Jan
26
2015
--

Here’s What You Need To Know From Microsoft’s $26B Quarter

microsoft-data Microsoft reported its fiscal second-quarter financial performance today, laid out its forecasts for its future performance and took questions from a number of analyst. It was a flurry of data, so let’s take a moment and dig through the big points that matter. Read More

Jan
26
2015
--

Sources Say IBM Planning On Laying Off 12,000 Over Next Year

IBM Logo Rumors have been swirling — and IBM’s stock has been rising — on reports that the company is planning a huge round of layoffs of up to 26% of its workforce, or 118,000 people. TechCrunch has been digging and has found out from two separate sources that there will in fact be job cuts, but not anywhere close to this magnitude. Multiple sources tell TechCrunch the 118,000… Read More

Jan
26
2015
--

Percona Toolkit 2.2.13 is now available

Percona ToolkitPercona is pleased to announce the availability of Percona Toolkit 2.2.13.  Released January 26, 2015. Percona Toolkit is a collection of advanced command-line tools to perform a variety of MySQL server and system tasks that are too difficult or complex for DBAs to perform manually. Percona Toolkit, like all Percona software, is free and open source.

This release is the current GA (Generally Available) stable release in the 2.2 series. It includes multiple bug fixes for pt-table-checksum with better support for Percona XtraDB Cluster, various other fixes, as well as continued preparation for MySQL 5.7 compatibility. Full details are below. Downloads are available here and from the Percona Software Repositories.

New Features:

  • pt-kill now supports new --query-id option. This option can be used to print a query fingerprint hash after killing a query to enable the cross-referencing with the pt-query-digest output. This option can be used along with --print option as well.

Bugs Fixed:

  • Fixed bug 1408375: Percona Toolkit was vulnerable to MITM attack which could allow exfiltration of MySQL configuration information via --version-check option. This vulnerability was logged as CVE 2015-1027
  • Fixed bug 1019479: pt-table-checksum now works with ONLY_FULL_GROUP_BY SQL mode.
  • Fixed bug 1394934: running pt-table-checksum in debug mode would cause an error.
  • Fixed bug 1396868: regression introduced in Percona Toolkit 2.2.12 caused pt-online-schema-change not to honor --ask-pass option.
  • Fixed bug 1399789: pt-table-checksum would fail to find Percona XtraDB Cluster nodes when variable wsrep_node_incoming_address was set to AUTO.
  • Fixed bug 1321297: pt-table-checksum was reporting differences on timestamp columns with replication from 5.5 to 5.6 server version, although the data was identical.
  • Fixed bug 1388870: pt-table-checksum was showing differences if the master and slave were in different time zone.
  • Fixed bug 1402668: pt-mysql-summary would exit if Percona XtraDB Cluster was in Donor/Desynced state.
  • Fixed bug 1266869: pt-stalk would fail to start if $HOME environment variable was not set.

Details of the release can be found in the release notes and the 2.2.13 milestone at Launchpad. Bugs can be reported on the Percona Toolkit launchpad bug tracker.

The post Percona Toolkit 2.2.13 is now available appeared first on MySQL Performance Blog.

Jan
26
2015
--

MySQL benchmarks on eXFlash DIMMs

In this blog post, we will discuss MySQL performance on eXFlash DIMMs. Earlier we measured the IO performance of these storage devices with sysbench fileio.

Environment

The benchmarking environment was the same as the one we did sysbench fileio in.

CPU: 2x Intel Xeon E5-2690 (hyper threading enabled)
FusionIO driver version: 3.2.6 build 1212
Operating system: CentOS 6.5
Kernel version: 2.6.32-431.el6.x86_64

In this case, we used a separate machine for testing which had a 10G ethernet connection to this server. This server executed sysbench. The client was not the bottleneck in this case. The environment is described in greater detail at the end of the blog post.

Sysbench OLTP write workload

exflash_sysbench_oltp_tp_partial

The graph shows throughput for sysbench OLTP, we will examine properties only for the dark areas of this graph: which is the read/write case for high concurrency.

