mirror of
https://github.com/kubeshark/kubeshark.git
synced 2026-07-27 17:22:59 +00:00
* Separate HTTP related code into `extensions/http` as a Go plugin * Move `extensions` folder into `tap` folder * Move HTTP files into `tap/extensions/lib` for now * Replace `orcaman/concurrent-map` with `sync.Map` * Remove `grpc_assembler.go` * Remove `github.com/up9inc/mizu/tap/extensions/http/lib` * Add a build script to automatically build extensions from a known path and load them * Start to define the extension API * Implement the `run()` function for the TCP stream * Add support of defining multiple ports to the extension API * Set the extension name inside the extension * Declare the `Dissect` function in the extension API * Dissect HTTP request from inside the HTTP extension * Make the distinction of outbound and inbound ports * Dissect HTTP response from inside the HTTP extension * Bring back the HTTP request-response pair matcher * Return a `*api.RequestResponsePair` from the dissection * Bring back the gRPC-HTTP/2 parser * Fix the issues in `handleHTTP1ClientStream` and `handleHTTP1ServerStream` * Call a function pointer to emit dissected data back to the `tap` package * roee changes - trying to fix agent to work with the "api" object) - ***still not working*** * small mistake in the conflicts * Fix the issues that are introduced by the merge conflict * Add `Emitter` interface to the API and send `OutputChannelItem`(s) to `OutputChannel` * Fix the `HTTP1` handlers * Set `ConnectionInfo` in HTTP handlers * Fix the `Dockerfile` to build the extensions * remove some unwanted code * no message * Re-enable `getStreamProps` function * Migrate back from `gopacket/tcpassembly` to `gopacket/reassembly` * Introduce `HTTPPayload` struct and `HTTPPayloader` interface to `MarshalJSON()` all the data structures that are returned by the HTTP protocol * Read `socketHarOutChannel` instead of `filteredHarChannel` * Connect `OutputChannelItem` to the last WebSocket means that finally the web UI started to work again * Add `.env.example` to React app * Marshal and unmarshal `*http.Request`, `*http.Response` pairs * Move `loadExtensions` into `main.go` and map extensions into `extensionsMap` * Add `Summarize()` method to the `Dissector` interface * Add `Analyze` method to the `Dissector` interface and `MizuEntry` to the extension API * Add `Protocol` struct and make it effect the UI * Refactor `BaseEntryDetails` struct and display the source and destination ports in the UI * Display the protocol name inside the details layout * Add `Represent` method to the `Dissector` interface and manipulate the UI through this method * Make the protocol color affect the details layout color and write protocol abbreviation vertically * Remove everything HTTP related from the `tap` package and make the extension system fully functional * Fix the TypeScript warnings * Bring in the files related AMQP into `amqp` directory * Add `--nodefrag` flag to the tapper and bring in the main AMQP code * Implement the AMQP `BasicPublish` and fix some issues in the UI when the response payload is missing * Implement `representBasicPublish` method * Fix several minor issues * Implement the AMQP `BasicDeliver` * Implement the AMQP `QueueDeclare` * Implement the AMQP `ExchangeDeclare` * Implement the AMQP `ConnectionStart` * Implement the AMQP `ConnectionClose` * Implement the AMQP `QueueBind` * Implement the AMQP `BasicConsume` * Fix an issue in `ConnectionStart` * Fix a linter error * Bring in the files related Kafka into `kafka` directory * Fix the build errors in Kafka Go files * Implement `Dissect` method of Kafka and adapt request-response pair matcher to asynchronous client-server stream * Do the "Is reversed?" checked inside `getStreamProps` and fix an issue in Kafka `Dissect` method * Implement `Analyze`, `Summarize` methods of Kafka * Implement the representations for Kafka `Metadata`, `RequestHeader` and `ResponseHeader` * Refactor the AMQP and Kafka implementations to create the summary string only inside the `Analyze` method * Implement the representations for Kafka `ApiVersions` * Implement the representations for Kafka `Produce` * Implement the representations for Kafka `Fetch` * Implement the representations for Kafka `ListOffsets`, `CreateTopics` and `DeleteTopics` * Fix the encoding of AMQP `BasicPublish` and `BasicDeliver` body * Remove the unnecessary logging * Remove more logging * Introduce `Version` field to `Protocol` struct for dynamically switching the HTTP protocol to HTTP/2 * Fix the issues in analysis and representation of HTTP/2 (gRPC) protocol * Fix the issues in summary section of details layout for HTTP/2 (gRPC) protocol * Fix the read errors that freezes the sniffer in HTTP and Kafka * Fix the issues in HTTP POST data * Fix one more issue in HTTP POST data * Fix an infinite loop in Kafka * Fix another freezing issue in Kafka * Revert "UI Infra - Support multiple entry types + refactoring (#211)" This reverts commitf74a52d4dc. * Fix more issues that are introduced by the merge * Fix the status code in the summary section * adding the cleaner again (why we removed it?). add TODO: on the extension loop . * fix dockerfile (remove deleting .env file) - it is found in dockerignore and fails to build if the file not exists * fix GetEntrties ("/entries" endpoint) - working with "tapApi.BaseEntryDetail" (moved from shared) * Fix an issue in the UI summary section * Refactor the protocol payload structs * Fix a log message in the passive tapper * Adapt `APP_PORTS` environment variable to the new extension system and change its format to `APP_PORTS='{"http": ["8001"]}' ` * Revert "fix dockerfile (remove deleting .env file) - it is found in dockerignore and fails to build if the file not exists" This reverts commit4f514ae1f4. * Bring in the necessary changes fromf74a52d4dc* Open the API server URL in the web browser as soon as Mizu is ready * Make the TCP reader consists of a single Go routine (instead of two) and try to dissect in both client and server mode by rewinding * Swap `TcpID` without overwriting it * Sort extension by priority * Try to dissect with looping through all the extensions * fix getStreamProps function. (it should be passed from CLI as it was before). * Turn TCP reader back into two Goroutines (client and server) * typo * Learn `isClient` from the TCP stream * Set `viewer` style `overflow: "auto"` * Fix the memory leaks in AMQP and Kafka dissectors * Revert some of the changes inbe7c65eb6d* Remove `allExtensionPorts` since it's no longer needed * Remove `APP_PORTS` since it's no longer needed * Fix all of the minor issues in the React code * Check Kafka header size and fail-fast * Break the dissectors loop upon a successful dissection * Don't break the dissector loop. Protocols might collide * Improve the HTTP request-response counter (still not perfect) * Make the HTTP request-response counter perfect * Revert "Revert some of the changes in be7c65eb6d3fb657a059707da3ca559937e59739" This reverts commit08e7d786d8. * Bring back `filterItems` and `isHealthCheckByUserAgent` functions * Remove some development artifacts * remove unused and commented lines that are not relevant * Fix the performance in TCP stream factory. Make it create two `tcpReader`(s) per extension * Change a log to debug * Make `*api.CounterPair` a field of `tcpReader` * Set `isTapTarget` to always `true` again since `filterAuthorities` implementation has problems * Remove a variable that's only used for logging even though not introduced by this branch * Bring back the `NumberOfRules` field of `ApplicableRules` struct * Remove the unused `NewEntry` function * Move `k8sResolver == nil` check to a more appropriate place * default healthChecksUserAgentHeaders should be empty array (like the default config value) * remove spam console.log * Rules button cause app to crash (access the service via incorrect property) * Ignore all .env* files in docker build. * Better caching in dockerfile: only copy go.mod before go mod download. * Check for errors while loading an extension * Add a comment about why `Protocol` is not a pointer * Bring back the call to `deleteOlderThan` * Remove the `nil` check * Reduce the maximum allowed AMQP message from 128MB to 1MB * Fix an error that only occurs when a Kafka broker is initiating * Revert the change inb2abd7b990* Fix the service name resolution in all protocols * Remove the `anydirection` flag and fix the issue in `filterAuthorities` * Pass `sync.Map` by reference to `deleteOlderThan` method * Fix the packet capture issue in standalone mode that's introduced by the removal of `anydirection` * Temporarily resolve the memory exhaustion in AMQP * Fix a nil pointer dereference error * Fix the CLI build error * Fix a memory leak that's identified by `pprof` Co-authored-by: Roee Gadot <roee.gadot@up9.com> Co-authored-by: Nimrod Gilboa Markevich <nimrod@up9.com>
