0
0
Fork 0
mirror of https://github.com/netdata/netdata.git synced 2025-04-10 16:17:36 +00:00
netdata_netdata/src/database/engine/page.h
Costa Tsaousis 5f72d4279b
Streaming improvements No 3 ()
* ML uses synchronous queries

* do not call malloc_trim() to free memory, since to locks everything

* Reschedule dimensions for training from worker threads.

* when we collect or read from the database, it is SAMPLES. When we generate points for a chart is POINTS

* keep the receiver send buffer 10x the default

* support autoscaling stream circular buffers

* nd_poll() prefers sending data vs receiving data - in an attempt to dequeue as soon as possible

* fix last commit

* allow removing receiver and senders inline, if the stream thread is not working on them

* fix logs

* Revert "nd_poll() prefers sending data vs receiving data - in an attempt to dequeue as soon as possible"

This reverts commit 51539a97da.

* do not access receiver or sender after it has been removed

* open cache hot2clean

* open cache hot2clean does not need flushing

* use aral for extent pages up to 65k

* track aral malloc and mmap allocations separately; add 8192 as a possible value to PGD

* do not evict too frequently if not needed

* fix aral metrics

* fix aral metrics again

* accurate accounting of memory for dictionaries, strings, labels and MRG

* log during shutdown the progress of dbengine flushing

* move metasync shutfown after dbengine

* max iterations per I/O events

* max iterations per I/O events - break the loop

* max iterations per I/O events - break the loop - again

* disable inline evictions for all caches

* when writing to sockets, send everything that can be sent

* cleanup code to trigger evictions

* fix calculation of eviction size

* fix calculation of eviction size once more

* fix calculation of eviction size once more - again

* ml and replication stop while backfilling is running

* process opcodes while draining the sockets; log with limit when asking to disconnect a node

* fix log

* ml stops when replication queries are running

* report pgd_padding to pulse

* aral precise memory accounting

* removed all alignas() and fix the 2 issues that resulted in unaligned memory accesses (one in mqtt and another in streaming)

* remove the bigger sizes from PGD, but keep multiples of gorilla buffers

* exclude judy from sanitizers

* use 16 bytes alignment on 32 bit machines

* internal check about memory alignment

* experiment: do not allow more children to connect while there is backfilling or replication queries running

* when the node is initializing, retry in 30 seconds

* connector cleanup and isolation of control logic about enabling/disabling various parts

* stop also health queries while backfilling is running

* tuning

* drain the input

* improve interactivity when suspending

* more interactive stream_control

* debug logs to find the connection issue

* abstracted everything about stream control

* Add ml_host_{start,stop} again.

* Do not create/update anomaly-detection charts when ML is not running for a host.

* rrdhost flag RECEIVER_DISCONNECTED has been reversed to COLLECTOR_ONLINE and has been used for localhost and virtual hosts too, to have a single point of truth about the availability of collected data or not

* ml_host_start() and ml_host_stop() are used by streaming receivers; ml_host_start() is used for localhost and virtual hosts

* fixed typo

* allow up to 3 backfills at a time

* add throttling based on user queries

* restore cache line paddings

* unify streaming logs to make it easier to grep logs

* tuning of stream_control

* more logs unification

* use mallocz_release_as_much_memory_to_the_system() under extreme conditions

* do not rely on the response code of evict_pages()

* log the gap of the database every time a node is connected

* updated ram requirements

---------

Co-authored-by: vkalintiris <vasilis@netdata.cloud>
2024-12-11 18:02:17 +02:00

63 lines
1.5 KiB
C

// SPDX-License-Identifier: GPL-3.0-or-later
#ifndef DBENGINE_PAGE_H
#define DBENGINE_PAGE_H
#ifdef __cplusplus
extern "C" {
#endif
#include "libnetdata/libnetdata.h"
typedef struct pgd_cursor {
struct pgd *pgd;
uint32_t position;
uint32_t slots;
gorilla_reader_t gr;
} PGDC;
#include "rrdengine.h"
typedef struct pgd PGD;
#define PGD_EMPTY (PGD *)(-1)
void pgd_init_arals(void);
PGD *pgd_create(uint8_t type, uint32_t slots);
PGD *pgd_create_from_disk_data(uint8_t type, void *base, uint32_t size);
void pgd_free(PGD *pg);
uint32_t pgd_type(PGD *pg);
bool pgd_is_empty(PGD *pg);
uint32_t pgd_slots_used(PGD *pg);
uint32_t pgd_buffer_memory_footprint(PGD *pg);
uint32_t pgd_memory_footprint(PGD *pg);
uint32_t pgd_capacity(PGD *pg);
uint32_t pgd_disk_footprint(PGD *pg);
struct aral_statistics *pgd_aral_stats(void);
size_t pgd_padding_bytes(void);
void pgd_copy_to_extent(PGD *pg, uint8_t *dst, uint32_t dst_size);
size_t pgd_append_point(PGD *pg,
usec_t point_in_time_ut,
NETDATA_DOUBLE n,
NETDATA_DOUBLE min_value,
NETDATA_DOUBLE max_value,
uint16_t count,
uint16_t anomaly_count,
SN_FLAGS flags,
uint32_t expected_slot);
void pgdc_reset(PGDC *pgdc, PGD *pgd, uint32_t position);
bool pgdc_get_next_point(PGDC *pgdc, uint32_t expected_position, STORAGE_POINT *sp);
#ifdef __cplusplus
}
#endif
#endif // DBENGINE_PAGE_H