Each table in the following sections has the following columns

column explanation
storage The device that was used for the measurement.
threads The number of sysbench client threads were used in the benchmark.
ro_rw Read-only or read-write. In the whitepaper you can find detailed information about read-only data as well.
sd The standard deviation of the metric in question.
mean The mean of the metric in question.
95thpct The 95th percentile of the metric in question (the maximum without the highest 5 percent of the samples).
max The maximum of the metric in question.

Sysbench OLTP throughput

storage threads ro_rw sd mean 95thpct max
eXFlash DIMM_4 128 rw 714.09605 5996.5105 7172.0725 7674.87
eXFlash DIMM_4 256 rw 470.95410 6162.4271 6673.0205 7467.99
eXFlash DIMM_8 128 rw 195.57857 7140.5038 7493.4780 7723.13
eXFlash DIMM_8 256 rw 173.51373 6498.1460 6736.1710 7490.95
fio 128 rw 588.14282 1855.4304 2280.2780 7179.95
fio 256 rw 599.88510 2187.5271 2584.1995 7467.13

Going from 4 to 8 eXFlash DIMMs will mostly mean more consistent throughput. The mean throughput is significantly higher in case of 8 DIMMs used, but the 95th percentile and the maximum values are not much different (the difference in standard deviation also shows this). The reason they are not much different is that these benchmark are CPU bound (check CPU idle time table later in this post or the graphs in the whitepaper). The PCI-E flash drive on the other hand can do less than half of the throughput of the eXFlash DIMMs (the most relevant is comparing the 95th percentile value).

Sysbench OLTP response time

storage threads ro_rw sd mean 95thpct max
eXFlash DIMM_4 128 rw 4.4187784 37.931489 44.2600 64.54
eXFlash DIMM_4 256 rw 9.6642741 90.789317 109.0450 176.45
eXFlash DIMM_8 128 rw 2.1004085 28.796017 32.1600 67.10
eXFlash DIMM_8 256 rw 5.5932572 94.060628 101.6300 121.92
fio 128 rw 51.2343587 138.052150 203.1160 766.11
fio 256 rw 72.9901355 304.851844 392.7660 862.00

The 95th percentile response time for the eXFlash DIMM’s case are less than 1/4 compared to the PCI-E flash device.

CPU idle percentage

storage threads ro_rw sd mean 95thpct max
eXFlash DIMM_4 128 rw 1.62846674 3.3683857 6.2600 22.18
eXFlash DIMM_4 256 rw 1.06980095 2.2930634 3.9170 26.37
eXFlash DIMM_8 128 rw 0.42987637 0.8553543 1.2900 15.28
eXFlash DIMM_8 256 rw 1.32328435 4.4861795 6.7100 9.40
fio 128 rw 4.21156996 26.1278994 31.5020 55.49
fio 256 rw 5.49489852 19.3123639 27.6715 47.34

The percentage of CPU being idle shows that the performance bottleneck in this benchmark was the CPU in case of eXFlash DIMMs (both with 4 and 8 DIMMs, this is why we didn’t see a substantial throughput difference between the 4 and the 8 DIMM setup). However, for the PCI-E flash, the storage device itself was the bottleneck.

If you are interested in more details, download the free white paper which contains the full analysis of sysbench OLTP and linkbench benchmarks.

The post MySQL benchmarks on eXFlash DIMMs appeared first on MySQL Performance Blog.

Jan
26
2015
--

As Google Looks To Expand Wallet Use, WePay Integrates Instant Buy API

google-wallet Google is reportedly eyeing up an acquisition of Softcard to expand Google Wallet services to more points of sale with retailers; but it also wants to grow its position in the wider world of mobile-based transactions to compete with the likes of PayPal, by way of its Instant Buy API. Originally launched for Android in 2013, today the Instant Buy API is taking a step forward: Google is looking… Read More

Jan
25
2015
--

A16Z Leads $58M Round In UK’s TransferWise To Ramp Up Its P2P Transfer Business

v3_for_TransferWise 6 TransferWise, the fast-growing UK-based P2P money transfer startup that has reportedly been in talks with Facebook for remittance services, has raised a large tranche of funding led by one of the social network’s earliest backers. Andreessen Horowitz is heading up a new investment of $58 million, a Series C round with participation also from previous backers Sir Richard Branson,… Read More

