2 var netdataDashboard = window.netdataDashboard || {};
4 // ----------------------------------------------------------------------------
7 // information about the main menus
9 netdataDashboard.menu = {
11 title: 'System Overview',
12 icon: '<i class="fa fa-bookmark" aria-hidden="true"></i>',
13 info: 'Overview of the key system metrics.'
17 title: 'systemd Services',
18 icon: '<i class="fa fa-cogs" aria-hidden="true"></i>',
19 info: 'Resources utilization of systemd services. netdata monitors all systemd services via cgroups (the resources accounting used by containers). '
23 title: 'Access Points',
24 icon: '<i class="fa fa-wifi" aria-hidden="true"></i>',
25 info: 'Performance metrics for the access points (i.e. wireless interfaces in AP mode) found on the system.'
29 title: 'Quality of Service',
30 icon: '<i class="fa fa-globe" aria-hidden="true"></i>',
31 info: 'Netdata collects and visualizes <code>tc</code> class utilization using its <a href="https://github.com/firehol/netdata/blob/master/plugins.d/tc-qos-helper.sh" target="_blank">tc-helper plugin</a>. If you also use <a href="http://firehol.org/#fireqos" target="_blank">FireQOS</a> for setting up QoS, netdata automatically collects interface and class names. If your QoS configuration includes overheads calculation, the values shown here will include these overheads (the total bandwidth for the same interface as reported in the Network Interfaces section, will be lower than the total bandwidth reported here). QoS data collection may have a slight time difference compared to the interface (QoS data collection uses a BASH script, so a shift in data collection of a few milliseconds should be justified).'
35 title: 'Network Interfaces',
36 icon: '<i class="fa fa-share-alt" aria-hidden="true"></i>',
37 info: 'Performance metrics for network interfaces.'
41 title: 'IPv4 Networking',
42 icon: '<i class="fa fa-cloud" aria-hidden="true"></i>',
43 info: 'Metrics for the IPv4 stack of the system. <a href="https://en.wikipedia.org/wiki/IPv4" target="_blank">Internet Protocol version 4 (IPv4)</a> is the fourth version of the Internet Protocol (IP). It is one of the core protocols of standards-based internetworking methods in the Internet. IPv4 is a connectionless protocol for use on packet-switched networks. It operates on a best effort delivery model, in that it does not guarantee delivery, nor does it assure proper sequencing or avoidance of duplicate delivery. These aspects, including data integrity, are addressed by an upper layer transport protocol, such as the Transmission Control Protocol (TCP).'
47 title: 'IPv6 Networking',
48 icon: '<i class="fa fa-cloud" aria-hidden="true"></i>',
49 info: 'Metrics for the IPv6 stack of the system. <a href="https://en.wikipedia.org/wiki/IPv6" target="_blank">Internet Protocol version 6 (IPv6)</a> is the most recent version of the Internet Protocol (IP), the communications protocol that provides an identification and location system for computers on networks and routes traffic across the Internet. IPv6 was developed by the Internet Engineering Task Force (IETF) to deal with the long-anticipated problem of IPv4 address exhaustion. IPv6 is intended to replace IPv4.'
53 title: 'IP Virtual Server',
54 icon: '<i class="fa fa-eye" aria-hidden="true"></i>',
55 info: '<a href="http://www.linuxvirtualserver.org/software/ipvs.html" target="_blank">IPVS (IP Virtual Server)</a> implements transport-layer load balancing inside the Linux kernel, so called Layer-4 switching. IPVS running on a host acts as a load balancer at the front of a cluster of real servers, it can direct requests for TCP/UDP based services to the real servers, and makes services of the real servers to appear as a virtual service on a single IP address.'
59 title: 'Firewall (netfilter)',
60 icon: '<i class="fa fa-shield" aria-hidden="true"></i>',
61 info: 'Performance metrics of the netfilter components.'
66 icon: '<i class="fa fa-bolt" aria-hidden="true"></i>',
67 info: 'Detailed information for each CPU of the system. A summary of the system for all CPUs can be found at the <a href="#menu_system">System Overview</a> section.'
72 icon: '<i class="fa fa-bolt" aria-hidden="true"></i>',
73 info: 'Detailed information about the memory management of the system.'
78 icon: '<i class="fa fa-folder" aria-hidden="true"></i>',
79 info: 'Charts with performance information for all the system disks. Special care has been given to present disk performance metrics in a way compatible with <code>iostat -x</code>. netdata by default prevents rendering performance charts for individual partitions and unmounted virtual disks. Disabled charts can still be enabled by configuring the relative settings in the netdata configuration file.'
84 icon: '<i class="fa fa-leaf" aria-hidden="true"></i>',
85 info: 'Readings of the configured system sensors.'
90 icon: '<i class="fa fa-leaf" aria-hidden="true"></i>',
91 info: 'The Intelligent Platform Management Interface (IPMI) is a set of computer interface specifications for an autonomous computer subsystem that provides management and monitoring capabilities independently of the host system\'s CPU, firmware (BIOS or UEFI) and operating system.'
96 icon: '<i class="fa fa-folder-open" aria-hidden="true"></i>',
97 info: 'Performance metrics of the Network File Server. NFS is a distributed file system protocol, allowing a user on a client computer to access files over a network, much like local storage is accessed. NFS, like many other protocols, builds on the Open Network Computing Remote Procedure Call (ONC RPC) system. The NFS is an open standard defined in Request for Comments (RFC).'
