zfs/cmd/zpool/zpool_iter.c

479 lines
11 KiB
C
Raw Normal View History

2008-11-20 20:01:55 +00:00
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2007 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
2008-11-20 20:01:55 +00:00
#include <libintl.h>
#include <libuutil.h>
#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <strings.h>
#include <libzfs.h>
#include <sys/zfs_context.h>
2008-11-20 20:01:55 +00:00
#include "zpool_util.h"
/*
* Private interface for iterating over pools specified on the command line.
* Most consumers will call for_each_pool, but in order to support iostat, we
* allow fined grained control through the zpool_list_t interface.
*/
typedef struct zpool_node {
zpool_handle_t *zn_handle;
uu_avl_node_t zn_avlnode;
int zn_mark;
} zpool_node_t;
struct zpool_list {
boolean_t zl_findall;
uu_avl_t *zl_avl;
uu_avl_pool_t *zl_pool;
zprop_list_t **zl_proplist;
};
/* ARGSUSED */
static int
zpool_compare(const void *larg, const void *rarg, void *unused)
{
zpool_handle_t *l = ((zpool_node_t *)larg)->zn_handle;
zpool_handle_t *r = ((zpool_node_t *)rarg)->zn_handle;
const char *lname = zpool_get_name(l);
const char *rname = zpool_get_name(r);
return (strcmp(lname, rname));
}
/*
* Callback function for pool_list_get(). Adds the given pool to the AVL tree
* of known pools.
*/
static int
add_pool(zpool_handle_t *zhp, void *data)
{
zpool_list_t *zlp = data;
zpool_node_t *node = safe_malloc(sizeof (zpool_node_t));
uu_avl_index_t idx;
node->zn_handle = zhp;
uu_avl_node_init(node, &node->zn_avlnode, zlp->zl_pool);
if (uu_avl_find(zlp->zl_avl, node, NULL, &idx) == NULL) {
if (zlp->zl_proplist &&
zpool_expand_proplist(zhp, zlp->zl_proplist) != 0) {
zpool_close(zhp);
free(node);
return (-1);
}
uu_avl_insert(zlp->zl_avl, node, idx);
} else {
zpool_close(zhp);
free(node);
return (-1);
}
return (0);
}
/*
* Create a list of pools based on the given arguments. If we're given no
* arguments, then iterate over all pools in the system and add them to the AVL
* tree. Otherwise, add only those pool explicitly specified on the command
* line.
*/
zpool_list_t *
pool_list_get(int argc, char **argv, zprop_list_t **proplist, int *err)
{
zpool_list_t *zlp;
zlp = safe_malloc(sizeof (zpool_list_t));
zlp->zl_pool = uu_avl_pool_create("zfs_pool", sizeof (zpool_node_t),
offsetof(zpool_node_t, zn_avlnode), zpool_compare, UU_DEFAULT);
if (zlp->zl_pool == NULL)
zpool_no_memory();
if ((zlp->zl_avl = uu_avl_create(zlp->zl_pool, NULL,
UU_DEFAULT)) == NULL)
zpool_no_memory();
zlp->zl_proplist = proplist;
if (argc == 0) {
(void) zpool_iter(g_zfs, add_pool, zlp);
zlp->zl_findall = B_TRUE;
} else {
int i;
for (i = 0; i < argc; i++) {
zpool_handle_t *zhp;
if ((zhp = zpool_open_canfail(g_zfs, argv[i]))) {
2008-11-20 20:01:55 +00:00
if (add_pool(zhp, zlp) != 0)
*err = B_TRUE;
} else {
*err = B_TRUE;
}
}
}
return (zlp);
}
/*
* Search for any new pools, adding them to the list. We only add pools when no
* options were given on the command line. Otherwise, we keep the list fixed as
* those that were explicitly specified.
*/
void
pool_list_update(zpool_list_t *zlp)
{
if (zlp->zl_findall)
(void) zpool_iter(g_zfs, add_pool, zlp);
}
/*
* Iterate over all pools in the list, executing the callback for each
*/
int
pool_list_iter(zpool_list_t *zlp, int unavail, zpool_iter_f func,
void *data)
{
zpool_node_t *node, *next_node;
int ret = 0;
for (node = uu_avl_first(zlp->zl_avl); node != NULL; node = next_node) {
next_node = uu_avl_next(zlp->zl_avl, node);
if (zpool_get_state(node->zn_handle) != POOL_STATE_UNAVAIL ||
unavail)
ret |= func(node->zn_handle, data);
}
return (ret);
}
/*
* Remove the given pool from the list. When running iostat, we want to remove
* those pools that no longer exist.