Jan
25
2015
--

Here’s How To Turn On Windows 10’s New, Hidden Calendar And Clock

windows 10 I presume by now that if you are a Windows kid, you are using the newest build of the Windows 10 operating system, the recently released 9926 edition. If you are, go ahead and select the clock in the lower right corner of your screen. It looks slightly mundane, does it not? I thought so. What if it could look like this (Image via Brad Sams): It’s not hard to turn on. I even managed it… Read More

Jan
25
2015
--

Wonderful thing about Tigger…

TiggerSmallThis is the special story of Tigger. I have shared most of my life with cats, typically 3-6 of them at any time. Though Pippin is my current favourite, Tigger remains the most dear to me. Let me tell you why.

When I was a young teen, living in rural Oxfordshire in England, my parents promised me a new cat. We drove a ways to an animal shelter (we always adopt cats). Naturally, I wanted a kitten and there were hundreds walking around in a huge indoor space. I had my heart set on this tiny, cute silver kitten, but it was yet too young to leave its mother. I kept looking at all the other kittens, but all the while this adorable little orange cat kept following me everywhere I went. He adopted me! Well I had to take him with me then, so that was the cat I chose – Tigger.

He didn't even need a cat carrier. He was so enamoured with me (and I with him) that he just curled up on my lap in the car and went to sleep. Incidentally, the only cat I have ever lived with that didn't mind being in the car.

Tigger was a red tabby, Maine Coon cross and wasn't he handsome? He was the friendliest cat, often too much so. As he grew up, he had a fondness for sitting in the middle of the road. House cats are not a common thing in England as they are in America. Most cats roamed free, coming into the house through their own kitty door. Luckily, the road in our residential area was curvy and no one seemed to speed. It was not uncommon for a driver to have to stop, get out of his car and lift Tigger to the sidewalk. Oh yes, Tigger adored the attention! He was a real character.

His favourite spot to sleep was on the back of our TV, one of those huge CRT kinds from the 70's and 80's. The vent at the back made a toasty spot for him to sprawl out. A common source of amusement was when he relaxed too much and we'd hear this frantic scrabbling sound as he rolled off the back of the TV. It never stopped him, however.

This is where the story turns sad but becomes most special. Tissues at the ready folks. We lived in a two-floor house and as Tigger reached a grand old age (incredible that he never got run over!) he lost interest in climbing the steep stairs to the second-floor. One weekend afternoon, I was sitting on my bedroom floor (I don't remember what I was doing) when in walked Tigger. My mother later told me that it had taken him ages to clamber up one stair after the other, taking several rests. Surprised to see him, I of course made a huge fuss of him. Purring, he curled up in a ball next to me on the floor… and died.

Whenever I feel down, I think of my special Tigger.

Whenever I feel that things are getting tough, I remember that my cat Tigger climbed agonizingly up the stairs to share his final moments with me.

I hope that pet heaven has plenty of warm TV grilles and no stairs.

 

Jan
25
2015
--

Social Customer Service Firm Sparkcentral Locks Up A $12M Series B

Screen Shot 2015-01-25 at 11.36.17 AM Sparkcentral, a company that provides tools to help businesses conduct customer support over social channels, has raised a $12 million Series B round of funding, led by Split Rock Partners. The company previously raised a total of $5.6 million, including a $4.5 million Series A round of capital in October of 2013, or around 15 months ago. That places the company’s Series B round inside of… Read More

Jan
23
2015
--

There’s A Big Difference Between Using Facebook ‘At Work’ And ‘For Work’

fb-work2 If you’re an employer, how do you solve a problem like Facebook?
Roughly 61% of office workers use social media during the day and Facebook takes up a huge share of that surfing. Its highest traffic actually occurs mid-week between 1 to 3 pm. All told, this 1.5% drop in productivity adds up to 12 billion hours wasted per year with a cost of $650 billion dollars to the employee’s… Read More

Powered by WordPress | Theme: Aeros 2.0 by TheBuckmaker.com