102 icon: '<i class="fa fa-folder-open" aria-hidden="true"></i>',
103 info: 'Performance metrics of the NFS operations of this system, acting as an NFS client.'
107 title: 'Applications',
108 icon: '<i class="fa fa-heartbeat" aria-hidden="true"></i>',
109 info: 'Per application statistics are collected using netdata\'s <code>apps.plugin</code>. This plugin walks through all processes and aggregates statistics for applications of interest, defined in <code>/etc/netdata/apps_groups.conf</code> (the default is <a href="https://github.com/firehol/netdata/blob/master/conf.d/apps_groups.conf" target="_blank">here</a>). The plugin internally builds a process tree (much like <code>ps fax</code> does), and groups processes together (evaluating both child and parent processes) so that the result is always a chart with a predefined set of dimensions (of course, only application groups found running are reported). The reported values are compatible with <code>top</code>, although the netdata plugin counts also the resources of exited children (unlike <code>top</code> which shows only the resources of the currently running processes). So for processes like shell scripts, the reported values include the resources used by the commands these scripts run within each timeframe.',
115 icon: '<i class="fa fa-user" aria-hidden="true"></i>',
116 info: 'Per user statistics are collected using netdata\'s <code>apps.plugin</code>. This plugin walks through all processes and aggregates statistics per user. The reported values are compatible with <code>top</code>, although the netdata plugin counts also the resources of exited children (unlike <code>top</code> which shows only the resources of the currently running processes). So for processes like shell scripts, the reported values include the resources used by the commands these scripts run within each timeframe.',
121 title: 'User Groups',
122 icon: '<i class="fa fa-users" aria-hidden="true"></i>',
123 info: 'Per user group statistics are collected using netdata\'s <code>apps.plugin</code>. This plugin walks through all processes and aggregates statistics per user group. The reported values are compatible with <code>top</code>, although the netdata plugin counts also the resources of exited children (unlike <code>top</code> which shows only the resources of the currently running processes). So for processes like shell scripts, the reported values include the resources used by the commands these scripts run within each timeframe.',
128 title: 'Netdata Monitoring',
129 icon: '<i class="fa fa-bar-chart" aria-hidden="true"></i>',
130 info: 'Performance metrics for the operation of netdata itself and its plugins.'
134 title: 'Example Charts',
135 info: 'Example charts, demonstrating the external plugin architecture.'
140 icon: '<i class="fa fa-th" aria-hidden="true"></i>',
141 info: 'Container resource utilization metrics. Netdata reads this information from <b>cgroups</b> (abbreviated from <b>control groups</b>), a Linux kernel feature that limits and accounts resource usage (CPU, memory, disk I/O, network, etc.) of a collection of processes. <b>cgroups</b> together with <b>namespaces</b> (that offer isolation between processes) provide what we usually call: <b>containers</b>.'
146 icon: '<i class="fa fa-th-large" aria-hidden="true"></i>',
147 info: 'QEMU virtual machine resource utilization metrics. QEMU (short for Quick Emulator) is a free and open-source hosted hypervisor that performs hardware virtualization.'
152 icon: '<i class="fa fa-exchange" aria-hidden="true"></i>',
153 info: 'Network latency statistics, via <b>fping</b>. <b>fping</b> is a program to send ICMP echo probes to network hosts, similar to <code>ping</code>, but much better performing when pinging multiple hosts. fping versions after 3.15 can be directly used as netdata plugins.'
158 icon: '<i class="fa fa-database" aria-hidden="true"></i>',
159 info: 'Performance metrics for <b>memcached</b>. Memcached is a general-purpose distributed memory caching system. It is often used to speed up dynamic database-driven websites by caching data and objects in RAM to reduce the number of times an external data source (such as a database or API) must be read.'
164 icon: '<i class="fa fa-database" aria-hidden="true"></i>',
165 info: 'Performance metrics for <b>mysql</b>, the open-source relational database management system (RDBMS).'
170 icon: '<i class="fa fa-database" aria-hidden="true"></i>',
171 info: 'Performance metrics for <b>PostgresSQL</b>, the object-relational database (ORDBMS).'
176 icon: '<i class="fa fa-database" aria-hidden="true"></i>',
177 info: 'Performance metrics for <b>redis</b>. Redis (REmote DIctionary Server) is a software project that implements data structure servers. It is open-source, networked, in-memory, and stores keys with optional durability.'
182 icon: '<i class="fa fa-share-alt" aria-hidden="true"></i>',
183 info: 'Performance metrics for <b>RetroShare</b>. RetroShare is open source software for encrypted filesharing, serverless email, instant messaging, online chat, and BBS, based on a friend-to-friend network built on GNU Privacy Guard (GPG).'
188 icon: '<i class="fa fa-folder-open" aria-hidden="true"></i>',
189 info: 'Performance metrics for the InterPlanetary File System (IPFS), a content-addressable, peer-to-peer hypermedia distribution protocol.'
194 icon: '<i class="fa fa-eye" aria-hidden="true"></i>',
195 info: 'Performance metrics for <b>PHP-FPM</b>, an alternative FastCGI implementation for PHP.'
