These counters can have a noticeable cost on large machines, though not
dramatic. There's no single good choice to keep them enabled or disabled.
This commit adds multiple choices:
- DEBUG_COUNTERS set to 2 will automatically enable them by default, while
1 will disable them by default
- the global "debug.counters on/off" will allow to change the setting at
boot, regardless of DEBUG_COUNTERS as long as it was at least 1.
- the CLI "debug counters on/off" will also allow to change the value at
run time, allowing to observe a phenomenon while it's happening, or to
disable counters if it's suspected that their cost is too high
Finally, the "debug counters" command will append "(stopped)" at the end
of the CNT lines when these counters are stopped.
Not that the whole mechanism would easily support being extended to all
counter types by specifying the types to apply to, but it doesn't seem
useful at all and would require the user to also type "cnt" on debug
lines. This may easily be changed in the future if it's found relevant.
Till now the per-line glitches counters were only enabled with the
confusingly named DEBUG_GLITCHES (which would not turn glitches off
when disabled). Let's instead change it to DEBUG_COUNTERS and make sure
it's enabled by default (though it can still be disabled with
-DDEBUG_GLITCHES=0 just like for DEBUG_STRICT). It will later be
expanded to cover more counters.
Some rare commands in the worker require to keep their input open and
terminate when it's closed ("show events -w", "wait"). Others maintain
a per-session context ("set anon on"). But in its default operation
mode, the master CLI passes commands one at a time to the worker, and
closes the CLI's input channel so that the command can immediately
close upon response. This effectively prevents these two specific cases
from being used.
Here the approach that we take is to introduce a bidirectional mode to
connect to the worker, where everything sent to the master is immediately
forwarded to the worker (including the raw command), allowing to queue
multiple commands at once in the same session, and to continue to watch
the input to detect when the client closes. It must be a client's choice
however, since doing so means that the client cannot batch many commands
at once to the master process, but must wait for these commands to complete
before sending new ones. For this reason we use the prefix "@@<pid>" for
this. It works exactly like "@" except that it maintains the channel
open during the whole execution. Similarly to "@<pid>" with no command,
"@@<pid>" will simply open an interactive CLI session to the worker, that
will be ended by "quit" or by closing the connection. This can be convenient
for the user, and possibly for clients willing to dedicate a connection to
the worker.
The '@' prefix permits to execute a single command at once in a worker.
It is very handy but comes with some limitations affecting rare commands,
which is better to be documented (one command per session, input closed)
since it can seldom have user-visible effects.
While the examples were clear, the text did not fully imply what was
reflected there. Better have the text explicitly mention that the
'@' command may be used as a prefix or wrapper in front of a command
as well as a standalone command.
Released version 3.2-dev10 with the following main changes :
- REORG: ssl: move curves2nid and nid2nist to ssl_utils
- BUG/MEDIUM: stream: Fix a possible freeze during a forced shut on a stream
- MEDIUM: stream: Save SC and channel flags earlier in process_steam()
- BUG/MINOR: peers: fix expire learned from a peer not converted from ms to ticks
- BUG/MEDIUM: peers: prevent learning expiration too far in futur from unsync node
- CI: spell check: allow manual trigger
- CI: codespell: add "pres" to spellcheck whitelist
- CLEANUP: assorted typo fixes in the code, commits and doc
- CLEANUP: atomics: remove support for gcc < 4.7
- CLEANUP: atomics: also replace __sync_synchronize() with __atomic_thread_fence()
- TESTS: Fix build for filltab25.c
- MEDIUM: ssl: replace "crt" lines by "ssl-f-use" lines
- DOC: configuration: replace "crt" by "ssl-f-use" in listeners
- MINOR: backend: mark srv as nonnull in alloc_dst_address()
- BUG/MINOR: server: ensure check-reuse-pool is copied from default-server