*/
void
pool_list_remove(zpool_list_t *zlp, zpool_handle_t *zhp)
{
zpool_node_t search, *node;
search.zn_handle = zhp;
if ((node = uu_avl_find(zlp->zl_avl, &search, NULL, NULL)) != NULL) {
uu_avl_remove(zlp->zl_avl, node);
zpool_close(node->zn_handle);
free(node);
}
}
/*
* Free all the handles associated with this list.
*/
void
pool_list_free(zpool_list_t *zlp)
{
uu_avl_walk_t *walk;
zpool_node_t *node;
if ((walk = uu_avl_walk_start(zlp->zl_avl, UU_WALK_ROBUST)) == NULL) {
(void) fprintf(stderr,
gettext("internal error: out of memory"));
exit(1);
}
while ((node = uu_avl_walk_next(walk)) != NULL) {
uu_avl_remove(zlp->zl_avl, node);
zpool_close(node->zn_handle);
free(node);
}
uu_avl_walk_end(walk);
uu_avl_destroy(zlp->zl_avl);
uu_avl_pool_destroy(zlp->zl_pool);
free(zlp);
}
/*
* Returns the number of elements in the pool list.
*/
int
pool_list_count(zpool_list_t *zlp)
{
return (uu_avl_numnodes(zlp->zl_avl));
}
/*
* High level function which iterates over all pools given on the command line,
* using the pool_list_* interfaces.
*/
int
for_each_pool(int argc, char **argv, boolean_t unavail,
zprop_list_t **proplist, zpool_iter_f func, void *data)
{
zpool_list_t *list;
int ret = 0;
if ((list = pool_list_get(argc, argv, proplist, &ret)) == NULL)
return (1);
if (pool_list_iter(list, unavail, func, data) != 0)
ret = 1;
pool_list_free(list);
return (ret);
}
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 18:05:23 +00:00
static int
for_each_vdev_cb(zpool_handle_t *zhp, nvlist_t *nv, pool_vdev_iter_f func,
void *data)
{
nvlist_t **child;
uint_t c, children;
int ret = 0;
int i;
char *type;
const char *list[] = {
ZPOOL_CONFIG_SPARES,
ZPOOL_CONFIG_L2CACHE,
ZPOOL_CONFIG_CHILDREN
};
for (i = 0; i < ARRAY_SIZE(list); i++) {
if (nvlist_lookup_nvlist_array(nv, list[i], &child,
&children) == 0) {
for (c = 0; c < children; c++) {
uint64_t ishole = 0;
(void) nvlist_lookup_uint64(child[c],
ZPOOL_CONFIG_IS_HOLE, &ishole);
if (ishole)
continue;
ret |= for_each_vdev_cb(zhp, child[c], func,
data);
}
}
}
if (nvlist_lookup_string(nv, ZPOOL_CONFIG_TYPE, &type) != 0)
return (ret);
/* Don't run our function on root vdevs */
if (strcmp(type, VDEV_TYPE_ROOT) != 0) {
ret |= func(zhp, nv, data);
}
return (ret);
}
/*
* This is the equivalent of for_each_pool() for vdevs. It iterates thorough
* all vdevs in the pool, ignoring root vdevs and holes, calling func() on
* each one.
