database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-28 23:42:10 +03:00
Code Activity

Report progress of startup operations that take a long time.

Browse Source 
Users sometimes get concerned whe they start the server and it
emits a few messages and then doesn't emit any more messages for
a long time. Generally, what's happening is either that the
system is taking a long time to apply WAL, or it's taking a
long time to reset unlogged relations, or it's taking a long
time to fsync the data directory, but it's not easy to tell
which is the case.

To fix that, add a new 'log_startup_progress_interval' setting,
by default 10s. When an operation that is known to be potentially
long-running takes more than this amount of time, we'll log a
status update each time this interval elapses.

To avoid undesirable log chatter, don't log anything about WAL
replay when in standby mode.

Nitin Jadhav and Robert Haas, reviewed by Amul Sul, Bharath
Rupireddy, Justin Pryzby, Michael Paquier, and Álvaro Herrera.

Discussion: https://postgr.es/m/CA+TgmoaHQrgDFOBwgY16XCoMtXxsrVGFB2jNCvb7-ubuEe1MGg@mail.gmail.com
Discussion: https://postgr.es/m/CAMm1aWaHF7VE69572_OLQ+MgpT5RUiUDgF1x5RrtkJBLdpRj3Q@mail.gmail.com
This commit is contained in:
Robert Haas
2021-10-25 11:51:57 -04:00
parent 732e6677a6
commit 9ce346eabf
10 changed files with 181 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
src/backend/postmaster/startup.c
View File

@ -59,6 +59,22 @@ static volatile sig_atomic_t promote_signaled = false;
*/
static volatile sig_atomic_t in_restore_command = false;
/*
* Time at which the most recent startup operation started.
*/
static TimestampTz startup_progress_phase_start_time;
/*
* Indicates whether the startup progress interval mentioned by the user is
* elapsed or not. TRUE if timeout occurred, FALSE otherwise.
*/
static volatile sig_atomic_t startup_progress_timer_expired = false;
/*
* Time between progress updates for long-running startup operations.
*/
int log_startup_progress_interval = 10000; /* 10 sec */
/* Signal handlers */
static void StartupProcTriggerHandler(SIGNAL_ARGS);
static void StartupProcSigHupHandler(SIGNAL_ARGS);
@ -282,3 +298,58 @@ ResetPromoteSignaled(void)
{
promote_signaled = false;
}
/*
* Set a flag indicating that it's time to log a progress report.
*/
void
startup_progress_timeout_handler(void)
{
startup_progress_timer_expired = true;
}
/*
* Set the start timestamp of the current operation and enable the timeout.
*/
void
begin_startup_progress_phase(void)
{
TimestampTz fin_time;
/* Feature is disabled. */
if (log_startup_progress_interval == 0)
return;
startup_progress_phase_start_time = GetCurrentTimestamp();
fin_time = TimestampTzPlusMilliseconds(startup_progress_phase_start_time,
log_startup_progress_interval);
enable_timeout_every(STARTUP_PROGRESS_TIMEOUT, fin_time,
log_startup_progress_interval);
}
/*
* Report whether startup progress timeout has occurred. Reset the timer flag
* if it did, set the elapsed time to the out parameters and return true,
* otherwise return false.
*/
bool
has_startup_progress_timeout_expired(long *secs, int *usecs)
{
long seconds;
int useconds;
TimestampTz now;
/* No timeout has occurred. */
if (!startup_progress_timer_expired)
return false;
/* Calculate the elapsed time. */
now = GetCurrentTimestamp();
TimestampDifference(startup_progress_phase_start_time, now, &seconds, &useconds);
*secs = seconds;
*usecs = useconds;
startup_progress_timer_expired = false;
return true;
}