- MINOR: server: activate automatically check reuse for rhttp@ protocol
- MINOR: check/backend: support conn reuse with SNI
- MINOR: check: implement check-pool-conn-name srv keyword
- MINOR: task: add thread safe notification_new and notification_wake variants
- BUG/MINOR: hlua_fcn: fix potential UAF with Queue:pop_wait()
- MINOR: hlua_fcn: register queue class using hlua_register_metatable()
- MINOR: hlua: add core.wait()
- MINOR: hlua: core.wait() takes optional delay paramater
- MINOR: hlua: split hlua_applet_tcp_recv_yield() in two functions
- MINOR: hlua: add AppletTCP:try_receive()
- MINOR: hlua_fcn: add Queue:alarm()
- MEDIUM: task: make notification_* API thread safe by default
- CLEANUP: log: adjust _lf_cbor_encode_byte() comment
- MEDIUM: ssl/crt-list: warn on negative wildcard filters
- MEDIUM: ssl/crt-list: warn on negative filters only
- BUILD: atomics: fix build issue on non-x86/non-arm systems
- BUG/MINOR: log: fix CBOR encoding with LOG_VARTEXT_START() + lf_encode_chunk()
- BUG/MEDIUM: sample: fix risk of overflow when replacing multiple regex back-refs
- DOC: configuration: rework the crt-list section
- MINOR: ring: support arbitrary delimiters through ring_dispatch_messages()
- MINOR: ring/cli: support delimiting events with a trailing \0 on "show events"
- DEV: h2: fix h2-tracer.lua nil value index
- BUG/MINOR: backend: do not use the source port when hashing clientip
- BUG/MINOR: hlua: fix invalid errmsg use in hlua_init()
- MINOR: proxy: add setup_new_proxy() function
- MINOR: checks: mark CHECKS-FE dummy frontend as internal
- MINOR: flt_spoe: mark spoe agent frontend as internal
- MEDIUM: tree-wide: avoid manually initializing proxies
- MINOR: proxy: add deinit_proxy() helper func
- MINOR: checks: deinit checks_fe upon deinit
- MINOR: flt_spoe: deinit spoe agent proxy upon agent release
At the moment it is not supported to produce multi-line events on the
"show events" output, simply because the LF character is used as the
default end-of-event mark. However it could be convenient to produce
well-formatted multi-line events, e.g. in JSON or other formats. UNIX
utilities have already faced similar needs in the past and added
"-print0" to "find" and "-0" to "xargs" to mention that the delimiter
is the NUL character. This makes perfect sense since it's never present
in contents, so let's do exactly the same here.
Thus from now on, "show events <ring> -0" will delimit messages using
a \0 instead of a \n, permitting a better and safer encapsulation.
Queue:alarm() sets a wakeup alarm on the task when new data becomes
available on Queue. It must be re-armed for each event.
Lua documentation was updated
This is the non-blocking variant for AppletTCP:receive(). It doesn't
take any argument, instead it tries to read as much data as available
at once. If no data is available, empty string is returned.
Lua documentation was updated.
core.wait() now accepts optional delay parameter in ms. Passed this delay
the task is woken up if no event woke the task before.
Lua documentation was updated.
Similar to core.yield(), except that the task is not woken up
automatically, instead it waits for events to trigger the task
wakeup.
Lua documentation was updated.
This commit is a direct follow-up of the previous one. It defines a new
server keyword check-pool-conn-name. It is used as the default value for
the name parameter of idle connection hash generation.
Its behavior is similar to server keyword pool-conn-name, but reserved
for checks reuse. If check-pool-conn-name is set, it is used in priority
to match a connection for reuse. If unset, a fallback is performed on
check-sni.
Without check-reuse-pool, it is impossible to perform check on server
using @rhttp protocol. This is due to the inherent nature of the
protocol which does not implement an active connect method.
Thus, ensure that check-reuse-pool is always set when a reverse HTTP
server is declared. This reduces server configuration and should prevent
any omission. Note that it is still require to add "check" server
keyword so activate server checks.
Replace the "crt" keyword from the frontend section with a "ssl-f-use"
keyword, "crt" could be ambigous in case we don't want to put a
certificate filename.