123 lines
3.3 KiB
Go
123 lines
3.3 KiB
Go
package database
|
|
|
|
import (
|
|
"log"
|
|
"os"
|
|
"strconv"
|
|
"time"
|
|
|
|
"github.com/fsnotify/fsnotify"
|
|
"github.com/romana/rlog"
|
|
"github.com/up9inc/mizu/shared"
|
|
"github.com/up9inc/mizu/shared/debounce"
|
|
"github.com/up9inc/mizu/shared/units"
|
|
tapApi "github.com/up9inc/mizu/tap/api"
|
|
)
|
|
|
|
const percentageOfMaxSizeBytesToPrune = 15
|
|
const defaultMaxDatabaseSizeBytes int64 = 200 * 1000 * 1000
|
|
|
|
func StartEnforcingDatabaseSize() {
|
|
watcher, err := fsnotify.NewWatcher()
|
|
if err != nil {
|
|
log.Fatalf("Error creating filesystem watcher for db size enforcement: %v\n", err)
|
|
return
|
|
}
|
|
|
|
maxEntriesDBByteSize, err := getMaxEntriesDBByteSize()
|
|
if err != nil {
|
|
log.Fatalf("Error parsing max db size: %v\n", err)
|
|
return
|
|
}
|
|
|
|
checkFileSizeDebouncer := debounce.NewDebouncer(5*time.Second, func() {
|
|
checkFileSize(maxEntriesDBByteSize)
|
|
})
|
|
|
|
go func() {
|
|
for {
|
|
select {
|
|
case event, ok := <-watcher.Events:
|
|
if !ok {
|
|
return // closed channel
|
|
}
|
|
if event.Op == fsnotify.Write {
|
|
checkFileSizeDebouncer.SetOn()
|
|
}
|
|
case err, ok := <-watcher.Errors:
|
|
if !ok {
|
|
return // closed channel
|
|
}
|
|
rlog.Errorf("filesystem watcher encountered error:%v", err)
|
|
}
|
|
}
|
|
}()
|
|
|
|
err = watcher.Add(DBPath)
|
|
if err != nil {
|
|
log.Fatalf("Error adding %s to filesystem watcher for db size enforcement: %v\n", DBPath, err)
|
|
}
|
|
}
|
|
|
|
func getMaxEntriesDBByteSize() (int64, error) {
|
|
maxEntriesDBByteSize := defaultMaxDatabaseSizeBytes
|
|
var err error
|
|
|
|
maxEntriesDBSizeByteSEnvVarValue := os.Getenv(shared.MaxEntriesDBSizeBytesEnvVar)
|
|
if maxEntriesDBSizeByteSEnvVarValue != "" {
|
|
maxEntriesDBByteSize, err = strconv.ParseInt(maxEntriesDBSizeByteSEnvVarValue, 10, 64)
|
|
}
|
|
return maxEntriesDBByteSize, err
|
|
}
|
|
|
|
func checkFileSize(maxSizeBytes int64) {
|
|
fileStat, err := os.Stat(DBPath)
|
|
if err != nil {
|
|
rlog.Errorf("Error checking %s file size: %v", DBPath, err)
|
|
} else {
|
|
if fileStat.Size() > maxSizeBytes {
|
|
pruneOldEntries(fileStat.Size())
|
|
}
|
|
}
|
|
}
|
|
|
|
func pruneOldEntries(currentFileSize int64) {
|
|
// sqlite locks the database while delete or VACUUM are running and sqlite is terrible at handling its own db lock while a lot of inserts are attempted, we prevent a significant bottleneck by handling the db lock ourselves here
|
|
IsDBLocked = true
|
|
defer func() { IsDBLocked = false }()
|
|
|
|
amountOfBytesToTrim := currentFileSize / (100 / percentageOfMaxSizeBytesToPrune)
|
|
|
|
rows, err := GetEntriesTable().Limit(10000).Order("id").Rows()
|
|
if err != nil {
|
|
rlog.Errorf("Error getting 10000 first db rows: %v", err)
|
|
return
|
|
}
|
|
|
|
entryIdsToRemove := make([]uint, 0)
|
|
bytesToBeRemoved := int64(0)
|
|
for rows.Next() {
|
|
if bytesToBeRemoved >= amountOfBytesToTrim {
|
|
break
|
|
}
|
|
var entry tapApi.MizuEntry
|
|
err = DB.ScanRows(rows, &entry)
|
|
if err != nil {
|
|
rlog.Errorf("Error scanning db row: %v", err)
|
|
continue
|
|
}
|
|
|
|
entryIdsToRemove = append(entryIdsToRemove, entry.ID)
|
|
bytesToBeRemoved += int64(entry.EstimatedSizeBytes)
|
|
}
|
|
|
|
if len(entryIdsToRemove) > 0 {
|
|
GetEntriesTable().Where(entryIdsToRemove).Delete(tapApi.MizuEntry{})
|
|
// VACUUM causes sqlite to shrink the db file after rows have been deleted, the db file will not shrink without this
|
|
DB.Exec("VACUUM")
|
|
rlog.Errorf("Removed %d rows and cleared %s", len(entryIdsToRemove), units.BytesToHumanReadable(bytesToBeRemoved))
|
|
} else {
|
|
rlog.Error("Found no rows to remove when pruning")
|
|
}
|
|
}
|