COLO proxy patch
cover COLO proxy patch
Hi Jason,
Please help me merge the COLO proxy patch to net branch.
Thanks
Chen
Rao, Lei (7):
Remove some duplicate trace code.
Fix the qemu crash when guest shutdown during checkpoint Optimize the function of filter_send
Remove migrate_set_block_enabled in checkpoint
Add a function named packet_new_nocopy for COLO.
Add the function of colo_compare_cleanup
Fixed calculation error of pkt->header_size in fill_pkt_tcp_info()
migration/colo.c | 6 ------ migration/migration.c | 4 ++++ net/colo-compare.c | 25 +++++++++++-------------- net/colo-compare.h | 1 + net/colo.c | 25 +++++++++++++++++-------- net/colo.h | 1 + net/filter-mirror.c | 8 ++++---- net/filter-rewriter.c | 3 +-- net/net.c | 4 ++++ softmmu/runstate.c | 1 + 10 files changed, 44 insertions(+), 34 deletions(-)
Signature · 1 line
2.25.1
PATCH 1/7 Remove some duplicate trace code.
From: "Rao, Lei" <[email protected]>
There is the same trace code in the colo_compare_packet_payload.
--- net/colo-compare.c | 13 ------------- 1 file changed, 13 deletions(-)
net/colo-compare.c +0 -13
@@ -590,19 +590,6 @@ static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)uint16_t offset = ppkt->vnet_hdr_len;trace_colo_compare_main ("compare other" ); -if (trace_event_get_state_backends (TRACE_COLO_COMPARE_IP_INFO )) { -char pri_ip_src[20 ], pri_ip_dst[20 ], sec_ip_src[20 ], sec_ip_dst[20 ]; - -strcpy (pri_ip_src,inet_ntoa (ppkt->ip->ip_src)); -strcpy (pri_ip_dst,inet_ntoa (ppkt->ip->ip_dst)); -strcpy (sec_ip_src,inet_ntoa (spkt->ip->ip_src)); -strcpy (sec_ip_dst,inet_ntoa (spkt->ip->ip_dst)); - -trace_colo_compare_ip_info (ppkt->size, pri_ip_src, - pri_ip_dst, spkt->size, - sec_ip_src, sec_ip_dst); - } -if (ppkt->size != spkt->size) {trace_colo_compare_main ("Other: payload size of packets are different" );return -1 ;
Signature · 1 line
2.25.1
PATCH 2/7 Fix the qemu crash when guest shutdown during checkpoint
In reply to Zhang ChenFrom: "Rao, Lei" <[email protected]>
This patch fixes the following:
qemu-system-x86_64: invalid runstate transition: 'colo' ->'shutdown' Aborted (core dumped)
--- softmmu/runstate.c | 1 + 1 file changed, 1 insertion(+)
softmmu/runstate.c +1 -0
@@ -126,6 +126,7 @@ static const RunStateTransition runstate_transitions_def[] = { { RUN_STATE_RESTORE_VM, RUN_STATE_PRELAUNCH }, { RUN_STATE_COLO, RUN_STATE_RUNNING }, + { RUN_STATE_COLO, RUN_STATE_SHUTDOWN}, { RUN_STATE_RUNNING, RUN_STATE_DEBUG }, { RUN_STATE_RUNNING, RUN_STATE_INTERNAL_ERROR },
Signature · 1 line
2.25.1
PATCH 3/7 Optimize the function of filter_send
In reply to Zhang ChenFrom: "Rao, Lei" <[email protected]>
The iov_size has been calculated in filter_send(). we can directly return the size.In this way, this is no need to repeat calculations in filter_redirector_receive_iov();
--- net/filter-mirror.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
net/filter-mirror.c +4 -4
@@ -88,7 +88,7 @@ static int filter_send(MirrorState *s, goto err; } -return 0 ; +return size; err:return ret <0 ? ret : -EIO ;
@@ -159,7 +159,7 @@ static ssize_t filter_mirror_receive_iov(NetFilterState *nf,int ret; ret =filter_send (s, iov, iovcnt); -if (ret) { +if (ret <0 ) {error_report ("filter mirror send failed(%s)" ,strerror (-ret)); }
@@ -182,10 +182,10 @@ static ssize_t filter_redirector_receive_iov(NetFilterState *nf,if (qemu_chr_fe_backend_connected (&s->chr_out)) { ret =filter_send (s, iov, iovcnt); -if (ret) { +if (ret <0 ) {error_report ("filter redirector send failed(%s)" ,strerror (-ret)); } -return iov_size (iov, iovcnt); +return ret; }else {return 0 ; }
Signature · 1 line
2.25.1
PATCH 4/7 Remove migrate_set_block_enabled in checkpoint
In reply to Zhang ChenFrom: "Rao, Lei" <[email protected]>
We can detect disk migration in migrate_prepare, if disk migration is enabled in COLO mode, we can directly report an error.and there is no need to disable block migration at every checkpoint.