Released version 3.2-dev9 with the following main changes :
- MINOR: quic: move global tune options into quic_tune
- CLEANUP: quic: reorganize TP flow-control initialization
- MINOR: quic: ignore uni-stream for initial max data TP
- MINOR: mux-quic: define config for max-data
- MINOR: quic: define max-stream-data configuration as a ratio
- MEDIUM: lb-chash: add directive hash-preserve-affinity
- MEDIUM: pools: be a bit smarter when merging comparable size pools
- REGTESTS: disable the test balance/balance-hash-maxqueue
- BUG/MINOR: log: fix gcc warn about truncating NUL terminator while init char arrays
- CI: fedora rawhide: allow "on: workflow_dispatch" in forks
- CI: fedora rawhide: install "awk" as a dependency
- CI: spellcheck: allow "on: workflow_dispatch" in forks
- CI: coverity scan: allow "on: workflow_dispatch" in forks
- CI: cross compile: allow "on: workflow_dispatch" in forks
- CI: Illumos: allow "on: workflow_dispatch" in forks
- CI: NetBSD: allow "on: workflow_dispatch" in forks
- CI: QUIC Interop on AWS-LC: allow "on: workflow_dispatch" in forks
- CI: QUIC Interop on LibreSSL: allow "on: workflow_dispatch" in forks
- MINOR: compiler: add __nonstring macro
- MINOR: thread: dump the CPU topology in thread_map_to_groups()
- MINOR: cpu-set: compare two cpu sets with ha_cpuset_isequal()
- MINOR: cpu-set: add a new function to print cpu-sets in human-friendly mode
- MINOR: cpu-topo: add a dump of thread-to-CPU mapping to -dc
- MINOR: cpu-topo: pass an extra argument to ha_cpu_policy
- MINOR: cpu-topo: add new cpu-policies "group-by-2-clusters" and above
- BUG/MINOR: config: silence .notice/.warning/.alert in discovery mode
- EXAMPLES: add "games.cfg" and an example game in Lua
- MINOR: jws: emit the JWK thumbprint
- TESTS: jws: change the jwk format
- MINOR: ssl/ckch: add substring parser for ckch_conf
- MINOR: mt_list: Implement mt_list_try_lock_prev().
- MINOR: lbprm: Add method to deinit server and proxy
- MINOR: threads: Add HA_RWLOCK_TRYRDTOWR()
- MAJOR: leastconn; Revamp the way servers are ordered.
- BUG/MINOR: ssl/ckch: leak in error path
- BUILD: ssl/ckch: potential null pointer dereference
- MINOR: log: support "raw" logformat node typecast
- CLEANUP: assorted typo fixes in the code and comments
- DOC: config: fix two missing "content" in "tcp-request" examples
- MINOR: cpu-topo: cpu_dump_topology() SMT info check little optimisation
- BUILD: compiler: undefine the CONCAT() macro if already defined
- BUG/MEDIUM: leastconn: Don't try to reposition if the server is down
- BUG/MINOR: rhttp: fix incorrect dst/dst_port values
- BUG/MINOR: backend: do not overwrite srv dst address on reuse
- BUG/MEDIUM: backend: fix reuse with set-dst/set-dst-port
- MINOR: sample: define bc_reused fetch
- REGTESTS: extend conn reuse test with transparent proxy
- MINOR: backend: fix comment when killing idle conns
- MINOR: backend: adjust conn_backend_get() API
- MINOR: backend: extract conn hash calculation from connect_server()
- MINOR: backend: extract conn reuse from connect_server()
- MINOR: backend: remove stream usage on connection reuse
- MINOR: check define check-reuse-pool server keyword
- MEDIUM: check: implement check-reuse-pool
- BUILD: backend: silence a build warning when not using ssl
- BUILD: quic_sock: address a strict-aliasing build warning with gcc 5 and 6
- BUILD: ssl_ckch: use my_strndup() instead of strndup()
- DOC: update INSTALL to reflect the minimum compiler version
Define a new server keyword check-reuse-pool, and its counterpart with a
"no" prefix. For the moment, only parsing is implemented. The real
behavior adjustment will be implemented in the next patch.
As reported by Uku Srmus in GitHub issue #2917, two "tcp-request" rules
in an example were mistakenly missing the "content" hook, rendering them
invalid.
This can be backported.
