then even a simple ls /home/jane will take many 10s of seconds to complete. In addition, an ls /backup will also take many tens of seconds, even though /backup is a different array on the same controller. As soon as the cp is done, everything is back to normal. cp /home/joe/BigFile /backup/BigFile does not exhibit this behavior. It's only when doing read/write to the same array.

  Read the article

• Running game server and webserver on EC2

  - by mazzzzz

  Hey guys, I have a webhost, and an EC2 server (to run a game server on). The problem is that I want to access/modify the EC2's files with php admin programs. I looked into a lot of options to just have the webhost communicate with the EC2 server (ssh, etc), but none of them panned out. My question is if I were to install a lightweight webserver (think lighttpd) on my EC2 server, how badly would it hurt the game server's performance? I was leaning away from this solution, even though the webserver (on the EC2 server) wouldn't get many hits (less than a 100 a day). Thanks for your thoughts, Max

  Read the article

• Troubleshooting a high SQL Server Compilation/Batch-Ratio

  - by Sleepless

  I have a SQL Server (quad core x86, 4GB RAM) that constantly has almost the same values for "SQLServer:SQL Statistics: SQL compilations/sec" and "SQLServer:SQL Statistics: SQL batches/sec". This could be interpreted as a server running 100% ad hoc queries, each one of which has to be recompiled, but this is not the case here. The sys.dm_exec_query_stats DMV lists hundreds of query plans with an execution_count much larger than 1. Does anybody have any idea how to interpret / troubleshoot this phenomenon? BTW, the server's general performance counters (CPU,I/O,RAM) all show very modest utilization.

  Read the article

• Monitoring bespoke software with Zenoss

  - by Andy S

  We've got a lot of back-end applications that we need to monitor the performance of (metrics such as orders waiting to be processed, time since last run, etc). Currently, this is done by an in-house watchdog application that fires out emails whenever a threshold is exceeded, but there's no way to acknowledge an issue and squelch these alerts. Rather than build our own complete alerting system, we'd like to tie in to the Zenoss installation we use to monitor our servers. I've found a few articles on creating events programmatically, but I'd rather Zenoss itself monitors the values that the current watchdog app is looking at (so we get the benefits of graphing and history as well). Is it possible, then, to programmatically provide a data feed (rather than an event) to Zenoss? Or is there another way to go about this?

  Read the article

• Do SSD hybrid drives perform better than HDD + ReadyBoost flash?

  - by Chris W. Rea

  Seagate has released a product called the Momentus XT Solid State Hybrid Drive. This looks exactly like what Windows ReadyBoost attempts to do with software at the OS level: Pairing the benefits of a large hard drive together with the performance of solid-state flash memory. Does the Momentus XT out-perform a similar ad-hoc pairing of a decent hard drive with similar flash memory storage under Windows ReadyBoost? Other than the obvious "a hardware implementation ought to be faster than a software implementation", why would ReadyBoost not be able to perform as well as such a hybrid device?

  Read the article

< Previous Page | 91 92 93 94 95 96 97 98 99 100 101 102  | Next Page >