--- migration/colo.c | 6 ------ migration/migration.c | 4 ++++ 2 files changed, 4 insertions(+), 6 deletions(-)
migration/colo.c +0 -6
@@ -435,12 +435,6 @@ static int colo_do_checkpoint_transaction(MigrationState *s,if (failover_get_state () !=FAILOVER_STATUS_NONE ) { goto out; } - -/* Disable block migration */ -migrate_set_block_enabled (false, &local_err); -if (local_err) { - goto out; - }qemu_mutex_lock_iothread ();#ifdef CONFIG_REPLICATION
migration/migration.c +4 -0
@@ -2214,6 +2214,10 @@ static bool migrate_prepare(MigrationState *s, bool blk, bool blk_inc, }if (blk || blk_inc) { +if (migrate_colo_enabled ()) { +error_setg (errp,"No disk migration is required in COLO mode" ); +return false; + }if (migrate_use_block () ||migrate_use_block_incremental ()) {error_setg (errp,"Command options are incompatible with " "current migration capabilities" );
Signature · 1 line
2.25.1
PATCH 5/7 Add a function named packet_new_nocopy for COLO.
In reply to Zhang ChenFrom: "Rao, Lei" <[email protected]>
Use the packet_new_nocopy instead of packet_new in the filter-rewriter module. There will be one less memory copy in the processing of each network packet.
--- net/colo.c | 25 +++++++++++++++++-------- net/colo.h | 1 + net/filter-rewriter.c | 3 +-- 3 files changed, 19 insertions(+), 10 deletions(-)
net/colo.c +17 -8
@@ -157,19 +157,28 @@ void connection_destroy(void *opaque)Packet *packet_new (const void *data,int size,int vnet_hdr_len) { -Packet *pkt =g_slice_new (Packet); +Packet *pkt =g_slice_new0 (Packet); pkt->data =g_memdup (data, size); pkt->size = size; pkt->creation_ms =qemu_clock_get_ms (QEMU_CLOCK_HOST ); pkt->vnet_hdr_len = vnet_hdr_len; - pkt->tcp_seq =0 ; - pkt->tcp_ack =0 ; - pkt->seq_end =0 ; - pkt->header_size =0 ; - pkt->payload_size =0 ; - pkt->offset =0 ; - pkt->flags =0 ; + +return pkt; +} + +/* +* packet_new_nocopy will not copy data, so the caller can't release +* the data. And it will be released in packet_destroy. +*/ +Packet *packet_new_nocopy (void *data,int size,int vnet_hdr_len) +{ +Packet *pkt =g_slice_new0 (Packet); + + pkt->data = data; + pkt->size = size; + pkt->creation_ms =qemu_clock_get_ms (QEMU_CLOCK_HOST ); + pkt->vnet_hdr_len = vnet_hdr_len;return pkt; }
net/colo.h +1 -0
@@ -101,6 +101,7 @@ bool connection_has_tracked(GHashTable *connection_track_table, ConnectionKey *key);void connection_hashtable_reset (GHashTable *connection_track_table);Packet *packet_new (const void *data,int size,int vnet_hdr_len); +Packet *packet_new_nocopy (void *data,int size,int vnet_hdr_len);void packet_destroy (void *opaque,void *user_data);void packet_destroy_partial (void *opaque,void *user_data);
net/filter-rewriter.c +1 -2
@@ -270,8 +270,7 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf, vnet_hdr_len = nf->netdev->vnet_hdr_len; } - pkt =packet_new (buf, size, vnet_hdr_len); -g_free (buf); + pkt =packet_new_nocopy (buf, size, vnet_hdr_len);/* * if we get tcp packet
Signature · 1 line
2.25.1
PATCH 6/7 Add the function of colo_compare_cleanup
In reply to Zhang ChenFrom: "Rao, Lei" <[email protected]>
This patch fixes the following:
#0 __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:50
#1 0x00007f6ae4559859 in __GI_abort () at abort.c:79
#2 0x0000559aaa386720 in error_exit (err=16, msg=0x559aaa5973d0 <__func__.16227> "qemu_mutex_destroy") at util/qemu-thread-posix.c:36
#3 0x0000559aaa3868c5 in qemu_mutex_destroy (mutex=0x559aabffe828) at util/qemu-thread-posix.c:69
#4 0x0000559aaa2f93a8 in char_finalize (obj=0x559aabffe800) at chardev/char.c:285
#5 0x0000559aaa23318a in object_deinit (obj=0x559aabffe800, type=0x559aabfd7d20) at qom/object.c:606
#6 0x0000559aaa2331b8 in object_deinit (obj=0x559aabffe800, type=0x559aabfd9060) at qom/object.c:610