Implement mt_list_try_lock_prev(), that does the same thing
as mt_list_lock_prev(), exceot if the list is locked, it
returns { NULL, NULL } instaed of waiting.
This adds "group-by-{2,3,4}-clusters", which, as its name implies,
create one thread group per X clusters. This can be useful when CPUs
are split into too small clusters, as well as when the total number
of assigned cores is not even between the clusters, to try to spread
the load between less different ones.
When using hash-based load balancing, requests are always assigned to
the server corresponding to the hash bucket for the balancing key,
without taking maxconn or maxqueue into account, unlike in other load
balancing methods like 'first'. This adds a new backend directive that
can be used to take maxconn and possibly maxqueue in that context. This
can be used when hashing is desired to achieve cache locality, but
sending requests to a different server is preferable to queuing for a
long time or failing requests when the initial server is saturated.
By default, affinity is preserved as was the case previously. When
'hash-preserve-affinity' is set to 'maxqueue', servers are considered
successively in the order of the hash ring until a server that does not
have a full queue is found.
When 'maxconn' is set on a server, queueing cannot be disabled, as
'maxqueue=0' means unlimited. To support picking a different server
when a server is at 'maxconn' irrespective of the queue,
'hash-preserve-affinity' can be set to 'maxconn'.
Define a new global configuration tune.quic.frontend.max-data. This
allows users to explicitely set the value for the corresponding QUIC TP
initial-max-data, with direct impact on haproxy memory consumption.
Released version 3.2-dev8 with the following main changes :
- MINOR: jws: implement JWS signing
- TESTS: jws: implement a test for JWS signing
- CI: github: add "jose" to apt dependencies
- CLEANUP: log-forward: remove useless options2 init
- CLEANUP: log: add syslog_process_message() helper
- MINOR: proxy: add proxy->options3
- MINOR: log: migrate log-forward options from proxy->options2 to options3
- MINOR: log: provide source address information in syslog_process_message()
- MINOR: tools: only print address in sa2str() when port == -1
- MINOR: log: add "option host" log-forward option
- MINOR: log: handle log-forward "option host"
- MEDIUM: log: change default "host" strategy for log-forward section
- BUG/MEDIUM: thread: use pthread_self() not ha_pthread[tid] in set_affinity
- MINOR: compiler: add a simple macro to concatenate resolved strings
- MINOR: compiler: add a new __decl_thread_var() macro to declare local variables
- BUILD: tools: silence a build warning when USE_THREAD=0
- BUILD: backend: silence a build warning when threads are disabled
- DOC: management: rename some last occurences from domain "dns" to "resolvers"
- BUG/MINOR: stats: fix capabilities and hide settings for some generic metrics
- MINOR: cli: export cli_io_handler() to ease symbol resolution
- MINOR: tools: improve symbol resolution without dl_addr
- MINOR: tools: ease the declaration of known symbols in resolve_sym_name()
- MINOR: tools: teach resolve_sym_name() a few more common symbols
- BUILD: tools: avoid a build warning on gcc-4.8 in resolve_sym_name()
- DEV: ncpu: also emulate sysconf() for _SC_NPROCESSORS_*
- DOC: design-thoughts: commit numa-auto.txt
- MINOR: cpuset: make the API support negative CPU IDs
- MINOR: thread: rely on the cpuset functions to count bound CPUs
- MINOR: cpu-topo: add ha_cpu_topo definition
- MINOR: cpu-topo: allocate and initialize the ha_cpu_topo array.