200 icon: '<i class="fa fa-envelope" aria-hidden="true"></i>',
206 icon: '<i class="fa fa-envelope" aria-hidden="true"></i>',
212 icon: '<i class="fa fa-thermometer-full" aria-hidden="true"></i>',
218 icon: '<i class="fa fa-eye" aria-hidden="true"></i>',
224 icon: '<i class="fa fa-eye" aria-hidden="true"></i>',
230 icon: '<i class="fa fa-file-text-o" aria-hidden="true"></i>',
231 info: 'Information extracted from a web server log file. <code>web_log</code> plugin incrementally parses the web server log file to provide, in real-time, a break down of key web server performance metrics. An extended log file format may optionally be used (for <code>nginx</code> and <code>apache</code>) offering timing information and bandwidth for both requests and responses. <code>web_log</code> plugin may also be configured to provide a break down of requests per URL pattern (check <a href="https://github.com/firehol/netdata/blob/master/conf.d/python.d/web_log.conf" target="_blank"><code>/etc/netdata/python.d/web_log.conf</code></a>).'
236 icon: '<i class="fa fa-tag" aria-hidden="true"></i>',
242 icon: '<i class="fa fa-exchange" aria-hidden="true"></i>',
248 icon: '<i class="fa fa-battery-half" aria-hidden="true"></i>',
254 icon: '<i class="fa fa-battery-half" aria-hidden="true"></i>',
259 title: 'Solar Power',
260 icon: '<i class="fa fa-sun-o" aria-hidden="true"></i>',
266 icon: '<i class="fa fa-random" aria-hidden="true"></i>',
273 // ----------------------------------------------------------------------------
276 // information to be shown, just below each submenu
278 // information about the submenus
279 netdataDashboard.submenu = {
280 'web_log.bandwidth': {
281 info: 'Bandwidth of requests (<code>received</code>) and responses (<code>sent</code>). <code>received</code> requires an extended log format (without it, the web server log does not have this information). This chart may present unusual spikes, since the bandwidth is accounted at the time the log line is saved by the web server, even if the time needed to serve it spans across a longer duration. We suggest to use QoS (e.g. <a href="http://firehol.org/#fireqos" target="_blank">FireQOS</a>) for accurate accounting of the web server bandwidth.'
285 info: 'Number of requests for each <code>URL pattern</code> defined in <a href="https://github.com/firehol/netdata/blob/master/conf.d/python.d/web_log.conf" target="_blank"><code>/etc/netdata/python.d/web_log.conf</code></a>. This chart counts all requests matching the URL patterns defined, independently of the web server response codes (i.e. both successful and unsuccessful).'
289 info: 'Charts showing the number of unique client IPs, accessing the web server.'
293 info: 'Web server response timings - the time the web server needed to prepare and respond to requests. This requires an extended log format and its meaning is web server specific. For most web servers this accounts the time from the reception of a complete request, to the dispatch of the last byte of the response. So, it includes the network delays of responses, but it does not include the network delays of requests.'
297 title: 'Memory Deduper',
298 info: 'Kernel Same-page Merging (KSM) performance monitoring, read from several files in <code>/sys/kernel/mm/ksm/</code>. KSM is a memory-saving de-duplication feature in the Linux kernel (since version 2.6.32). The KSM daemon ksmd periodically scans those areas of user memory which have been registered with it, looking for pages of identical content which can be replaced by a single write-protected page (which is automatically copied if a process later wants to update its content). KSM was originally developed for use with KVM (where it was known as Kernel Shared Memory), to fit more virtual machines into physical memory, by sharing the data common between them. But it can be useful to any application which generates many instances of the same data.'
302 info: 'Non-Uniform Memory Access (NUMA) is a hierarchical memory design the memory access time is dependent on locality. Under NUMA, a processor can access its own local memory faster than non-local memory (memory local to another processor or memory shared between processors). The individual metrics are described in the <a href="https://www.kernel.org/doc/Documentation/numastat.txt" target="_blank">Linux kernel documentation</a>.'
306 info: '<a href="https://en.wikipedia.org/wiki/Explicit_Congestion_Notification" target="_blank">Explicit Congestion Notification (ECN)</a> is a TCP extension that allows end-to-end notification of network congestion without dropping packets. ECN is an optional feature that may be used between two ECN-enabled endpoints when the underlying network infrastructure also supports it.'
309 'netfilter.conntrack': {
310 title: 'Connection Tracker',
311 info: 'Netfilter Connection Tracker performance metrics. The connection tracker keeps track of all connections of the machine, inbound and outbound. It works by keeping a database with all open connections, tracking network and address translation and connection expectations.'
314 'netfilter.nfacct': {
315 title: 'Bandwidth Accounting',
316 info: 'The following information is read using the <code>nfacct.plugin</code>.'
319 'netfilter.synproxy': {
320 title: 'DDoS Protection',
321 info: 'DDoS protection performance metrics. <a href="https://github.com/firehol/firehol/wiki/Working-with-SYNPROXY" target="_blank">SYNPROXY</a> is a TCP SYN packets proxy. It is used to protect any TCP server (like a web server) from SYN floods and similar DDoS attacks. It is a netfilter module, in the Linux kernel (since version 3.12). It is optimized to handle millions of packets per second utilizing all CPUs available without any concurrency locking between the connections. It can be used for any kind of TCP traffic (even encrypted), since it does not interfere with the content itself.'