*
* @zhp: Zpool handle
* @func: Function to call on each vdev
* @data: Custom data to pass to the function
*/
int
for_each_vdev(zpool_handle_t *zhp, pool_vdev_iter_f func, void *data)
{
nvlist_t *config, *nvroot = NULL;
Add -lhHpw options to "zpool iostat" for avg latency, histograms, & queues Update the zfs module to collect statistics on average latencies, queue sizes, and keep an internal histogram of all IO latencies. Along with this, update "zpool iostat" with some new options to print out the stats: -l: Include average IO latencies stats: total_wait disk_wait syncq_wait asyncq_wait scrub read write read write read write read write wait ----- ----- ----- ----- ----- ----- ----- ----- ----- - 41ms - 2ms - 46ms - 4ms - - 5ms - 1ms - 1us - 4ms - - 5ms - 1ms - 1us - 4ms - - - - - - - - - - - 49ms - 2ms - 47ms - - - - - - - - - - - - - 2ms - 1ms - - - 1ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- 1ms 1ms 1ms 413us 16us 25us - 5ms - 1ms 1ms 1ms 413us 16us 25us - 5ms - 2ms 1ms 2ms 412us 26us 25us - 5ms - - 1ms - 413us - 25us - 5ms - - 1ms - 460us - 29us - 5ms - 196us 1ms 196us 370us 7us 23us - 5ms - ----- ----- ----- ----- ----- ----- ----- ----- ----- -w: Print out latency histograms: sdb total disk sync_queue async_queue latency read write read write read write read write scrub ------- ------ ------ ------ ------ ------ ------ ------ ------ ------ 1ns 0 0 0 0 0 0 0 0 0 ... 33us 0 0 0 0 0 0 0 0 0 66us 0 0 107 2486 2 788 12 12 0 131us 2 797 359 4499 10 558 184 184 6 262us 22 801 264 1563 10 286 287 287 24 524us 87 575 71 52086 15 1063 136 136 92 1ms 152 1190 5 41292 4 1693 252 252 141 2ms 245 2018 0 50007 0 2322 371 371 220 4ms 189 7455 22 162957 0 3912 6726 6726 199 8ms 108 9461 0 102320 0 5775 2526 2526 86 17ms 23 11287 0 37142 0 8043 1813 1813 19 34ms 0 14725 0 24015 0 11732 3071 3071 0 67ms 0 23597 0 7914 0 18113 5025 5025 0 134ms 0 33798 0 254 0 25755 7326 7326 0 268ms 0 51780 0 12 0 41593 10002 10002 0 537ms 0 77808 0 0 0 64255 13120 13120 0 1s 0 105281 0 0 0 83805 20841 20841 0 2s 0 88248 0 0 0 73772 14006 14006 0 4s 0 47266 0 0 0 29783 17176 17176 0 9s 0 10460 0 0 0 4130 6295 6295 0 17s 0 0 0 0 0 0 0 0 0 34s 0 0 0 0 0 0 0 0 0 69s 0 0 0 0 0 0 0 0 0 137s 0 0 0 0 0 0 0 0 0 ------------------------------------------------------------------------------- -h: Help -H: Scripted mode. Do not display headers, and separate fields by a single tab instead of arbitrary space. -q: Include current number of entries in sync & async read/write queues, and scrub queue: syncq_read syncq_write asyncq_read asyncq_write scrubq_read pend activ pend activ pend activ pend activ pend activ ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 0 0 78 29 0 0 0 0 0 0 0 0 78 29 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 - - - - - - - - - - 0 0 0 0 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- 0 0 227 394 0 19 0 0 0 0 0 0 227 394 0 19 0 0 0 0 0 0 108 98 0 19 0 0 0 0 0 0 19 98 0 0 0 0 0 0 0 0 78 98 0 0 0 0 0 0 0 0 19 88 0 0 0 0 0 0 ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- -p: Display numbers in parseable (exact) values. Also, update iostat syntax to allow the user to specify specific vdevs to show statistics for. The three options for choosing pools/vdevs are: Display a list of pools: zpool iostat ... [pool ...] Display a list of vdevs from a specific pool: zpool iostat ... [pool vdev ...] Display a list of vdevs from any pools: zpool iostat ... [vdev ...] Lastly, allow zpool command "interval" value to be floating point: zpool iostat -v 0.5 Signed-off-by: Tony Hutter <hutter2@llnl.gov Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4433
2016-02-29 18:05:23 +00:00
if ((config = zpool_get_config(zhp, NULL)) != NULL) {
verify(nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
&nvroot) == 0);
}
return (for_each_vdev_cb(zhp, nvroot, func, data));
}
/* Thread function run for each vdev */
static void
vdev_run_cmd_thread(void *cb_cmd_data)
{
vdev_cmd_data_t *data = cb_cmd_data;
char *pos = NULL;
FILE *fp;
size_t len = 0;
char cmd[_POSIX_ARG_MAX];
/* Set our VDEV_PATH and VDEV_UPATH env vars and run command */
if (snprintf(cmd, sizeof (cmd), "VDEV_PATH=%s && VDEV_UPATH=%s && %s",
data->path, data->upath ? data->upath : "\"\"", data->cmd) >=
sizeof (cmd)) {
/* Our string was truncated */
return;
}
fp = popen(cmd, "r");
if (fp == NULL)
return;
data->line = NULL;
/* Save the first line of output from the command */
if (getline(&data->line, &len, fp) != -1) {
/* Success. Remove newline from the end, if necessary. */
if ((pos = strchr(data->line, '\n')) != NULL)
*pos = '\0';
} else {
data->line = NULL;
}
pclose(fp);
}
/* For each vdev in the pool run a command */
static int
for_each_vdev_run_cb(zpool_handle_t *zhp, nvlist_t *nv, void *cb_vcdl)
{
vdev_cmd_data_list_t *vcdl = cb_vcdl;
vdev_cmd_data_t *data;
char *path = NULL;
int i;
if (nvlist_lookup_string(nv, ZPOOL_CONFIG_PATH, &path) != 0)
return (1);
/* Spares show more than once if they're in use, so skip if exists */
for (i = 0; i < vcdl->count; i++) {
if ((strcmp(vcdl->data[i].path, path) == 0) &&
(strcmp(vcdl->data[i].pool, zpool_get_name(zhp)) == 0)) {
/* vdev already exists, skip it */
return (0);
}
}
/*
* Resize our array and add in the new element.