- MINOR: cpu-topo: rely on _SC_NPROCESSORS_CONF to trim maxcpus
- MINOR: cpu-topo: add a function to dump CPU topology
- MINOR: cpu-topo: update CPU topology from excluded CPUs at boot
- REORG: cpu-topo: move bound cpu detection from cpuset to cpu-topo
- MINOR: cpu-topo: add detection of online CPUs on Linux
- MINOR: cpu-topo: add detection of online CPUs on FreeBSD
- MINOR: cpu-topo: try to detect offline cpus at boot
- MINOR: cpu-topo: add CPU topology detection for linux
- MINOR: cpu-topo: also store the sibling ID with SMT
- MINOR: cpu-topo: add NUMA node identification to CPUs on Linux
- MINOR: cpu-topo: add NUMA node identification to CPUs on FreeBSD
- MINOR: thread: turn thread_cpu_mask_forced() into an init-time variable
- MINOR: cfgparse: move the binding detection into numa_detect_topology()
- MINOR: cfgparse: use already known offline CPU information
- MINOR: global: add a command-line option to enable CPU binding debugging
- MINOR: cpu-topo: add a new "cpu-set" global directive to choose cpus
- MINOR: cpu-topo: add "drop-cpu" and "only-cpu" to cpu-set
- MEDIUM: thread: start to detect thread groups and threads min/max
- MEDIUM: cpu-topo: make sure to properly assign CPUs to threads as a fallback
- MEDIUM: thread: reimplement first numa node detection
- MEDIUM: cfgparse: remove now unused numa & thread-count detection
- MINOR: cpu-topo: refine cpu dump output to better show kept/dropped CPUs
- MINOR: cpu-topo: fall back to nominal_perf and scaling_max_freq for the capacity
- MINOR: cpu-topo: use cpufreq before acpi cppc
- MINOR: cpu-topo: boost the capacity of performance cores with cpufreq
- MINOR: cpu-topo: skip CPU detection when /sys/.../cpu does not exist
- MINOR: cpu-topo: skip identification of non-existing CPUs
- MINOR: cpu-topo: skip CPU properties that we've verified do not exist
- MINOR: cpu-topo: implement a sorting mechanism for CPU index
- MINOR: cpu-topo: implement a sorting mechanism by CPU locality
- MINOR: cpu-topo: implement a CPU sorting mechanism by cluster ID
- MINOR: cpu-topo: ignore single-core clusters
- MINOR: cpu-topo: assign clusters to cores without and renumber them
- MINOR: cpu-topo: make sure we don't leave unassigned IDs in the cpu_topo
- MINOR: cpu-topo: assign an L3 cache if more than 2 L2 instances
- MINOR: cpu-topo: renumber cores to avoid holes and make them contiguous
- MINOR: cpu-topo: add a function to sort by cluster+capacity
- MINOR: cpu-topo: consider capacity when forming clusters
- MINOR: cpu-topo: create an array of the clusters
- MINOR: cpu-topo: ignore excess of too small clusters
- MINOR: cpu-topo: add "only-node" and "drop-node" to cpu-set
- MINOR: cpu-topo: add "only-thread" and "drop-thread" to cpu-set
- MINOR: cpu-topo: add "only-core" and "drop-core" to cpu-set
- MINOR: cpu-topo: add "only-cluster" and "drop-cluster" to cpu-set
- MINOR: cpu-topo: add a CPU policy setting to the global section
- MINOR: cpu-topo: add a 'first-usable-node' cpu policy
- MEDIUM: cpu-topo: use the "first-usable-node" cpu-policy by default
- CLEANUP: thread: now remove the temporary CPU node binding code
- MINOR: cpu-topo: add cpu-policy "group-by-cluster"
- MEDIUM: cpu-topo: let the "group-by-cluster" split groups
- MINOR: cpu-topo: add a new "performance" cpu-policy
- MINOR: cpu-topo: add a new "efficiency" cpu-policy
- MINOR: cpu-topo: add a new "resource" cpu-policy
- MINOR: jws: add new functions in jws.h
- MINOR: cpu-topo: fix unused stack var 'cpu2' reported by coverity
- MINOR: hlua: add an optional timeout to AppletTCP:receive()
- MINOR: jws: use jwt_alg type instead of a char
- BUG/MINOR: log: prevent saddr NULL deref in syslog_io_handler()
- MINOR: stream: decrement srv->served after detaching from the list
- BUG/MINOR: hlua: fix optional timeout argument index for AppletTCP:receive()
- MINOR: server: simplify srv_has_streams()
- CLEANUP: server: make it clear that srv_check_for_deletion() is thread-safe
- MINOR: cli/server: don't take thread isolation to check for srv-removable
- BUG/MINOR: limits: compute_ideal_maxconn: don't cap remain if fd_hard_limit=0
- MINOR: limits: fix check_if_maxsock_permitted description
