aboutsummaryrefslogtreecommitdiffstats
path: root/lib/libzpool/taskq.c
diff options
context:
space:
mode:
authorMatthew Ahrens <[email protected]>2020-03-03 10:29:38 -0800
committerGitHub <[email protected]>2020-03-03 10:29:38 -0800
commitb3212d2fa6ab8d7d8373373e8a6b8acbbf45508e (patch)
tree2e5fc480593300e98addaea9959405cf4e4bf7bb /lib/libzpool/taskq.c
parent0a0f9a7dc6e4f215089cf0aabb230d5dd5dfbd1e (diff)
Improve performance of zio_taskq_member
__zio_execute() calls zio_taskq_member() to determine if we are running in a zio interrupt taskq, in which case we may need to switch to processing this zio in a zio issue taskq. The call to zio_taskq_member() can become a performance bottleneck when we are processing a high rate of zio's. zio_taskq_member() calls taskq_member() on each of the zio interrupt taskqs, of which there are 21. This is slow because each call to taskq_member() does tsd_get(taskq_tsd), which on Linux is relatively slow. This commit improves the performance of zio_taskq_member() by having it cache the value of tsd_get(taskq_tsd), reducing the number of those calls to 1/21th of the current behavior. In a test case running `zfs send -c >/dev/null` of a filesystem with small blocks (average 2.5KB/block), zio_taskq_member() was using 6.7% of one CPU, and with this change it is reduced to 1.3%. Overall time to perform the `zfs send` reduced by 10% (~150,000 block/sec to ~165,000 blocks/sec). Reviewed-by: Brian Behlendorf <[email protected]> Reviewed-by: Serapheim Dimitropoulos <[email protected]> Reviewed-by: Ryan Moeller <[email protected]> Reviewed-by: Tony Nguyen <[email protected]> Signed-off-by: Matthew Ahrens <[email protected]> Closes #10070
Diffstat (limited to 'lib/libzpool/taskq.c')
-rw-r--r--lib/libzpool/taskq.c12
1 files changed, 12 insertions, 0 deletions
diff --git a/lib/libzpool/taskq.c b/lib/libzpool/taskq.c
index ae67906fe..456080f7f 100644
--- a/lib/libzpool/taskq.c
+++ b/lib/libzpool/taskq.c
@@ -34,6 +34,8 @@ int taskq_now;
taskq_t *system_taskq;
taskq_t *system_delay_taskq;
+static pthread_key_t taskq_tsd;
+
#define TASKQ_ACTIVE 0x00010000
static taskq_ent_t *
@@ -213,6 +215,8 @@ taskq_thread(void *arg)
taskq_ent_t *t;
boolean_t prealloc;
+ VERIFY0(pthread_setspecific(taskq_tsd, tq));
+
mutex_enter(&tq->tq_lock);
while (tq->tq_flags & TASKQ_ACTIVE) {
if ((t = tq->tq_task.tqent_next) == &tq->tq_task) {
@@ -343,6 +347,12 @@ taskq_member(taskq_t *tq, kthread_t *t)
return (0);
}
+taskq_t *
+taskq_of_curthread(void)
+{
+ return (pthread_getspecific(taskq_tsd));
+}
+
int
taskq_cancel_id(taskq_t *tq, taskqid_t id)
{
@@ -352,6 +362,7 @@ taskq_cancel_id(taskq_t *tq, taskqid_t id)
void
system_taskq_init(void)
{
+ VERIFY0(pthread_key_create(&taskq_tsd, NULL));
system_taskq = taskq_create("system_taskq", 64, maxclsyspri, 4, 512,
TASKQ_DYNAMIC | TASKQ_PREPOPULATE);
system_delay_taskq = taskq_create("delay_taskq", 4, maxclsyspri, 4,
@@ -365,4 +376,5 @@ system_taskq_fini(void)
system_taskq = NULL; /* defensive */
taskq_destroy(system_delay_taskq);
system_delay_taskq = NULL;
+ VERIFY0(pthread_key_delete(taskq_tsd));
}