324 'system.softnet_stat': {
328 return 'Statistics for CPUs SoftIRQs related to network receive work. Break down per CPU core can be found at <a href="#menu_cpu_submenu_softnet_stat">CPU / softnet statistics</a>. <b>processed</b> states the number of packets processed, <b>dropped</b> is the number packets dropped because the network device backlog was full (to fix them on Linux use <code>sysctl</code> to increase <code>net.core.netdev_max_backlog</code>), <b>squeezed</b> is the number of packets dropped because the network device budget ran out (to fix them on Linux use <code>sysctl</code> to increase <code>net.core.netdev_budget</code>). More information about identifying and troubleshooting network driver related issues can be found at <a href="https://access.redhat.com/sites/default/files/attachments/20150325_network_performance_tuning.pdf" target="_blank">Red Hat Enterprise Linux Network Performance Tuning Guide</a>.';
330 return 'Statistics for CPUs SoftIRQs related to network receive work.';
334 'cpu.softnet_stat': {
338 return 'Statistics for per CPUs core SoftIRQs related to network receive work. Total for all CPU cores can be found at <a href="#menu_system_submenu_softnet_stat">System / softnet statistics</a>. <b>processed</b> states the number of packets processed, <b>dropped</b> is the number packets dropped because the network device backlog was full (to fix them on Linux use <code>sysctl</code> to increase <code>net.core.netdev_max_backlog</code>), <b>squeezed</b> is the number of packets dropped because the network device budget ran out (to fix them on Linux use <code>sysctl</code> to increase <code>net.core.netdev_budget</code>). More information about identifying and troubleshooting network driver related issues can be found at <a href="https://access.redhat.com/sites/default/files/attachments/20150325_network_performance_tuning.pdf" target="_blank">Red Hat Enterprise Linux Network Performance Tuning Guide</a>.';
340 return 'Statistics for per CPUs core SoftIRQs related to network receive work. Total for all CPU cores can be found at <a href="#menu_system_submenu_softnet_stat">System / softnet statistics</a>.';
347 // ----------------------------------------------------------------------------
350 // information works on the context of a chart
351 // Its purpose is to set:
353 // info: the text above the charts
354 // heads: the representation of the chart at the top the subsection (second level menu)
355 // mainheads: the representation of the chart at the top of the section (first level menu)
356 // colors: the dimension colors of the chart (the default colors are appended)
357 // height: the ratio of the chart height relative to the default
359 netdataDashboard.context = {
363 return 'Total CPU utilization (all cores). 100% here means there is no CPU idle time at all. You can get per core usage at the <a href="#menu_cpu">CPUs</a> section and per application usage at the <a href="#menu_apps">Applications Monitoring</a> section.'
364 + netdataDashboard.sparkline('<br/>Keep an eye on <b>iowait</b> ', 'system.cpu', 'iowait', '%', '. If it is constantly high, your disks are a bottleneck and they slow your system down.')
365 + netdataDashboard.sparkline('<br/>An important metric worth monitoring, is <b>softirq</b> ', 'system.cpu', 'softirq', '%', '. A constantly high percentage of softirq may indicate network driver issues.');
367 valueRange: "[0, 100]"
371 info: 'Current system load, i.e. the number of processes using CPU or waiting for system resources (usually CPU and disk). The 3 metrics refer to 1, 5 and 15 minute averages. The system calculates this once every 5 seconds. For more information check <a href="https://en.wikipedia.org/wiki/Load_(computing)" target="_blank">this wikipedia article</a>',
376 info: 'Total Disk I/O, for all disks. You can get detailed information about each disk at the <a href="#menu_disk">Disks</a> section and per application Disk usage at the <a href="#menu_apps">Applications Monitoring</a> section.'
380 info: 'Total Swap I/O. (netdata measures both <code>in</code> and <code>out</code>. If either of them is not shown in the chart, it is because it is zero - you can change the page settings to always render all the available dimensions on all charts).'
384 info: 'Total page faults. <b>Major page faults</b> indicates that the system is using its swap. You can find which applications use the swap at the <a href="#menu_apps">Applications Monitoring</a> section.'
389 info: '<a href="https://en.wikipedia.org/wiki/Entropy_(computing)" target="_blank">Entropy</a>, is like a pool of random numbers (<a href="https://en.wikipedia.org/wiki//dev/random" target="_blank">/dev/random</a>) that are mainly used in cryptography. It is advised that the pool remains always <a href="https://blog.cloudflare.com/ensuring-randomness-with-linuxs-random-number-generator/" target="_blank">above 200</a>. If the pool of entropy gets empty, you risk your security to be predictable and you should install a user-space random numbers generating daemon, like <code>haveged</code> or <code>rng-tools</code> (i.e. <b>rngd</b>), to keep the pool in healthy levels.'
394 info: 'Number of new processes created.'
399 info: 'Total number of CPU interrupts. Check <code>system.interrupts</code> that gives more detail about each interrupt and also the <a href="#menu_cpu">CPUs</a> section where interrupts are analyzed per CPU core.'
402 'system.interrupts': {
403 info: 'CPU interrupts in detail. At the <a href="#menu_cpu">CPUs</a> section, interrupts are analyzed per CPU core.'