- BUG/MEDIUM: hlua/cli: fix cli applet UAF in hlua_applet_wakeup()
- MINOR: tools: path_base() concatenates a path with a base path
- MEDIUM: ssl/ckch: make the ckch_conf more generic
- BUG/MINOR: mux-h2: Reset streams with NO_ERROR code if full response was already sent
- MINOR: stats: add .generic explicit field in stat_col struct
- MINOR: stats: STATS_PX_CAP___B_ macro
- MINOR: stats: add .cap for some static metrics
- MINOR: stats: use stat_col storage stat_cols_info
- MEDIUM: promex: switch to using stat_cols_info for global metrics
- MINOR: promex: expose ST_I_INF_WARNINGS (AKA total_warnings) metric
- MEDIUM: promex: switch to using stat_cols_px for front/back/server metrics
- MINOR: stats: explicitly add frontend cap for ST_I_PX_REQ_TOT
- CLEANUP: promex: remove unused PROMEX_FL_{INFO,FRONT,BACK,LI,SRV} flags
- BUG/MEDIUM: mux-quic: fix crash on RS/SS emission if already close local
- BUG/MINOR: mux-quic: remove extra BUG_ON() in _qcc_send_stream()
- MEDIUM: mt_list: Reduce the max number of loops with exponential backoff
- MINOR: stats: add alt_name field to stat_col struct
- MINOR: stats: add alt name info to stat_cols_info where relevant
- MINOR: promex: get rid of promex_global_metric array
- MINOR: stats-proxy: add alt_name field for ME_NEW_{FE,BE,PX} helpers
- MINOR: stats-proxy: add alt name info to stat_cols_px where relevant
- MINOR: promex: get rid of promex_st_metrics array
- MINOR: pools: rename the "by_what" field of the show pools context to "how"
- MINOR: cli/pools: record the list of pool registrations even when merging them
By default, create_pool() tries to merge similar pools into one. But when
dealing with certain bugs, it's hard to say which ones were merged together.
We do have the information at registration time, so let's just create a
list of registrations ("pool_registration") attached to each pool, that
will store that information. It can then be consulted on the CLI using
"show pools detailed", where the names, sizes, alignment and flags are
reported.
TCP services might want to be interactive, and without a timeout on
receive(), the possibilities are a bit limited. Let's add an optional
timeout in the 3rd argument to possibly limit the wait time. In this
case if the timeout strikes before the requested size is complete,
a possibly incomplete block will be returned.
This cpu policy keeps the smallest CPU cluster. This can
be used to limit the resource usage to the strict minimum
that still delivers decent performance, for example to
try to further reduce power consumption or minimize the
number of cores needed on some rented systems for a
sidecar setup, in order to scale the system down more
easily. Note that if a single cluster is present, it
will still be fully used.
When started on a 64-core EPYC gen3, it uses only one CCX
with 8 cores and 16 threads, all in the same group.
This cpu policy tries to evict performant core clusters and only
focuses on efficiency-oriented ones. On an intel i9-14900k, we can
get 525k rps using 8 performance cores, versus 405k when using all
24 efficiency cores. In some cases the power savings might be more
desirable (e.g. scalability tests on a developer's laptop), or the
performance cores might be better suited for another component
(application or security component).
This cpu policy tries to evict efficient core clusters and only
focuses on performance-oriented ones. On an intel i9-14900k, we can
get 525k rps using only 8 cores this way, versus 594k when using all
24 cores. The gains from using all these codes are not significant
enough to waste them on this. Also these cores can be much slower
at doing SSL handshakes so it can make sense to evict them. Better
keep the efficiency cores for network interrupts for example.
Also, on a developer's machine it can be convenient to keep all these
cores for the local tasks and extra tools (load generators etc).
This policy forms thread groups from the CPU clusters, and bind all the
threads in them to all the CPUs of the cluster. This is recommended on
system with bad inter-CCX latencies. It was shown to simply triple the
performance with queuing on a 64-core EPYC without having to manually
assign the cores with cpu-map.
