Tag Info

New answers tagged

1

To me it looks like that the plugin does simply so heavy processing for every request that the requests take such a long time. You should ask the plugin provider if they can explain the slowdown in any way.


0

Bit late to the party here, but for what it's worth "attached" SSDs in Azure have their IOPs throttled based on the machine size. It wasn't mentioned in the pricing anywhere but I raised this issue as a ticket with technical support when they referred me to the blog post below. See this link: ...


6

You might know what a core is from shopping for desktops and laptops. It's the CPU, the processor, the bit that does the work. Here's a wikipedia link that might help. I plugged your site into this tool and most of the complaints were CSS and javascript that had to fully download before your site could fully render. Of course, I imagine we're viewing the ...


0

Maybe it can be useful: http://www.alfaexploit.com/ficheros_web/leer.php?id=161 In the link above you will find an useful script generating files between 1-4Mb, in that way the read/write speed can be checked.


2

Most of the writers here are just ignorant of "write hole". This is the basis which allows for crying out for battey backup units of hardware RAIDs vs. absense of a such for software RAIDs. Well, for e. g., Linux software RAID implementation either supports bitmaps of write operations or does full "parity" re-calculation in case of not-clean shutdown. ZFS ...


27

In short: if using a low-end RAID card (without cache), do yourself a favor and switch to software RAID. If using a mid-to-high-end card (with BBU or NVRAM), then hardware is often (but not always! see below) a good choice. Long answer: when computing power was limited, hardware RAID cards had the significantly advantage to offload parity/syndrome ...


3

The RAID-controller you have your eye one is a cheap one and is basically a fakeraid. It even depends on your mainboard to provide some functions like memory and not a lot of mainboards have support for it which results in that you can't load the driver. About HW vs SW-RAID itself. I'm not using HW-RAID anymore unless it is a box with an EMC logo on it for ...


3

You'll want a battery or flash-backed cache solution for any hardware controller you purchase. Most regret not doing so. But to answer your question, most controllers have configurable cache ratios... so 100% read cache and 0 % write cache negates the need for BBU protection. Your write performance will just suck. I can't address your software RAID ...


0

With innodb you might be filling your transaction log (innodb_log_size). While inserting, InnoDB first writes everything to the transaction log. Once in the log transactions get applied to the database itself. So that if server crashes mid-transaction, it can replay the log (reapply the transactions) to keep the data consistent. This actually means, every ...


0

Increase the pool size can surely have a very pronounced influence on InnoDB performance. Try to increase it to 128/256 MB and retry your test. Here you can found some more informations.


2

MLC SSD really need a fast private DRAM cache for delivering high IOPS values. While your controller has its own cache and it is enabled, your disk's private DRAM cache is disabled. This is a safety measure, as enabling that unprotected (from power losses) cache can put your data at risk. Sometime it is safe to reenable it (eg: your disks has power loss ...


4

There are a few issues here. You don't have any controller write cache or a battery-backed or flash-capacitor. The HP Smart Array P410 controller is limited in IOPS capacity. It's not a good match for SSDs. Using SATA drives on a Smart Array P410 causes the interface speed to downshift to 3.0Gbps instead of 6.0Gbps. Please try with RAID 1+0. RAID5 is not ...


0

After contacting Netgear support, it appears that: If you use 2 stations (1 client/1 server), it will actually only use one link (hence the 1Gbps/940mbps), the link used is decided by the LACP hashing algorithm. To go above the 1Gbps limit, you will need to test with more that 1 client. Source: Netgear support ticket response The same ticket ...


2

The cache on the card is getting in the way. The raid card cache is designed to enhance the performance of spinning drives. The best option on most ssd array is direct io and write through. You can test the different performance using hdtune or various other tools. You can leave the drive cache enabled.


1

http://veerapen.blogspot.com/2011/09/tuning-redhat-enterprise-linux-rhel-54.html Configuring the Linux scheduler on systems with hardware RAID and changing the default from [cfq] to [noop] gives I/O improvements. Use the nfsstat command, to calculate percentage of reads/writes. Set the RAID controller cache ratio to match. For heavy workloads you will ...


9

At first, the client requests will get queued, until there is a process/thread that gets free on the apache server. So, the clients will see a delay in loading the page. See the MaxClients parameter documentation for more information. When placed in the backlog queue, the client request can eventually time out on the client side. Then the user will see ...


0

You'd want to make sure your MaxClients is set to something comfortably above the typical peaks (which is sounds like is 10 in your case but you saw a burst up to 86 once, so maybe 150 to allow some breathing room in case you get a bigger burst). This way you won't run out of connections should that happen and users experience slowness. Be sure you have ...


2

It can be a problem related to packet size and latency. Try the following: enable jumbo frames (MTU >= 9000 bytes) on both machines use UDP or, alternatively, manually increase TCP window size on both machines The report back your results.


0

After some years in the trench, my answer is ZFS and SmartOS. Here's a paper on the benchmarks: https://www.joyent.com/public-cloud/benchmarks/postgresql


0

Depending on your urgency you could wait for adoption of "Salsa20" and "ChaCha" in particular that is intended to be direct replacement for RC4 in terms of performance. However, right now only google Chrome and latest releases of Android OS support it on the client side and it is not in OpenSSL yet, so no servers support yet. Otherwise I agree with others on ...


1

Of course it would be great if someone could give an answer which allows to fix your problem right away. But I fear, there is no obvious answer. But there might be some directions of attacking the problem not attempted yet: Under the hypothesis, that some of your machines sometimes show the behavior and others never do, one could conclude subtle hardware ...


1

On old Qemu/KVM versions, Qcow2 backend was very slow when not preallocated, more so if used without writeback cache enabled. See here for more information. On more recent Qemu versions, Qcow2 files are much faster, even when using no preallocation (or metadata-only preallocation). Still, LVM volumes remain faster. A note on the cache modes: writeback ...


3

You can set up a caching proxy (assuming we're talking about HTTP - and potentially HTTPS if you are okay to set up HTTPS interception) such as Squid to cache the server's responses. Tinkering with the refresh patterns and using non-standard options (such as ignoring Cache-Control headers) may yield even better results at the expense of breaking the HTTP ...


5

No, it's unlikely that the distance from France to Canada is making any significant difference, or that getting a Canadian VPN would help. If the server is overloaded, then there's nothing that you can do except for doing your download at a quieter time. The server's operators need to upgrade it. The only exception to this would be if the server's external ...


2

The best tool I know about is Comcast. With it, you can limit your bandwidth as well as your latency and packet-loss. As the owner of the project say "Simulating shitty network connections so you can build better systems."


1

If you're running your vms with a single command, for arguments you can use kvm -drive file=/path_to.qcow2,if=virtio,cache=off <...> It got me from 3MB/s to 70MB/s


1

If this is a desktop system, this will likely get marked as off-topic and redirected to SuperUser - FYI. More hardware specifications would be needed to answer with any degree of certainty (what motherboard, which PCI slot the card is in, etc). However, that LSI card may well be the performance bottleneck. I would suggest you set up a single-drive RAID0 ...



Top 50 recent answers are included