407 info: 'CPU softirqs in detail. At the <a href="#menu_cpu">CPUs</a> section, softirqs are analyzed per CPU core.'
410 'system.processes': {
411 info: 'System processes. <b>Running</b> are the processes in the CPU. <b>Blocked</b> are processes that are willing to enter the CPU, but they cannot, e.g. because they wait for disk activity.'
414 'system.active_processes': {
415 info: 'All system processes.'
419 info: '<a href="https://en.wikipedia.org/wiki/Context_switch" target="_blank">Context Switches</a>, is the switching of the CPU from one process, task or thread to another. If there are many processes or threads willing to execute and very few CPU cores available to handle them, the system is making more context switching to balance the CPU resources among them. The whole process is computationally intensive. The more the context switches, the slower the system gets.'
422 'system.idlejitter': {
424 info: 'Idle jitter is calculated by netdata. A thread is spawned that requests to sleep for a few microseconds. When the system wakes it up, it measures how many microseconds have passed. The difference between the requested and the actual duration of the sleep, is the <b>idle jitter</b>. This number is useful in real-time environments, where CPU jitter can affect the quality of the service (like VoIP media gateways).'
428 info: 'Total IPv4 Traffic.'
432 info: 'Total IPv6 Traffic.'
436 info: 'System Random Access Memory (i.e. physical memory) usage.'
440 info: 'System swap memory usage. Swap space is used when the amount of physical memory (RAM) is full. When the system needs more memory resources and the RAM is full, inactive pages in memory are moved to the swap space (usually a disk, a disk partition or a file).'
443 // ------------------------------------------------------------------------
448 netdataDashboard.gaugeChart('Saved', '12%', 'savings', '#0099CC')
456 return '<div data-netdata="' + id + '"'
457 + ' data-gauge-max-value="100"'
458 + ' data-chart-library="gauge"'
459 + ' data-title="Savings"'
460 + ' data-units="percentage %"'
461 + ' data-gauge-adjust="width"'
462 + ' data-width="12%"'
464 + ' data-after="-CHART_DURATION"'
465 + ' data-points="CHART_DURATION"'
466 + ' role="application"></div>';
472 info: 'A <a href="https://en.wikipedia.org/wiki/Page_fault" target="_blank">page fault</a> is a type of interrupt, called trap, raised by computer hardware when a running program accesses a memory page that is mapped into the virtual address space, but not actually loaded into main memory. If the page is loaded in memory at the time the fault is generated, but is not marked in the memory management unit as being loaded in memory, then it is called a <b>minor</b> or soft page fault. A <b>major</b> page fault is generated when the system needs to load the memory page from disk or swap memory.'
476 colors: NETDATA.colors[3],
477 info: 'Committed Memory, is the sum of all memory which has been allocated by processes.'
481 info: '<b>Dirty</b> is the amount of memory waiting to be written to disk. <b>Writeback</b> is how much memory is actively being written to disk.'
485 info: 'The total ammount of memory being used by the kernel. <b>Slab</b> is the amount of memory used by the kernel to cache data structures for its own use. <b>KernelStack</b> is the amount of memory allocated for each task done by the kernel. <b>PageTables</b> is the amount of memory decicated to the lowest level of page tables (A page table is used to turn a virtual address into a physical memory address). <b>VmallocUsed</b> is the amount of memory being used as virtual address space.'
489 info: '<b>Reclaimable</b> is the amount of memory which the kernel can reuse. <b>Unreclaimable</b> can not be reused even when the kernel is lacking memory.'
492 // ------------------------------------------------------------------------
493 // network interfaces
496 info: 'Packets that have been dropped at the network interface level. These are the same counters reported by <code>ifconfig</code> as <code>RX dropped</code> (inbound) and <code>TX dropped</code> (outbound). <b>inbound</b> packets can be dropped at the network interface level due to <a href="#menu_system_submenu_softnet_stat">softnet backlog</a> overflow, bad / unintented VLAN tags, unknown or unregistered protocols, IPv6 frames when the server is not configured for IPv6. Check <a href="https://www.novell.com/support/kb/doc.php?id=7007165" target="_blank">this document</a> for more information.'
499 // ------------------------------------------------------------------------
502 'ipv4.tcpmemorypressures': {
503 info: 'Number of times a socket was put in <b>memory pressure</b> due to a non fatal memory allocation failure (the kernel attempts to work around this situation by reducing the send buffers, etc).'
506 'ipv4.tcpconnaborts': {
507 info: 'TCP connection aborts. <b>baddata</b> (<code>TCPAbortOnData</code>) happens while the connection is on <code>FIN_WAIT1</code> and the kernel receives a packet with a sequence number beyond the last one for this connection - the kernel responds with <code>RST</code> (closes the connection). <b>userclosed</b> (<code>TCPAbortOnClose</code>) happens when the kernel receives data on an already closed connection and responds with <code>RST</code>. <b>nomemory</b> (<code>TCPAbortOnMemory</code> happens when there are too many orphaned sockets (not attached to an fd) and the kernel has to drop a connection - sometimes it will send an <code>RST</code>, sometimes it won\'t. <b>timeout</b> (<code>TCPAbortOnTimeout</code>) happens when a connection times out. <b>linger</b> (<code>TCPAbortOnLinger</code>) happens when the kernel killed a socket that was already closed by the application and lingered around for long enough. <b>failed</b> (<code>TCPAbortFailed</code>) happens when the kernel attempted to send an <code>RST</code> but failed because there was no memory available.'