#7 0x0000559aaa233200 in object_finalize (data=0x559aabffe800) at qom/object.c:620
#8 0x0000559aaa234202 in object_unref (obj=0x559aabffe800) at qom/object.c:1074
#9 0x0000559aaa2356b6 in object_finalize_child_property (obj=0x559aac0dac10, name=0x559aac778760 "compare0-0", opaque=0x559aabffe800) at qom/object.c:1584
#10 0x0000559aaa232f70 in object_property_del_all (obj=0x559aac0dac10) at qom/object.c:557
#11 0x0000559aaa2331ed in object_finalize (data=0x559aac0dac10) at qom/object.c:619
#12 0x0000559aaa234202 in object_unref (obj=0x559aac0dac10) at qom/object.c:1074
#13 0x0000559aaa2356b6 in object_finalize_child_property (obj=0x559aac0c75c0, name=0x559aac0dadc0 "chardevs", opaque=0x559aac0dac10) at qom/object.c:1584
#14 0x0000559aaa233071 in object_property_del_child (obj=0x559aac0c75c0, child=0x559aac0dac10, errp=0x0) at qom/object.c:580
#15 0x0000559aaa233155 in object_unparent (obj=0x559aac0dac10) at qom/object.c:599
#16 0x0000559aaa2fb721 in qemu_chr_cleanup () at chardev/char.c:1159
#17 0x0000559aa9f9b110 in main (argc=54, argv=0x7ffeb62fa998, envp=0x7ffeb62fab50) at vl.c:4539When chardev is cleaned up, chr_write_lock needs to be destroyed. But the colo-compare module is not cleaned up normally before it when the guest poweroff. It is holding chr_write_lock at this time. This will cause qemu crash.So we add the function of colo_compare_cleanup() before qemu_chr_cleanup() to fix the bug.
--- net/colo-compare.c | 10 ++++++++++ net/colo-compare.h | 1 + net/net.c | 4 ++++ 3 files changed, 15 insertions(+)
net/colo-compare.c +10 -0
@@ -1402,6 +1402,16 @@ static void colo_compare_init(Object *obj) compare_set_vnet_hdr); } +void colo_compare_cleanup (void ) +{ +CompareState *tmp =NULL ; +CompareState *n =NULL ; + + QTAILQ_FOREACH_SAFE(tmp, &net_compares, next, n) { +object_unparent (OBJECT (tmp)); + } +} +static void colo_compare_finalize (Object *obj) {CompareState *s =COLO_COMPARE (obj);
net/colo-compare.h +1 -0
@@ -20,5 +20,6 @@void colo_notify_compares_event (void *opaque,int event,Error **errp);void colo_compare_register_notifier (Notifier *notify);void colo_compare_unregister_notifier (Notifier *notify); +void colo_compare_cleanup (void );#endif /* QEMU_COLO_COMPARE_H */
net/net.c +4 -0
@@ -52,6 +52,7 @@#include "qapi/error.h" #include "qapi/opts-visitor.h" #include "sysemu/runstate.h" +#include "net/colo-compare.h" #include "net/filter.h" #include "qapi/string-output-visitor.h"
@@ -1402,6 +1403,9 @@ void net_cleanup(void) {NetClientState *nc; +/*cleanup colo compare module for COLO*/ +colo_compare_cleanup (); +/* We may del multiple entries during qemu_del_net_client(), * so QTAILQ_FOREACH_SAFE() is also not safe here. */
Signature · 1 line
2.25.1
PATCH 7/7 Fixed calculation error of pkt->header_size in fill_pkt_tcp_info()
In reply to Zhang ChenFrom: "Rao, Lei" <[email protected]>
The data pointer has skipped vnet_hdr_len in the function of parse_packet_early().So, we can not subtract vnet_hdr_len again when calculating pkt->header_size in fill_pkt_tcp_info(). Otherwise, it will cause network packet comparsion errors and greatly increase the frequency of checkpoints.
--- net/colo-compare.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/colo-compare.c +1 -1
@@ -211,7 +211,7 @@ static void fill_pkt_tcp_info(void *data, uint32_t *max_ack) pkt->tcp_ack =ntohl (tcphd->th_ack); *max_ack = *max_ack > pkt->tcp_ack ? *max_ack : pkt->tcp_ack; pkt->header_size = pkt->transport_header - (uint8_t *)pkt->data - + (tcphd->th_off <<2 ) - pkt->vnet_hdr_len; + + (tcphd->th_off <<2 ); pkt->payload_size = pkt->size - pkt->header_size; pkt->seq_end = pkt->tcp_seq + pkt->payload_size; pkt->flags = tcphd->th_flags;
Signature · 1 line
2.25.1