*/
if (!(vcdl->data = realloc(vcdl->data,
sizeof (*vcdl->data) * (vcdl->count + 1))))
return (ENOMEM); /* couldn't realloc */
data = &vcdl->data[vcdl->count];
data->pool = strdup(zpool_get_name(zhp));
data->path = strdup(path);
data->upath = zfs_get_underlying_path(path);
data->cmd = vcdl->cmd;
vcdl->count++;
return (0);
}
/* Get the names and count of the vdevs */
static int
all_pools_for_each_vdev_gather_cb(zpool_handle_t *zhp, void *cb_vcdl)
{
return (for_each_vdev(zhp, for_each_vdev_run_cb, cb_vcdl));
}
/*
* Now that vcdl is populated with our complete list of vdevs, spawn
* off the commands.
*/
static void
all_pools_for_each_vdev_run_vcdl(vdev_cmd_data_list_t *vcdl)
{
taskq_t *t;
int i;
/* 5 * boot_ncpus selfishly chosen since it works best on LLNL's HW */
int max_threads = 5 * boot_ncpus;
/*
* Under Linux we use a taskq to parallelize running a command
* on each vdev. It is therefore necessary to initialize this
* functionality for the duration of the threads.
*/
thread_init();
t = taskq_create("z_pool_cmd", max_threads, defclsyspri, max_threads,
INT_MAX, 0);
if (t == NULL)
return;
/* Spawn off the command for each vdev */
for (i = 0; i < vcdl->count; i++) {
(void) taskq_dispatch(t, vdev_run_cmd_thread,
(void *) &vcdl->data[i], TQ_SLEEP);
}
/* Wait for threads to finish */
taskq_wait(t);
taskq_destroy(t);
thread_fini();
}
/*
* Run command 'cmd' on all vdevs in all pools. Saves the first line of output
* from the command in vcdk->data[].line for all vdevs.
*
* Returns a vdev_cmd_data_list_t that must be freed with
* free_vdev_cmd_data_list();
*/
vdev_cmd_data_list_t *
all_pools_for_each_vdev_run(int argc, char **argv, char *cmd)
{
vdev_cmd_data_list_t *vcdl;
vcdl = safe_malloc(sizeof (vdev_cmd_data_list_t));
vcdl->cmd = cmd;
/* Gather our list of all vdevs in all pools */
for_each_pool(argc, argv, B_TRUE, NULL,
all_pools_for_each_vdev_gather_cb, vcdl);
/* Run command on all vdevs in all pools */
all_pools_for_each_vdev_run_vcdl(vcdl);
return (vcdl);
}
/*
* Free the vdev_cmd_data_list_t created by all_pools_for_each_vdev_run()
*/
void
free_vdev_cmd_data_list(vdev_cmd_data_list_t *vcdl)
{
int i;
for (i = 0; i < vcdl->count; i++) {
free(vcdl->data[i].path);
free(vcdl->data[i].pool);
free(vcdl->data[i].upath);
free(vcdl->data[i].line);
}
free(vcdl->data);
free(vcdl);
}