510 // ------------------------------------------------------------------------
518 info: 'Real memory (RAM) used by applications. This does not include shared memory.'
522 info: 'Virtual memory allocated by applications. Please check <a href="https://github.com/firehol/netdata/wiki/netdata-virtual-memory-size" target="_blank">this article</a> for more information.'
533 // ------------------------------------------------------------------------
541 info: 'Real memory (RAM) used per user. This does not include shared memory.'
545 info: 'Virtual memory allocated per user. Please check <a href="https://github.com/firehol/netdata/wiki/netdata-virtual-memory-size" target="_blank">this article</a> for more information.'
556 // ------------------------------------------------------------------------
564 info: 'Real memory (RAM) used per user group. This does not include shared memory.'
568 info: 'Virtual memory allocated per user group. Please check <a href="https://github.com/firehol/netdata/wiki/netdata-virtual-memory-size" target="_blank">this article</a> for more information.'
579 // ------------------------------------------------------------------------
587 if(id.match(/.*-ifb$/))
588 return netdataDashboard.gaugeChart('Inbound', '12%', '', '#5555AA');
590 return netdataDashboard.gaugeChart('Outbound', '12%', '', '#AA9900');
595 // ------------------------------------------------------------------------
596 // NETWORK INTERFACES
600 netdataDashboard.gaugeChart('Received', '12%', 'received'),
601 netdataDashboard.gaugeChart('Sent', '12%', 'sent')
605 // ------------------------------------------------------------------------
608 'netfilter.sockets': {
611 netdataDashboard.gaugeChart('Active Connections', '12%', '', '#88AA00')
617 netdataDashboard.gaugeChart('New Connections', '12%', 'new', '#5555AA')
621 // ------------------------------------------------------------------------
627 netdataDashboard.gaugeChart('Utilization', '12%', '', '#FF5588')
629 info: 'Disk Utilization measures the amount of time the disk was busy with something. This is not related to its performance. 100% means that the system always had an outstanding operation on the disk. Keep in mind that depending on the underlying technology of the disk, 100% here may or may not be an indication of congestion.'
634 info: 'Backlog is an indication of the duration of pending disk operations. On every I/O event the system is multiplying the time spent doing I/O since the last update of this field with the number of pending operations. While not accurate, this metric can provide an indication of the expected completion time of the operations in progress.'
639 netdataDashboard.gaugeChart('Read', '12%', 'reads'),
640 netdataDashboard.gaugeChart('Write', '12%', 'writes')
642 info: 'Amount of data transferred to and from disk.'
646 info: 'Completed disk I/O operations. Keep in mind the number of operations requested might be higher, since the system is able to merge adjacent to each other (see merged operations chart).'
650 info: 'I/O operations currently in progress. This metric is a snapshot - it is not an average over the last interval.'
655 info: 'The sum of the duration of all completed I/O operations. This number can exceed the interval if the disk is able to execute I/O operations in parallel.'
659 info: 'The number of merged disk operations. The system is able to merge adjacent I/O operations, for example two 4KB reads can become one 8KB read before given to disk.'
663 info: 'The average service time for completed I/O operations. This metric is calculated using the total busy time of the disk and the number of completed operations. If the disk is able to execute multiple parallel operations the reporting average service time will be misleading.'
667 info: 'The average I/O operation size.'
671 info: 'The average time for I/O requests issued to the device to be served. This includes the time spent by the requests in queue and the time spent servicing them.'
675 info: 'Disk space utilization. reserved for root is automatically reserved by the system to prevent the root user from getting out of space.'
678 info: 'inodes (or index nodes) are filesystem objects (e.g. files and directories). On many types of file system implementations, the maximum number of inodes is fixed at filesystem creation, limiting the maximum number of files the filesystem can hold. It is possible for a device to run out of inodes. When this happens, new files cannot be created on the device, even though there may be free space available.'
682 info: 'The amount of data sent to mysql clients (<strong>out</strong>) and received from mysql clients (<strong>in</strong>).'