This now turns the cpu-policy to "first-usable-node" by default, so that
we preserve the current default behavior consisting in binding to the
first node if nothing was forced. If a second node is found,
global.nbthread is set and the previous code will be skipped.
This is a reimplemlentation of the current default policy. It binds to
the first node having usable CPUs if found, and drops CPUs from the
second and next nodes.
These are processed after the topology is detected, and they allow to
restrict binding to or evict CPUs matching the indicated hardware
cluster number(s). It can be used to bind to only some clusters, such
as CCX or different energy efficiency cores. For this reason, here we
use the cluster's local ID (local to the node).
These are processed after the topology is detected, and they allow to
restrict binding to or evict CPUs matching the indicated hardware
core number(s). It can be used to bind to only some clusters as well
as to evict efficient cores whose number is known.
These are processed after the topology is detected, and they allow to
restrict binding to or evict CPUs matching the indicated hardware
thread number(s). It can be used to reserve even threads for HW IRQs
and odd threads for haproxy for example, or to evict efficient cores
that do only have thread #0.
For now it's limited, it only supports "reset" to ask that any previous
"taskset" be ignored. The goal will be to later add more actions that
allow to symbolically define sets of cpus to bind to or to drop. This
also clears the cpu_mask_forced variable that is used to detect
that a taskset had been used.
During development, everything related to CPU binding and the CPU topology
is debugged using state dumps at various places, but it does make sense to
have a real command line option so that this remains usable in production
to help users figure why some CPUs are not used by default. Let's add
"-dc" for this. Since the list of global.tune.options values is almost
full and does not 100% match this option, let's add a new "tune.debug"
field for this.
Lots of collected data and observations aggregated into a single commit
so as not to lose them. Some parts below come from several commit
messages and are incremental.
Add captures and analysis of intel 14900 where it's not easy to draw
the line between the desired P and E cores.
The 14900 raises some questions (imagine a dual-die variant in multi-socket).
That's the start of an algorithmic distribution of performance cores into
thread groups.
cpu-map currently conflicts a lot with the choices after auto-detection
but it doesn't have to. The problem is the inability to configure the
threads for the whole process like taskset does. By offering this ability
we can also start to designate groups of CPUs symbolically (package, die,
ccx, cores, smt).
It can also be useful to exploit the info from cpuinfo that is not
available in /sys, such as the model number. At least on arm, higher
numbers indicate bigger cores and can be useful to distinguish cores
inside a cluster. It will not indicate big vs medium ones of the same
type (e.g. a78 3.0 vs 2.4 GHz) but can still be effective at identifying
the efficient ones.
In short, infos such as cluster ID not always reliable, and are
local to the package. die_id as well. die number is not reported
here but should definitely be used, as a higher priority than L3.
We're still missing a discriminant between the l3 and cluster number
in order to address heterogenous CPUs (e.g. intel 14900), though in
terms of locality that's currently done correctly.
CPU selection is also a full topic, and some thoughts were noted
regarding sorting by perf vs locality so as never to mix inter-
socket CPUs due to sorting.
The proposed cpu-selection cannot work as-is, because it acts both on
restriction and preference, and these two are not actions but a sequence.
First restrictions must be enforced, and second the remaining CPUs are
sorted according to the preferred criterion, and a number of threads are
selected.
Currently we refine the OS-exposed cluster number but it's not correct
as we can end up with something poorly numbered. We need to respect the
LLC in any case so let's explain the approach.
This is a complementary patch to cf913c2f9 ("DOC: management: rename show
stats domain cli "dns" to "resolvers"). The doc still refered to the
legacy "dns" domain filter for stat command. Let's rename those occurences
to "resolvers".
It may be backported to all stable versions.
Historically, log-forward proxy used to preserve host field from input
message as much as possible, and if syslog host wasn't provided
(rfc5424 '-' or bad rfc3164 or rfc5424 message) then "localhost" or "-"
would be used as host when outputting message using rfc3164 or rfc5424.
We change that behavior (which corresponds to "keep" host option), so that
log-forward now uses "fill" strategy as default: if the host is provided
in input message, it is preserved. However if it is missing and IP address
from sender is available, we use it.