685 // ------------------------------------------------------------------------
689 info: 'The number of statements executed by the server.<ul>' +
690 '<li><strong>queries</strong> counts the statements executed within stored SQL programs.</li>' +
691 '<li><strong>questions</strong> counts the statements sent to the mysql server by mysql clients.</li>' +
692 '<li><strong>slow queries</strong> counts the number of statements that took more than <a href="http://dev.mysql.com/doc/refman/5.7/en/server-system-variables.html#sysvar_long_query_time" target="_blank">long_query_time</a> seconds to be executed.' +
693 ' For more information about slow queries check the mysql <a href="http://dev.mysql.com/doc/refman/5.7/en/slow-query-log.html" target="_blank">slow query log</a>.</li>' +
698 info: 'Usage of the internal handlers of mysql. This chart provides very good insights of what the mysql server is actually doing.' +
699 ' (if the chart is not showing all these dimensions it is because they are zero - set <strong>Which dimensions to show?</strong> to <strong>All</strong> from the dashboard settings, to render even the zero values)<ul>' +
700 '<li><strong>commit</strong>, the number of internal <a href="http://dev.mysql.com/doc/refman/5.7/en/commit.html" target="_blank">COMMIT</a> statements.</li>' +
701 '<li><strong>delete</strong>, the number of times that rows have been deleted from tables.</li>' +
702 '<li><strong>prepare</strong>, a counter for the prepare phase of two-phase commit operations.</li>' +
703 '<li><strong>read first</strong>, the number of times the first entry in an index was read. A high value suggests that the server is doing a lot of full index scans; e.g. <strong>SELECT col1 FROM foo</strong>, with col1 indexed.</li>' +
704 '<li><strong>read key</strong>, the number of requests to read a row based on a key. If this value is high, it is a good indication that your tables are properly indexed for your queries.</li>' +
705 '<li><strong>read next</strong>, the number of requests to read the next row in key order. This value is incremented if you are querying an index column with a range constraint or if you are doing an index scan.</li>' +
706 '<li><strong>read prev</strong>, the number of requests to read the previous row in key order. This read method is mainly used to optimize <strong>ORDER BY ... DESC</strong>.</li>' +
707 '<li><strong>read rnd</strong>, the number of requests to read a row based on a fixed position. A high value indicates you are doing a lot of queries that require sorting of the result. You probably have a lot of queries that require MySQL to scan entire tables or you have joins that do not use keys properly.</li>' +
708 '<li><strong>read rnd next</strong>, the number of requests to read the next row in the data file. This value is high if you are doing a lot of table scans. Generally this suggests that your tables are not properly indexed or that your queries are not written to take advantage of the indexes you have.</li>' +
709 '<li><strong>rollback</strong>, the number of requests for a storage engine to perform a rollback operation.</li>' +
710 '<li><strong>savepoint</strong>, the number of requests for a storage engine to place a savepoint.</li>' +
711 '<li><strong>savepoint rollback</strong>, the number of requests for a storage engine to roll back to a savepoint.</li>' +
712 '<li><strong>update</strong>, the number of requests to update a row in a table.</li>' +
713 '<li><strong>write</strong>, the number of requests to insert a row in a table.</li>' +
717 'mysql.table_locks': {
718 info: 'MySQL table locks counters: <ul>' +
719 '<li><strong>immediate</strong>, the number of times that a request for a table lock could be granted immediately.</li>' +
720 '<li><strong>waited</strong>, the number of times that a request for a table lock could not be granted immediately and a wait was needed. If this is high and you have performance problems, you should first optimize your queries, and then either split your table or tables or use replication.</li>' +
724 // ------------------------------------------------------------------------
727 'apache.connections': {
728 colors: NETDATA.colors[4],
730 netdataDashboard.gaugeChart('Connections', '12%', '', NETDATA.colors[4])
735 colors: NETDATA.colors[0],
737 netdataDashboard.gaugeChart('Requests', '12%', '', NETDATA.colors[0])
742 colors: NETDATA.colors[3],
744 netdataDashboard.gaugeChart('Bandwidth', '12%', '', NETDATA.colors[3])
752 return '<div data-netdata="' + id + '"'
753 + ' data-dimensions="busy"'
754 + ' data-append-options="percentage"'
755 + ' data-gauge-max-value="100"'
756 + ' data-chart-library="gauge"'
757 + ' data-title="Workers Utilization"'
758 + ' data-units="percentage %"'
759 + ' data-gauge-adjust="width"'
760 + ' data-width="12%"'
762 + ' data-after="-CHART_DURATION"'
763 + ' data-points="CHART_DURATION"'
764 + ' role="application"></div>';
769 'apache.bytesperreq': {
770 colors: NETDATA.colors[3],
774 'apache.reqpersec': {
775 colors: NETDATA.colors[4],
779 'apache.bytespersec': {
780 colors: NETDATA.colors[6],
785 // ------------------------------------------------------------------------
788 'nginx.connections': {
789 colors: NETDATA.colors[4],
791 netdataDashboard.gaugeChart('Connections', '12%', '', NETDATA.colors[4])
796 colors: NETDATA.colors[0],
798 netdataDashboard.gaugeChart('Requests', '12%', '', NETDATA.colors[0])
802 // ------------------------------------------------------------------------
805 'netdata.response_time': {
806 info: 'The netdata API response time measures the time netdata needed to serve requests. This time includes everything, from the reception of the first byte of a request, to the dispatch of the last byte of its reply, therefore it includes all network latencies involved (i.e. a client over a slow network will influence these metrics).'
809 // ------------------------------------------------------------------------
812 'retroshare.bandwidth': {
813 info: 'RetroShare inbound and outbound traffic.',
815 netdataDashboard.gaugeChart('Received', '12%', 'bandwidth_down_kb'),
816 netdataDashboard.gaugeChart('Sent', '12%', 'bandwidth_up_kb')
820 'retroshare.peers': {
821 info: 'Number of (connected) RetroShare friends.',
825 return '<div data-netdata="' + id + '"'
826 + ' data-dimensions="peers_connected"'
827 + ' data-append-options="friends"'
828 + ' data-chart-library="easypiechart"'
829 + ' data-title="connected friends"'
833 + ' data-after="-CHART_DURATION"'
834 + ' data-points="CHART_DURATION"'
835 + ' role="application"></div>';
841 info: 'Statistics about RetroShare\'s DHT. These values are estimated!'
844 // ------------------------------------------------------------------------
848 colors: NETDATA.colors[10],
856 'web_log.response_statuses': {
857 info: 'Web server responses by type. <code>success</code> includes <b>1xx</b>, <b>2xx</b> and <b>304</b>, <code>error</code> includes <b>5xx</b>, <code>redirect</code> includes <b>3xx</b> except <b>304</b>, <code>bad</code> includes <b>4xx</b>, <code>other</code> are all the other responses.',
861 return '<div data-netdata="' + id + '"'
862 + ' data-dimensions="success"'
863 + ' data-chart-library="gauge"'
864 + ' data-title="Successful"'
865 + ' data-units="requests/s"'
866 + ' data-gauge-adjust="width"'
867 + ' data-width="12%"'
869 + ' data-after="-CHART_DURATION"'
870 + ' data-points="CHART_DURATION"'
871 + ' data-common-max="' + id + '"'
872 + ' data-colors="' + NETDATA.colors[0] + '"'
873 + ' data-decimal-digits="0"'
874 + ' role="application"></div>';
879 return '<div data-netdata="' + id + '"'
880 + ' data-dimensions="redirect"'
881 + ' data-chart-library="gauge"'
882 + ' data-title="Redirects"'
883 + ' data-units="requests/s"'
884 + ' data-gauge-adjust="width"'
885 + ' data-width="12%"'
887 + ' data-after="-CHART_DURATION"'
888 + ' data-points="CHART_DURATION"'
889 + ' data-common-max="' + id + '"'
890 + ' data-colors="' + NETDATA.colors[2] + '"'
891 + ' data-decimal-digits="0"'
892 + ' role="application"></div>';
897 return '<div data-netdata="' + id + '"'
898 + ' data-dimensions="bad"'
899 + ' data-chart-library="gauge"'
900 + ' data-title="Bad Requests"'
901 + ' data-units="requests/s"'
902 + ' data-gauge-adjust="width"'
903 + ' data-width="12%"'
905 + ' data-after="-CHART_DURATION"'
906 + ' data-points="CHART_DURATION"'
907 + ' data-common-max="' + id + '"'
908 + ' data-colors="' + NETDATA.colors[3] + '"'
909 + ' data-decimal-digits="0"'
910 + ' role="application"></div>';
915 return '<div data-netdata="' + id + '"'
916 + ' data-dimensions="error"'
917 + ' data-chart-library="gauge"'
918 + ' data-title="Server Errors"'
919 + ' data-units="requests/s"'
920 + ' data-gauge-adjust="width"'
921 + ' data-width="12%"'
923 + ' data-after="-CHART_DURATION"'
924 + ' data-points="CHART_DURATION"'
925 + ' data-common-max="' + id + '"'
926 + ' data-colors="' + NETDATA.colors[1] + '"'
927 + ' data-decimal-digits="0"'
928 + ' role="application"></div>';
933 'web_log.response_codes': {
934 info: 'Web server responses by code family. According to the standards <code>1xx</code> are informational responses, <code>2xx</code> are successful responses, <code>3xx</code> are redirects (although they include <b>304</b> which is used as "<b>not modified</b>"), <code>4xx</code> are bad requests, <code>5xx</code> are internal server errors, <code>other</code> are non-standard responses, <code>unmatched</code> counts the lines in the log file that are not matched by the plugin (<a href="https://github.com/firehol/netdata/issues/new?title=web_log%20reports%20unmatched%20lines&body=web_log%20plugin%20reports%20unmatched%20lines.%0A%0AThis%20is%20my%20log:%0A%0A%60%60%60txt%0A%0Aplease%20paste%20your%20web%20server%20log%20here%0A%0A%60%60%60" target="_blank">let us know</a> if you have any unmatched).'
937 'web_log.response_time': {
941 return '<div data-netdata="' + id + '"'
942 + ' data-dimensions="avg"'
943 + ' data-chart-library="gauge"'
944 + ' data-title="Average Response Time"'
945 + ' data-units="milliseconds"'
946 + ' data-gauge-adjust="width"'
947 + ' data-width="12%"'
949 + ' data-after="-CHART_DURATION"'
950 + ' data-points="CHART_DURATION"'
951 + ' data-colors="' + NETDATA.colors[4] + '"'
952 + ' data-decimal-digits="2"'
953 + ' role="application"></div>';
958 'web_log.detailed_response_codes': {
959 info: 'Number of responses for each response code individually.'
962 'web_log.requests_per_ipproto': {
963 info: 'Web server requests received per IP protocol version.'
967 info: 'Unique client IPs accessing the web server, within each data collection iteration. If data collection is <b>per second</b>, this chart shows <b>unique client IPs per second</b>.'
970 'web_log.clients_all': {
971 info: 'Unique client IPs accessing the web server since the last restart of netdata. This plugin keeps in memory all the unique IPs that have accessed the web server. On very busy web servers (several millions of unique IPs) you may want to disable this chart (check <a href="https://github.com/firehol/netdata/blob/master/conf.d/python.d/web_log.conf" target="_blank"><code>/etc/netdata/python.d/web_log.conf</code></a>).'